{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":65,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":65,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"8b096c79865a","filters":{"venue":"Bioinformatics Advances"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04813062175676968,"gpt":0.3011984307456495,"spread":0.2530678089888798,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003112767,0.0002194293,0.000181329,0.00009106306,0.0001934833,0.0001121261,0.00050709,0.0001400144,0.000004425395],"category_scores_gemma":[0.0001119077,0.0002118488,0.00005340531,0.0002912839,0.00006293596,0.0001113955,0.0001085606,0.00006687319,0.00003360179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002939896,"about_ca_system_score_gemma":0.0001622164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009809046,"about_ca_topic_score_gemma":0.00002022999,"domain_scores_codex":[0.9986255,0.00002367363,0.0004650101,0.0003166486,0.0001836455,0.0003855797],"domain_scores_gemma":[0.9988349,0.00003517106,0.0002033581,0.0006565549,0.0001818334,0.00008815886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001313945,0.00008451771,0.0001975155,0.0004026951,0.00001977074,0.000002026087,0.0003822964,0.005181468,0.9761408,0.00001769914,0.003681777,0.01375804],"study_design_scores_gemma":[0.00118666,0.0008768142,0.000064876,0.00003575914,0.00004179916,0.00000707563,0.000932672,0.4408789,0.5016875,0.00007162101,0.05367381,0.0005425858],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9725662,0.000728194,0.0217651,0.00005077204,0.00114483,0.0007123028,0.0005672602,0.0004871517,0.001978152],"genre_scores_gemma":[0.9155199,0.0008213226,0.07081461,0.0003020884,0.0003341254,0.00003306247,0.01158788,0.00007044854,0.0005165929],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4744534,"threshold_uncertainty_score":0.8638944,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06966997547000747,"gpt":0.3625614829663176,"spread":0.2928915074963101,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002100143,0.0002095966,0.0002089138,0.00009990302,0.0003011487,0.00005801633,0.0004053776,0.00008384888,0.000001790769],"category_scores_gemma":[0.0001211574,0.0001883951,0.00008715875,0.0001733066,0.00005671951,0.00005659304,0.000407547,0.00005714599,0.00001989441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003504129,"about_ca_system_score_gemma":0.0002965589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002502374,"about_ca_topic_score_gemma":0.00003556086,"domain_scores_codex":[0.9987386,0.00001282277,0.0004343582,0.000311756,0.00009418423,0.0004082136],"domain_scores_gemma":[0.998899,0.00003705834,0.0002053006,0.0005980803,0.0001065728,0.0001539772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008205797,0.001075722,0.6393335,0.0170062,0.00135724,0.00001247511,0.005453395,0.1348646,0.1488422,0.001631568,0.02932482,0.02027766],"study_design_scores_gemma":[0.0005258434,0.0000431473,0.004685589,0.00004676781,0.00006359712,0.000004205032,0.000113679,0.9755995,0.0002081622,0.00006748047,0.01838252,0.0002595408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7018338,0.002225309,0.2867727,0.0003255514,0.000906282,0.001732455,0.005578785,0.0002953677,0.0003297068],"genre_scores_gemma":[0.7801226,0.001102855,0.210147,0.0001517208,0.0003690654,0.00004759654,0.0074183,0.00006654538,0.0005743014],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8407349,"threshold_uncertainty_score":0.7682527,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02197307786622078,"gpt":0.3223211017238577,"spread":0.3003480238576369,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008858414,0.0007985719,0.001214402,0.0007638651,0.0004010389,0.0004639722,0.00173404,0.0003453056,0.000006866334],"category_scores_gemma":[0.0001048795,0.0004711975,0.0004032169,0.001847938,0.0004118738,0.001264125,0.001093788,0.001509282,0.000143494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001459327,"about_ca_system_score_gemma":0.0001472483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002321181,"about_ca_topic_score_gemma":0.00002167198,"domain_scores_codex":[0.9962911,0.0002804732,0.001383458,0.0006760331,0.0006287269,0.0007401815],"domain_scores_gemma":[0.9974239,0.0007137192,0.0008578463,0.000697356,0.00007001123,0.000237196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005064158,0.00004918819,0.00006933852,0.008036601,0.00007904167,0.00004959047,0.002304575,0.00001970559,8.809108e-8,0.001157413,0.002543922,0.9856855],"study_design_scores_gemma":[0.0002706378,0.0001056607,0.00000716502,0.006511226,0.0001572979,0.0004281407,0.0002416374,0.005476393,3.145072e-7,0.003082555,0.9832287,0.0004902993],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001673349,0.9891195,0.007153403,0.0002077809,0.001095705,0.001004393,0.00009886292,0.0003474573,0.0009561108],"genre_scores_gemma":[0.0000315685,0.9894068,0.009514823,0.0001126472,0.0003510161,0.0002182613,0.0001178312,0.00004431693,0.0002027239],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9851952,"threshold_uncertainty_score":0.999774,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.00998602961376684,"gpt":0.2305397237886313,"spread":0.2205536941748644,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000363326,0.000268043,0.0001989172,0.0001760661,0.000264516,0.0001064923,0.0002792465,0.0001659479,0.00001484913],"category_scores_gemma":[0.00005592763,0.0002451797,0.0001434139,0.0004712301,0.00009271537,0.00004542662,0.0001439165,0.0001520753,0.0001361958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001971235,"about_ca_system_score_gemma":0.00008931897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004188146,"about_ca_topic_score_gemma":0.00001647445,"domain_scores_codex":[0.9984353,0.0000200794,0.0005394026,0.0002226426,0.0002678978,0.0005147001],"domain_scores_gemma":[0.9990362,0.00001213569,0.0002819919,0.0004586731,0.00008877584,0.0001222292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001137916,0.0002441541,0.002995202,0.003218307,0.0004937883,0.00002116962,0.0008148765,0.09871135,0.2509147,0.009083945,0.0125431,0.6198215],"study_design_scores_gemma":[0.004404766,0.002184614,0.001541864,0.0009808973,0.0001016393,0.00002588982,0.001769994,0.2857419,0.1583259,0.01388297,0.528308,0.00273158],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7929319,0.001603966,0.1932906,0.0002585963,0.0009797278,0.001696265,0.00006644515,0.0003891674,0.008783329],"genre_scores_gemma":[0.9818309,0.0001619029,0.01601361,0.0003793704,0.0003796247,0.0001892909,0.0004360381,0.00004440857,0.0005648566],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6170899,"threshold_uncertainty_score":0.9998137,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02440852627287932,"gpt":0.3178043947498375,"spread":0.2933958684769581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001041744,0.0001739844,0.0001476959,0.0002783037,0.0002158596,0.000898756,0.0002652057,0.00004062354,0.000002073873],"category_scores_gemma":[0.0002286805,0.0001523013,0.0000612899,0.0004905657,0.00008736421,0.006048484,0.0003000039,0.0001662913,0.00001338329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008895434,"about_ca_system_score_gemma":0.0001117763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000578149,"about_ca_topic_score_gemma":0.000002805564,"domain_scores_codex":[0.9986083,0.0001789678,0.0003838506,0.0002595381,0.0003311952,0.0002381836],"domain_scores_gemma":[0.9987877,0.0007859753,0.0001004201,0.0001999589,0.00004876995,0.00007716464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000161062,0.00006057978,0.001401484,0.0005958517,0.00009329284,0.00003589023,0.009265445,0.2572615,0.001930002,0.01324474,0.00006267631,0.7158875],"study_design_scores_gemma":[0.0001787078,0.0000401517,0.004007437,0.0001218538,0.000009785033,0.00006046772,0.000304921,0.9880123,0.000241643,0.001309265,0.005535138,0.0001783604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1793057,0.002508284,0.8168214,0.0001312208,0.0007433855,0.0001263756,0.00001101266,0.0002263432,0.0001262275],"genre_scores_gemma":[0.394801,0.0002093654,0.6046771,0.00005500869,0.00005159472,0.000008508692,0.000008702639,0.0000139007,0.0001748744],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7307508,"threshold_uncertainty_score":0.8666724,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01643830154938968,"gpt":0.2404196319931348,"spread":0.2239813304437452,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001458029,0.0001292306,0.0001682316,0.0001022346,0.00007704356,0.00001682711,0.0001624365,0.00006832073,0.00001072195],"category_scores_gemma":[0.00002180981,0.0001259937,0.00005959221,0.0001825758,0.00005383999,0.0001579441,0.00007000003,0.00009281695,0.000001125788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003407691,"about_ca_system_score_gemma":0.00004226785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001708468,"about_ca_topic_score_gemma":0.000005184257,"domain_scores_codex":[0.9988602,0.0000357738,0.0006567069,0.00008850107,0.0002325239,0.0001263026],"domain_scores_gemma":[0.999148,0.00001789542,0.0005360816,0.0001776681,0.00009903729,0.00002134466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001607007,0.0001926833,0.0001335751,0.0002704812,0.000002968317,1.228083e-7,0.002050483,0.2487143,0.7445386,0.00003426618,0.00005701091,0.003844785],"study_design