{"meta":{"query_hash":"8b096c79865a","filters":{"venue":"Bioinformatics Advances"},"cohort_total":65,"direct_labels_cover":0,"predictions_cover":65,"exported":65,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/8b096c79865a","api":"https://metacan.xera.ac/api/v1/cohort?venue=Bioinformatics+Advances"},"results":[{"id":"W3179038740","doi":"10.1093/bioadv/vbac033","title":"Sufficient principal component regression for pattern discovery in transcriptomic data","year":2022,"lang":"en","type":"preprint","venue":"Bioinformatics Advances","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Subspace topology; Principal component analysis; Context (archaeology); Computer science; Data mining; Regression; Principal component regression; Machine learning; Artificial intelligence; Pattern recognition (psychology); Mathematics; Biology; Statistics","score_opus":0.0465884028724005,"score_gpt":0.3316644022699577,"score_spread":0.2850759993975572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3179038740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7839659,0.013008945,0.18929401,0.00060730433,0.0043952563,0.002939725,0.004637828,0.000053657932,0.001097361],"genre_scores_gemma":[0.96400785,0.005645981,0.007153627,0.0003282825,0.00027900474,0.0006651041,0.021278061,0.00005041745,0.0005916886],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99822706,0.00004952718,0.0006267112,0.0005351699,0.00028722157,0.00027433792],"domain_scores_gemma":[0.99813944,0.00001620756,0.00041984374,0.0013226052,0.00004029101,0.0000616183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035818518,0.00027562983,0.00027314672,0.00012631986,0.00010535641,0.000083876745,0.0010529625,0.00017292415,0.000017153081],"category_scores_gemma":[0.000036529873,0.00023997584,0.00011030314,0.00007290462,0.00005167871,0.000028122158,0.0013606538,0.00025317652,0.0000015754788],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004028453,0.0035962693,0.025360508,0.014745512,0.00054479233,0.0000149453645,0.008230117,0.1162713,0.27592278,0.0008149496,0.06009611,0.49037427],"study_design_scores_gemma":[0.0016684431,0.0002494382,0.0026453116,0.00037460844,0.000042018102,0.0000039104866,0.002056064,0.06894666,0.015274822,0.00010991594,0.9078351,0.00079371023],"about_ca_topic_score_codex":0.000012333448,"about_ca_topic_score_gemma":0.000079695514,"teacher_disagreement_score":0.847739,"about_ca_system_score_codex":0.00008252482,"about_ca_system_score_gemma":0.00025158742,"threshold_uncertainty_score":0.97859305},"labels":[],"label_agreement":null},{"id":"W3201257126","doi":"10.1093/bioadv/vbab021","title":"CRIS: complete reconstruction of immunoglobulin <i>V-D-J</i> sequences from RNA-seq data","year":2021,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Chronic Lymphocytic Leukemia Research","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Terry Fox Research Institute; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Cancer Institute; National Human Genome Research Institute; Canadian Institutes of Health Research","keywords":"RNA-Seq; Computational biology; Antibody; Biology; Genetics; Gene; Transcriptome; Gene expression","score_opus":0.061407976704869756,"score_gpt":0.3298371960912405,"score_spread":0.26842921938637077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201257126","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82793576,0.06807673,0.017494665,0.0020273458,0.003041318,0.001509235,0.0045299963,0.00034907355,0.07503589],"genre_scores_gemma":[0.47350666,0.021316571,0.49931437,0.00078914186,0.00057425845,0.000024078958,0.0037502395,0.000053513886,0.0006711847],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980883,0.00003635773,0.0007593488,0.00024400053,0.0005880609,0.0002839483],"domain_scores_gemma":[0.9978404,0.00023981922,0.0002921891,0.0012061478,0.00030530375,0.00011614438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026045975,0.00015843737,0.00043535742,0.0000750947,0.00007609579,0.000043636526,0.00041265044,0.00008572138,0.00030641418],"category_scores_gemma":[0.00047750343,0.00013402918,0.000071295835,0.0003475226,0.0003041139,0.00085419154,0.0003551345,0.00017832397,0.00009391964],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008549942,0.00037736446,0.0031075808,0.003934447,0.0010338406,0.0003406131,0.0024629324,0.00036879594,0.04341821,0.0014222519,0.007198715,0.93548024],"study_design_scores_gemma":[0.026658019,0.00063517626,0.0011432237,0.0032872239,0.0005577048,0.002997089,0.017621502,0.47354487,0.20082822,0.0054084742,0.2662137,0.0011048191],"about_ca_topic_score_codex":0.00048443067,"about_ca_topic_score_gemma":0.00009115839,"teacher_disagreement_score":0.93437546,"about_ca_system_score_codex":0.00095988193,"about_ca_system_score_gemma":0.004029973,"threshold_uncertainty_score":0.7148999},"labels":[],"label_agreement":null},{"id":"W3201645418","doi":"10.1093/bioadv/vbab018","title":"Balanced Functional Module Detection in genomic data","year":2021,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Outcome (game theory); Property (philosophy); Computer science; Set (abstract data type); Consistency (knowledge bases); Variable (mathematics); Feature selection; Data mining; Artificial intelligence; Theoretical computer science; Machine learning; Mathematics","score_opus":0.014696382845612456,"score_gpt":0.2381064015665066,"score_spread":0.22341001872089414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201645418","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42377886,0.013723012,0.53837305,0.00035636884,0.0025622768,0.0006206622,0.00038964092,0.00007273202,0.020123359],"genre_scores_gemma":[0.9577661,0.002683695,0.03552693,0.00070842064,0.00045245478,0.000020762756,0.0023284613,0.000024721847,0.0004884443],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989918,0.000016291742,0.00040430875,0.00021166677,0.00012579134,0.00025014818],"domain_scores_gemma":[0.999084,0.0000115820585,0.00012867498,0.00065378344,0.00006251834,0.0000594712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020089795,0.00014111544,0.00014227684,0.000045776353,0.00007457563,0.00004832401,0.00026296696,0.00011463987,0.00002681709],"category_scores_gemma":[0.000053102238,0.00014030212,0.000041189196,0.00014453456,0.00004319521,0.000044699274,0.00035327955,0.00010707979,0.00003873241],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035189607,0.00029137768,0.006911534,0.00048269125,0.00021046857,0.000017423037,0.00036987674,0.036561478,0.17676906,0.0012029803,0.007653801,0.7691774],"study_design_scores_gemma":[0.0022624638,0.00017284272,0.012254311,0.000056305027,0.000026855294,0.00014478454,0.0009293383,0.43489563,0.044946812,0.0015969862,0.50188607,0.00082761457],"about_ca_topic_score_codex":0.0000036363015,"about_ca_topic_score_gemma":0.00026608378,"teacher_disagreement_score":0.76834977,"about_ca_system_score_codex":0.000026390004,"about_ca_system_score_gemma":0.00012261546,"threshold_uncertainty_score":0.57213545},"labels":[],"label_agreement":null},{"id":"W3217126935","doi":"10.1093/bioadv/vbab032","title":"An expectation–maximization approach to quantifying protein stoichiometry with single-molecule imaging","year":2021,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Advanced Fluorescence Microscopy Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Python (programming language); Photobleaching; Maximization; Rendering (computer graphics); Benchmark (surveying); Single-molecule experiment; Software; Algorithm; Resampling; Biological system; Artificial intelligence; Fluorescence; Physics; Mathematics; Optics; Mathematical optimization","score_opus":0.01365889790151077,"score_gpt":0.28657783493185246,"score_spread":0.2729189370303417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217126935","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086966634,0.0005125097,0.9101752,0.000035631318,0.000034669232,0.00037906886,0.000013982042,0.00008527557,0.0017970188],"genre_scores_gemma":[0.28694382,0.000031154872,0.71233255,0.00019837357,0.000042802592,0.00007016108,0.00031325672,0.000028493934,0.00003939883],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988458,0.000032069525,0.00029721195,0.00032519887,0.0002133401,0.0002863347],"domain_scores_gemma":[0.9990188,0.0000052116675,0.00015578524,0.00045361122,0.00025659968,0.00011001609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008108189,0.00020549848,0.00015404308,0.000120621284,0.00015121717,0.00011623802,0.00021523153,0.000059938455,0.000003025959],"category_scores_gemma":[0.00010021432,0.00019089929,0.000034374752,0.0004606372,0.000071387854,0.000096165895,0.00008011124,0.00007650791,0.0000038017915],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004642894,0.00013429929,0.0008454351,0.000084075655,0.000010560147,0.0000023349312,0.0002990118,0.001739704,0.98666936,0.00019578726,0.0000375998,0.009935376],"study_design_scores_gemma":[0.00024111322,0.00023826158,0.00008631505,0.00006692244,0.0000074809773,0.000031478,0.0019682422,0.0044148993,0.9897066,0.0000347969,0.0028712444,0.00033264782],"about_ca_topic_score_codex":0.0000013920711,"about_ca_topic_score_gemma":0.000008202838,"teacher_disagreement_score":0.1999772,"about_ca_system_score_codex":0.00003246455,"about_ca_system_score_gemma":0.00008402332,"threshold_uncertainty_score":0.77846473},"labels":[],"label_agreement":null},{"id":"W4210673729","doi":"10.1093/bioadv/vbab044","title":"From pairwise to multiple spliced alignment","year":2022,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Université de Sherbrooke","keywords":"Pairwise comparison; RNA splicing; Gene; Computer science; Computational biology; Alignment-free sequence analysis; Gene family; Gene Annotation; Heuristic; Context (archaeology); Annotation; Gene prediction; Genome; Genetics; Biology; Sequence alignment; Artificial intelligence; RNA; Peptide sequence","score_opus":0.010446553364173973,"score_gpt":0.2654293748247018,"score_spread":0.2549828214605278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210673729","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99058294,0.00050252903,0.0065542343,0.00030753302,0.00019219096,0.00031434742,0.00018488793,0.000020150494,0.0013411951],"genre_scores_gemma":[0.9747881,0.00014686132,0.021338228,0.0013940916,0.00018725322,0.00017900528,0.00035434365,0.000017843493,0.0015942709],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906564,0.000025552288,0.00020860744,0.00015438301,0.0002823263,0.00026351208],"domain_scores_gemma":[0.9994488,0.000020100802,0.000060675684,0.00030226188,0.000027093953,0.00014108712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001521827,0.00010395161,0.00009802259,0.00004415306,0.00020529503,0.000027938086,0.00027739775,0.000022959219,0.000067944566],"category_scores_gemma":[0.00007687536,0.00009830201,0.000053153315,0.00009907563,0.00001958812,0.000009337726,0.0003951061,0.00006853806,0.000045087483],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044972484,0.00016896527,0.0049450453,0.000058401634,0.000098036326,0.000008828349,0.0010225326,0.010343097,0.85626584,0.00010659591,0.031322286,0.09521062],"study_design_scores_gemma":[0.0007975403,0.0005804776,0.00044557377,0.000009185235,0.000006048512,0.000004634023,0.0027609367,0.008304842,0.11981687,0.000080111364,0.8668891,0.00030468425],"about_ca_topic_score_codex":0.000057172383,"about_ca_topic_score_gemma":0.000032762724,"teacher_disagreement_score":0.8355668,"about_ca_system_score_codex":0.00003242291,"about_ca_system_score_gemma":0.00004108579,"threshold_uncertainty_score":0.40086395},"labels":[],"label_agreement":null},{"id":"W4226251181","doi":"10.1093/bioadv/vbac030","title":"Expanding the Galaxy’s reference data","year":2022,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke; BC Centre for Disease Control","funders":"National Human Genome Research Institute; Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; National Cancer Institute; National Institutes of Health; European Commission; Vlaamse regering; National Research Foundation; UK Research and Innovation; Cleveland Clinic","keywords":"Computer science; Galaxy; Task (project management); Interface (matter); Reference data; Information retrieval; Database; Astrophysics; Operating system; Physics; Engineering","score_opus":0.037415753046130866,"score_gpt":0.28645728237098694,"score_spread":0.24904152932485607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226251181","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9081101,0.03769581,0.0044445302,0.0010344674,0.0016883144,0.00084382267,0.001272684,0.000026687976,0.044883575],"genre_scores_gemma":[0.99164313,0.002258397,0.0048854523,0.0004240548,0.00012123761,0.000048251542,0.0002687724,0.0000102982685,0.000340393],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993119,0.000024450766,0.00018951578,0.0001514282,0.0001482925,0.00017441231],"domain_scores_gemma":[0.9991344,0.000019034911,0.0001070216,0.0006892953,0.000023518945,0.000026714566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002567378,0.0000963407,0.00007971211,0.000017364886,0.000493009,0.000027668188,0.0007695163,0.000017498684,0.000024781755],"category_scores_gemma":[0.000039969033,0.00006918008,0.000024208366,0.000071249604,0.00006393311,0.0000031454083,0.0013694748,0.000079544945,0.0000065872177],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005450403,0.00033978026,0.040039748,0.00039988558,0.00095986546,0.000012036922,0.0062010176,0.016949246,0.3151118,0.008051053,0.1406212,0.47076935],"study_design_scores_gemma":[0.00019211123,0.00014699029,0.001091523,0.000002220089,0.0000124557455,0.00002121259,0.0025675367,0.0007818964,0.0027800014,0.00031586766,0.9919189,0.00016925987],"about_ca_topic_score_codex":0.000005864408,"about_ca_topic_score_gemma":0.000017324042,"teacher_disagreement_score":0.85129774,"about_ca_system_score_codex":0.000009623059,"about_ca_system_score_gemma":0.000048143942,"threshold_uncertainty_score":0.37918764},"labels":[],"label_agreement":null},{"id":"W4281294657","doi":"10.1093/bioadv/vbac038","title":"HPiP: an R/Bioconductor package for predicting host–pathogen protein–protein interactions from protein sequences using ensemble machine learning approach","year":2022,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Bioconductor; Computational biology; Host (biology); Computer science; Machine learning; Biology; Artificial intelligence; Bioinformatics; Genetics; Gene","score_opus":0.021306430047910288,"score_gpt":0.2605602040231485,"score_spread":0.23925377397523823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281294657","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8389117,0.0013770396,0.15510647,0.00003804989,0.00025146373,0.0024711038,0.0010492575,0.00007908525,0.00071580376],"genre_scores_gemma":[0.79856026,0.000025353434,0.19686523,0.000100609985,0.00040609136,0.00085679675,0.0025970188,0.00005974856,0.0005289033],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785656,0.00011923062,0.000775796,0.00039496855,0.0003106626,0.0005427746],"domain_scores_gemma":[0.99850416,0.000022224296,0.0007038929,0.00049142353,0.000115818555,0.00016245256],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057421095,0.00036912764,0.00032849994,0.0001066472,0.0010644874,0.00016411199,0.00051363074,0.00012833785,0.000041486634],"category_scores_gemma":[0.00010356836,0.00035614154,0.00016676885,0.00018577775,0.00010360508,0.000140528,0.000387826,0.0004317624,0.0000035885225],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019424445,0.00012847653,0.00023196351,0.00022771583,0.00011140538,0.0000012946875,0.0010227589,0.0076411935,0.9813974,0.00028812294,0.0000348294,0.008720581],"study_design_scores_gemma":[0.0018048306,0.0018319282,0.000023018378,0.00014734994,0.00009259778,0.00006447453,0.008155259,0.64249045,0.22408865,0.0016821681,0.118247814,0.0013714727],"about_ca_topic_score_codex":0.00007704384,"about_ca_topic_score_gemma":0.000038215858,"teacher_disagreement_score":0.7573088,"about_ca_system_score_codex":0.000084172454,"about_ca_system_score_gemma":0.00016972148,"threshold_uncertainty_score":0.9998891},"labels":[],"label_agreement":null},{"id":"W4288051411","doi":"10.1093/bioadv/vbac049","title":"More accurate estimation of cell composition in bulk expression through robust integration of single-cell information","year":2022,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Health Canada","funders":"","keywords":"Covariance; Collinearity; Univariate; Computer science; Expression (computer science); RNA-Seq; Data mining; Analysis of covariance; Computational biology; Algorithm; Biological system; Gene expression; Mathematics; Gene; Multivariate statistics; Transcriptome; Biology; Statistics; Machine learning; Genetics","score_opus":0.01643830154938968,"score_gpt":0.24041963199313485,"score_spread":0.22398133044374516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288051411","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82501143,0.00023874934,0.17272037,0.000020798012,0.00018026229,0.00028527586,0.000093088885,0.000010154087,0.0014398482],"genre_scores_gemma":[0.9528873,0.00015044083,0.045735687,0.00006092971,0.000012739481,0.000022059774,0.0011106185,0.0000075992266,0.000012634587],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988602,0.0000357738,0.00065670686,0.00008850107,0.00023252387,0.00012630262],"domain_scores_gemma":[0.99914795,0.000017895421,0.0005360816,0.00017766813,0.000099037294,0.000021344662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014580286,0.00012923063,0.00016823162,0.00010223461,0.00007704356,0.000016827114,0.0001624365,0.000068320725,0.000010721947],"category_scores_gemma":[0.00002180981,0.00012599365,0.000059592214,0.0001825758,0.00005383999,0.00015794412,0.00007000003,0.000092816954,0.0000011257882],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016070067,0.00019268334,0.00013357514,0.0002704812,0.0000029683167,1.2280829e-7,0.0020504834,0.2487143,0.7445386,0.00003426618,0.000057010908,0.0038447848],"study_design_scores_gemma":[0.00078384735,0.00041206795,0.00008565765,0.00005072715,0.000008687869,0.000002199133,0.0019291082,0.077751875,0.917834,0.000049063903,0.0009527139,0.00014009168],"about_ca_topic_score_codex":0.00001708468,"about_ca_topic_score_gemma":0.0000051842567,"teacher_disagreement_score":0.17329533,"about_ca_system_score_codex":0.000034076907,"about_ca_system_score_gemma":0.000042267853,"threshold_uncertainty_score":0.5137872},"labels":[],"label_agreement":null},{"id":"W4297231023","doi":"10.1093/bioadv/vbac069","title":"High-throughput