_scores_gemma":[0.0007838474,0.000412068,0.00008565765,0.00005072715,0.000008687869,0.000002199133,0.001929108,0.07775187,0.917834,0.0000490639,0.0009527139,0.0001400917],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8250114,0.0002387493,0.1727204,0.00002079801,0.0001802623,0.0002852759,0.00009308889,0.00001015409,0.001439848],"genre_scores_gemma":[0.9528873,0.0001504408,0.04573569,0.00006092971,0.00001273948,0.00002205977,0.001110618,0.000007599227,0.00001263459],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1732953,"threshold_uncertainty_score":0.5137872,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01358583109972697,"gpt":0.240774630662151,"spread":0.2271887995624241,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001459258,0.0001666066,0.0001524159,0.00005578075,0.0002351696,0.00003991782,0.0001758775,0.00007558219,0.000007074405],"category_scores_gemma":[0.00009230008,0.0001608599,0.00006956344,0.0001274164,0.00006263651,0.000004822355,0.0002278139,0.00007570063,0.00002795962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001546811,"about_ca_system_score_gemma":0.00003092333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003055889,"about_ca_topic_score_gemma":0.00003396034,"domain_scores_codex":[0.9990906,0.00001290975,0.000292625,0.0001880139,0.0001165803,0.000299253],"domain_scores_gemma":[0.9995099,0.00003578583,0.0001624325,0.0001858989,0.0000474379,0.00005854662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007931037,0.00002286254,0.07492121,0.00008077327,0.0002618687,0.000001424482,0.00108493,0.07128993,0.8080968,0.00004579388,0.00009239782,0.04402273],"study_design_scores_gemma":[0.002235893,0.0006639165,0.09350401,0.0001081935,0.0001693406,0.00001873702,0.01188741,0.6917344,0.041433,0.0006070693,0.1560999,0.001538197],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904574,0.002328593,0.005336562,0.00001583116,0.0003418517,0.0001234934,0.00005012442,0.00002572202,0.001320385],"genre_scores_gemma":[0.9651415,0.002125172,0.03204978,0.00007753421,0.000316713,0.00001025187,0.0001398817,0.00002906802,0.0001100874],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7666638,"threshold_uncertainty_score":0.6559677,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.015503383659866,"gpt":0.3227780611302261,"spread":0.3072746774703601,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007831453,0.0002335309,0.0002257582,0.00009786788,0.0004160383,0.0004845984,0.0002455572,0.0001722445,0.000004586972],"category_scores_gemma":[0.0008353583,0.0001551615,0.00008462232,0.0001538561,0.0004640044,0.00006036815,0.0001586013,0.0001750331,0.000006115062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002041598,"about_ca_system_score_gemma":0.0004687916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001080474,"about_ca_topic_score_gemma":0.000009323525,"domain_scores_codex":[0.9983818,0.00002270556,0.0006344147,0.0001895581,0.0003290638,0.0004424749],"domain_scores_gemma":[0.9989071,0.000266944,0.0001290655,0.0003027278,0.0001793844,0.0002147054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007439554,0.00001786575,0.00003261917,0.00132523,0.00006240343,2.652327e-7,0.001712874,0.000002627677,0.0002918919,0.009225694,0.002944981,0.9843091],"study_design_scores_gemma":[0.0004766777,0.0009988354,0.0001214059,0.0004840806,0.00004874309,0.00004996384,0.009218093,0.03511646,0.001330202,0.01706406,0.9346793,0.0004121896],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0570234,0.2147556,0.6853494,0.008034229,0.005382557,0.006148946,0.0009977024,0.0003197696,0.02198837],"genre_scores_gemma":[0.1718061,0.1186116,0.704452,0.00153679,0.001169027,0.0003612273,0.0004595475,0.00008436285,0.001519304],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.983897,"threshold_uncertainty_score":0.6327303,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.004768933118316525,"gpt":0.2879238221660577,"spread":0.2831548890477412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001497918,0.0001887293,0.0001590323,0.000126738,0.0000896742,0.0000679433,0.0001035752,0.00008477353,0.000005201399],"category_scores_gemma":[0.0000182325,0.0001659921,0.00005450226,0.0001752078,0.00003960133,0.00003495581,0.00006817904,0.0001263538,0.000002844834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004208161,"about_ca_system_score_gemma":0.00006092187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008518764,"about_ca_topic_score_gemma":0.00001836339,"domain_scores_codex":[0.9990521,0.00001276646,0.0002874671,0.0002017425,0.0001695894,0.000276344],"domain_scores_gemma":[0.9996699,0.00003215879,0.00005353951,0.0001554538,0.0000293112,0.0000596441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005055763,0.00006357628,0.007573706,0.002587584,0.0001410722,0.00003208904,0.0006760165,0.2601697,0.7004493,0.00009060244,0.0003638718,0.02780189],"study_design_scores_gemma":[0.0006927984,0.000448217,0.001614312,0.0008506181,0.00005302465,0.0001025119,0.0003640699,0.4145714,0.5429031,0.00008029793,0.03765237,0.0006673271],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8568426,0.01383226,0.1248222,0.00001224474,0.0006627049,0.0002732283,0.00002293106,0.00008520202,0.003446573],"genre_scores_gemma":[0.9284951,0.0004301344,0.07025481,0.00006840391,0.0003490994,0.00002748426,0.00009339159,0.00004569472,0.000235869],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1575463,"threshold_uncertainty_score":0.6768962,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2320234359275722,"gpt":0.440254693494518,"spread":0.2082312575669458,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008626283,0.0002569617,0.0004865834,0.0005287688,0.0001173332,0.0007428308,0.00272358,0.0001104056,0.00005724721],"category_scores_gemma":[0.01028023,0.000128135,0.0001422761,0.001524972,0.0004200061,0.0004579038,0.0009116872,0.0004727762,0.0003774076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003140889,"about_ca_system_score_gemma":0.0001392713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004356035,"about_ca_topic_score_gemma":0.0004001514,"domain_scores_codex":[0.9944757,0.0002146195,0.00182167,0.0005498622,0.002645167,0.0002929585],"domain_scores_gemma":[0.9909697,0.00685346,0.000584241,0.001323124,0.0002347142,0.0000347912],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001175587,0.00004575398,0.000007659153,0.00006075999,0.000008852522,0.00001860058,0.001157146,0.0005167106,0.00000137132,0.005770829,0.8446008,0.1477998],"study_design_scores_gemma":[0.00002056573,0.00005953504,0.00000538228,0.0001090174,0.00001119359,7.301708e-7,0.005546525,0.01360383,0.00002294377,0.02373381,0.9567239,0.0001625433],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.0002088083,0.002308407,0.1116383,0.0002268982,0.8788761,0.0004635121,0.001795503,0.00004314192,0.004439319],"genre_scores_gemma":[0.008874612,0.004501619,0.1282632,0.0005273704,0.8472723,0.0001669596,0.008076198,0.00006045541,0.002257235],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.1476372,"threshold_uncertainty_score":0.9980566,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06140797670486976,"gpt":0.3298371960912405,"spread":0.2684292193863708,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002604598,0.0001584374,0.0004353574,0.0000750947,0.00007609579,0.00004363653,0.0004126504,0.00008572138,0.0003064142],"category_scores_gemma":[0.0004775034,0.0001340292,0.00007129584,0.0003475226,0.0003041139,0.0008541915,0.0003551345,0.000178324,0.00009391964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009598819,"about_ca_system_score_gemma":0.004029973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004844307,"about_ca_topic_score_gemma":0.00009115839,"domain_scores_codex":[0.9980883,0.00003635773,0.0007593488,0.0002440005,0.0005880609,0.0002839483],"domain_scores_gemma":[0.9978404,0.0002398192,0.0002921891,0.001206148,0.0003053038,0.0001161444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008549942,0.0003773645,0.003107581,0.003934447,0.001033841,0.0003406131,0.002462932,0.0003687959,0.04341821,0.001422252,0.007198715,0.9354802],"study_design_scores_gemma":[0.02665802,0.0006351763,0.001143224,0.003287224,0.0005577048,0.002997089,0.0176215,0.4735449,0.2008282,0.005408474,0.2662137,0.001104819],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8279358,0.06807673,0.01749467,0.002027346,0.003041318,0.001509235,0.004529996,0.0003490736,0.07503589],"genre_scores_gemma":[0.4735067,0.02131657,0.4993144,0.0007891419,0.0005742584,0.00002407896,0.003750239,0.00005351389,0.0006711847],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9343755,"threshold_uncertainty_score":0.7148999,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02130643004791029,"gpt":0.2605602040231485,"spread":0.2392537739752382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005742109,0.0003691276,0.0003284999,0.0001066472,0.001064487,0.000164112,0.0005136307,0.0001283379,0.00004148663],"category_scores_gemma":[0.0001035684,0.0003561415,0.0001667688,0.0001857778,0.0001036051,0.000140528,0.000387826,0.0004317624,0.000003588523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008417245,"about_ca_system_score_gemma":0.0001697215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007704384,"about_ca_topic_score_gemma":0.00003821586,"domain_scores_codex":[0.9978566,0.0001192306,0.000775796,0.0003949685,0.0003106626,0.0005427746],"domain_scores_gemma":[0.9985042,0.0000222243,0.0007038929,0.0004914235,0.0001158186,0.0001624526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001942445,0.0001284765,0.0002319635,0.0002277158,0.0001114054,0.000001294688,0.001022759,0.007641193,0.9813974,0.0002881229,0.0000348294,0.008720581],"study_design_scores_gemma":[0.001804831,0.001831928,0.00002301838,0.0001473499,0.00009259778,0.00006447453,0.008155259,0.6424904,0.2240887,0.001682168,0.1182478,0.001371473],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8389117,0.00137704,0.1551065,0.00003804989,0.0002514637,0.002471104,0.001049257,0.00007908525,0.0007158038],"genre_scores_gemma":[0.7985603,0.00002535343,0.1968652,0.00010061,0.0004060914,0.0008567967,0.002597019,0.00005974856,0.0005289033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7573088,"threshold_uncertainty_score":0.9998891,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01044655336417397,"gpt":0.2654293748247018,"spread":0.2549828214605278,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001521827,0.0001039516,0.00009802259,0.00004415306,0.000205295,0.00002793809,0.0002773977,0.00002295922,0.00006794457],"category_scores_gemma":[0.00007687536,0.00009830201,0.00005315332,0.00009907563,0.00001958812,0.000009337726,0.0003951061,0.00006853806,0.00004508748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003242291,"about_ca_system_score_gemma":0.00004108579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005717238,"about_ca_topic_score_gemma":0.00003276272,"domain_scores_codex":[0.9990656,0.00002555229,0.0002086074,0.000154383,0.0002823263,0.0002635121],"domain_scores_gemma":[0.9994488,0.0000201008,0.00006067568,0.0003022619,0.00002709395,0.0001410871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004497248,0.0001689653,0.004945045,0.00005840163,0.00009803633,0.000008828349,0.001022533,0.0103431,0.8562658,0.0001065959,0.03132229,0.09521062],"study_design_scores_gemma":[0.0007975403,0.0005804776,0.0004455738,0.000009185235,0.000006048512,0.000004634023,0.002760937,0.008304842,0.1198169,0.00008011136,0.8668891,0.0003046842],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9905829,0.000502529,0.006554234,0.000307533,0.000192191,0.0003143474,0.0001848879,0.00002015049,0.001341195],"genre_scores_gemma":[0.9747881,0.0001468613,0.02133823,0.001394092,0.0001872532,0.0001790053,0.0003543436,0.00001784349,0.001594271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8355668,"threshold_uncertainty_score":0.4008639,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03916500014261359,"gpt":0.355114292073487,"spread":0.3159492919308735,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000499069,0.0001329924,0.000154027,0.0001088196,0.000241135,0.00006495871,0.0001927334,0.00008214828,0.00009755916],"category_scores_gemma":[0.0005314002,0.0001006079,0.00006834175,0.0001388681,0.0001150565,0.000317036,0.00007257252,0.0001819246,0.0007416712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000569335,"about_ca_system_score_gemma":0.00006894523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006274473,"about_ca_topic_score_gemma":0.000005399063,"domain_scores_codex":[0.9991229,0.00008905561,0.0003017299,0.0001442073,0.00004008387,0.0003020339],"domain_scores_gemma":[0.9991268,0.0005059824,0.00008475493,0.0002031588,0.00004426946,0.0000350463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003857516,0.00005037305,0.001682112,0.0006464491,0.0003138462,0.000001188545,0.00174345,0.00006492704,0.04288044,0.01394633,0.007234257,0.931398],"study_design_scores_gemma":[0.0007688925,0.0002577937,0.0001599848,0.00008949241,0.00004254423,0.00001641663,0.0006686157,0.02654661,0.02162208,0.002522584,0.9471385,0.000166429],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01060468,0.145412,0.8100829,0.004506301,0.002460534,0.002337732,0.001175827,0.001100563,0.0223195],"genre_scores_gemma":[0.1339328,0.003342785,0.8451777,0.000198894,0.0001177881,0.0005447178,0.0050592,0.00006224723,0.01156392],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9399043,"threshold_uncertainty_score":0.953293,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04017187588871809,"gpt":0.2551354453461746,"spread":0.2149635694574565,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001847388,0.0002548091,0.0002059328,0.00009661428,0.0001692551,0.0001047328,0.0006413082,0.0001091203,0.000008418778],"category_scores_gemma":[0.00004077726,0.0002092019,0.0000561011,0.0003468524,0.000128087,0.0000580825,0.0002204354,0.0001036042,0.00005006072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001049894,"about_ca_system_score_gemma":0.00007432445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001439235,"about_ca_topic_score_gemma":0.00008741119,"domain_scores_codex":[0.9986206,0.00001850461,0.0003570551,0.0003313291,0.0002469744,0.0004254907],"domain_scores_gemma":[0.9987286,0.00002608085,0.0001610064,0.000890567,0.00007217781,0.0001215834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006764581,0.0003933682,0.0202424,0.0009974039,0.0002617406,0.00004535775,0.001029483,0.005591715,0.9030588,0.0001348805,0.007356555,0.06021185],"study_design_scores_gemma":[0.003399429,0.001552501,0.001118756,0.0001707243,0.0001185618,0.00005003938,0.001535868,0.02332872,0.6131064,0.0001477764,0.3539514,0.001519883],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9703512,0.001835131,0.02144184,0.0001188844,0.0006692511,0.0004522402,0.0005780797,0.0001950538,0.004358309],"genre_scores_gemma":[0.9512679,0.00319216,0.03968528,0.0004250296,0.0004591124,0.00002697347,0.004222197,0.00009525118,0.0006260733],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3465948,"threshold_uncertainty_score":0.8531007,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.007110007031997439,"gpt":0.2391215279493388,"spread":0.2320115209173414,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001071565,0.000118753,0.00022458,0.0001724235,0.00006251015,0.00005914523,0.00007081398,0.00002897904,0.00002959586],"category_scores_gemma":[0.00003390784,0.00006496841,0.00009297156,0.0005126626,0.00006222141,0.0003861176,0.00007817748,0.00009879476,0.000002650026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006975119,"about_ca_system_score_gemma":0.00005895582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003940665,"about_ca_topic_score_gemma":0.00002466698,"domain_scores_codex":[0.9990743,0.00001762238,0.00037566,0.0001015975,0.0002950465,0.0001358071],"domain_scores_gemma":[0.9996068,0.00002516806,0.0001073972,0.0001586699,0.00006331701,0.00003857778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002823832,0.0006143738,0.8028719,0.004628418,0.001554452,0.00003462587,0.01057871,0.005616982,0.001473043,0.0004144374,0.000092811,0.1718379],"study_design_scores_gemma":[0.002030099,0.0005060603,0.2527952,0.004104689,0.002248261,0.00002436906,0.001718903,0.7295621,0.001977138,0.0001427782,0.004534848,0.0003555914],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9952987,0.0003901204,0.001780818,0.00005338311,0.0003307628,0.0003449058,0.00009143097,0.00003492625,0.001674995],"genre_scores_gemma":[0.9962252,0.0001353834,0.003442002,0.00004148086,0.00004506184,0.000009618922,0.00004546033,0.00001278078,0.0000430107],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7239451,"threshold_uncertainty_score":0.2649335,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02329046184857348,"gpt":0.2499431431405594,"spread":0.2266526812919859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003012273,0.0002049645,0.0002933449,0.0002249773,0.00006713717,0.00004771689,0.0002664299,0.0001462825,0.000005960308],"category_scores_gemma":[0.00009753006,0.000193964,0.0002130896,0.0005989606,0.00009526016,0.00003839514,0.00008761912,0.0001171016,0.0000107046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002938096,"about_ca_system_score_gemma":0.0000785763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001880012,"about_ca_topic_score_gemma":0.0002667725,"domain_scores_codex":[0.9986461,0.0000253361,0.0005237252,0.0002611091,0.000173332,0.0003703895],"domain_scores_gemma":[0.9993692,0.00003043663,0.0001406749,0.0003253566,0.00005066741,0.00008367641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004164279,0.0003055869,0.006722047,0.0003336331,0.0002998674,0.000004438248,0.006948936,0.1758245,0.735035,0.00009353106,0.0002098065,0.07380629],"study_design_scores_gemma":[0.00120014,0.0002856604,0.0004635194,0.00002338191,0.0001314543,0.000001112419,0.002163432,0.920497,0.07108972,0.0004048858,0.00322427,0.0005153905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.949392,0.0002771257,0.04497312,0.00004839431,0.0003278592,0.0002075745,0.00006554185,0.00006266032,0.00464569],"genre_scores_gemma":[0.9874762,0.000241751,0.01160591,0.0001161604,0.00007320147,0.00001670274,0.000235716,0.00001685676,0.0002175463],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7446725,"threshold_uncertainty_score":0.7909622,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03687343643295704,"gpt":0.3371535968671262,"spread":0.3002801604341692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001625088,0.0001041892,0.0001572941,0.00003235545,0.0000774977,0.00001952525,0.0003282185,0.00008841229,0.00003762092],"category_scores_gemma":[0.0000651446,0.00009378715,0.00004104762,0.00006120998,0.0001066572,0