design of bacterial anti-sense RNAs using CAREng","year":2022,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bacterial Genetics and Biotechnology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Computational biology; Gene; Antisense RNA; Functional genomics; RNA; Transfer RNA; Genetics; Genome; Genomics","score_opus":0.01569035333574757,"score_gpt":0.2419148205237434,"score_spread":0.22622446718799585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297231023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97341317,0.000948063,0.023830848,0.000035480305,0.0011894534,0.0002762971,0.0002073796,0.000019920439,0.00007938345],"genre_scores_gemma":[0.905566,0.0007168166,0.09317204,0.000076242504,0.00020023885,0.000014164548,0.00020638619,0.000022011001,0.000026118298],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99889225,0.00005700257,0.00043646482,0.00018273432,0.00017107023,0.00026046042],"domain_scores_gemma":[0.9992122,0.000011719206,0.00031483755,0.00034969367,0.00006913172,0.000042424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019359872,0.000169559,0.00024102314,0.00007524533,0.00017437474,0.000019440298,0.00024349567,0.00011750384,0.00006130657],"category_scores_gemma":[0.000036661142,0.00016505575,0.00006998491,0.00014938877,0.00012815584,0.000011272983,0.0003996054,0.00009893298,0.0000020054752],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013260185,0.000048813727,0.000041723557,0.000043131222,0.000043786462,0.0000034826303,0.00008945943,0.009160289,0.98510045,0.00017512195,0.00016677073,0.0049943686],"study_design_scores_gemma":[0.0011083777,0.0010462027,0.00008158454,0.000011524342,0.00003739353,0.00008591031,0.0005904077,0.003645187,0.89988774,0.0001680805,0.09295056,0.00038700533],"about_ca_topic_score_codex":0.00001676911,"about_ca_topic_score_gemma":0.0000035405242,"teacher_disagreement_score":0.09278379,"about_ca_system_score_codex":0.000021847629,"about_ca_system_score_gemma":0.00010869403,"threshold_uncertainty_score":0.6730778},"labels":[],"label_agreement":null},{"id":"W4313800421","doi":"10.1093/bioadv/vbac099","title":"GlobeCorr: interactive globe-based visualization for correlation datasets","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; McGill University Health Centre; Simon Fraser University","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Metadata; Visualization; Computer science; MIT License; Pairwise comparison; Data mining; Correlation; Interactive visualization; Data visualization; Information retrieval; Globe; License; Data science; World Wide Web; Artificial intelligence; Biology","score_opus":0.016107814823444484,"score_gpt":0.3134939633144855,"score_spread":0.297386148491041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313800421","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044544704,0.000040183557,0.94361305,0.00033840784,0.0007619182,0.0018333729,0.0010256437,0.00032419292,0.007518499],"genre_scores_gemma":[0.921429,0.0004073252,0.0638902,0.0032307738,0.00016506063,0.00045351515,0.009966822,0.000076874414,0.00038045933],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875224,0.000033037973,0.0003686532,0.00022959303,0.00029940993,0.0003170422],"domain_scores_gemma":[0.9991323,0.00027854647,0.00025755836,0.00022917737,0.000010226681,0.000092214505],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00043827604,0.00014585245,0.0001252721,0.000075444965,0.00022332201,0.00004268316,0.00015866967,0.000053374817,0.0002463036],"category_scores_gemma":[0.00030519045,0.0001415483,0.000040702354,0.00038816157,0.00008777619,0.0013561879,0.000099014134,0.000068915404,0.0016661171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023754267,0.00024712947,0.04913094,0.0005111633,0.000036792608,0.0000062236695,0.0029541946,0.19359808,0.000941663,0.0009154217,0.029627841,0.721793],"study_design_scores_gemma":[0.00054031034,0.00010224943,0.012937013,0.000043842854,0.000013648934,0.0000011375352,0.0005344934,0.79700345,0.00085001544,0.00055543706,0.18720227,0.0002161545],"about_ca_topic_score_codex":0.000020891237,"about_ca_topic_score_gemma":0.000053043626,"teacher_disagreement_score":0.8797229,"about_ca_system_score_codex":0.00024304842,"about_ca_system_score_gemma":0.00001824077,"threshold_uncertainty_score":0.9991112},"labels":[],"label_agreement":null},{"id":"W4319341254","doi":"10.1093/bioadv/vbad010","title":"NSPA: characterizing the disease association of multiple genetic interactions at single-subject resolution","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Association (psychology); Subject (documents); Resolution (logic); Genetic association; Computational biology; Computer science; Biology; Genetics; Artificial intelligence; Psychology; Genotype; Single-nucleotide polymorphism; Gene; Library science","score_opus":0.01775615102493194,"score_gpt":0.26334134266902914,"score_spread":0.2455851916440972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319341254","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946809,0.00048332685,0.002493256,0.00095599453,0.00045403282,0.0002235629,0.0001115196,0.000030024099,0.0005673825],"genre_scores_gemma":[0.9937542,0.0011680977,0.0031055235,0.00020197687,0.00015965285,0.000044519682,0.00039939766,0.000011972403,0.0011546311],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99901384,0.00007515046,0.00040515128,0.00012322304,0.00014047808,0.00024214819],"domain_scores_gemma":[0.99897325,0.0001593058,0.00046247928,0.00024886895,0.00010436331,0.000051717725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033749745,0.00010576304,0.00013138446,0.0000564009,0.00020781833,0.000013859075,0.00013941493,0.00006756686,0.000008739394],"category_scores_gemma":[0.0010568573,0.0000832594,0.000098350596,0.00018010012,0.000047231297,0.00001418701,0.0001292922,0.00005732339,0.000049984053],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002033888,0.00014644327,0.73256856,0.00019990679,0.0002617791,0.0000015402173,0.0009755137,0.016870065,0.2046255,0.000069404385,0.022853985,0.021223921],"study_design_scores_gemma":[0.00051068614,0.00015959115,0.7182747,0.000038216545,0.000066602275,0.000004359952,0.00053228956,0.04396134,0.008327866,0.00017207502,0.22768435,0.0002679485],"about_ca_topic_score_codex":0.0000066668713,"about_ca_topic_score_gemma":0.0001088067,"teacher_disagreement_score":0.20483036,"about_ca_system_score_codex":0.00007562394,"about_ca_system_score_gemma":0.000034932098,"threshold_uncertainty_score":0.33952197},"labels":[],"label_agreement":null},{"id":"W4323066661","doi":"10.1093/bioadv/vbad023","title":"GPTree Cluster: phylogenetic tree cluster generator in the context of supertree inference","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Supertree; Phylogenetic tree; Computational phylogenetics; Tree (set theory); Context (archaeology); Phylogenetic network; Tree rearrangement; Cluster analysis; Inference; Biology; Computer science; Sister group; Python (programming language); Phylogenetics; Theoretical computer science; Artificial intelligence; Mathematics; Combinatorics; Genetics; Clade","score_opus":0.015122267526134965,"score_gpt":0.25754650968047427,"score_spread":0.2424242421543393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323066661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99406064,0.0030902762,0.00030168868,0.00031509777,0.0001998084,0.0003632829,0.00007165714,0.000006293392,0.0015912823],"genre_scores_gemma":[0.9939753,0.0034579297,0.0015215519,0.00072584185,0.00010399373,0.000059010148,0.000058400165,0.000013757846,0.00008426245],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987807,0.000054928743,0.00048622722,0.00017818561,0.0001920278,0.00030792423],"domain_scores_gemma":[0.99920225,0.00009797713,0.00014552021,0.00043468253,0.00007999103,0.000039554307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032119238,0.00019549539,0.000225774,0.00009348763,0.00007912346,0.000025733138,0.00044260293,0.00008949386,0.0000030741137],"category_scores_gemma":[0.0001264971,0.0001375376,0.0000906151,0.000269077,0.00015468459,0.000004612269,0.00020713212,0.0000691869,0.00002073144],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047936072,0.00038552706,0.2088951,0.00091643207,0.00040706337,0.00001042688,0.01718564,0.009968309,0.38382652,0.0019797029,0.014251543,0.36169437],"study_design_scores_gemma":[0.008734398,0.0031653112,0.2049778,0.00021841437,0.0001604028,0.0000539509,0.033702612,0.039083485,0.21488209,0.0023970555,0.490225,0.0023994958],"about_ca_topic_score_codex":0.000014912628,"about_ca_topic_score_gemma":0.00065327063,"teacher_disagreement_score":0.47597346,"about_ca_system_score_codex":0.0000075675944,"about_ca_system_score_gemma":0.00005467131,"threshold_uncertainty_score":0.56086206},"labels":[],"label_agreement":null},{"id":"W4323816133","doi":"10.1093/bioadv/vbad028","title":"Predicting phenotypes from novel genomic markers using deep learning","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Single-nucleotide polymorphism; Convolutional neural network; Biology; Computational biology; SNP; Pearson product-moment correlation coefficient; Genetics; Phenotype; DNA sequencing; Artificial intelligence; Genotype; Computer science; DNA; Statistics; Gene; Mathematics","score_opus":0.01358583109972697,"score_gpt":0.24077463066215105,"score_spread":0.22718879956242408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323816133","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9904574,0.0023285926,0.0053365617,0.000015831161,0.00034185173,0.00012349339,0.00005012442,0.00002572202,0.0013203853],"genre_scores_gemma":[0.96514153,0.0021251724,0.03204978,0.00007753421,0.00031671303,0.000010251866,0.00013988173,0.000029068022,0.000110087356],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990906,0.000012909749,0.00029262502,0.00018801393,0.00011658032,0.00029925304],"domain_scores_gemma":[0.9995099,0.000035785833,0.00016243254,0.00018589887,0.000047437905,0.000058546615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014592585,0.00016660664,0.00015241587,0.00005578075,0.00023516963,0.000039917817,0.0001758775,0.00007558219,0.000007074405],"category_scores_gemma":[0.000092300084,0.00016085993,0.000069563444,0.00012741635,0.00006263651,0.0000048223546,0.00022781391,0.00007570063,0.00002795962],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007931037,0.000022862541,0.074921206,0.00008077327,0.0002618687,0.0000014244823,0.0010849297,0.07128993,0.80809677,0.000045793877,0.00009239782,0.04402273],"study_design_scores_gemma":[0.0022358927,0.0006639165,0.09350401,0.00010819347,0.0001693406,0.000018737017,0.011887409,0.6917344,0.041432995,0.0006070693,0.15609986,0.001538197],"about_ca_topic_score_codex":0.000030558895,"about_ca_topic_score_gemma":0.000033960343,"teacher_disagreement_score":0.7666638,"about_ca_system_score_codex":0.00001546811,"about_ca_system_score_gemma":0.000030923326,"threshold_uncertainty_score":0.6559677},"labels":[],"label_agreement":null},{"id":"W4324045291","doi":"10.1093/bioadv/vbad030","title":"scAnnotate: an automated cell-type annotation tool for single-cell RNA-sequencing data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Universities Space Research Association; Genome British Columbia; Western Canada Research Grid; Compute Canada","keywords":"Annotation; Dropout (neural networks); Computer science; Artificial intelligence; Data mining; Computational biology; Machine learning; Biology","score_opus":0.04813062175676968,"score_gpt":0.3011984307456495,"score_spread":0.2530678089888798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324045291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97256625,0.00072819396,0.021765104,0.000050772043,0.0011448304,0.0007123028,0.0005672602,0.00048715167,0.0019781515],"genre_scores_gemma":[0.9155199,0.00082132255,0.07081461,0.00030208836,0.00033412536,0.000033062468,0.011587879,0.00007044854,0.0005165929],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99862546,0.000023673632,0.0004650101,0.0003166486,0.00018364555,0.0003855797],"domain_scores_gemma":[0.9988349,0.00003517106,0.00020335811,0.00065655494,0.00018183335,0.00008815886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031127667,0.00021942932,0.00018132896,0.000091063055,0.00019348325,0.000112126065,0.00050709,0.00014001442,0.0000044253948],"category_scores_gemma":[0.000111907655,0.00021184882,0.000053405314,0.00029128394,0.00006293596,0.00011139549,0.0001085606,0.00006687319,0.000033601795],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013139448,0.000084517706,0.00019751546,0.00040269506,0.000019770745,0.000002026087,0.0003822964,0.005181468,0.9761408,0.000017699143,0.0036817766,0.013758044],"study_design_scores_gemma":[0.0011866597,0.0008768142,0.000064876,0.000035759138,0.000041799158,0.00000707563,0.000932672,0.44087887,0.50168747,0.00007162101,0.05367381,0.0005425858],"about_ca_topic_score_codex":0.000009809046,"about_ca_topic_score_gemma":0.00002022999,"teacher_disagreement_score":0.47445336,"about_ca_system_score_codex":0.000029398958,"about_ca_system_score_gemma":0.0001622164,"threshold_uncertainty_score":0.8638944},"labels":[],"label_agreement":null},{"id":"W4327575955","doi":"10.1093/bioadv/vbad031","title":"Motif elucidation in ChIP-seq datasets with a knockout control","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of New Brunswick; Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; University of Toronto; Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Research, Innovation and Science; Princess Margaret Cancer Foundation","keywords":"Chromatin immunoprecipitation; Motif (music); Computational biology; Computer science; Transcription factor; Chromatin; Biology; Artificial intelligence; Genetics; Gene; Promoter; Gene expression","score_opus":0.0042766906147950635,"score_gpt":0.22518562408588258,"score_spread":0.2209089334710875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327575955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9900674,0.00026712083,0.007055741,0.000120759025,0.00012561648,0.00034529038,0.00048180073,0.00003878125,0.0014974613],"genre_scores_gemma":[0.99008197,0.00065378967,0.0058166515,0.0001787344,0.00006166493,0.000037180267,0.003037124,0.000019334402,0.000113549206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991879,0.000013165655,0.00027735712,0.0001504061,0.00012509461,0.00024606244],"domain_scores_gemma":[0.99947876,0.000013091186,0.00012860673,0.00029903656,0.000029242228,0.000051243573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016001775,0.00013856043,0.00013397532,0.00008580381,0.000056072608,0.000037347105,0.00018230843,0.000067755056,0.000005117874],"category_scores_gemma":[0.00003922573,0.000115825795,0.000028315178,0.00019587108,0.00004427213,0.000021177804,0.0000643268,0.000058743208,0.000051298386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016335916,0.0007933075,0.101352565,0.0023497406,0.00069408986,0.00010250315,0.0033307085,0.26554316,0.27529415,0.004241362,0.02590027,0.31876454],"study_design_scores_gemma":[0.011524537,0.0019382907,0.07502273,0.0002871249,0.000093109964,0.00009103747,0.003505525,0.6022985,0.03932766,0.0013657341,0.2622573,0.0022884673],"about_ca_topic_score_codex":0.000004874995,"about_ca_topic_score_gemma":0.00013401308,"teacher_disagreement_score":0.3367553,"about_ca_system_score_codex":0.000014054074,"about_ca_system_score_gemma":0.000049216265,"threshold_uncertainty_score":0.4723239},"labels":[],"label_agreement":null},{"id":"W4377047057","doi":"10.1093/bioadv/vbad059","title":"A self-knowledge distillation-driven CNN-LSTM model for predicting disease outcomes using longitudinal microbiome data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Western University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Manitoba Medical Service Foundation","keywords":"Microbiome; Computer science; Artificial intelligence; Convolutional neural network; Deep learning; Inference; Machine learning; Data mining; Bioinformatics; Biology","score_opus":0.06966997547000747,"score_gpt":0.36256148296631757,"score_spread":0.2928915074963101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377047057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70183384,0.002225309,0.28677267,0.00032555137,0.00090628205,0.0017324548,0.005578785,0.0002953677,0.0003297068],"genre_scores_gemma":[0.78012264,0.0011028548,0.21014698,0.00015172079,0.00036906535,0.00004759654,0.0074183005,0.00006654538,0.0005743014],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873865,0.000012822768,0.00043435823,0.00031175598,0.00009418423,0.0004082136],"domain_scores_gemma":[0.998899,0.00003705834,0.00020530062,0.0005980803,0.00010657278,0.0001539772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002100143,0.00020959665,0.00020891376,0.00009990302,0.0003011487,0.000058016332,0.0004053776,0.000083848885,0.0000017907686],"category_scores_gemma":[0.00012115742,0.00018839506,0.000087158754,0.0001733066,0.00005671951,0.000056593042,0.00040754705,0.000057145993,0.000019894409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008205797,0.001075722,0.63933355,0.017006204,0.0013572397,0.000012475107,0.0054533947,0.13486457,0.14884223,0.0016315681,0.029324817,0.020277657],"study_design_scores_gemma":[0.00052584335,0.000043147298,0.004685589,0.00004676781,0.00006359712,0.000004205032,0.000113678994,0.97559947,0.00020816222,0.00006748047,0.018382523,0.0002595408],"about_ca_topic_score_codex":0.0000025023742,"about_ca_topic_score_gemma":0.000035560864,"teacher_disagreement_score":0.8407349,"about_ca_system_score_codex":0.000035041292,"about_ca_system_score_gemma":0.00029655886,"threshold_uncertainty_score":0.76825273},"labels":[],"label_agreement":null},{"id":"W4379276041","doi":"10.1093/bioadv/vbad068","title":"DataCurator.jl: efficient, portable and reproducible validation, curation and transformation of large heterogeneous datasets using human-readable recipes compiled into machine-verifiable templates","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Computer science; Executable; Scalability; Python (programming language); Preprocessor; Workflow; Data mining; Verifiable secret sharing; Data curation; Database; Programming language","score_opus":0.09799458101637326,"score_gpt":0.40687124975629274,"score_spread":0.3088766687399195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379276041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9373771,0.00082737015,0.05807723,0.00011234595,0.00054702087,0.0006436531,0.001797902,0.0001407036,0.00047669408],"genre_scores_gemma":[0.9800448,0.00023462376,0.015821965,0.00003989186,0.000030730927,0.000009660789,0.0036834716,0.000012726531,0.00012215022],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704266,0.000074515665,0.0012135962,0.00051566365,0.0008547709,0.0002988273],"domain_scores_gemma":[0.99782497,0.00026922725,0.0006319826,0.0009906247,0.0001928415,0.0000903447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050232736,0.00017910471,0.00032096118,0.0005057193,0.0007010265,0.0005820518,0.00041488116,0.000043654243,0.00003767332],"category_scores_gemma":[0.0006414028,0.00014275716,0.00003329574,0.0011175342,0.000111850946,0.0028055634,0.00034516165,0.000066440094,0.00003320528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003296826,0.00081770786,0.034970317,0.0038546256,0.0003283104,0.0000243926,0.029612655,0.6428764,0.018019566,0.018547082,0.060974076,0.18964519],"study_design_scores_gemma":[0.0005320617,0.000065654225,0.00039121383,0.000082563696,0.00003070918,0.0000128802085,0.0030100006,0.93604714,0.008890735,0.0026501524,0.048041258,0.0002456584],"about_ca_topic_score_codex":0.000091745365,"about_ca_topic_score_gemma":0.00006470878,"teacher_disagreement_score":0.2931707,"about_ca_system_score_codex":0.000020375364,"about_ca_system_score_gemma":0.000032776177,"threshold_uncertainty_score":0.58214676},"labels":[],"label_agreement":null},{"id":"W4380867105","doi":"10.1093/bioadv/vbad072","title":"GDockScore: a graph-based protein–protein docking scoring function","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of New Brunswick","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada","keywords":"Docking (animal); Computer science; Macromolecular docking; Graph; Protein–ligand docking; Artificial intelligence; Machine learning; Computational biology; Virtual screening; Theoretical computer science; Protein structure; Bioinformatics; Drug discovery; Biology; Biochemistry","score_opus":0.00998602961376684,"score_gpt":0.23053972378863127,"score_spread":0.22055369417486442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380867105","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7929319,0.0016039665,0.19329056,0.00025859632,0.0009797278,0.0016962647,0.00006644515,0.00038916737,0.008783329],"genre_scores_gemma":[0.9818309,0.00016190292,0.016013611,0.00037937038,0.00037962472,0.00018929093,0.00043603807,0.00004440857,0.00056485663],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99843526,0.000020079404,0.0005394026,0.00022264261,0.00026789782,0.0005147001],"domain_scores_gemma":[0.9990362,0.000012135691,0.0002819919,0.00045867305,0.000088775836,0.0001222292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036332605,0.00026804296,0.00019891719,0.00017606613,0.00026451604,0.000106492305,0.00027924654,0.00016594787,0.000014849127],"category_scores_gemma":[0.000055927634,0.0002451797,0.00014341391,0.00047123013,0.00009271537,0.000045426616,0.0001439165,0.00015207526,0.00013619578],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011379162,0.00024415407,0.0029952019,0.0032183067,0.00049378834,0.000021169624,0.00081487646,0.09871135,0.25091472,0.009083945,0.012543099,0.6198215],"study_design_scores_gemma":[0.0044047665,0.0021846143,0.0015418637,0.0009808973,0.000101639314,0.000025889816,0.0017699937,0.28574187,0.15832594,0.013882973,0.528308,0.00273158],"about_ca_topic_score_codex":0.000004188146,"about_ca_topic_score_gemma":0.000016474454,"teacher_disagreement_score":0.6170899,"about_ca_system_score_codex":0.000019712352,"about_ca_system_score_gemma":0.00008931897,"threshold_uncertainty_score":0.99981374},"labels":[],"label_agreement":null},{"id":"W4384397972","doi":"10.1093/bioadv/vbad091","title":"Measuring the relative contribution to predictive power of modern nucleotide substitution modeling approaches","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Substitution (logic); Predictive power; Model selection; Inference; Statistical model; Set (abstract data type); Computer science; Mixture model; Bayesian probability; Nucleotide; Probabilistic logic; Phylogenetic tree; Bayesian inference; Range (aeronautics); Selection (genetic algorithm); Computational biology; Econometrics; Mathematics; Artificial intelligence; Biology; Genetics; Engineering; Physics","score_opus":0.03347243952663514,"score_gpt":0.23591228002251383,"score_spread":0.20243984049587868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384397972","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8368408,0.0014766443,0.16012654,0.00008789837,0.00012530778,0.00032856932,0.00005723048,0.000009670134,0.00094734126],"genre_scores_gemma":[0.99681,0.0004429459,0.00258692,0.000029635881,0.000039152776,0.000031919397,0.00003237326,0.00000781298,0.000019247998],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992604,0.0000189392,0.00026447728,0.00012411716,0.00015069697,0.00018135754],"domain_scores_gemma":[0.9995013,0.000021137184,0.00010732125,0.00019356098,0.00014029648,0.000036423255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027259032,0.00011050773,0.0001224851,0.000046315938,0.00015015999,0.0000127713465,0.00014369652,0.00004965788,4.8099304e-7],"category_scores_gemma":[0.00016455125,0.00008072394,0.00006223122,0.00015324191,0.0000687003,0.0000072230255,0.00012881625,0.00004721156,0.0000076446195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017670279,0.000030637515,0.0014362149,0.000060248436,0.00021935056,3.232475e-7,0.0039072563,0.9266742,0.055460233,0.0063033714,0.000069146576,0.005662336],"study_design_scores_gemma":[0.00067688804,0.00048989337,0.004002317,0.00008070789,0.000066184635,0.0000038976805,0.0028271212,0.9059312,0.07135876,0.00840276,0.0057479497,0.00041235454],"about_ca_topic_score_codex":0.0000020927216,"about_ca_topic_score_gemma":0.0000057593193,"teacher_disagreement_score":0.15996918,"about_ca_system_score_codex":0.000014261326,"about_ca_system_score_gemma":0.000029799143,"threshold_uncertainty_score":0.32918268},"labels":[],"label_agreement":null},{"id":"W4385520436","doi":"10.1093/bioadv/vbad097","title":"Toward computing attributions for dimensionality reduction techniques","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute; Université de Montréal; Montreal Heart Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données","keywords":"Dimensionality reduction; MNIST database; Python (programming language); Computer science; Artificial intelligence; Curse of dimensionality; Benchmark (surveying); Computation; Machine learning; Context (archaeology); Data mining; Reduction (mathematics); Pattern recognition (psychology); Deep learning; Algorithm; Mathematics","score_opus":0.03755720374093063,"score_gpt":0.2994449990200561,"score_spread":0.2618877952791255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385520436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5439645,0.00086762256,0.44927663,0.00078730955,0.0015086695,0.0010667301,0.00034513415,0.00045115835,0.0017322148],"genre_scores_gemma":[0.9220359,0.0006309971,0.075273804,0.00012453568,0.00040535108,0.000041272033,0.0012499522,0.000018631295,0.00021957592],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99933124,0.00000969488,0.0002479038,0.00012476089,0.00009075015,0.00019563969],"domain_scores_gemma":[0.99960846,0.00001763152,0.00008419302,0.00014166282,0.00010636481,0.000041687585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020618094,0.000100656755,0.00010268663,0.000043768556,0.00019139347,0.000023166953,0.00010100057,0.000079864156,0.0000016291608],"category_scores_gemma":[0.000065506276,0.00009331399,0.00008178645,0.00013234526,0.00005830791,0.000013826324,0.000043361506,0.000042002146,0.000008651689],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020976883,0.00015900326,0.0011116758,0.00071913295,0.00011260002,9.946591e-7,0.0006333692,0.0016070764,0.7668,0.004932312,0.018012192,0.20570189],"study_design_scores_gemma":[0.00053135323,0.00036980046,0.00053377135,0.00005878931,0.000025397763,0.000019282661,0.0007081786,0.014190547,0.62965983,0.0016278868,0.35186845,0.00040674556],"about_ca_topic_score_codex":0.0000028078425,"about_ca_topic_score_gemma":0.000002239465,"teacher_disagreement_score":0.37807137,"about_ca_system_score_codex":0.000012502812,"about_ca_system_score_gemma":0.000032943582,"threshold_uncertainty_score":0.3805234},"labels":[],"label_agreement":null},{"id":"W4387731260","doi":"10.1093/bioadv/vbad150","title":"Single-cell gene set scoring with nearest neighbor graph smoothed data (gssnng)","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of California, San Francisco; Cancer Research UK; McGill University","keywords":"Smoothing; Computer science; Visualization; Data mining; Graph; Significance analysis of microarrays; Python (programming language); Data visualization; Software; Sample size determination; Gene expression profiling; Computational biology; Gene expression; Gene; Theoretical computer science; Mathematics; Genetics; Biology; Statistics","score_opus":0.04017187588871809,"score_gpt":0.2551354453461746,"score_spread":0.2149635694574565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387731260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9703512,0.0018351314,0.02144184,0.000118884396,0.00066925114,0.0004522402,0.00057807966,0.00019505376,0.004358309],"genre_scores_gemma":[0.9512679,0.00319216,0.03968528,0.0004250296,0.00045911237,0.000026973468,0.0042221975,0.000095251184,0.00062607334],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986206,0.00001850461,0.00035705513,0.00033132907,0.00024697438,0.00042549073],"domain_scores_gemma":[0.9987286,0.00002608085,0.00016100638,0.000890567,0.00007217781,0.000121583405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018473885,0.0002548091,0.0002059328,0.000096614276,0.0001692551,0.00010473276,0.0006413082,0.000109120316,0.000008418778],"category_scores_gemma":[0.00004077726,0.00020920191,0.000056101104,0.00034685244,0.00012808698,0.000058082504,0.00022043537,0.00010360418,0.000050060724],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006764581,0.0003933682,0.020242404,0.0009974039,0.00026174056,0.000045357752,0.0010294828,0.005591715,0.90305877,0.00013488054,0.007356555,0.06021185],"study_design_scores_gemma":[0.0033994294,0.0015525005,0.0011187564,0.00017072428,0.00011856176,0.000050039383,0.001535868,0.023328722,0.61310637,0.00014777637,0.35395136,0.0015198827],"about_ca_topic_score_codex":0.000014392349,"about_ca_topic_score_gemma":0.00008741119,"teacher_disagreement_score":0.3465948,"about_ca_system_score_codex":0.000010498942,"about_ca_system_score_gemma":0.000074324445,"threshold_uncertainty_score":0.85310066},"labels":[],"label_agreement":null},{"id":"W4388643693","doi":"10.1093/bioadv/vbad162","title":"aaHash: recursive amino acid sequence hashing","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Dynamic perfect hashing; Hash function; Computer science; String (physics); Universal hashing; Context (archaeology); K-independent hashing; Theoretical computer science; Hash table; Algorithm; Locality-sensitive hashing; Double hashing; Biology; Mathematics; Programming language","score_opus":0.02459884249832153,"score_gpt":0.27694233884263164,"score_spread":0.25234349634431014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388643693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9800145,0.0048093786,0.0021261242,0.00033935986,0.0008613028,0.00032638898,0.00014302591,0.000048577487,0.011331368],"genre_scores_gemma":[0.9738334,0.007729465,0.016730893,0.00043323473,0.00027613886,0.000044507495,0.00017340967,0.000026263948,0.0007526787],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990846,0.000012862121,0.000264439,0.00017851763,0.0001388048,0.00032081225],"domain_scores_gemma":[0.99942714,0.000018072808,0.00012520338,0.0002846505,0.00007615861,0.00006877628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015593716,0.00016236925,0.000142542,0.00005902452,0.0001705908,0.000040475716,0.00024307182,0.00007459406,0.000004794247],"category_scores_gemma":[0.000111803056,0.00014709512,0.00007099761,0.0001834722,0.00010227752,0.0000056616277,0.00018611745,0.000059032445,0.0001192867],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008225313,0.00004997134,0.0058194236,0.00030457388,0.0002411784,0.000013977869,0.0026036226,0.0021256583,0.78771687,0.0022625562,0.014998084,0.18378183],"study_design_scores_gemma":[0.00076798676,0.000532195,0.003881132,0.00006320468,0.00003551203,0.00003283452,0.0034790148,0.002619937,0.24316697,0.0028611172,0.7417176,0.00084249885],"about_ca_topic_score_codex":0.0000029023738,"about_ca_topic_score_gemma":0.00001345742,"teacher_disagreement_score":0.7267195,"about_ca_system_score_codex":0.000011445625,"about_ca_system_score_gemma":0.00004772931,"threshold_uncertainty_score":0.59983647},"labels":[],"label_agreement":null},{"id":"W4388928478","doi":"10.1093/bioadv/vbad166","title":"Adversarial training improves model interpretability in single-cell RNA-seq analysis","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Lunenfeld-Tanenbaum Research Institute; University Health Network; University of Toronto; Sinai Health System; University of Waterloo","funders":"","keywords":"Interpretability; Robustness (evolution); Machine learning; Computer science; Artificial intelligence; Classifier (UML); Data mining; Biology; Gene","score_opus":0.023290461848573484,"score_gpt":0.24994314314055938,"score_spread":0.2266526812919859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388928478","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.949392,0.00027712568,0.04497312,0.000048394315,0.00032785925,0.0002075745,0.00006554185,0.00006266032,0.0046456903],"genre_scores_gemma":[0.98747617,0.00024175098,0.011605913,0.0001161604,0.000073201474,0.000016702743,0.00023571595,0.000016856764,0.00021754632],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986461,0.000025336096,0.0005237252,0.00026110915,0.00017333202,0.00037038952],"domain_scores_gemma":[0.9993692,0.000030436628,0.00014067492,0.00032535664,0.000050667408,0.00008367641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003012273,0.00020496451,0.00029334493,0.0002249773,0.00006713717,0.000047716894,0.00026642988,0.00014628247,0.0000059603076],"category_scores_gemma":[0.000097530065,0.00019396399,0.00021308962,0.0005989606,0.00009526016,0.000038395145,0.00008761912,0.000117101576,0.0000107046035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041642794,0.00030558693,0.0067220475,0.0003336331,0.00029986736,0.0000044382477,0.006948936,0.17582446,0.735035,0.00009353106,0.00020980647,0.073806286],"study_design_scores_gemma":[0.0012001403,0.00028566035,0.00046351936,0.000023381906,0.00013145429,0.000001112419,0.0021634316,0.920497,0.07108972,0.00040488582,0.00322427,0.0005153905],"about_ca_topic_score_codex":0.000018800123,"about_ca_topic_score_gemma":0.00026677246,"teacher_disagreement_score":0.74467254,"about_ca_system_score_codex":0.000029380957,"about_ca_system_score_gemma":0.0000785763,"threshold_uncertainty_score":0.7909622},"labels":[],"label_agreement":null},{"id":"W4391244160","doi":"10.1093/bioadv/vbae010","title":"MMDRP: drug response prediction and biomarker discovery using multi-modal deep learning","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Ministry of Colleges and Universities","keywords":"Biomarker discovery; Modal; Drug discovery; Deep learning; Biomarker; Artificial intelligence; Computer science; Drug response; Machine learning; Drug; Computational biology; Medicine; Biology; Bioinformatics; Pharmacology; Proteomics; Chemistry","score_opus":0.02440852627287932,"score_gpt":0.31780439474983746,"score_spread":0.29339586847695814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391244160","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17930573,0.0025082843,0.8168214,0.0001312208,0.00074338546,0.00012637564,0.0000110126575,0.0002263432,0.00012622752],"genre_scores_gemma":[0.39480096,0.00020936537,0.6046771,0.00005500869,0.000051594725,0.000008508692,0.000008702639,0.000013900696,0.00017487435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986083,0.00017896778,0.00038385057,0.00025953812,0.00033119516,0.0002381836],"domain_scores_gemma":[0.9987877,0.0007859753,0.00010042014,0.0001999589,0.000048769954,0.000077164645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010417445,0.00017398439,0.00014769587,0.00027830366,0.00021585965,0.00089875597,0.00026520566,0.00004062354,0.000002073873],"category_scores_gemma":[0.00022868051,0.00015230129,0.0000612899,0.00049056567,0.000087364206,0.0060484842,0.00030000394,0.00016629127,0.000013383286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016106197,0.00006057978,0.0014014835,0.00059585174,0.00009329284,0.000035890225,0.009265445,0.25726148,0.0019300018,0.0132447425,0.000062676314,0.7158875],"study_design_scores_gemma":[0.00017870779,0.000040151703,0.004007437,0.00012185381,0.000009785033,0.000060467723,0.00030492098,0.98801225,0.00024164296,0.0013092653,0.005535138,0.0001783604],"about_ca_topic_score_codex":0.0000057814905,"about_ca_topic_score_gemma":0.0000028055645,"teacher_disagreement_score":0.7307508,"about_ca_system_score_codex":0.000088954344,"about_ca_system_score_gemma":0.00011177631,"threshold_uncertainty_score":0.8666724},"labels":[],"label_agreement":null},{"id":"W4391463569","doi":"10.1093/bioadv/vbae016","title":"HiTaxon: a hierarchical ensemble framework for taxonomic classification of short reads","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ministry of Agriculture, Food and Rural Affairs; University of Toronto; Compute Canada; Canada Foundation for Innovation; Ontario Ministry of Agriculture, Food and Rural Affairs; Government of Ontario","keywords":"Metagenomics; Biological classification; Computer science; Taxonomy (biology); Taxonomic rank; Microbiome; Key (lock); Artificial intelligence; Taxon; Data mining; Machine learning; Biology; Bioinformatics; Evolutionary biology; Ecology; Genetics","score_opus":0.026361272046267495,"score_gpt":0.29361646681389775,"score_spread":0.26725519476763027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391463569","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4018608,0.018612314,0.5706702,0.0003444573,0.0009782679,0.00078204623,0.00025998082,0.000021767299,0.0064701843],"genre_scores_gemma":[0.84320974,0.0017629054,0.15455538,0.00004662148,0.0001970273,0.00008471179,0.00005746886,0.00001344935,0.00007271062],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992472,0.000008119995,0.00033335196,0.00016330046,0.00007733761,0.00017070367],"domain_scores_gemma":[0.9995387,0.00006656922,0.000061653394,0.00023261127,0.000058601352,0.000041868243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000141891,0.0001242131,0.00015225794,0.000047577792,0.000055089447,0.000027071887,0.00014154053,0.00010442934,0.000002376307],"category_scores_gemma":[0.000079766425,0.00010789053,0.00010791846,0.000068910595,0.00009176358,0.000003574525,0.000056741184,0.00005690727,0.0000043243317],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023904942,0.0000966485,0.0016054282,0.001454266,0.0003822776,8.1895325e-7,0.00059221796,0.00042852003,0.46645382,0.1269068,0.0047331555,0.397107],"study_design_scores_gemma":[0.00027049007,0.0008388154,0.0020254327,0.00015907615,0.000080502046,0.00001359548,0.00070219836,0.015426178,0.11606308,0.019446323,0.84449184,0.00048246144],"about_ca_topic_score_codex":7.2812793e-7,"about_ca_topic_score_gemma":0.000005240627,"teacher_disagreement_score":0.8397587,"about_ca_system_score_codex":0.000010677235,"about_ca_system_score_gemma":0.00006375611,"threshold_uncertainty_score":0.43996483},"labels":[],"label_agreement":null},{"id":"W4394762701","doi":"10.1093/bioadv/vbae047","title":"Text-mining-based feature selection for anticancer drug response prediction","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Stem Cell Network","keywords":"Feature selection; Pharmacogenomics; Machine learning; Computer science; Artificial intelligence; Feature (linguistics); Drug response; Selection (genetic algorithm); Support vector machine; Data mining; Bioinformatics; Drug; Biology","score_opus":0.012497927457812086,"score_gpt":0.3089335441867941,"score_spread":0.296435616728982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394762701","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066945325,0.0008820697,0.98779917,0.0020329505,0.0013884334,0.00034036045,0.000056746598,0.00046499635,0.0003407518],"genre_scores_gemma":[0.10489742,0.000036259607,0.89389396,0.00038641642,0.00019659146,0.00010603047,0.000028068978,0.000016971351,0.00043827604],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883604,0.00007398161,0.00028454215,0.0002367538,0.00033865683,0.00023000555],"domain_scores_gemma":[0.9982146,0.0013093012,0.00009175432,0.00019689543,0.00012635907,0.00006107614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009291839,0.00015234688,0.00013349889,0.00025424277,0.00016354704,0.00041299997,0.00031922714,0.000049388767,0.000004282332],"category_scores_gemma":[0.00024639373,0.0001330383,0.0000929462,0.0007104487,0.00004079276,0.0019997873,0.000053606356,0.00010668735,0.000015941809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045273095,0.00006970414,0.00036405952,0.0009971439,0.000069112735,0.0000031100947,0.002966373,0.40793666,0.00040715918,0.031688306,0.02560291,0.5294427],"study_design_scores_gemma":[0.00018849329,0.00010577802,0.0005963061,0.000107312255,0.000009525088,0.000008770433,0.000053393105,0.8823998,0.0013582014,0.0027814768,0.11225419,0.00013676021],"about_ca_topic_score_codex":9.27258e-7,"about_ca_topic_score_gemma":0.000003831843,"teacher_disagreement_score":0.529306,"about_ca_system_score_codex":0.00012521917,"about_ca_system_score_gemma":0.00036012413,"threshold_uncertainty_score":0.54251444},"labels":[],"label_agreement":null},{"id":"W4396722621","doi":"10.1093/bioadv/vbae066","title":"Network depth affects inference of gene sets from bacterial transcriptomes using denoising autoencoders","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Artificial intelligence; Transcriptome; Noise reduction; Pattern recognition (psychology); Computer science; Gene; Computational biology; Biology; Gene expression; Genetics","score_opus":0.015222515311411207,"score_gpt":0.2686701019971908,"score_spread":0.2534475866857796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396722621","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5132156,0.016127588,0.46615663,0.00003566905,0.002200613,0.00036551463,0.00022122773,0.00006540243,0.0016117392],"genre_scores_gemma":[0.8513198,0.0009498758,0.14664863,0.00013138245,0.0005101551,0.0000066617204,0.00038013296,0.00003056109,0.00002282905],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986593,0.000026310378,0.0005412242,0.00019946594,0.00019086865,0.00038281124],"domain_scores_gemma":[0.9993006,0.00005432719,0.000193578,0.00030511196,0.000049867645,0.00009650619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020425701,0.000259174,0.00028750338,0.000066033346,0.00010038983,0.0001269845,0.00026175028,0.0001878307,0.000021120019],"category_scores_gemma":[0.000025253034,0.00023097952,0.00013291798,0.00018309882,0.00012387017,0.00006470136,0.000079417674,0.00012266867,0.000008976956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054886274,0.00013138444,0.002519509,0.0025293967,0.001190834,0.00002203593,0.005255109,0.22404811,0.49910572,0.0019106945,0.006271606,0.25646675],"study_design_scores_gemma":[0.0014440906,0.0006544987,0.00080487033,0.0011466147,0.00029847,0.000053022653,0.0009210812,0.80719703,0.11106257,0.004076639,0.07082437,0.0015167422],"about_ca_topic_score_codex":0.00001751277,"about_ca_topic_score_gemma":0.000048811013,"teacher_disagreement_score":0.58314896,"about_ca_system_score_codex":0.000023603332,"about_ca_system_score_gemma":0.00016568259,"threshold_uncertainty_score":0.94190717},"labels":[],"label_agreement":null},{"id":"W4398222897","doi":"10.1093/bioadv/vbae069","title":"Biology’s transformation: from observation through experiment to computation","year":2024,"lang":"en","type":"editorial","venue":"Bioinformatics Advances","topic":"Philosophy and History of Science","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto","keywords":"Transformation (genetics); Computation; Biology; Computer science; Computational biology; Algorithm; Genetics","score_opus":0.05479374890839916,"score_gpt":0.30229577410893804,"score_spread":0.24750202520053888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398222897","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001102597,0.0029205014,0.005726336,0.00068065315,0.8923918,0.00039424683,0.0017504018,0.00021533543,0.09581045],"genre_scores_gemma":[0.0023025826,0.00073226925,0.020823916,0.00076601934,0.9677932,0.00017300392,0.005635563,0.0000477523,0.0017256732],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841857,0.000015054401,0.0006236188,0.00023428556,0.0004953339,0.00021316131],"domain_scores_gemma":[0.9991777,0.00016217868,0.00022980169,0.00016886414,0.00019718282,0.000064283115],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001332938,0.00027890923,0.00030493436,0.00013403343,0.00040405028,0.0003857184,0.00033232957,0.00017487996,0.00017943454],"category_scores_gemma":[0.00004433615,0.00023831421,0.00009844779,0.00007069499,0.00023789126,0.0018532677,0.000043302938,0.0002635821,0.0008623272],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015331963,0.000019218338,8.774052e-8,0.00022166088,0.000025158357,5.2435706e-7,0.10922921,0.00007081217,0.000008009594,0.05664724,0.8255416,0.008221118],"study_design_scores_gemma":[0.000121058074,0.00016001056,1.902269e-7,0.0002130783,0.000029463534,9.293236e-8,0.0030510298,0.0007656956,0.00003720849,0.03485645,0.9604546,0.00031110976],"about_ca_topic_score_codex":0.00013504867,"about_ca_topic_score_gemma":0.00019345376,"teacher_disagreement_score":0.13491298,"about_ca_system_score_codex":0.0001563471,"about_ca_system_score_gemma":0.000120286284,"threshold_uncertainty_score":0.9999156},"labels":[],"label_agreement":null},{"id":"W4399880261","doi":"10.1093/bioadv/vbae095","title":"SlowMoMan: a web app for discovery of important features along user-drawn trajectories in 2D embeddings","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Embedding; Computer science; Discriminative model; Manifold (fluid mechanics); Nonlinear dimensionality reduction; Inference; sort; Code (set theory); Path (computing); Space (punctuation); Theoretical computer science; Information retrieval; Data mining; Artificial intelligence; Programming language; Dimensionality reduction","score_opus":0.007143956142107216,"score_gpt":0.25038757708409864,"score_spread":0.24324362094199142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399880261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97767013,0.012223674,0.008005988,0.00006556477,0.0007877859,0.00041207855,0.00029334245,0.000035838948,0.0005055733],"genre_scores_gemma":[0.9878786,0.0015065313,0.00976717,0.00006356206,0.00015978912,0.000040666662,0.00017952936,0.000024944893,0.00037917614],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989084,0.000007936298,0.00052035105,0.00018500569,0.00013210284,0.00024618092],"domain_scores_gemma":[0.9995823,0.000042300024,0.000109272594,0.0001833085,0.00004434934,0.00003849458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001623974,0.00018776408,0.00023198508,0.00009347819,0.00005490728,0.00012381315,0.00017708614,0.00012484292,0.0000017872851],"category_scores_gemma":[0.00006201919,0.00015492084,0.00014937134,0.00014852222,0.00011922262,0.000063123574,0.000033628017,0.00008298066,8.146916e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009863998,0.0003240469,0.021965872,0.0064562703,0.0003614136,0.000019506615,0.00549736,0.0008612277,0.9161561,0.0100671975,0.0046021715,0.03270241],"study_design_scores_gemma":[0.0018629966,0.0011245423,0.0016390148,0.0006613019,0.000099734054,0.000041926072,0.0026203224,0.0128717,0.6920202,0.001093035,0.28501245,0.000952814],"about_ca_topic_score_codex":0.000022760349,"about_ca_topic_score_gemma":0.00041798802,"teacher_disagreement_score":0.28041026,"about_ca_system_score_codex":0.000015574687,"about_ca_system_score_gemma":0.00015896889,"threshold_uncertainty_score":0.6317488},"labels":[],"label_agreement":null},{"id":"W4400638857","doi":"10.1093/bioadv/vbae098","title":"loco-pipe: an automated pipeline for population genomics with low-coverage whole-genome sequencing","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of General Medical Sciences; North Pacific Research Board","keywords":"Pipeline (software); Genomics; Computer science; Streamlines, streaklines, and pathlines; Population; Set (abstract data type); Pipeline transport; Genome; Computational biology; Biology; Engineering; Genetics; Medicine; Operating system; Gene; Programming language","score_opus":0.0092613412800591,"score_gpt":0.2608134375166964,"score_spread":0.25155209623663727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400638857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9116266,0.0056423643,0.080173194,0.00006854038,0.00038183277,0.0007597925,0.00066868326,0.000108181186,0.00057082076],"genre_scores_gemma":[0.96747196,0.0008364073,0.029318653,0.00018496752,0.00034499812,0.0000645148,0.0015041109,0.000047182915,0.0002271847],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893713,0.000011453753,0.00037345637,0.0002661882,0.000115744246,0.00029600266],"domain_scores_gemma":[0.99940693,0.000018779692,0.00011430249,0.0002809017,0.00009993196,0.00007912492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001694038,0.00023328346,0.00019292647,0.00007000207,0.00015689636,0.00012457425,0.00016403056,0.0000947022,0.000002204485],"category_scores_gemma":[0.000021581558,0.00019127021,0.00007084332,0.00010885278,0.000049891143,0.00001791621,0.00005706149,0.0000572389,0.0000086683185],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029856493,0.000073154835,0.0009404434,0.001458185,0.00029022485,0.0000072018943,0.0013702988,0.0730907,0.8631619,0.0005522884,0.0005150734,0.058241922],"study_design_scores_gemma":[0.0014380964,0.0013173418,0.0017906582,0.00016770436,0.0001447618,0.00007244616,0.0010332225,0.5314842,0.04279692,0.000866928,0.4176296,0.0012581323],"about_ca_topic_score_codex":0.0000090129915,"about_ca_topic_score_gemma":0.000057920377,"teacher_disagreement_score":0.820365,"about_ca_system_score_codex":0.00005314536,"about_ca_system_score_gemma":0.000115894065,"threshold_uncertainty_score":0.7799773},"labels":[],"label_agreement":null},{"id":"W4400726464","doi":"10.1093/bioadv/vbae097","title":"Knowledge graph embeddings in the biomedical domain: are they useful? A look at link prediction, rule learning, and downstream polypharmacy tasks","year":2024,"lang":"en","type":"review","venue":"Bioinformatics Advances","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Engineering and Physical Sciences Research Council; UK Research and Innovation; Institute for Catastrophic Loss Reduction; Science and Technology Facilities Council; European Commission; Dell EMC; Accenture; Cisco Systems","keywords":"Computer science; Interpretability; Embedding; Machine learning; Artificial intelligence; Knowledge graph; Field (mathematics); Downstream (manufacturing); Graph; Data science; Theoretical computer science","score_opus":0.021973077866220783,"score_gpt":0.3223211017238577,"score_spread":0.3003480238576369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400726464","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016733491,0.9891195,0.0071534025,0.00020778086,0.0010957049,0.0010043929,0.00009886292,0.0003474573,0.0009561108],"genre_scores_gemma":[0.000031568503,0.9894068,0.009514823,0.000112647154,0.0003510161,0.00021826127,0.00011783122,0.00004431693,0.00020272394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962911,0.00028047324,0.0013834581,0.00067603315,0.0006287269,0.0007401815],"domain_scores_gemma":[0.9974239,0.0007137192,0.0008578463,0.000697356,0.00007001123,0.00023719604],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008858414,0.00079857185,0.0012144024,0.00076386513,0.00040103888,0.00046397216,0.0017340397,0.00034530557,0.0000068663344],"category_scores_gemma":[0.000104879495,0.0004711975,0.0004032169,0.0018479379,0.00041187377,0.0012641248,0.0010937877,0.0015092819,0.00014349396],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050641584,0.000049188195,0.000069338515,0.008036601,0.000079041674,0.000049590468,0.0023045752,0.000019705592,8.809108e-8,0.0011574134,0.002543922,0.98568547],"study_design_scores_gemma":[0.00027063783,0.000105660736,0.0000071650197,0.006511226,0.00015729791,0.00042814075,0.00024163743,0.005476393,3.145072e-7,0.0030825553,0.9832287,0.0004902993],"about_ca_topic_score_codex":0.0000023211815,"about_ca_topic_score_gemma":0.000021671984,"teacher_disagreement_score":0.98519516,"about_ca_system_score_codex":0.00014593275,"about_ca_system_score_gemma":0.00014724833,"threshold_uncertainty_score":0.999774},"labels":[],"label_agreement":null},{"id":"W4401200522","doi":"10.1093/bioadv/vbae108","title":"Investigating alignment-free machine learning methods for HIV-1 subtype classification","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"HIV Research and Treatment","field":"Immunology and Microbiology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Canada Research Chairs","keywords":"Human immunodeficiency virus (HIV); Computer science; Artificial intelligence; Machine learning; Virology; Computational biology; Medicine; Biology","score_opus":0.03916500014261359,"score_gpt":0.35511429207348705,"score_spread":0.31594929193087345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401200522","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010604684,0.14541195,0.8100829,0.0045063007,0.0024605345,0.0023377317,0.0011758268,0.0011005629,0.0223195],"genre_scores_gemma":[0.13393281,0.003342785,0.84517765,0.00019889403,0.00011778806,0.00054471777,0.0050592,0.00006224723,0.011563918],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991229,0.00008905561,0.0003017299,0.00014420727,0.000040083865,0.00030203388],"domain_scores_gemma":[0.9991268,0.00050598243,0.00008475493,0.00020315875,0.00004426946,0.0000350463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000499069,0.00013299241,0.00015402705,0.000108819564,0.00024113501,0.00006495871,0.00019273342,0.00008214828,0.00009755916],"category_scores_gemma":[0.0005314002,0.0001006079,0.000068341746,0.0001388681,0.000115056515,0.00031703597,0.00007257252,0.00018192458,0.0007416712],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038575155,0.000050373048,0.0016821116,0.0006464491,0.00031384622,0.0000011885453,0.0017434501,0.00006492704,0.04288044,0.0139463255,0.007234257,0.93139803],"study_design_scores_gemma":[0.00076889247,0.00025779367,0.00015998482,0.00008949241,0.00004254423,0.000016416634,0.0006686157,0.026546607,0.021622077,0.002522584,0.94713855,0.00016642903],"about_ca_topic_score_codex":0.0000062744725,"about_ca_topic_score_gemma":0.000005399063,"teacher_disagreement_score":0.93990433,"about_ca_system_score_codex":0.000056933495,"about_ca_system_score_gemma":0.00006894523,"threshold_uncertainty_score":0.95329297},"labels":[],"label_agreement":null},{"id":"W4402914764","doi":"10.1093/bioadv/vbae146","title":"Chronogram: an R package for data curation and analysis of infection and vaccination