.00001832628,0.0003485577,0.00005288025,0.00003227568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000189965,"about_ca_system_score_gemma":0.00008583754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002369874,"about_ca_topic_score_gemma":0.0001056051,"domain_scores_codex":[0.9991472,0.00002146564,0.000390032,0.0001947377,0.00009870868,0.0001479068],"domain_scores_gemma":[0.9993313,0.00007095164,0.0001455337,0.0003657867,0.00004532472,0.00004112372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001117242,0.0002636554,0.4946676,0.001092715,0.0009260578,0.000005642132,0.001667136,0.05994702,0.2493836,0.002886649,0.05227872,0.1367695],"study_design_scores_gemma":[0.001327688,0.000704509,0.2694463,0.0002546045,0.0001801611,0.00002206162,0.0009479243,0.3832493,0.01571884,0.01727034,0.3097022,0.001176141],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9649525,0.006882804,0.02504881,0.0001131275,0.0002553089,0.0001009742,0.001010159,0.0000181214,0.001618185],"genre_scores_gemma":[0.9515955,0.0006782787,0.04384879,0.00008450243,0.0001453197,0.000005368394,0.003485098,0.000008799008,0.0001483621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3233022,"threshold_uncertainty_score":0.3824529,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02636127204626749,"gpt":0.2936164668138977,"spread":0.2672551947676303,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000141891,0.0001242131,0.0001522579,0.00004757779,0.00005508945,0.00002707189,0.0001415405,0.0001044293,0.000002376307],"category_scores_gemma":[0.00007976643,0.0001078905,0.0001079185,0.00006891059,0.00009176358,0.000003574525,0.00005674118,0.00005690727,0.000004324332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001067723,"about_ca_system_score_gemma":0.00006375611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.281279e-7,"about_ca_topic_score_gemma":0.000005240627,"domain_scores_codex":[0.9992472,0.000008119995,0.000333352,0.0001633005,0.00007733761,0.0001707037],"domain_scores_gemma":[0.9995387,0.00006656922,0.00006165339,0.0002326113,0.00005860135,0.00004186824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002390494,0.0000966485,0.001605428,0.001454266,0.0003822776,8.189533e-7,0.000592218,0.00042852,0.4664538,0.1269068,0.004733155,0.397107],"study_design_scores_gemma":[0.0002704901,0.0008388154,0.002025433,0.0001590762,0.00008050205,0.00001359548,0.0007021984,0.01542618,0.1160631,0.01944632,0.8444918,0.0004824614],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4018608,0.01861231,0.5706702,0.0003444573,0.0009782679,0.0007820462,0.0002599808,0.0000217673,0.006470184],"genre_scores_gemma":[0.8432097,0.001762905,0.1545554,0.00004662148,0.0001970273,0.00008471179,0.00005746886,0.00001344935,0.00007271062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8397587,"threshold_uncertainty_score":0.4399648,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02159284074302592,"gpt":0.2865238643842546,"spread":0.2649310236412287,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001029498,0.0001318641,0.0001336696,0.0001997445,0.00005235953,0.00008399155,0.0001120276,0.00005131255,0.00048262],"category_scores_gemma":[0.00002419582,0.0001202105,0.00002198816,0.0003053884,0.00005214697,0.0002929921,0.00004447078,0.0001428229,0.00001808922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000132934,"about_ca_system_score_gemma":0.00004127032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001454638,"about_ca_topic_score_gemma":0.00000487738,"domain_scores_codex":[0.9991874,0.000003559324,0.0002665737,0.0001776847,0.0001817303,0.0001831052],"domain_scores_gemma":[0.9996802,0.00007711603,0.00005167023,0.0001086597,0.00003212687,0.00005026806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001204647,0.0001051887,0.0008387343,0.001248572,0.00006438028,0.00000989187,0.004606514,0.00008498712,0.001047082,0.7920298,0.000222897,0.1997299],"study_design_scores_gemma":[0.0007046403,0.00009490152,0.003352762,0.0006786435,0.00002730767,0.000077804,0.02040659,0.05212003,0.007539536,0.3174605,0.5964811,0.001056119],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.03038261,0.126216,0.02866211,0.007871973,0.0001764724,0.0004908959,0.0001533246,0.001144618,0.804902],"genre_scores_gemma":[0.5369591,0.05816135,0.4044309,0.00002749851,0.0000567698,0.000071257,0.00004301627,0.00001869551,0.0002314812],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8046705,"threshold_uncertainty_score":0.5284351,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03347243952663514,"gpt":0.2359122800225138,"spread":0.2024398404958787,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002725903,0.0001105077,0.0001224851,0.00004631594,0.00015016,0.00001277135,0.0001436965,0.00004965788,4.80993e-7],"category_scores_gemma":[0.0001645513,0.00008072394,0.00006223122,0.0001532419,0.0000687003,0.000007223025,0.0001288162,0.00004721156,0.000007644619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001426133,"about_ca_system_score_gemma":0.00002979914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002092722,"about_ca_topic_score_gemma":0.000005759319,"domain_scores_codex":[0.9992604,0.0000189392,0.0002644773,0.0001241172,0.000150697,0.0001813575],"domain_scores_gemma":[0.9995013,0.00002113718,0.0001073212,0.000193561,0.0001402965,0.00003642325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001767028,0.00003063752,0.001436215,0.00006024844,0.0002193506,3.232475e-7,0.003907256,0.9266742,0.05546023,0.006303371,0.00006914658,0.005662336],"study_design_scores_gemma":[0.000676888,0.0004898934,0.004002317,0.00008070789,0.00006618464,0.00000389768,0.002827121,0.9059312,0.07135876,0.00840276,0.00574795,0.0004123545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8368408,0.001476644,0.1601265,0.00008789837,0.0001253078,0.0003285693,0.00005723048,0.000009670134,0.0009473413],"genre_scores_gemma":[0.99681,0.0004429459,0.00258692,0.00002963588,0.00003915278,0.0000319194,0.00003237326,0.00000781298,0.000019248],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1599692,"threshold_uncertainty_score":0.3291827,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03960482596782377,"gpt":0.3467256947207792,"spread":0.3071208687529554,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003369793,0.0001031188,0.0001748753,0.0001404974,0.00007102118,0.00007719758,0.00006987804,0.00005224295,0.000001164839],"category_scores_gemma":[0.00009255167,0.00008313102,0.00003410561,0.0001877793,0.00003150674,0.0002063473,0.0001051766,0.00002658863,2.100779e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007426279,"about_ca_system_score_gemma":0.00001931525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005364821,"about_ca_topic_score_gemma":0.00005741695,"domain_scores_codex":[0.9993705,0.000009362162,0.0003224775,0.0001405078,0.00006843695,0.00008874079],"domain_scores_gemma":[0.9994602,0.00002796147,0.0001213665,0.0002747312,0.00009037813,0.00002533859],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000150355,0.0001284438,0.05771406,0.006389934,0.008078814,2.569928e-7,0.004061079,0.0008189791,0.01112635,0.004954223,0.001242668,0.9053348],"study_design_scores_gemma":[0.0003883705,0.0006189602,0.03066038,0.00005001608,0.00142632,0.000006729196,0.001259733,0.9406741,0.006210307,0.0003553728,0.01807266,0.0002770972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8213131,0.02141316,0.1560916,0.00005184824,0.0001673107,0.0005282668,0.0002470696,0.0000259185,0.0001617715],"genre_scores_gemma":[0.9489509,0.02695801,0.02028564,0.00002577084,0.00005891853,0.00003779079,0.003646904,0.00001066299,0.0000253424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9398551,"threshold_uncertainty_score":0.3389985,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01469638284561246,"gpt":0.2381064015665066,"spread":0.2234100187208941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002008979,0.0001411154,0.0001422768,0.00004577635,0.00007457563,0.00004832401,0.000262967,0.0001146399,0.00002681709],"category_scores_gemma":[0.00005310224,0.0001403021,0.0000411892,0.0001445346,0.00004319521,0.00004469927,0.0003532796,0.0001070798,0.00003873241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002639,"about_ca_system_score_gemma":0.0001226155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003636301,"about_ca_topic_score_gemma":0.0002660838,"domain_scores_codex":[0.9989918,0.00001629174,0.0004043088,0.0002116668,0.0001257913,0.0002501482],"domain_scores_gemma":[0.999084,0.00001158206,0.000128675,0.0006537834,0.00006251834,0.0000594712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003518961,0.0002913777,0.006911534,0.0004826912,0.0002104686,0.00001742304,0.0003698767,0.03656148,0.1767691,0.00120298,0.007653801,0.7691774],"study_design_scores_gemma":[0.002262464,0.0001728427,0.01225431,0.00005630503,0.00002685529,0.0001447845,0.0009293383,0.4348956,0.04494681,0.001596986,0.5018861,0.0008276146],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4237789,0.01372301,0.5383731,0.0003563688,0.002562277,0.0006206622,0.0003896409,0.00007273202,0.02012336],"genre_scores_gemma":[0.9577661,0.002683695,0.03552693,0.0007084206,0.0004524548,0.00002076276,0.002328461,0.00002472185,0.0004884443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7683498,"threshold_uncertainty_score":0.5721354,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