cohort studies","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"Medical Research Council; Francis Crick Institute; Cancer Research UK; Wellcome Trust; London School of Hygiene and Tropical Medicine","keywords":"Cohort; Vaccination; R package; Cohort study; Data curation; Biology; Data science; Environmental health; Computational biology; Medicine; Virology; Computer science; Internal medicine","score_opus":0.03960482596782377,"score_gpt":0.3467256947207792,"score_spread":0.3071208687529554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402914764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8213131,0.021413164,0.15609159,0.000051848237,0.0001673107,0.00052826677,0.00024706963,0.000025918496,0.00016177153],"genre_scores_gemma":[0.94895095,0.026958006,0.020285642,0.000025770836,0.00005891853,0.000037790793,0.0036469037,0.000010662987,0.000025342402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937046,0.000009362162,0.0003224775,0.0001405078,0.00006843695,0.00008874079],"domain_scores_gemma":[0.9994602,0.000027961472,0.00012136651,0.00027473122,0.00009037813,0.000025338592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033697934,0.00010311876,0.00017487528,0.00014049742,0.000071021175,0.000077197576,0.00006987804,0.000052242947,0.0000011648386],"category_scores_gemma":[0.00009255167,0.000083131024,0.00003410561,0.00018777925,0.000031506745,0.00020634731,0.000105176565,0.000026588626,2.1007786e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015035497,0.00012844383,0.057714056,0.006389934,0.008078814,2.569928e-7,0.004061079,0.00081897905,0.0111263525,0.004954223,0.0012426677,0.90533483],"study_design_scores_gemma":[0.0003883705,0.0006189602,0.030660383,0.00005001608,0.0014263204,0.0000067291962,0.0012597335,0.94067407,0.0062103067,0.00035537282,0.018072657,0.00027709722],"about_ca_topic_score_codex":0.0000053648214,"about_ca_topic_score_gemma":0.000057416953,"teacher_disagreement_score":0.9398551,"about_ca_system_score_codex":0.0000074262794,"about_ca_system_score_gemma":0.000019315246,"threshold_uncertainty_score":0.33899847},"labels":[],"label_agreement":null},{"id":"W4403924852","doi":"10.1093/bioadv/vbae168","title":"Population-aware permutation-based significance thresholds for genome-wide association studies","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Bundesministerium für Bildung und Forschung","keywords":"Genome-wide association study; Genetic association; Association (psychology); Population; Genetics; Permutation (music); Biology; Computational biology; Evolutionary biology; Single-nucleotide polymorphism; Medicine; Psychology; Genotype; Gene; Environmental health; Physics","score_opus":0.018915421484220853,"score_gpt":0.3156294565846542,"score_spread":0.2967140351004333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403924852","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49347258,0.0346657,0.45822456,0.006596334,0.0026652159,0.0020148132,0.00087693194,0.00023764196,0.0012462337],"genre_scores_gemma":[0.97061056,0.0012000817,0.024295932,0.00113302,0.00031096072,0.00024419755,0.0013046522,0.000024100433,0.0008764709],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989082,0.000032301854,0.00044274522,0.00020878924,0.00014206393,0.00026586952],"domain_scores_gemma":[0.99875885,0.00058756483,0.00021205128,0.00016515228,0.0002327724,0.000043624324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048829854,0.00015597242,0.00020994966,0.000068982205,0.00017443881,0.00005220452,0.00011413657,0.00013932746,0.000007064422],"category_scores_gemma":[0.0014585172,0.00013915419,0.00012422801,0.00012642532,0.000032159573,0.000022327864,0.000025443951,0.00005681261,0.000016209591],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001293182,0.00013118729,0.75351983,0.002628055,0.0013190111,0.0000021918347,0.0015054195,0.14099273,0.002677551,0.0017614771,0.062705114,0.03262812],"study_design_scores_gemma":[0.0014045477,0.00088878954,0.11428968,0.00018391163,0.00027298715,0.0000036442316,0.0031714176,0.18944876,0.0025730017,0.00883368,0.6776076,0.0013219997],"about_ca_topic_score_codex":0.0000043765313,"about_ca_topic_score_gemma":0.000046876008,"teacher_disagreement_score":0.63923013,"about_ca_system_score_codex":0.00012433478,"about_ca_system_score_gemma":0.00010205379,"threshold_uncertainty_score":0.56745434},"labels":[],"label_agreement":null},{"id":"W4404509197","doi":"10.1093/bioadv/vbae166","title":"The ISCB competency framework v. 3: a revised and extended standard for bioinformatics education and training","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Common Fund; National Human Genome Research Institute; UK Research and Innovation; European Commission; Government of Ontario; European Molecular Biology Laboratory; National Institutes of Health; Ontario Institute for Cancer Research","keywords":"Computer science; Bioinformatics; Computational biology; Biology","score_opus":0.015503383659866005,"score_gpt":0.32277806113022606,"score_spread":0.3072746774703601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404509197","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0570234,0.21475561,0.6853494,0.008034229,0.0053825574,0.0061489455,0.0009977024,0.00031976964,0.021988373],"genre_scores_gemma":[0.17180605,0.11861165,0.70445204,0.0015367899,0.0011690274,0.0003612273,0.00045954747,0.00008436285,0.0015193039],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983818,0.000022705555,0.00063441467,0.00018955814,0.00032906377,0.00044247493],"domain_scores_gemma":[0.99890715,0.00026694403,0.00012906548,0.00030272783,0.00017938443,0.00021470539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078314525,0.00023353087,0.00022575822,0.00009786788,0.0004160383,0.0004845984,0.0002455572,0.0001722445,0.000004586972],"category_scores_gemma":[0.0008353583,0.00015516151,0.00008462232,0.00015385608,0.0004640044,0.000060368147,0.00015860128,0.00017503308,0.000006115062],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007439554,0.00001786575,0.000032619166,0.0013252298,0.00006240343,2.6523267e-7,0.0017128736,0.0000026276768,0.00029189186,0.0092256935,0.0029449807,0.98430914],"study_design_scores_gemma":[0.0004766777,0.0009988354,0.0001214059,0.00048408058,0.00004874309,0.000049963845,0.009218093,0.035116456,0.0013302023,0.017064063,0.93467927,0.00041218963],"about_ca_topic_score_codex":0.0000010804737,"about_ca_topic_score_gemma":0.000009323525,"teacher_disagreement_score":0.983897,"about_ca_system_score_codex":0.000020415979,"about_ca_system_score_gemma":0.00046879158,"threshold_uncertainty_score":0.6327303},"labels":[],"label_agreement":null},{"id":"W4404647992","doi":"10.1093/bioadv/vbag121","title":"New algorithms for unsupervised cell clustering from scRNA-seq data","year":2024,"lang":"en","type":"preprint","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Misericordia Community Hospital","funders":"","keywords":"Cluster analysis; Computer science; Biclustering; Artificial intelligence; Data mining; Algorithm; Correlation clustering; CURE data clustering algorithm","score_opus":0.050223387224697366,"score_gpt":0.2958406344081931,"score_spread":0.2456172471834957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404647992","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016960151,0.0368357,0.92385143,0.00025219013,0.007178768,0.001454134,0.009415839,0.00015328651,0.0038985],"genre_scores_gemma":[0.022170074,0.009483367,0.937468,0.0004934275,0.0034448395,0.0000800349,0.024693118,0.0001702052,0.0019969374],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980888,0.000014442435,0.00066158664,0.0006409211,0.00022113217,0.00037312522],"domain_scores_gemma":[0.998126,0.00003477077,0.00022392548,0.0013652258,0.00008152114,0.00016860233],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017146877,0.0004544949,0.00040131173,0.000072907744,0.00009012114,0.0002678802,0.0013076555,0.00044768606,0.00001848448],"category_scores_gemma":[0.000043108073,0.0004256705,0.0002012579,0.000063226,0.0000517555,0.000021533951,0.002039894,0.00033020118,0.000030306175],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068899157,0.00028123875,0.00030259305,0.010990035,0.0011205189,0.000015915968,0.0021946093,0.012509798,0.10577121,0.00008962166,0.053471245,0.81256425],"study_design_scores_gemma":[0.0018080756,0.00028627203,0.000017740302,0.000601754,0.0003614875,0.0000071910817,0.0004701145,0.47068733,0.073326744,0.0040891096,0.44685304,0.0014911252],"about_ca_topic_score_codex":0.00016246989,"about_ca_topic_score_gemma":0.00016473501,"teacher_disagreement_score":0.8110731,"about_ca_system_score_codex":0.00002976118,"about_ca_system_score_gemma":0.00042594274,"threshold_uncertainty_score":0.9998195},"labels":[],"label_agreement":null},{"id":"W4405910570","doi":"10.1093/bioadv/vbae184","title":"Predicting CRISPR-Cas9 off-target effects in human primary cells using bidirectional LSTM with BERT embedding","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; National Research Council Canada; McGill University","funders":"National Research Council Canada","keywords":"CRISPR; Embedding; Primary (astronomy); Computer science; Computational biology; Biology; Artificial intelligence; Genetics; Gene; Physics","score_opus":0.004768933118316525,"score_gpt":0.2879238221660577,"score_spread":0.2831548890477412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405910570","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85684264,0.013832256,0.12482222,0.000012244741,0.00066270493,0.00027322827,0.000022931057,0.000085202024,0.003446573],"genre_scores_gemma":[0.9284951,0.00043013445,0.07025481,0.00006840391,0.0003490994,0.000027484259,0.000093391594,0.000045694716,0.00023586904],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990521,0.000012766456,0.00028746715,0.00020174251,0.00016958942,0.00027634396],"domain_scores_gemma":[0.9996699,0.000032158794,0.00005353951,0.00015545382,0.0000293112,0.0000596441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014979175,0.00018872932,0.00015903226,0.00012673798,0.0000896742,0.0000679433,0.000103575185,0.00008477353,0.0000052013993],"category_scores_gemma":[0.000018232498,0.00016599211,0.000054502256,0.00017520775,0.00003960133,0.00003495581,0.00006817904,0.00012635384,0.0000028448337],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005055763,0.000063576284,0.007573706,0.002587584,0.0001410722,0.00003208904,0.0006760165,0.2601697,0.7004493,0.000090602436,0.00036387178,0.027801892],"study_design_scores_gemma":[0.0006927984,0.000448217,0.0016143122,0.00085061806,0.000053024654,0.000102511905,0.00036406994,0.4145714,0.54290307,0.000080297934,0.037652373,0.00066732714],"about_ca_topic_score_codex":0.000008518764,"about_ca_topic_score_gemma":0.000018363395,"teacher_disagreement_score":0.15754627,"about_ca_system_score_codex":0.000042081614,"about_ca_system_score_gemma":0.000060921873,"threshold_uncertainty_score":0.67689615},"labels":[],"label_agreement":null},{"id":"W4406713780","doi":"10.1093/bioadv/vbae209","title":"<u>Imp</u>utation for <u>Li</u>pidomics and <u>Met</u>abolomics (ImpLiMet): a web-based application for optimization and method selection for missing data imputation","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; University of Toronto; McGill Genome Centre; National Research Council Canada; McGill University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Computer science; Mathematics; Statistics","score_opus":0.05619849722513385,"score_gpt":0.42300350110061274,"score_spread":0.3668050038754789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406713780","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017037433,0.00047243387,0.9950651,0.0002882147,0.00019883507,0.0025175784,0.001111414,0.00015106761,0.000024991916],"genre_scores_gemma":[0.0015957478,0.00014265177,0.9966095,0.00010434243,0.00012867077,0.0005600781,0.0008074139,0.000044539043,0.0000070238825],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984791,0.000045670826,0.0006849645,0.00038903317,0.00013951355,0.0002617026],"domain_scores_gemma":[0.9931763,0.0059265653,0.00033121777,0.00022196994,0.0002597127,0.00008427875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014761523,0.00023105802,0.00033161265,0.00019406578,0.00028980174,0.00033543745,0.00013611504,0.00014117315,0.0000016518302],"category_scores_gemma":[0.0022834057,0.00021196068,0.000052497704,0.00023787403,0.00006227684,0.0009175297,0.000039358558,0.000076287746,3.6112985e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013575997,0.000025978385,0.000019742667,0.0035158482,0.000039933653,3.4198752e-8,0.00020616845,0.0027386567,0.00041240195,0.19378905,0.00022517734,0.79889125],"study_design_scores_gemma":[0.00072823814,0.00018934622,0.0000044847807,0.0000869578,0.00017678078,0.000005528139,0.00010491179,0.67449385,0.0006671151,0.3198528,0.0035089483,0.00018101619],"about_ca_topic_score_codex":0.0000025659563,"about_ca_topic_score_gemma":0.000007178225,"teacher_disagreement_score":0.7987102,"about_ca_system_score_codex":0.000061071434,"about_ca_system_score_gemma":0.00014902445,"threshold_uncertainty_score":0.86435056},"labels":[],"label_agreement":null},{"id":"W4407174948","doi":"10.1093/bioadv/vbaf014","title":"Leveraging LASSO-based methodologies for enhanced SNP analysis in plant genomes","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph; Algoma University; Thompson Rivers University","funders":"Natural Sciences and Engineering Research Council of Canada; Thompson Rivers University","keywords":"Lasso (programming language); SNP; Computational biology; Genome; Biology; Genomic selection; Computer science; Genetics; Single-nucleotide polymorphism; Genotype; World Wide Web; Gene","score_opus":0.04697469140103604,"score_gpt":0.3454984677685396,"score_spread":0.29852377636750355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407174948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15973766,0.006634419,0.83175296,0.00031149937,0.00029023926,0.0002657744,0.00014645375,0.000037450962,0.0008235392],"genre_scores_gemma":[0.7325749,0.0011678668,0.26514935,0.00025570538,0.00007446617,0.00009283978,0.0005269164,0.0000106477555,0.00014730006],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899745,0.00005374996,0.0003976479,0.00020314343,0.00006998333,0.00027804408],"domain_scores_gemma":[0.99935645,0.0002796388,0.00010559766,0.00018212845,0.00004277821,0.00003338753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006693537,0.00013641907,0.00026751187,0.00021341842,0.000057153462,0.000035144883,0.00014183756,0.00011230799,0.000007853565],"category_scores_gemma":[0.00032066222,0.00011484865,0.0001691053,0.00029919515,0.000040992843,0.0000101695005,0.000039682982,0.00005762469,0.000004462729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033854158,0.00014602579,0.078680575,0.0016542955,0.0030942392,0.0000075542903,0.0027393072,0.5039003,0.063318945,0.0019932594,0.0053364905,0.33879048],"study_design_scores_gemma":[0.0013697258,0.0006313443,0.025558023,0.00010169731,0.0005710262,0.0000047252506,0.002952048,0.5883162,0.08380283,0.004849144,0.2907289,0.0011143502],"about_ca_topic_score_codex":0.000006801452,"about_ca_topic_score_gemma":0.000098213575,"teacher_disagreement_score":0.57283723,"about_ca_system_score_codex":0.000030256442,"about_ca_system_score_gemma":0.00007648782,"threshold_uncertainty_score":0.4683392},"labels":[],"label_agreement":null},{"id":"W4407603264","doi":"10.1093/bioadv/vbag179","title":"CycleMix: Gaussian Mixture Modeling of the Cell Cycle","year":2025,"lang":"en","type":"preprint","venue":"Bioinformatics Advances","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Gaussian; Mixture model; Computer science; Statistical physics; Artificial intelligence; Physics; Chemistry; Computational chemistry","score_opus":0.005661072395691977,"score_gpt":0.23241871094834993,"score_spread":0.22675763855265796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407603264","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6975938,0.068839885,0.14393021,0.00062879064,0.003610606,0.0021667327,0.00095342245,0.00009715065,0.08217941],"genre_scores_gemma":[0.9793973,0.0025747123,0.016527321,0.00014814436,0.00019826023,0.000026041898,0.00020083362,0.000019375515,0.00090799807],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985814,0.000044044653,0.0006096629,0.00026288998,0.00025445534,0.00024755805],"domain_scores_gemma":[0.99818355,0.00000922423,0.0005032742,0.0011154042,0.0001334335,0.000055126042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016764755,0.00029555126,0.0003452105,0.0000707572,0.00010206892,0.000028869807,0.00080718036,0.00036940785,0.000005789315],"category_scores_gemma":[0.00003254759,0.0002182959,0.00040499697,0.00016399665,0.0000872016,0.000006061849,0.0011511191,0.00025575553,0.0000018314821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016576829,0.00003882184,0.00060880365,0.0010327874,0.00015479814,1.7479157e-7,0.00015782817,0.99119794,0.001967815,0.000050452032,0.0008430027,0.0039310115],"study_design_scores_gemma":[0.0003270959,0.00003920829,0.00006867102,0.0003770982,0.00029216116,0.0000021762826,0.00036867143,0.8994758,0.07535574,0.0016405723,0.02149513,0.0005576462],"about_ca_topic_score_codex":0.000008608641,"about_ca_topic_score_gemma":0.000033220524,"teacher_disagreement_score":0.28180352,"about_ca_system_score_codex":0.00002159362,"about_ca_system_score_gemma":0.00023621373,"threshold_uncertainty_score":0.8901848},"labels":[],"label_agreement":null},{"id":"W4408389020","doi":"10.1093/bioadv/vbaf052","title":"RegionScan: a comprehensive R package for region-level genome-wide association testing with integration and visualization of multiple-variant and single-variant hypothesis testing","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Hospital for Sick Children; Lunenfeld-Tanenbaum Research Institute","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Visualization; Linkage disequilibrium; Scalability; Genetic association; Data mining; Biology; Genetics; Allele; Haplotype; Single-nucleotide polymorphism; Database","score_opus":0.05280040378514868,"score_gpt":0.26921073306269605,"score_spread":0.2164103292775474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408389020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37252644,0.0019109455,0.6241704,0.000362719,0.00008873346,0.0005687536,0.00010112332,0.000034350633,0.00023653588],"genre_scores_gemma":[0.7620458,0.00039004654,0.23714103,0.00013399354,0.000066115994,0.000039074057,0.00011156812,0.000017691353,0.00005467994],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990584,0.000046264424,0.00041329933,0.00020172149,0.00009393359,0.00018634081],"domain_scores_gemma":[0.9971979,0.0018869934,0.00040040526,0.00011981702,0.00034979984,0.0000450687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026936384,0.00015102918,0.00021508557,0.00008259264,0.00013045962,0.000055364402,0.000053410644,0.00012270654,2.9988283e-7],"category_scores_gemma":[0.006295631,0.00012412416,0.00003066805,0.0001801152,0.000064919936,0.000032771815,0.000040322284,0.000046871635,3.43182e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041295166,0.00028502205,0.4521124,0.0033862712,0.0009631021,0.000017057282,0.0052020266,0.005088328,0.2144904,0.0019887097,0.0022107495,0.31384295],"study_design_scores_gemma":[0.004283159,0.0054153837,0.30998337,0.002318104,0.0007707172,0.00048160585,0.008245701,0.61389756,0.021325812,0.005599909,0.025661644,0.002017013],"about_ca_topic_score_codex":0.000021400652,"about_ca_topic_score_gemma":0.000070427566,"teacher_disagreement_score":0.60880923,"about_ca_system_score_codex":0.000041106614,"about_ca_system_score_gemma":0.00006561294,"threshold_uncertainty_score":0.7536913},"labels":[],"label_agreement":null},{"id":"W4408714891","doi":"10.1093/bioadv/vbaf044","title":"Biological databases in the age of generative artificial intelligence","year":2024,"lang":"en","type":"editorial","venue":"Bioinformatics Advances","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Clinical Research Institute","funders":"H2020 European Research Council","keywords":"Stewardship (theology); Computer science; Data science; Generative grammar; Biological data; Database; Artificial intelligence; Political science","score_opus":0.23202343592757224,"score_gpt":0.440254693494518,"score_spread":0.20823125756694577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408714891","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020880825,0.0023084066,0.11163831,0.00022689818,0.8788761,0.00046351214,0.0017955031,0.000043141918,0.0044393186],"genre_scores_gemma":[0.008874612,0.004501619,0.12826325,0.0005273704,0.8472723,0.00016695964,0.008076198,0.000060455408,0.0022572349],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944757,0.00021461949,0.0018216702,0.00054986216,0.0026451673,0.00029295846],"domain_scores_gemma":[0.99096966,0.0068534603,0.000584241,0.0013231236,0.0002347142,0.000034791203],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008626283,0.00025696168,0.00048658342,0.0005287688,0.00011733323,0.0007428308,0.0027235795,0.00011040564,0.000057247205],"category_scores_gemma":[0.010280232,0.00012813497,0.00014227613,0.0015249718,0.00042000608,0.0004579038,0.0009116872,0.0004727762,0.0003774076],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011755874,0.00004575398,0.000007659153,0.000060759987,0.000008852522,0.000018600582,0.0011571462,0.0005167106,0.0000013713203,0.005770829,0.8446008,0.14779978],"study_design_scores_gemma":[0.000020565734,0.000059535043,0.00000538228,0.000109017405,0.0000111935915,7.301708e-7,0.0055465247,0.013603834,0.000022943772,0.023733806,0.9567239,0.00016254326],"about_ca_topic_score_codex":0.00004356035,"about_ca_topic_score_gemma":0.00040015136,"teacher_disagreement_score":0.14763723,"about_ca_system_score_codex":0.000031408887,"about_ca_system_score_gemma":0.00013927127,"threshold_uncertainty_score":0.9980566},"labels":[],"label_agreement":null},{"id":"W4409105075","doi":"10.1093/bioadv/vbaf021","title":"Transfer learning improves performance in volumetric electron microscopy organelle segmentation across tissues","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Lunenfeld-Tanenbaum Research Institute; Vector Institute; University of Toronto; University Health Network","funders":"","keywords":"Computer science; Transfer of learning; Segmentation; Benchmark (surveying); Artificial intelligence; Annotation; Pattern recognition (psychology); Deep learning; Identification (biology); Organelle; Endoplasmic reticulum; Image segmentation; Volume (thermodynamics); Microscopy; Biology; Pathology; Physics","score_opus":0.004681615284073407,"score_gpt":0.3218662588925711,"score_spread":0.3171846436084977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409105075","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92769784,0.009976396,0.061438244,0.00004453401,0.000080452766,0.00034073475,0.000016286229,0.00010295711,0.00030258024],"genre_scores_gemma":[0.96254396,0.014866629,0.021152807,0.00008411119,0.00008408386,0.000112090565,0.00025659837,0.00003627486,0.00086342404],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99893343,0.000012027354,0.00032648662,0.00023820545,0.000102646656,0.0003872047],"domain_scores_gemma":[0.99971247,0.0000121953535,0.00004088621,0.0001572106,0.00003669825,0.00004052498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014470471,0.00017982036,0.0001321845,0.00007074428,0.0001390941,0.0000868989,0.00015684652,0.00009852593,0.000007852701],"category_scores_gemma":[0.00001320717,0.00017172919,0.000047348614,0.00045753882,0.000060724757,0.00008613707,0.000039824965,0.00019271697,0.000025116418],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022825297,0.00002094844,0.0005130465,0.00017161488,0.000009802821,4.118997e-7,0.00025793602,0.0006735248,0.9063895,0.00006365598,0.000071371505,0.09180537],"study_design_scores_gemma":[0.0001490271,0.00032868274,0.000120853045,0.000038650134,0.0000053405856,0.0000088079605,0.00025198786,0.0033423682,0.8273247,0.000034932786,0.16819741,0.00019728282],"about_ca_topic_score_codex":0.0000050517665,"about_ca_topic_score_gemma":0.000018969098,"teacher_disagreement_score":0.16812603,"about_ca_system_score_codex":0.000051733536,"about_ca_system_score_gemma":0.000041582167,"threshold_uncertainty_score":0.70029134},"labels":[],"label_agreement":null},{"id":"W4409285046","doi":"10.1093/bioadv/vbaf083","title":"“Neuropathological function estimations”: a user-friendly module for analyzing neural activity in neurological disorders","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Montreal Neurological Institute and Hospital; Douglas Mental Health University Institute; McGill University; Dawson College","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Réseau en Bio-Imagerie du Quebec","keywords":"Neuroscience; User Friendly; Function (biology); Computer science; Artificial neural network; Medicine; Physical medicine and rehabilitation; Artificial intelligence; Psychology; Biology; Operating system","score_opus":0.028425696911020124,"score_gpt":0.29264562433775343,"score_spread":0.2642199274267333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409285046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7229122,0.00041428418,0.26722518,0.005117055,0.0018311437,0.0009535943,0.00008733688,0.00057549943,0.00088372553],"genre_scores_gemma":[0.9932913,0.00011724739,0.005402989,0.000847419,0.00007370771,0.00019554414,0.0000051745205,0.000016521875,0.000050094688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984905,0.00009687716,0.00033977546,0.00044826977,0.00025684517,0.00036770012],"domain_scores_gemma":[0.9952285,0.0044107963,0.00009114179,0.00018696349,0.000028465005,0.000054128122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030358112,0.00022159232,0.0002330229,0.00025122453,0.00027639238,0.00016258034,0.00018411958,0.00006956058,0.000010167777],"category_scores_gemma":[0.005931677,0.00017757675,0.00012481645,0.00067445263,0.00017820353,0.0015547711,0.00011661903,0.00027712376,0.000031980053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018216553,0.001098878,0.03698795,0.002004668,0.00005174166,0.0001106645,0.00094805926,0.14346768,0.019743549,0.08066178,0.0047541023,0.7083493],"study_design_scores_gemma":[0.0003759206,0.0008392453,0.019000178,0.000029044058,0.0000197095,0.000026336073,0.00004175839,0.9508417,0.0009054173,0.0057785595,0.021848073,0.0002940417],"about_ca_topic_score_codex":0.000002257481,"about_ca_topic_score_gemma":0.000025761412,"teacher_disagreement_score":0.80737406,"about_ca_system_score_codex":0.000033457625,"about_ca_system_score_gemma":0.000027625987,"threshold_uncertainty_score":0.72413695},"labels":[],"label_agreement":null},{"id":"W4409908023","doi":"10.1093/bioadv/vbaf103","title":"Assessing accuracy and specificity of faecal source library for microbial source-tracking, using SourceTracker as case study","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Fecal contamination and water quality","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Melbourne Water","keywords":"Source tracking; Open source; Tracking (education); Computer science; Psychology; World Wide Web; Software","score_opus":0.04425365662850683,"score_gpt":0.3352390906556071,"score_spread":0.29098543402710025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409908023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9454834,0.00016433508,0.053169318,0.000042290227,0.00015776895,0.00043280984,0.000021083057,0.00008326699,0.00044575462],"genre_scores_gemma":[0.9830667,0.000015175915,0.016496077,0.000084175066,0.000074467134,0.0000053047606,0.00000735167,0.000019482868,0.00023129799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988051,0.00005080403,0.0005078909,0.00020238833,0.00021733741,0.00021645955],"domain_scores_gemma":[0.99928665,0.0003002833,0.00016713937,0.0001482412,0.000011899005,0.00008579767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039797893,0.00016504424,0.000200016,0.00006602274,0.00020699212,0.00044899923,0.00012879001,0.00005831235,0.00012867738],"category_scores_gemma":[0.00008734293,0.00013711903,0.00006747508,0.0001818026,0.00019078163,0.002923658,0.00018714434,0.00012173563,0.000019687006],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074378244,0.000450075,0.04168353,0.0011559076,0.000074157644,0.00013950013,0.054414082,0.003192651,0.0044921925,0.000116631236,0.00055379537,0.8936531],"study_design_scores_gemma":[0.0018523352,0.0006979481,0.0061416756,0.00036552263,0.00020567965,0.0015486035,0.1041643,0.60805684,0.030386973,0.0007604849,0.24456011,0.0012595063],"about_ca_topic_score_codex":0.00007791151,"about_ca_topic_score_gemma":0.000020603908,"teacher_disagreement_score":0.8923936,"about_ca_system_score_codex":0.000040986397,"about_ca_system_score_gemma":0.000019537796,"threshold_uncertainty_score":0.55915517},"labels":[],"label_agreement":null},{"id":"W4409962274","doi":"10.1093/bioadv/vbaf098","title":"<i>bamSliceR</i> : a Bioconductor package for rapid, cross-cohort variant and allelic bias analysis","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; Hope Foundation; National Institutes of Health; National Cancer Institute; Genome Canada; Van Andel Research Institute","keywords":"Bioconductor; R package; Allele; Cohort; Genetics; Biology; Computational biology; Statistics; Computer science; Medicine; Mathematics; Gene","score_opus":0.021049864766813527,"score_gpt":0.3088681925524286,"score_spread":0.28781832778561506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409962274","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.593446,0.051128153,0.34460816,0.00078832667,0.001507101,0.0017679438,0.0007086242,0.0001915485,0.0058541237],"genre_scores_gemma":[0.97564644,0.007556068,0.013372632,0.0005005649,0.00031816502,0.00027074435,0.0006983117,0.00003068287,0.001606414],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990267,0.000015194827,0.00033641077,0.00028955785,0.00012805707,0.00020406592],"domain_scores_gemma":[0.99936867,0.000028173752,0.00010199523,0.000328994,0.000080958634,0.00009122268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026380748,0.00016401983,0.00017524825,0.00015043115,0.00010819249,0.00020932792,0.00014302977,0.000107450614,0.000027727938],"category_scores_gemma":[0.00006512728,0.00013043091,0.00015048157,0.000315916,0.000084961415,0.000035361845,0.00005956467,0.00005043146,0.000009186296],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035825366,0.00017551333,0.014428321,0.002250074,0.003644844,0.000007398285,0.0014333031,0.0005222456,0.6440794,0.006708044,0.025083637,0.30130896],"study_design_scores_gemma":[0.0003835849,0.00016620403,0.0020837812,0.000028070552,0.00024680007,0.000010263851,0.00023208349,0.009361851,0.07276026,0.00019546576,0.9142159,0.00031573093],"about_ca_topic_score_codex":0.000002789188,"about_ca_topic_score_gemma":0.000008707763,"teacher_disagreement_score":0.88913226,"about_ca_system_score_codex":0.000011965511,"about_ca_system_score_gemma":0.000067150526,"threshold_uncertainty_score":0.5318818},"labels":[],"label_agreement":null},{"id":"W4411332264","doi":"10.1093/bioadv/vbaf129","title":"NRGSuite-Qt: a PyMOL plugin for high-throughput virtual screening, molecular docking, normal-mode analysis, the study of molecular interactions, and the detection of binding-site similarities","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Plug-in; Docking (animal); Virtual screening; Computational biology; Computer science; Binding site; Chemistry; Bioinformatics; Drug discovery; Biology; Operating system; Medicine; Biochemistry","score_opus":0.0045888944274993905,"score_gpt":0.2638198506195027,"score_spread":0.2592309561920033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411332264","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6825826,0.0044544516,0.31191114,0.00005765715,0.00012961683,0.0006468373,0.00014988454,0.00001296701,0.00005484813],"genre_scores_gemma":[0.996072,0.00045073815,0.0031152135,0.00007184019,0.000041270006,0.00009025306,0.000114715294,0.000015500334,0.000028468265],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99885416,0.00006065581,0.0005071368,0.00019018452,0.00021497715,0.00017285823],"domain_scores_gemma":[0.99911577,0.00009690058,0.00027735464,0.00036485586,0.000116878175,0.000028265587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003226819,0.00019111592,0.0002834759,0.00015675368,0.00014636302,0.000078114506,0.00022210674,0.000075549404,0.0000017947735],"category_scores_gemma":[0.00009623541,0.00011983765,0.00018097945,0.0003263789,0.0002334165,0.000044254626,0.00015401072,0.00012296691,3.1517703e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033517927,0.00043241953,0.0021419465,0.0022542137,0.014650152,0.000020378464,0.017007487,0.24032639,0.51798767,0.02522134,0.00019679037,0.1764094],"study_design_scores_gemma":[0.004261841,0.0026313725,0.00042454942,0.00019739316,0.0035869598,0.000056822362,0.01208373,0.37564257,0.58117133,0.0022643453,0.01686592,0.00081315055],"about_ca_topic_score_codex":0.0000968206,"about_ca_topic_score_gemma":0.00033790877,"teacher_disagreement_score":0.3134894,"about_ca_system_score_codex":0.000009470329,"about_ca_system_score_gemma":0.00003038731,"threshold_uncertainty_score":0.48868373},"labels":[],"label_agreement":null},{"id":"W4411436820","doi":"10.1093/bioadv/vbaf140","title":"Prediction of the infecting organism in peritoneal dialysis patients with acute peritonitis using interpretable Tsetlin Machines","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Dialysis and Renal Disease Management","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"Engineering and Physical Sciences Research Council; Medical Research Council; National Institute for Health and Care Research","keywords":"Peritoneal dialysis; Peritonitis; Organism; Medicine; Dialysis; Intensive care medicine; Computational biology; Internal medicine; Biology; Genetics","score_opus":0.007110007031997439,"score_gpt":0.23912152794933883,"score_spread":0.2320115209173414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411436820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9952987,0.00039012037,0.0017808183,0.00005338311,0.00033076282,0.00034490577,0.00009143097,0.00003492625,0.001674995],"genre_scores_gemma":[0.9962252,0.00013538335,0.0034420025,0.000041480864,0.000045061843,0.000009618922,0.00004546033,0.000012780783,0.000043010703],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990743,0.00001762238,0.00037565996,0.0001015975,0.00029504645,0.00013580713],"domain_scores_gemma":[0.99960685,0.000025168058,0.000107397194,0.0001586699,0.00006331701,0.00003857778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010715647,0.00011875299,0.00022458,0.0001724235,0.00006251015,0.000059145226,0.00007081398,0.000028979044,0.00002959586],"category_scores_gemma":[0.00003390784,0.00006496841,0.00009297156,0.00051266263,0.00006222141,0.00038611764,0.00007817748,0.00009879476,0.0000026500263],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028238323,0.0006143738,0.8028719,0.004628418,0.0015544522,0.00003462587,0.010578709,0.0056169815,0.0014730425,0.00041443738,0.000092811,0.1718379],"study_design_scores_gemma":[0.0020300993,0.0005060603,0.25279516,0.0041046888,0.0022482611,0.000024369056,0.0017189034,0.7295621,0.0019771382,0.00014277818,0.0045348476,0.00035559144],"about_ca_topic_score_codex":0.000039406652,"about_ca_topic_score_gemma":0.000024666984,"teacher_disagreement_score":0.72394514,"about_ca_system_score_codex":0.000069751186,"about_ca_system_score_gemma":0.000058955822,"threshold_uncertainty_score":0.2649335},"labels":[],"label_agreement":null},{"id":"W4412033199","doi":"10.1093/bioadv/vbaf163","title":"Optimal solution to the set cover problem with a vicinity constraint for estimating genotype tissue expression profiles","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Cover (algebra); Set (abstract data type); Set cover problem; Expression (computer science); Constraint (computer-aided design); Computer science; Dynamic programming; Algorithm; Data mining; Computational