03741575304613087,"gpt":0.2864572823709869,"spread":0.2490415293248561,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002567378,0.0000963407,0.00007971211,0.00001736489,0.000493009,0.00002766819,0.0007695163,0.00001749868,0.00002478176],"category_scores_gemma":[0.00003996903,0.00006918008,0.00002420837,0.0000712496,0.00006393311,0.000003145408,0.001369475,0.00007954495,0.000006587218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009623059,"about_ca_system_score_gemma":0.00004814394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005864408,"about_ca_topic_score_gemma":0.00001732404,"domain_scores_codex":[0.9993119,0.00002445077,0.0001895158,0.0001514282,0.0001482925,0.0001744123],"domain_scores_gemma":[0.9991344,0.00001903491,0.0001070216,0.0006892953,0.00002351895,0.00002671457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005450403,0.0003397803,0.04003975,0.0003998856,0.0009598655,0.00001203692,0.006201018,0.01694925,0.3151118,0.008051053,0.1406212,0.4707693],"study_design_scores_gemma":[0.0001921112,0.0001469903,0.001091523,0.000002220089,0.00001245575,0.00002121259,0.002567537,0.0007818964,0.002780001,0.0003158677,0.9919189,0.0001692599],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9081101,0.03769581,0.00444453,0.001034467,0.001688314,0.0008438227,0.001272684,0.00002668798,0.04488358],"genre_scores_gemma":[0.9916431,0.002258397,0.004885452,0.0004240548,0.0001212376,0.00004825154,0.0002687724,0.00001029827,0.000340393],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8512977,"threshold_uncertainty_score":0.3791876,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01512226752613497,"gpt":0.2575465096804743,"spread":0.2424242421543393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003211924,0.0001954954,0.000225774,0.00009348763,0.00007912346,0.00002573314,0.0004426029,0.00008949386,0.000003074114],"category_scores_gemma":[0.0001264971,0.0001375376,0.0000906151,0.000269077,0.0001546846,0.000004612269,0.0002071321,0.0000691869,0.00002073144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007567594,"about_ca_system_score_gemma":0.00005467131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001491263,"about_ca_topic_score_gemma":0.0006532706,"domain_scores_codex":[0.9987807,0.00005492874,0.0004862272,0.0001781856,0.0001920278,0.0003079242],"domain_scores_gemma":[0.9992023,0.00009797713,0.0001455202,0.0004346825,0.00007999103,0.00003955431],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004793607,0.0003855271,0.2088951,0.0009164321,0.0004070634,0.00001042688,0.01718564,0.009968309,0.3838265,0.001979703,0.01425154,0.3616944],"study_design_scores_gemma":[0.008734398,0.003165311,0.2049778,0.0002184144,0.0001604028,0.0000539509,0.03370261,0.03908348,0.2148821,0.002397056,0.490225,0.002399496],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940606,0.003090276,0.0003016887,0.0003150978,0.0001998084,0.0003632829,0.00007165714,0.000006293392,0.001591282],"genre_scores_gemma":[0.9939753,0.00345793,0.001521552,0.0007258418,0.0001039937,0.00005901015,0.00005840016,0.00001375785,0.00008426245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4759735,"threshold_uncertainty_score":0.5608621,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.004681615284073407,"gpt":0.3218662588925711,"spread":0.3171846436084977,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001447047,0.0001798204,0.0001321845,0.00007074428,0.0001390941,0.0000868989,0.0001568465,0.00009852593,0.000007852701],"category_scores_gemma":[0.00001320717,0.0001717292,0.00004734861,0.0004575388,0.00006072476,0.00008613707,0.00003982496,0.000192717,0.00002511642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005173354,"about_ca_system_score_gemma":0.00004158217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005051766,"about_ca_topic_score_gemma":0.0000189691,"domain_scores_codex":[0.9989334,0.00001202735,0.0003264866,0.0002382055,0.0001026467,0.0003872047],"domain_scores_gemma":[0.9997125,0.00001219535,0.00004088621,0.0001572106,0.00003669825,0.00004052498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000228253,0.00002094844,0.0005130465,0.0001716149,0.000009802821,4.118997e-7,0.000257936,0.0006735248,0.9063895,0.00006365598,0.00007137151,0.09180537],"study_design_scores_gemma":[0.0001490271,0.0003286827,0.000120853,0.00003865013,0.000005340586,0.000008807961,0.0002519879,0.003342368,0.8273247,0.00003493279,0.1681974,0.0001972828],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9276978,0.009976396,0.06143824,0.00004453401,0.00008045277,0.0003407348,0.00001628623,0.0001029571,0.0003025802],"genre_scores_gemma":[0.962544,0.01486663,0.02115281,0.00008411119,0.00008408386,0.0001120906,0.0002565984,0.00003627486,0.000863424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.168126,"threshold_uncertainty_score":0.7002913,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04697469140103604,"gpt":0.3454984677685396,"spread":0.2985237763675035,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006693537,0.0001364191,0.0002675119,0.0002134184,0.00005715346,0.00003514488,0.0001418376,0.000112308,0.000007853565],"category_scores_gemma":[0.0003206622,0.0001148486,0.0001691053,0.0002991951,0.00004099284,0.0000101695,0.00003968298,0.00005762469,0.000004462729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003025644,"about_ca_system_score_gemma":0.00007648782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006801452,"about_ca_topic_score_gemma":0.00009821358,"domain_scores_codex":[0.9989974,0.00005374996,0.0003976479,0.0002031434,0.00006998333,0.0002780441],"domain_scores_gemma":[0.9993564,0.0002796388,0.0001055977,0.0001821285,0.00004277821,0.00003338753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003385416,0.0001460258,0.07868057,0.001654295,0.003094239,0.00000755429,0.002739307,0.5039003,0.06331895,0.001993259,0.00533649,0.3387905],"study_design_scores_gemma":[0.001369726,0.0006313443,0.02555802,0.0001016973,0.0005710262,0.000004725251,0.002952048,0.5883162,0.08380283,0.004849144,0.2907289,0.00111435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1597377,0.006634419,0.831753,0.0003114994,0.0002902393,0.0002657744,0.0001464537,0.00003745096,0.0008235392],"genre_scores_gemma":[0.7325749,0.001167867,0.2651494,0.0002557054,0.00007446617,0.00009283978,0.0005269164,0.00001064776,0.0001473001],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5728372,"threshold_uncertainty_score":0.4683392,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01522251531141121,"gpt":0.2686701019971908,"spread":0.2534475866857796,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000204257,0.000259174,0.0002875034,0.00006603335,0.0001003898,0.0001269845,0.0002617503,0.0001878307,0.00002112002],"category_scores_gemma":[0.00002525303,0.0002309795,0.000132918,0.0001830988,0.0001238702,0.00006470136,0.00007941767,0.0001226687,0.000008976956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002360333,"about_ca_system_score_gemma":0.0001656826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001751277,"about_ca_topic_score_gemma":0.00004881101,"domain_scores_codex":[0.9986593,0.00002631038,0.0005412242,0.0001994659,0.0001908687,0.0003828112],"domain_scores_gemma":[0.9993006,0.00005432719,0.000193578,0.000305112,0.00004986765,0.00009650619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005488627,0.0001313844,0.002519509,0.002529397,0.001190834,0.00002203593,0.005255109,0.2240481,0.4991057,0.001910695,0.006271606,0.2564667],"study_design_scores_gemma":[0.001444091,0.0006544987,0.0008048703,0.001146615,0.00029847,0.00005302265,0.0009210812,0.807197,0.1110626,0.004076639,0.07082437,0.001516742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5132156,0.01612759,0.4661566,0.00003566905,0.002200613,0.0003655146,0.0002212277,0.00006540243,0.001611739],"genre_scores_gemma":[0.8513198,0.0009498758,0.1466486,0.0001313824,0.0005101551,0.00000666172,0.000380133,0.00003056109,0.00002282905],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.583149,"threshold_uncertainty_score":0.9419072,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09799458101637326,"gpt":0.4068712497562927,"spread":0.3088766687399195,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005023274,0.0001791047,0.0003209612,0.0005057193,0.0007010265,0.0005820518,0.0004148812,0.00004365424,0.00003767332],"category_scores_gemma":[0.0006414028,0.0001427572,0.00003329574,0.001117534,0.0001118509,0.002805563,0.0003451617,0.00006644009,0.00003320528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002037536,"about_ca_system_score_gemma":0.00003277618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009174537,"about_ca_topic_score_gemma":0.00006470878,"domain_scores_codex":[0.9970427,0.00007451566,0.001213596,0.0005156636,0.0008547709,0.0002988273],"domain_scores_gemma":[0.997825,0.0002692273,0.0006319826,0.0009906247,0.0001928415,0.0000903447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003296826,0.0008177079,0.03497032,0.003854626,0.0003283104,0.0000243926,0.02961265,0.6428764,0.01801957,0.01854708,0.06097408,0.1896452],"study_design_scores_gemma":[0.0005320617,0.00006565423,0.0003912138,0.0000825637,0.00003070918,0.00001288021,0.003010001,0.9360471,0.008890735,0.002650152,0.04804126,0.0002456584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9373771,0.0008273702,0.05807723,0.000112346,0.0005470209,0.0006