biology; Biology; Mathematics; Engineering","score_opus":0.015646280706486673,"score_gpt":0.2950535653670106,"score_spread":0.27940728466052395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412033199","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01593412,0.00097633956,0.9801823,0.0006641788,0.00027219622,0.0009824209,0.000100615885,0.000043280117,0.00084453117],"genre_scores_gemma":[0.33611917,0.00008355454,0.66197157,0.00028321138,0.00032073882,0.00046907814,0.00027369833,0.00002253155,0.0004564453],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992536,0.000015792446,0.00022164504,0.00018349409,0.00014162892,0.00018385974],"domain_scores_gemma":[0.9995351,0.00002121674,0.00008741644,0.00020658349,0.000091416245,0.000058291986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018496883,0.00013087987,0.000088103974,0.000036847203,0.00017603257,0.000097168486,0.0001421932,0.000060818013,0.000011129168],"category_scores_gemma":[0.000042842585,0.00007791268,0.000031370255,0.00010816159,0.000055863955,0.000025770627,0.000057229125,0.00005918624,0.000020487967],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000469281,0.000050089457,0.000052464493,0.0011906096,0.000067548855,0.0000010676017,0.002869238,0.055214476,0.6753826,0.0007530515,0.05017031,0.21377926],"study_design_scores_gemma":[0.00032151904,0.0005229008,0.000024626552,0.0002566916,0.000020402102,0.000015786478,0.0007856796,0.08028109,0.34457186,0.000064222404,0.5729143,0.00022092243],"about_ca_topic_score_codex":0.0000013315229,"about_ca_topic_score_gemma":0.0000045951315,"teacher_disagreement_score":0.522744,"about_ca_system_score_codex":0.000018543025,"about_ca_system_score_gemma":0.00012063193,"threshold_uncertainty_score":0.31771868},"labels":[],"label_agreement":null},{"id":"W4412033208","doi":"10.1093/bioadv/vbaf162","title":"Volcano: a pipeline to characterize long terminal repeat-retrotransposons families in plants","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Innovation, Science and Economic Development Canada","funders":"Beijing Academy of Agricultural and Forestry Sciences; Chinese Academy of Sciences","keywords":"Retrotransposon; Long terminal repeat; Genome; Biology; Pipeline (software); Computational biology; Genetics; Computer science; Gene; Transposable element","score_opus":0.01568206321207271,"score_gpt":0.23696252220651856,"score_spread":0.22128045899444584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412033208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941925,0.00060100993,0.00024611733,0.0017878205,0.00034731464,0.00027116534,0.00049337704,0.00011067459,0.0019500466],"genre_scores_gemma":[0.99674267,0.00054458244,0.0015332971,0.0002813912,0.00026132452,0.000039991577,0.00019118153,0.0000012407081,0.0004043505],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990702,0.000011525722,0.00033719168,0.00015914546,0.00016956501,0.00025232343],"domain_scores_gemma":[0.9997103,0.00009032661,0.000035890655,0.000051895175,0.000019848501,0.00009172476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009798821,0.00013404529,0.00015330187,0.000041157633,0.00008309432,0.00010983732,0.0001770584,0.000048991238,0.00012325442],"category_scores_gemma":[0.000023800201,0.000054996955,0.000055268505,0.0003788525,0.000025161473,0.00032100233,0.00003845382,0.00008606176,0.0001388826],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005244639,0.00007476565,0.008377604,0.00017150337,0.000014634779,0.00009786497,0.0020040176,0.000112372036,0.045911923,0.0003376038,0.000588601,0.9422567],"study_design_scores_gemma":[0.00029017095,0.0005406975,0.3444285,0.0006727593,0.000022480035,0.00013427367,0.0015562768,0.00981361,0.004889619,0.00067105034,0.6362251,0.0007554191],"about_ca_topic_score_codex":0.00005110774,"about_ca_topic_score_gemma":0.0014370304,"teacher_disagreement_score":0.94150126,"about_ca_system_score_codex":0.000023375978,"about_ca_system_score_gemma":0.000013869244,"threshold_uncertainty_score":0.22427107},"labels":[],"label_agreement":null},{"id":"W4412397007","doi":"10.1093/bioadv/vbaf170","title":"Hybrid representation learning for human m6A modifications with chromosome-level generalizability","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Generalizability theory; Chromosome; Representation (politics); Computational biology; Psychology; Computer science; Biology; Artificial intelligence; Genetics; Developmental psychology; Gene","score_opus":0.03558883257704904,"score_gpt":0.3212112618748866,"score_spread":0.28562242929783754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412397007","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3064439,0.0024984216,0.6866928,0.00034072352,0.00018942248,0.00063931796,0.00016581378,0.000087854525,0.0029417905],"genre_scores_gemma":[0.972869,0.00052156806,0.023355193,0.000069122536,0.0001870664,0.00032681483,0.0009594335,0.000021929081,0.001689864],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99922895,0.000015288475,0.00025937278,0.00022214784,0.00011309771,0.00016112054],"domain_scores_gemma":[0.9994362,0.000016255657,0.00008481886,0.0002933113,0.0001226581,0.000046732926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012683315,0.0001193527,0.00009571667,0.000048059268,0.00023280605,0.000102914964,0.00012628047,0.00004000715,0.000011981187],"category_scores_gemma":[0.000036463105,0.00009808249,0.00006448197,0.00010257262,0.0000807847,0.00003911626,0.000024416668,0.000058697136,0.00000796042],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021525325,0.00030818518,0.0026513138,0.0019922145,0.00050031673,0.0000030436804,0.0014427622,0.083771415,0.59238863,0.03435519,0.017970953,0.2644007],"study_design_scores_gemma":[0.0007426508,0.0006085885,0.0009372123,0.00008124042,0.00007902433,0.000029173694,0.0005676247,0.08444175,0.22410783,0.002180121,0.68563366,0.00059113343],"about_ca_topic_score_codex":0.000006705445,"about_ca_topic_score_gemma":0.0000147959945,"teacher_disagreement_score":0.6676627,"about_ca_system_score_codex":0.000024796931,"about_ca_system_score_gemma":0.00007312721,"threshold_uncertainty_score":0.3999688},"labels":[],"label_agreement":null},{"id":"W4412626392","doi":"10.1093/bioadv/vbaf178","title":"Gene-set enrichment analysis and visualization on the web using EnrichmentMap:RNASeq","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"National Institutes of Health","keywords":"Visualization; Computational biology; Set (abstract data type); Biology; Computer science; Genetics; World Wide Web; Data mining; Programming language","score_opus":0.012826118544825463,"score_gpt":0.278922961500048,"score_spread":0.2660968429552225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412626392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.701874,0.018747535,0.27100945,0.0004774583,0.001005716,0.00088010373,0.00027742205,0.00010075961,0.0056275674],"genre_scores_gemma":[0.98689157,0.005456336,0.006069229,0.0008155,0.00022079566,0.000020223328,0.00030037173,0.000019155155,0.00020683467],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990264,0.000023556337,0.00036770807,0.00017031383,0.00018684236,0.000225156],"domain_scores_gemma":[0.9994562,0.00003834651,0.00011606433,0.00028406887,0.000038202015,0.00006707675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030977538,0.0001872814,0.00014988617,0.00014448697,0.00016890281,0.00019277824,0.00014986657,0.00008965448,0.00002018437],"category_scores_gemma":[0.000019675896,0.00012495946,0.00010519402,0.00041096206,0.000073983334,0.00002453351,0.00010633089,0.000079739344,0.00001553949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005778306,0.0005289556,0.012072378,0.0030482484,0.014509061,0.00003926508,0.009983886,0.117119394,0.15635969,0.11416703,0.0581212,0.51347303],"study_design_scores_gemma":[0.00024406254,0.00022860184,0.0001551495,0.000055187844,0.0003572051,0.000017440863,0.000608852,0.81555015,0.013175894,0.00047317613,0.1687197,0.00041461893],"about_ca_topic_score_codex":0.0000031669636,"about_ca_topic_score_gemma":0.000010345789,"teacher_disagreement_score":0.6984307,"about_ca_system_score_codex":0.000024586383,"about_ca_system_score_gemma":0.00005140438,"threshold_uncertainty_score":0.5095699},"labels":[],"label_agreement":null},{"id":"W4412701268","doi":"10.1093/bioadv/vbaf173","title":"SW-actors: accelerating the Smith–Waterman algorithm via actors","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Parallel computing","score_opus":0.01153603087821653,"score_gpt":0.2502597154997679,"score_spread":0.23872368462155136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412701268","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8145531,0.0845286,0.07461046,0.0010141302,0.0050246036,0.0011820733,0.00030165722,0.00012274683,0.018662624],"genre_scores_gemma":[0.97148955,0.0047033452,0.021692483,0.00035179223,0.00086501887,0.000050639057,0.000068441725,0.000039927345,0.0007388201],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907446,0.000017008202,0.00030996982,0.0001813697,0.00013641943,0.00028074815],"domain_scores_gemma":[0.9995107,0.000030233028,0.00007441926,0.00028275113,0.00004733258,0.000054586402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015325734,0.0002047761,0.0001344649,0.000036181616,0.00021850722,0.00016857327,0.00027025866,0.00007368931,0.000013336724],"category_scores_gemma":[0.000020858351,0.0001297135,0.00010309828,0.000100701676,0.000101276164,0.000009204308,0.00017746333,0.00009846882,0.00004939199],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019349618,0.000042827898,0.0007934492,0.00038340566,0.00043020063,0.000006655581,0.0026219191,0.00059448095,0.11119943,0.00030212593,0.0054143607,0.87819177],"study_design_scores_gemma":[0.00017000384,0.00020710904,0.0006012067,0.000050208415,0.000037123955,0.00003069154,0.0006851135,0.02233956,0.066862315,0.00031575267,0.90831053,0.00039037698],"about_ca_topic_score_codex":0.00000530263,"about_ca_topic_score_gemma":0.000005311116,"teacher_disagreement_score":0.90289617,"about_ca_system_score_codex":0.00001348049,"about_ca_system_score_gemma":0.000049887538,"threshold_uncertainty_score":0.5289563},"labels":[],"label_agreement":null},{"id":"W4413056432","doi":"10.1093/bioadv/vbaf179","title":"<i>Struc2mapGAN</i>: improving synthetic cryogenic electron microscopy density maps with generative adversarial networks","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Generator (circuit theory); Computer science; Generative grammar; Adversarial system; Artificial intelligence; Generative adversarial network; Raw data; Deep learning; Pattern recognition (psychology); Machine learning; Theoretical computer science; Physics","score_opus":0.00301896666668887,"score_gpt":0.26785414162269267,"score_spread":0.2648351749560038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413056432","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05976193,0.008649865,0.92961496,0.0000949211,0.00020957399,0.0005663197,0.00006341056,0.00017996712,0.00085904094],"genre_scores_gemma":[0.7285928,0.0044664787,0.26404554,0.00051255326,0.00067609525,0.00021370922,0.00065129023,0.00010363804,0.0007378676],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986769,0.0000181569,0.00031831846,0.0003755406,0.00013330292,0.00047777593],"domain_scores_gemma":[0.99930704,0.000018055533,0.000124916,0.00038041445,0.000080415855,0.00008916961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011479832,0.00029072945,0.000192753,0.00005816218,0.00022304534,0.00012531984,0.00023097302,0.00014292987,0.0000065350123],"category_scores_gemma":[0.000013745323,0.00024036948,0.00009184367,0.00022147164,0.00015177802,0.000047319576,0.00008978561,0.00021863091,0.000011541981],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015064907,0.000031427,0.00004634444,0.00011965796,0.000081846934,0.0000033946192,0.00006733805,0.001931431,0.9758817,0.0019000988,0.0016423431,0.018143801],"study_design_scores_gemma":[0.00023185005,0.00050190877,0.000006080618,0.000052122934,0.00005120256,0.0000760477,0.00006132883,0.0077820914,0.8938951,0.00038533375,0.096561015,0.00039594827],"about_ca_topic_score_codex":0.0000062191684,"about_ca_topic_score_gemma":0.0000398948,"teacher_disagreement_score":0.66883093,"about_ca_system_score_codex":0.0000570171,"about_ca_system_score_gemma":0.00014984272,"threshold_uncertainty_score":0.9801983},"labels":[],"label_agreement":null},{"id":"W4413109704","doi":"10.1093/bioadv/vbaf131","title":"Next generation biobanking ontology: introducing–omics contextual data to biobanking ontology","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; Simon Fraser University","funders":"King Fahad Medical City","keywords":"Biobank; Ontology; Computer science; Data science; Ontology-based data integration; Data discovery; Open Biomedical Ontologies; Data integration; Information retrieval; Metadata; Data management; World Wide Web; Data mining; Semantic Web; Suggested Upper Merged Ontology; Bioinformatics","score_opus":0.08394483396799426,"score_gpt":0.3364466195746183,"score_spread":0.25250178560662406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413109704","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5096661,0.06994753,0.39761266,0.006991413,0.009896616,0.0011176338,0.00068935606,0.00065395446,0.0034247371],"genre_scores_gemma":[0.75868374,0.003370181,0.22815216,0.0033898074,0.0029681232,0.000055234806,0.0028751085,0.00006517613,0.00044046718],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980445,0.000051123618,0.0005953862,0.00059850625,0.00021293471,0.00049754773],"domain_scores_gemma":[0.9987134,0.00007022211,0.00012387143,0.0008758704,0.000082469014,0.0001341636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054379617,0.00028649537,0.00031320503,0.00017034092,0.00018096663,0.00022061415,0.0007674654,0.0003025139,0.000022596814],"category_scores_gemma":[0.00064064545,0.000243414,0.00007075524,0.00025324515,0.00023628696,0.00006668218,0.00055416324,0.00020523809,0.00009513434],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071834285,0.00004443726,0.00035972174,0.00019956219,0.00014832511,0.000014898776,0.0008281247,0.00017110488,0.0911022,0.0014775338,0.026557071,0.87902516],"study_design_scores_gemma":[0.00033525404,0.00050636963,0.000089186986,0.00010076794,0.000049539452,0.0001132577,0.0008563268,0.04297824,0.0136824045,0.0001678853,0.94063306,0.00048772167],"about_ca_topic_score_codex":0.000027289998,"about_ca_topic_score_gemma":0.0004079971,"teacher_disagreement_score":0.914076,"about_ca_system_score_codex":0.000041290376,"about_ca_system_score_gemma":0.0001701561,"threshold_uncertainty_score":0.99261355},"labels":[],"label_agreement":null},{"id":"W4413890799","doi":"10.1093/bioadv/vbaf169","title":"Opportunities and considerations for using artificial intelligence in bioinformatics education","year":2024,"lang":"en","type":"editorial","venue":"Bioinformatics Advances","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada; Ontario Institute for Cancer Research","funders":"National Center for Advancing Translational Sciences; Government of Ontario; Bill and Melinda Gates Foundation; National Institutes of Health; National Science Foundation","keywords":"Scope (computer science); Computer science; Artificial intelligence; Bioinformatics; Data science; Biology","score_opus":0.06368501628049607,"score_gpt":0.36218987482045306,"score_spread":0.298504858539957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413890799","genre_codex":"editorial","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014134288,0.02350048,0.13191204,0.0011643209,0.8250939,0.004771549,0.0047242464,0.00012462478,0.007295361],"genre_scores_gemma":[0.0021077844,0.06400537,0.58991903,0.0006765009,0.33320835,0.0005336447,0.007881278,0.00020213408,0.0014658753],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972199,0.000029923196,0.0013625723,0.00029145132,0.00057877135,0.0005173638],"domain_scores_gemma":[0.99817985,0.00035878897,0.0003620437,0.0003778604,0.0005074074,0.00021406253],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074195536,0.00042135763,0.000433429,0.0004698893,0.00017962269,0.00039790483,0.0002763181,0.00077584,0.000010374383],"category_scores_gemma":[0.002370912,0.00038558178,0.00012495162,0.00015738222,0.0004345212,0.000063904765,0.00027512707,0.00038844426,0.000014701225],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013667379,0.0002181138,0.0000040626724,0.009996004,0.00016590665,0.0000039331567,0.0014883421,0.0002168743,0.00027124616,0.010337192,0.61382616,0.36333546],"study_design_scores_gemma":[0.0001629717,0.00045706413,5.7718927e-7,0.00053332077,0.00007395956,0.0000138383975,0.005650982,0.069468416,0.0012094587,0.017359607,0.904418,0.0006518276],"about_ca_topic_score_codex":0.000015413165,"about_ca_topic_score_gemma":0.00016524983,"teacher_disagreement_score":0.4918856,"about_ca_system_score_codex":0.00007913085,"about_ca_system_score_gemma":0.0022801303,"threshold_uncertainty_score":0.99985963},"labels":[],"label_agreement":null},{"id":"W4413913923","doi":"10.1093/bioadv/vbaf193","title":"Exploration of chaos game representation and integrative deep learning approaches for whole-genome sequencing-based grapevine genetic testing","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Horticultural and Viticultural Research","field":"Agricultural and Biological Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Whole genome sequencing; CHAOS (operating system); Representation (politics); Artificial intelligence; Computational biology; Genome; DNA sequencing; Biology; Computer science; Evolutionary biology; Machine learning; Genetics; Gene","score_opus":0.13288676251102186,"score_gpt":0.30668923682132865,"score_spread":0.1738024743103068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413913923","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9821472,0.003550156,0.011864725,0.0008131998,0.000087011045,0.0009771046,0.00008118785,0.0001364677,0.00034292016],"genre_scores_gemma":[0.9889563,0.00022043874,0.010222347,0.00001696681,0.00009346914,0.000097221186,0.00029675354,0.0000014028241,0.000095149124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990404,0.000035321493,0.00034300983,0.00017648893,0.00020279003,0.00020197974],"domain_scores_gemma":[0.99913484,0.00047816863,0.00011784097,0.000030734303,0.00017377287,0.00006467409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001803247,0.00013652044,0.00017033862,0.000028395238,0.00014691323,0.0001440763,0.00009557665,0.000047461912,0.00000833277],"category_scores_gemma":[0.00039363146,0.000047933612,0.00006229862,0.00043790496,0.00009365817,0.0008898759,0.000031091095,0.00010203675,0.0000049936716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025215513,0.000014777527,0.0003263719,0.00040509034,0.000018752595,0.0000012024523,0.0020175972,0.00438036,0.13958766,0.000263943,0.0000048699794,0.85295415],"study_design_scores_gemma":[0.00020378431,0.001301434,0.0068117157,0.00032980638,0.000040931936,0.000010949651,0.019976655,0.94870996,0.013666979,0.0016281347,0.0069790464,0.00034061537],"about_ca_topic_score_codex":0.000022068954,"about_ca_topic_score_gemma":0.00009222132,"teacher_disagreement_score":0.94432956,"about_ca_system_score_codex":0.000031187745,"about_ca_system_score_gemma":0.00001399352,"threshold_uncertainty_score":0.19546759},"labels":[],"label_agreement":null},{"id":"W4414457949","doi":"10.1093/bioadv/vbaf228","title":"Deep Active Learning based Experimental Design to Uncover Synergistic Genetic Interactions for Host Targeted Therapeutics","year":2025,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Vector Institute","funders":"","keywords":"Gene knockdown; Scalability; Gene; Identification (biology); Host (biology); Pairwise comparison; Deep learning; Representation (politics)","score_opus":0.026535857626650637,"score_gpt":0.34220779857183364,"score_spread":0.315671940945183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414457949","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012818495,0.0003308791,0.99610555,0.00025348648,0.0007536983,0.00059230195,0.0000074254185,0.00010904581,0.00056573906],"genre_scores_gemma":[0.20129345,0.0000072362377,0.7974954,0.000925483,0.000024836703,0.00015023325,0.000009183807,0.000008643803,0.00008549112],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884814,0.00009666329,0.00035976875,0.00021646837,0.00022039181,0.00025856128],"domain_scores_gemma":[0.9979342,0.0014384455,0.00015004727,0.00025001704,0.00015935914,0.00006792682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018583397,0.00018314092,0.00017731664,0.0002542276,0.00025978475,0.00020616922,0.00049364613,0.000032201242,0.000007983811],"category_scores_gemma":[0.00021199697,0.00017515349,0.00008153789,0.00053646805,0.000036265956,0.00081182766,0.00014122993,0.000108120155,0.000017768303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059397433,0.000063249296,0.000013960298,0.000032567474,0.000039643222,5.922377e-7,0.0009614747,0.91789454,0.0012365353,0.0033862472,0.000070573864,0.07624124],"study_design_scores_gemma":[0.00035368055,0.0001659272,0.00024501389,0.000043528427,0.00001421358,9.753371e-7,0.0004230615,0.9443396,0.04255021,0.0014504603,0.010220052,0.00019328484],"about_ca_topic_score_codex":0.0000024024653,"about_ca_topic_score_gemma":0.000003103874,"teacher_disagreement_score":0.20001161,"about_ca_system_score_codex":0.00017897855,"about_ca_system_score_gemma":0.00020908761,"threshold_uncertainty_score":0.71425515},"labels":[],"label_agreement":null},{"id":"W4414683622","doi":"10.1093/bioadv/vbaf222","title":"An overview of computational methods for gene prediction in eukaryotes: strengths, limitations, and future directions","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Benchmark (surveying); Gene prediction; Scripting language; Gene; Sequence (biology); DNA sequencing","score_opus":0.02498786159813313,"score_gpt":0.3762993471727817,"score_spread":0.35131148557464853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414683622","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07315348,0.18411379,0.73698175,0.0005388521,0.0014315034,0.0012626009,0.00081704295,0.0001505475,0.0015504297],"genre_scores_gemma":[0.019390294,0.025429266,0.9536635,0.00007892338,0.00022198465,0.000055880428,0.0011091662,0.000017392485,0.00003356517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992088,0.000042038744,0.00042647257,0.000119275624,0.000087476226,0.00011590061],"domain_scores_gemma":[0.99948055,0.00014891534,0.00010826241,0.0001414705,0.000078010984,0.000042804073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036746048,0.00011670084,0.00013139252,0.00013132064,0.00006193014,0.00004269175,0.00008472797,0.00008826439,0.0000042428724],"category_scores_gemma":[0.00014370451,0.00010633293,0.000046819427,0.00017035226,0.000053392683,0.00006329678,0.000027547849,0.00007690553,9.434279e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028886605,0.000053061696,0.00058389414,0.0011359095,0.000062834166,1.3225791e-7,0.001274788,0.0113996025,0.0010428918,0.0048033376,0.00021359684,0.97940105],"study_design_scores_gemma":[0.00032071772,0.00040651765,0.0023170547,0.00008364588,0.000033429482,0.000016711507,0.00069078215,0.59502023,0.0017923866,0.0018317999,0.3973203,0.00016640221],"about_ca_topic_score_codex":0.0000022428683,"about_ca_topic_score_gemma":0.000012224162,"teacher_disagreement_score":0.97923464,"about_ca_system_score_codex":0.00001261343,"about_ca_system_score_gemma":0.000062507286,"threshold_uncertainty_score":0.43361312},"labels":[],"label_agreement":null},{"id":"W4415491818","doi":"10.1093/bioadv/vbaf265","title":"MutSeqR: an open source R package for standardized analysis of error-corrected next-generation sequencing data in genetic toxicology","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Carcinogens and Genotoxicity Assessment","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa; Health Canada","funders":"Health Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Open source; R package; Sequence (biology); License; DNA sequencing; MIT License","score_opus":0.0931933158410629,"score_gpt":0.3659723816727946,"score_spread":0.2727790658317317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415491818","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7695422,0.0017065626,0.22688526,0.00003532979,0.00018799127,0.00060298195,0.000907236,0.000014483002,0.00011791079],"genre_scores_gemma":[0.93355596,0.0004654627,0.061345827,0.00012104234,0.00009782638,0.00006156842,0.00426262,0.000020138885,0.00006952957],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986906,0.00004597696,0.0005464486,0.00033948204,0.0001499012,0.00022758788],"domain_scores_gemma":[0.9989476,0.000036699745,0.00015203156,0.0007099411,0.00009390606,0.00005979815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005030903,0.00015662525,0.0003365589,0.00022654334,0.000065115666,0.00016011672,0.00057687744,0.000110470486,0.000018820327],"category_scores_gemma":[0.00009074842,0.00014468037,0.00007938441,0.0004610278,0.000053639567,0.00008444102,0.00035702376,0.00005887034,8.140953e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001236312,0.00006649747,0.0008713017,0.0002180755,0.0004942885,0.0000027105868,0.0006666606,0.014661478,0.92544514,0.00009341286,0.00035846562,0.056998353],"study_design_scores_gemma":[0.00065814645,0.0006556699,0.0006863907,0.000034251563,0.000401669,0.00000660439,0.0014952923,0.8426508,0.12947579,0.000046714737,0.02357496,0.00031373548],"about_ca_topic_score_codex":0.0000725327,"about_ca_topic_score_gemma":0.0036733851,"teacher_disagreement_score":0.8279893,"about_ca_system_score_codex":0.00005890705,"about_ca_system_score_gemma":0.00026455394,"threshold_uncertainty_score":0.58998936},"labels":[],"label_agreement":null},{"id":"W4416098230","doi":"10.1093/bioadv/vbaf287","title":"ntRoot: computational inference of human ancestry at scale from genomic data","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"Canadian Institutes of Health Research","keywords":"Inference; Scale (ratio); Genomics; Big data; Genetic data; Computational model","score_opus":0.03687343643295704,"score_gpt":0.3371535968671262,"score_spread":0.30028016043416916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416098230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9649525,0.0068828035,0.025048815,0.0001131275,0.00025530893,0.000100974234,0.0010101594,0.000018121404,0.001618185],"genre_scores_gemma":[0.9515955,0.0006782787,0.043848794,0.00008450243,0.00014531975,0.000005368394,0.0034850975,0.000008799008,0.00014836212],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991472,0.000021465643,0.00039003202,0.00019473773,0.000098708675,0.00014790682],"domain_scores_gemma":[0.9993313,0.00007095164,0.00014553368,0.00036578666,0.000045324723,0.000041123723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016250876,0.00010418922,0.00015729407,0.000032355452,0.0000774977,0.000019525249,0.0003282185,0.00008841229,0.000037620917],"category_scores_gemma":[0.0000651446,0.00009378715,0.00004104762,0.000061209976,0.000106657186,0.000018326284,0.00034855775,0.000052880252,0.000032275675],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000111724235,0.00026365538,0.4946676,0.0010927153,0.0009260578,0.000005642132,0.0016671355,0.059947018,0.24938358,0.0028866488,0.052278724,0.13676952],"study_design_scores_gemma":[0.0013276879,0.00070450903,0.2694463,0.00025460453,0.00018016108,0.000022061624,0.00094792433,0.38324925,0.015718844,0.017270342,0.30970216,0.0011761409],"about_ca_topic_score_codex":0.000023698743,"about_ca_topic_score_gemma":0.00010560505,"teacher_disagreement_score":0.32330224,"about_ca_system_score_codex":0.0000189965,"about_ca_system_score_gemma":0.00008583754,"threshold_uncertainty_score":0.3824529},"labels":[],"label_agreement":null},{"id":"W4416548752","doi":"10.1093/bioadv/vbaf286","title":"Are the tools fit for purpose? Network inference algorithms evaluated on a simulated lipidomics network","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa; University of Victoria; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Key (lock); Identification (biology); Feature (linguistics); Pattern recognition (psychology)","score_opus":0.041787844238959294,"score_gpt":0.3276315467898132,"score_spread":0.2858437025508539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416548752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2961699,0.23296171,0.4140658,0.00506063,0.022594692,0.0118856905,0.0020483874,0.0008234871,0.014389675],"genre_scores_gemma":[0.8964269,0.031330913,0.055272806,0.0049474314,0.007856462,0.0005498446,0.000847489,0.00016547731,0.0026026901],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985158,0.000035669043,0.00046029803,0.0002777558,0.00020234087,0.0005081322],"domain_scores_gemma":[0.9988201,0.0003153536,0.0002426413,0.00040393483,0.00015148787,0.00006642746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055591605,0.0002837001,0.00029956002,0.000042847227,0.00032017415,0.00023038764,0.00032753684,0.00013472376,0.000009925108],"category_scores_gemma":[0.0004922729,0.00018665788,0.00017208964,0.0003484315,0.00009886404,0.000025754438,0.00015430762,0.00015734517,0.000022460805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006646623,0.00012284845,0.00072415103,0.000667535,0.0012670627,0.000005840629,0.00037095812,0.6727924,0.0013412226,0.015488655,0.09255692,0.21399775],"study_design_scores_gemma":[0.00046882016,0.00041799655,0.0001851474,0.00012935196,0.000082946586,0.000003944894,0.0002121432,0.23354493,0.00088345044,0.00279181,0.76093066,0.0003487992],"about_ca_topic_score_codex":0.0000011639158,"about_ca_topic_score_gemma":0.00001627456,"teacher_disagreement_score":0.66837376,"about_ca_system_score_codex":0.000022558732,"about_ca_system_score_gemma":0.00006820912,"threshold_uncertainty_score":0.7611687},"labels":[],"label_agreement":null},{"id":"W4416751600","doi":"10.1093/bioadv/vbaf307","title":"Omics BioAnalytics: an RShiny application for multimodal biomarker panel discovery and assessment","year":2025,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; University of British Columbia; Prevention of Organ Failure; Stornoway Diamond (Canada); Providence Health Care","funders":"National Institute of Allergy and Infectious Diseases; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Biomarker discovery; Biomarker; Omics; Genomics; Precision medicine","score_opus":0.013368177004067927,"score_gpt":0.3011272475436773,"score_spread":0.28775907053960936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416751600","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053701986,0.0015348797,0.93975323,0.0002476447,0.0003163018,0.0009383106,0.00022628291,0.000028784105,0.003252552],"genre_scores_gemma":[0.78619283,0.0023662637,0.20792897,0.0010556134,0.00017798139,0.00019631084,0.0014597598,0.000027928445,0.00059432356],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893856,0.000012441748,0.00047109937,0.00021739796,0.00009442242,0.00026607187],"domain_scores_gemma":[0.99919796,0.00003433623,0.00020473261,0.00039440207,0.00008855885,0.00007998192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000295574,0.00020582136,0.00019781137,0.00008213682,0.00017567094,0.0001466027,0.00022222663,0.00015834895,8.505109e-7],"category_scores_gemma":[0.000027884626,0.00018208814,0.00007599332,0.000099606455,0.00012288723,0.00007756514,0.00013052062,0.0000766642,0.0000013563313],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029897716,0.00021464049,0.0037929593,0.0008707355,0.00032795762,2.724067e-7,0.00025172217,0.001445989,0.018247116,0.027880108,0.0014948942,0.94517463],"study_design_scores_gemma":[0.0016128899,0.00030783057,0.002895879,0.000043049477,0.00009651846,0.0000057041857,0.0011005457,0.7632313,0.0042175753,0.005728451,0.22022012,0.00054014416],"about_ca_topic_score_codex":0.000006719747,"about_ca_topic_score_gemma":0.00003693765,"teacher_disagreement_score":0.9446345,"about_ca_system_score_codex":0.000025738113,"about_ca_system_score_gemma":0.00011668325,"threshold_uncertainty_score":0.74253386},"labels":[],"label_agreement":null},{"id":"W4417046158","doi":"10.1093/bioadv/vbaf311","title":"Mapping educational needs in bioinformatics in Brazil: adapting ISCB 3.0 competencies to a regional context","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Context (archaeology); Curriculum; Socioeconomic status; Scalability; Curriculum framework","score_opus":0.02452441183690168,"score_gpt":0.30692260802188703,"score_spread":0.28239819618498535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417046158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86216754,0.02289878,0.050886095,0.017172923,0.0030128052,0.003261964,0.00034354866,0.00019537762,0.040060982],"genre_scores_gemma":[0.896901,0.004028619,0.09257966,0.0036996126,0.000571261,0.00015573486,0.000552609,0.000052988173,0.0014584884],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972851,0.00003428359,0.001160607,0.00022397972,0.00059880025,0.0006972246],"domain_scores_gemma":[0.99899703,0.00015055097,0.00012768358,0.0003276754,0.0001379105,0.00025912008],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007818095,0.00030406777,0.00030958274,0.0010147097,0.00009645884,0.00020495916,0.00050517166,0.00019441386,0.000038489812],"category_scores_gemma":[0.00046711377,0.0002700307,0.00011421256,0.001087665,0.00022403293,0.0001023708,0.00029312464,0.0002916783,0.00019296164],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033493593,0.00050048484,0.013547425,0.0057486966,0.00021546193,0.000026064552,0.04482907,0.003308308,0.016241822,0.009598131,0.041290287,0.8643593],"study_design_scores_gemma":[0.0011567954,0.0005634983,0.0046381447,0.0013912241,0.000008773578,0.0000777119,0.034658156,0.114948384,0.0026820104,0.0010580237,0.83782,0.0009972579],"about_ca_topic_score_codex":0.000040635117,"about_ca_topic_score_gemma":0.0004345158,"teacher_disagreement_score":0.8633621,"about_ca_system_score_codex":0.0001102268,"about_ca_system_score_gemma":0.00052523625,"threshold_uncertainty_score":0.9999752},"labels":[],"label_agreement":null},{"id":"W4417501327","doi":"10.1093/bioadv/vbaf301","title":"Perspectives in computational mass spectrometry: recent developments and key challenges","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Mass Spectrometry Techniques and Applications","field":"Chemistry","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council; Chan Zuckerberg Initiative; Wellcome Trust; Wellcome","keywords":"Grand Challenges; Key (lock); Field (mathematics); Cornerstone; Computational model","score_opus":0.021592840743025917,"score_gpt":0.28652386438425465,"score_spread":0.2649310236412287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417501327","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03038261,0.12621598,0.02866211,0.007871973,0.0001764724,0.0004908959,0.00015332457,0.0011446179,0.804902],"genre_scores_gemma":[0.53695905,0.058161348,0.4044309,0.000027498512,0.000056769804,0.000071257,0.000043016273,0.000018695513,0.0002314812],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99918735,0.0000035593239,0.00026657365,0.00017768466,0.00018173027,0.00018310522],"domain_scores_gemma":[0.99968016,0.00007711603,0.000051670228,0.0001086597,0.000032126874,0.000050268063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000102949794,0.00013186407,0.00013366962,0.00019974452,0.00005235953,0.00008399155,0.000112027585,0.000051312552,0.00048261997],"category_scores_gemma":[0.000024195822,0.0001202105,0.000021988159,0.0003053884,0.000052146966,0.0002929921,0.000044470784,0.00014282292,0.000018089222],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012046474,0.000105188745,0.0008387343,0.0012485721,0.00006438028,0.00000989187,0.0046065142,0.00008498712,0.0010470818,0.7920298,0.000222897,0.19972993],"study_design_scores_gemma":[0.00070464035,0.000094901516,0.0033527624,0.00067864347,0.000027307666,0.000077804,0.020406594,0.05212003,0.007539536,0.3174605,0.59648114,0.0010561192],"about_ca_topic_score_codex":0.0000014546383,"about_ca_topic_score_gemma":0.0000048773804,"teacher_disagreement_score":0.8046705,"about_ca_system_score_codex":0.00013293396,"about_ca_system_score_gemma":0.000041270316,"threshold_uncertainty_score":0.52843505},"labels":[],"label_agreement":null}]}