436531,0.001797902,0.0001407036,0.0004766941],"genre_scores_gemma":[0.9800448,0.0002346238,0.01582197,0.00003989186,0.00003073093,0.000009660789,0.003683472,0.00001272653,0.0001221502],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2931707,"threshold_uncertainty_score":0.5821468,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01365889790151077,"gpt":0.2865778349318525,"spread":0.2729189370303417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008108189,0.0002054985,0.0001540431,0.0001206213,0.0001512172,0.000116238,0.0002152315,0.00005993845,0.000003025959],"category_scores_gemma":[0.0001002143,0.0001908993,0.00003437475,0.0004606372,0.00007138785,0.0000961659,0.00008011124,0.00007650791,0.000003801792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003246455,"about_ca_system_score_gemma":0.00008402332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001392071,"about_ca_topic_score_gemma":0.000008202838,"domain_scores_codex":[0.9988458,0.00003206953,0.000297212,0.0003251989,0.0002133401,0.0002863347],"domain_scores_gemma":[0.9990188,0.000005211667,0.0001557852,0.0004536112,0.0002565997,0.0001100161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004642894,0.0001342993,0.0008454351,0.00008407565,0.00001056015,0.000002334931,0.0002990118,0.001739704,0.9866694,0.0001957873,0.0000375998,0.009935376],"study_design_scores_gemma":[0.0002411132,0.0002382616,0.00008631505,0.00006692244,0.000007480977,0.000031478,0.001968242,0.004414899,0.9897066,0.0000347969,0.002871244,0.0003326478],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08696663,0.0005125097,0.9101752,0.00003563132,0.00003466923,0.0003790689,0.00001398204,0.00008527557,0.001797019],"genre_scores_gemma":[0.2869438,0.00003115487,0.7123325,0.0001983736,0.00004280259,0.00007016108,0.0003132567,0.00002849393,0.00003939883],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1999772,"threshold_uncertainty_score":0.7784647,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01775615102493194,"gpt":0.2633413426690291,"spread":0.2455851916440972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003374974,0.000105763,0.0001313845,0.0000564009,0.0002078183,0.00001385907,0.0001394149,0.00006756686,0.000008739394],"category_scores_gemma":[0.001056857,0.0000832594,0.0000983506,0.0001801001,0.0000472313,0.00001418701,0.0001292922,0.00005732339,0.00004998405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007562394,"about_ca_system_score_gemma":0.0000349321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006666871,"about_ca_topic_score_gemma":0.0001088067,"domain_scores_codex":[0.9990138,0.00007515046,0.0004051513,0.000123223,0.0001404781,0.0002421482],"domain_scores_gemma":[0.9989733,0.0001593058,0.0004624793,0.0002488689,0.0001043633,0.00005171773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002033888,0.0001464433,0.7325686,0.0001999068,0.0002617791,0.000001540217,0.0009755137,0.01687006,0.2046255,0.00006940438,0.02285399,0.02122392],"study_design_scores_gemma":[0.0005106861,0.0001595911,0.7182747,0.00003821655,0.00006660228,0.000004359952,0.0005322896,0.04396134,0.008327866,0.000172075,0.2276843,0.0002679485],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946809,0.0004833268,0.002493256,0.0009559945,0.0004540328,0.0002235629,0.0001115196,0.0000300241,0.0005673825],"genre_scores_gemma":[0.9937542,0.001168098,0.003105524,0.0002019769,0.0001596528,0.00004451968,0.0003993977,0.0000119724,0.001154631],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2048304,"threshold_uncertainty_score":0.339522,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01282611854482546,"gpt":0.278922961500048,"spread":0.2660968429552225,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003097754,0.0001872814,0.0001498862,0.000144487,0.0001689028,0.0001927782,0.0001498666,0.00008965448,0.00002018437],"category_scores_gemma":[0.0000196759,0.0001249595,0.000105194,0.0004109621,0.00007398333,0.00002453351,0.0001063309,0.00007973934,0.00001553949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002458638,"about_ca_system_score_gemma":0.00005140438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003166964,"about_ca_topic_score_gemma":0.00001034579,"domain_scores_codex":[0.9990264,0.00002355634,0.0003677081,0.0001703138,0.0001868424,0.000225156],"domain_scores_gemma":[0.9994562,0.00003834651,0.0001160643,0.0002840689,0.00003820202,0.00006707675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005778306,0.0005289556,0.01207238,0.003048248,0.01450906,0.00003926508,0.009983886,0.1171194,0.1563597,0.114167,0.0581212,0.513473],"study_design_scores_gemma":[0.0002440625,0.0002286018,0.0001551495,0.00005518784,0.0003572051,0.00001744086,0.000608852,0.8155501,0.01317589,0.0004731761,0.1687197,0.0004146189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.701874,0.01874753,0.2710094,0.0004774583,0.001005716,0.0008801037,0.000277422,0.0001007596,0.005627567],"genre_scores_gemma":[0.9868916,0.005456336,0.006069229,0.0008155,0.0002207957,0.00002022333,0.0003003717,0.00001915516,0.0002068347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6984307,"threshold_uncertainty_score":0.5095699,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.004588894427499391,"gpt":0.2638198506195027,"spread":0.2592309561920033,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003226819,0.0001911159,0.0002834759,0.0001567537,0.000146363,0.00007811451,0.0002221067,0.0000755494,0.000001794774],"category_scores_gemma":[0.00009623541,0.0001198376,0.0001809794,0.0003263789,0.0002334165,0.00004425463,0.0001540107,0.0001229669,3.15177e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009470329,"about_ca_system_score_gemma":0.00003038731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000968206,"about_ca_topic_score_gemma":0.0003379088,"domain_scores_codex":[0.9988542,0.00006065581,0.0005071368,0.0001901845,0.0002149771,0.0001728582],"domain_scores_gemma":[0.9991158,0.00009690058,0.0002773546,0.0003648559,0.0001168782,0.00002826559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003351793,0.0004324195,0.002141946,0.002254214,0.01465015,0.00002037846,0.01700749,0.2403264,0.5179877,0.02522134,0.0001967904,0.1764094],"study_design_scores_gemma":[0.004261841,0.002631373,0.0004245494,0.0001973932,0.00358696,0.00005682236,0.01208373,0.3756426,0.5811713,0.002264345,0.01686592,0.0008131505],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6825826,0.004454452,0.3119111,0.00005765715,0.0001296168,0.0006468373,0.0001498845,0.00001296701,0.00005484813],"genre_scores_gemma":[0.996072,0.0004507382,0.003115213,0.00007184019,0.00004127001,0.00009025306,0.0001147153,0.00001550033,0.00002846826],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3134894,"threshold_uncertainty_score":0.4886837,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06368501628049607,"gpt":0.3621898748204531,"spread":0.298504858539957,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007419554,0.0004213576,0.000433429,0.0004698893,0.0001796227,0.0003979048,0.0002763181,0.00077584,0.00001037438],"category_scores_gemma":[0.002370912,0.0003855818,0.0001249516,0.0001573822,0.0004345212,0.00006390476,0.0002751271,0.0003884443,0.00001470123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007913085,"about_ca_system_score_gemma":0.00228013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001541316,"about_ca_topic_score_gemma":0.0001652498,"domain_scores_codex":[0.9972199,0.0000299232,0.001362572,0.0002914513,0.0005787713,0.0005173638],"domain_scores_gemma":[0.9981799,0.000358789,0.0003620437,0.0003778604,0.0005074074,0.0002140625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001366738,0.0002181138,0.000004062672,0.009996004,0.0001659066,0.000003933157,0.001488342,0.0002168743,0.0002712462,0.01033719,0.6138262,0.3633355],"study_design_scores_gemma":[0.0001629717,0.0004570641,5.771893e-7,0.0005333208,0.00007395956,0.0000138384,0.005650982,0.06946842,0.001209459,0.01735961,0.904418,0.0006518276],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"methods","genre_scores_codex":[0.001413429,0.02350048,0.131912,0.001164321,0.8250939,0.004771549,0.004724246,0.0001246248,0.007295361],"genre_scores_gemma":[0.002107784,0.06400537,0.589919,0.0006765009,0.3332084,0.0005336447,0.007881278,0.0002021341,0.001465875],"genre_candidate":"editorial","genre_consensus":null,"teacher_disagreement_score":0.4918856,"threshold_uncertainty_score":0.9998596,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01891542148422085,"gpt":0.3156294565846542,"spread":0.2967140351004333,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004882985,0.0001559724,0.0002099497,0.0000689822,0.0001744388,0.00005220452,0.0001141366,0.0001393275,0.000007064422],"category_scores_gemma":[0.001458517,0.0001391542,0.000124228,0.0001264253,0.00003215957,0.00002232786,0.00002544395,0.00005681261,0.00001620959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001243348,"about_ca_system_score_gemma":0.0001020538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004376531,"about_ca_topic_score_gemma":0.00004687601,"domain_scores_codex":[0.9989082,0.00003230185,0.0004427452,0.0002087892,0.0001420639,0.0002658695],"domain_scores_gemma":[0.9987589,0.0005875648,0.0002120513,0.0001651523,0.0002327724,0.00004362432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001293182,0.0001311873,0.7535198,0.002628055,0.001319011,0.000002191835,0.001505419,0.1409927,0.002677551,0.001761477,0.06270511,0.03262812],"study_design_scores_gemma":[0.001404548,0.0008887895,0.1142897,0.0001839116,0.0002729871,0.000003644232,0.003171418,0.1894488,0.002573002,0.00883368,0.6776076,0.001322],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4934726,0.0346657,0.4582246,0.006596334,0.002665216,0.002014813,0.0008769319,0.000237642,0.001246234],"genre_scores_gemma":[0.9706106,0.001200082,0.02429593,0.00113302,0.0003109607,0.0002441976,0.001304652,0.00002410043,0.0008764709],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6392301,"threshold_uncertainty_score":0.5674543,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02498786159813313,"gpt":0.3762993471727817,"spread":0.3513114855746485,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003674605,0.0001167008,0.0001313925,0.0001313206,0.00006193014,0.00004269175,0.00008472797,0.00008826439,0.000004242872],"category_scores_gemma":[0.0001437045,0.0001063329,0.00004681943,0.0001703523,0.00005339268,0.00006329678,0.00002754785,0.00007690553,9.434279e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001261343,"about_ca_system_score_gemma":0.00006250729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002242868,"about_ca_topic_score_gemma":0.00001222416,"domain_scores_codex":[0.9992088,0.00004203874,0.0004264726,0.0001192756,0.00008747623,0.0001159006],"domain_scores_gemma":[0.9994805,0.0001489153,0.0001082624,0.0001414705,0.00007801098,0.00004280407],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000288866,0.0000530617,0.0005838941,0.001135909,0.00006283417,1.322579e-7,0.001274788,0.0113996,0.001042892,0.004803338,0.0002135968,0.9794011],"study_design_scores_gemma":[0.0003207177,0.0004065176,0.002317055,0.00008364588,0.00003342948,0.00001671151,0.0006907822,0.5950202,0.001792387,0.0018318,0.3973203,0.0001664022],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07315348,0.1841138,0.7369817,0.0005388521,0.001431503,0.001262601,0.000817043,0.0001505475,0.00155043],"genre_scores_gemma":[0.01939029,0.02542927,0.9536635,0.00007892338,0.0002219847,0.00005588043,0.001109166,0.00001739249,0.00003356517],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9792346,"threshold_uncertainty_score":0.4336131,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.04178784423895929,"gpt":0.3276315467898132,"spread":0.2858437025508539,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000555916,0.0002837001,0.00029956,0.00004284723,0.0003201741,0.0002303876,0.0003275368,0.0001347238,0.000009925108],"category_scores_gemma":[0.0004922729,0.0001866579,0.0001720896,0.0003484315,0.00009886404,0.00002575444,0.0001543076,0.0001573452,0.0000224608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002255873,"about_ca_system_score_gemma":0.00006820912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001163916,"about_ca_topic_score_gemma":0.00001627456,"domain_scores_codex":[0.9985158,0.00003566904,0.000460298,0.0002777558,0.0002023409,0.0005081322],"domain_scores_gemma":[0.9988201,0.0003153536,0.0002426413,0.0004039348,0.0001514879,0.00006642746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006646623,0.0001228484,0.000724151,0.000667535,0.001267063,0.000005840629,0.0003709581,0.6727924,0.001341223,0.01548866,0.09255692,0.2139978],"study_design_scores_gemma":[0.0004688202,0.0004179965,0.0001851474,0.000129352,0.00008294659,0.000003944894,0.0002121432,0.2335449,0.0008834504,0.00279181,0.7609307,0.0003487992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2961699,0.2329617,0.4140658,0.00506063,0.02259469,0.01188569,0.002048387,0.0008234871,0.01438968],"genre_scores_gemma":[0.8964269,0.03133091,0.05527281,0.004947431,0.007856462,0.0005498446,0.000847489,0.0001654773,0.00260269],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6683738,"threshold_uncertainty_score":0.7611687,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01569035333574757,"gpt":0.2419148205237434,"spread":0.2262244671879959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001935987,0.000169559,0.0002410231,0.00007524533,0.0001743747,0.0000194403,0.0002434957,0.0001175038,0.00006130657],"category_scores_gemma":[0.00003666114,0.0001650558,0.00006998491,0.0001493888,0.0001281558,0.00001127298,0.0003996054,0.00009893298,0.000002005475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002184763,"about_ca_system_score_gemma":0.000108694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001676911,"about_ca_topic_score_gemma":0.000003540524,"domain_scores_codex":[0.9988922,0.00005700257,0.0004364648,0.0001827343,0.0001710702,0.0002604604],"domain_scores_gemma":[0.9992122,0.00001171921,0.0003148376,0.0003496937,0.00006913172,0.000042424],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001326019,0.00004881373,0.00004172356,0.00004313122,0.00004378646,0.00000348263,0.00008945943,0.009160289,0.9851004,0.000175122,0.0001667707,0.004994369],"study_design_scores_gemma":[0.001108378,0.001046203,0.00008158454,0.00001152434,0.00003739353,0.00008591031,0.0005904077,0.003645187,0.8998877,0.0001680805,0.09295056,0.0003870053],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9734132,0.000948063,0.02383085,0.00003548031,0.001189453,0.0002762971,0.0002073796,0.00001992044,0.00007938345],"genre_scores_gemma":[0.905566,0.0007168166,0.09317204,0.0000762425,0.0002002389,0.00001416455,0.0002063862,0.000022011,0.0000261183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09278379,"threshold_uncertainty_score":0.6730778,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0931933158410629,"gpt":0.3659723816727946,"spread":0.2727790658317317,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005030903,0.0001566252,0.0003365589,0.0002265433,0.00006511567,0.0001601167,0.0005768774,0.0001104705,0.00001882033],"category_scores_gemma":[0.00009074842,0.0001446804,0.00007938441,0.0004610278,0.00005363957,0.00008444102,0.0003570238,0.00005887034,8.140953e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005890705,"about_ca_system_score_gemma":0.0002645539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000725327,"about_ca_topic_score_gemma":0.003673385,"domain_scores_codex":[0.9986906,0.00004597696,0.0005464486,0.000339482,0.0001499012,0.0002275879],"domain_scores_gemma":[0.9989476,0.00003669974,0.0001520316,0.0007099411,0.00009390606,0.00005979815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001236312,0.00006649747,0.0008713017,0.0002180755,0.0004942885,0.000002710587,0.0006666606,0.01466148,0.9254451,0.00009341286,0.0003584656,0.05699835],"study_design_scores_gemma":[0.0006581465,0.0006556699,0.0006863907,0.00003425156,0.000401669,0.00000660439,0.001495292,0.8426508,0.1294758,0.00004671474,0.02357496,0.0003137355],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7695422,0.001706563,0.2268853,0.00003532979,0.0001879913,0.0006029819,0.000907236,0.000014483,0.0001179108],"genre_scores_gemma":[0.933556,0.0004654627,0.06134583,0.0001210423,0.00009782638,0.00006156842,0.00426262,0.00002013888,0.00006952957],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8279893,"threshold_uncertainty_score":0.5899894,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04425365662850683,"gpt":0.3352390906556071,"spread":0.2909854340271003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003979789,0.0001650442,0.000200016,0.00006602274,0.0002069921,0.0004489992,0.00012879,0.00005831235,0.0001286774],"category_scores_gemma":[0.00008734293,0.000137119,0.00006747508,0.0001818026,0.0001907816,0.002923658,0.0001871443,0.0001217356,0.00001968701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000409864,"about_ca_system_score_gemma":0.0000195378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007791151,"about_ca_topic_score_gemma":0.00002060391,"domain_scores_codex":[0.9988051,0.00005080403,0.0005078909,0.0002023883,0.0002173374,0.0002164595],"domain_scores_gemma":[0.9992867,0.0003002833,0.0001671394,0.0001482412,0.000011899,0.00008579767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007437824,0.000450075,0.04168353,0.001155908,0.00007415764,0.0001395001,0.05441408,0.003192651,0.004492193,0.0001166312,0.0005537954,0.8936531],"study_design_scores_gemma":[0.001852335,0.0006979481,0.006141676,0.0003655226,0.0002056797,0.001548604,0.1041643,0.6080568,0.03038697,0.0007604849,0.2445601,0.001259506],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9454834,0.0001643351,0.05316932,0.00004229023,0.000157769,0.0004328098,0.00002108306,0.00008326699,0.0004457546],"genre_scores_gemma":[0.9830667,0.00001517591,0.01649608,0.00008417507,0.00007446713,0.000005304761,0.00000735167,0.00001948287,0.000231298],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8923936,"threshold_uncertainty_score":0.5591552,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01336817700406793,"gpt":0.3011272475436773,"spread":0.2877590705396094,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000295574,0.0002058214,0.0001978114,0.00008213682,0.0001756709,0.0001466027,0.0002222266,0.000158349,8.505109e-7],"category_scores_gemma":[0.00002788463,0.0001820881,0.00007599332,0.00009960646,0.0001228872,0.00007756514,0.0001305206,0.0000766642,0.000001356331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002573811,"about_ca_system_score_gemma":0.0001166833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006719747,"about_ca_topic_score_gemma":0.00003693765,"domain_scores_codex":[0.9989386,0.00001244175,0.0004710994,0.000217398,0.00009442242,0.0002660719],"domain_scores_gemma":[0.999198,0.00003433623,0.0002047326,0.0003944021,0.00008855885,0.00007998192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002989772,0.0002146405,0.003792959,0.0008707355,0.0003279576,2.724067e-7,0.0002517222,0.001445989,0.01824712,0.02788011,0.001494894,0.9451746],"study_design_scores_gemma":[0.00161289,0.0003078306,0.002895879,0.00004304948,0.00009651846,0.000005704186,0.001100546,0.7632313,0.004217575,0.005728451,0.2202201,0.0005401442],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05370199,0.00153488,0.9397532,0.0002476447,0.0003163018,0.0009383106,0.0002262829,0.0000287841,0.003252552],"genre_scores_gemma":[0.7861928,0.002366264,0.207929,0.001055613,0.0001779814,0.0001963108,0.00145976,0.00002792844,0.0005943236],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9446345,"threshold_uncertainty_score":0.7425339,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01249792745781209,"gpt":0.3089335441867941,"spread":0.296435616728982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009291839,0.0001523469,0.0001334989,0.0002542428,0.000163547,0.000413,0.0003192271,0.00004938877,0.000004282332],"category_scores_gemma":[0.0002463937,0.0001330383,0.0000929462,0.0007104487,0.00004079276,0.001999787,0.00005360636,0.0001066874,0.00001594181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001252192,"about_ca_system_score_gemma":0.0003601241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.27258e-7,"about_ca_topic_score_gemma":0.000003831843,"domain_scores_codex":[0.998836,0.00007398161,0.0002845422,0.0002367538,0.0003386568,0.0002300055],"domain_scores_gemma":[0.9982146,0.001309301,0.00009175432,0.0001968954,0.0001263591,0.00006107614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000452731,0.00006970414,0.0003640595,0.0009971439,0.00006911274,0.000003110095,0.002966373,0.4079367,0.0004071592,0.03168831,0.02560291,0.5294427],"study_design_scores_gemma":[0.0001884933,0.000105778,0.0005963061,0.0001073123,0.000009525088,0.000008770433,0.00005339311,0.8823998,0.001358201,0.002781477,0.1122542,0.0001367602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006694532,0.0008820697,0.9877992,0.002032951,0.001388433,0.0003403604,0.0000567466,0.0004649964,0.0003407518],"genre_scores_gemma":[0.1048974,0.00003625961,0.893894,0.0003864164,0.0001965915,0.0001060305,0.00002806898,0.00001697135,0.000438276],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.529306,"threshold_uncertainty_score":0.5425144,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05619849722513385,"gpt":0.4230035011006127,"spread":0.3668050038754789,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001476152,0.000231058,0.0003316127,0.0001940658,0.0002898017,0.0003354374,0.000136115,0.0001411732,0.00000165183],"category_scores_gemma":[0.002283406,0.0002119607,0.0000524977,0.000237874,0.00006227684,0.0009175297,0.00003935856,0.00007628775,3.611298e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006107143,"about_ca_system_score_gemma":0.0001490244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002565956,"about_ca_topic_score_gemma":0.000007178225,"domain_scores_codex":[0.9984791,0.00004567083,0.0006849645,0.0003890332,0.0001395135,0.0002617026],"domain_scores_gemma":[0.9931763,0.005926565,0.0003312178,0.0002219699,0.0002597127,0.00008427875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00013576,0.00002597838,0.00001974267,0.003515848,0.00003993365,3.419875e-8,0.0002061684,0.002738657,0.0004124019,0.193789,0.0002251773,0.7988912],"study_design_scores_gemma":[0.0007282381,0.0001893462,0.000004484781,0.0000869578,0.0001767808,0.000005528139,0.0001049118,0.6744938,0.0006671151,0.3198528,0.003508948,0.0001810162],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001703743,0.0004724339,0.9950651,0.0002882147,0.0001988351,0.002517578,0.001111414,0.0001510676,0.00002499192],"genre_scores_gemma":[0.001595748,0.0001426518,0.9966095,0.0001043424,0.0001286708,0.0005600781,0.0008074139,0.00004453904,0.000007023883],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7987102,"threshold_uncertainty_score":0.8643506,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02459884249832153,"gpt":0.2769423388426316,"spread":0.2523434963443101,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001559372,0.0001623693,0.000142542,0.00005902452,0.0001705908,0.00004047572,0.0002430718,0.00007459406,0.000004794247],"category_scores_gemma":[0.0001118031,0.0001470951,0.00007099761,0.0001834722,0.0001022775,0.000005661628,0.0001861175,0.00005903245,0.0001192867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001144563,"about_ca_system_score_gemma":0.00004772931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002902374,"about_ca_topic_score_gemma":0.00001345742,"domain_scores_codex":[0.9990846,0.00001286212,0.000264439,0.0001785176,0.0001388048,0.0003208123],"domain_scores_gemma":[0.9994271,0.00001807281,0.0001252034,0.0002846505,0.00007615861,0.00006877628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008225313,0.00004997134,0.005819424,0.0003045739,0.0002411784,0.00001397787,0.002603623,0.002125658,0.7877169,0.002262556,0.01499808,0.1837818],"study_design_scores_gemma":[0.0007679868,0.000532195,0.003881132,0.00006320468,0.00003551203,0.00003283452,0.003479015,0.002619937,0.243167,0.002861117,0.7417176,0.0008424988],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9800145,0.004809379,0.002126124,0.0003393599,0.0008613028,0.000326389,0.0001430259,0.00004857749,0.01133137],"genre_scores_gemma":[0.9738334,0.007729465,0.01673089,0.0004332347,0.0002761389,0.00004450749,0.0001734097,0.00002626395,0.0007526787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7267195,"threshold_uncertainty_score":0.5998365,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1328867625110219,"gpt":0.3066892368213286,"spread":0.1738024743103068,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001803247,0.0001365204,0.0001703386,0.00002839524,0.0001469132,0.0001440763,0.00009557665,0.00004746191,0.00000833277],"category_scores_gemma":[0.0003936315,0.00004793361,0.00006229862,0.000437905,0.00009365817,0.0008898759,0.00003109109,0.0001020367,0.000004993672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003118774,"about_ca_system_score_gemma":0.00001399352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002206895,"about_ca_topic_score_gemma":0.00009222132,"domain_scores_codex":[0.9990404,0.00003532149,0.0003430098,0.0001764889,0.00020279,0.0002019797],"domain_scores_gemma":[0.9991348,0.0004781686,0.000117841,0.0000307343,0.0001737729,0.00006467409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002521551,0.00001477753,0.0003263719,0.0004050903,0.00001875259,0.000001202452,0.002017597,0.00438036,0.1395877,0.000263943,0.000004869979,0.8529541],"study_design_scores_gemma":[0.0002037843,0.001301434,0.006811716,0.0003298064,0.00004093194,0.00001094965,0.01997666,0.94871,0.01366698,0.001628135,0.006979046,0.0003406154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9821472,0.003550156,0.01186472,0.0008131998,0.00008701105,0.0009771046,0.00008118785,0.0001364677,0.0003429202],"genre_scores_gemma":[0.9889563,0.0002204387,0.01022235,0.00001696681,0.00009346914,0.00009722119,0.0002967535,0.000001402824,0.00009514912],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9443296,"threshold_uncertainty_score":0.1954676,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02104986476681353,"gpt":0.3088681925524286,"spread":0.2878183277856151,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002638075,0.0001640198,0.0001752482,0.0001504312,0.0001081925,0.0002093279,0.0001430298,0.0001074506,0.00002772794],"category_scores_gemma":[0.00006512728,0.0001304309,0.0001504816,0.000315916,0.00008496142,0.00003536185,0.00005956467,0.00005043146,0.000009186296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001196551,"about_ca_system_score_gemma":0.00006715053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002789188,"about_ca_topic_score_gemma":0.000008707763,"domain_scores_codex":[0.9990267,0.00001519483,0.0003364108,0.0002895579,0.0001280571,0.0002040659],"domain_scores_gemma":[0.9993687,0.00002817375,0.0001019952,0.000328994,0.00008095863,0.00009122268],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003582537,0.0001755133,0.01442832,0.002250074,0.003644844,0.000007398285,0.001433303,0.0005222456,0.6440794,0.006708044,0.02508364,0.301309],"study_design_scores_gemma":[0.0003835849,0.000166204,0.002083781,0.00002807055,0.0002468001,0.00001026385,0.0002320835,0.009361851,0.07276026,0.0001954658,0.9142159,0.0003157309],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.593446,0.05112815,0.3446082,0.0007883267,0.001507101,0.001767944,0.0007086242,0.0001915485,0.005854124],"genre_scores_gemma":[0.9756464,0.007556068,0.01337263,0.0005005649,0.000318165,0.0002707443,0.0006983117,0.00003068287,0.001606414],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8891323,"threshold_uncertainty_score":0.5318818,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0092613412800591,"gpt":0.2608134375166964,"spread":0.2515520962366373,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001694038,0.0002332835,0.0001929265,0.00007000207,0.0001568964,0.0001245742,0.0001640306,0.0000947022,0.000002204485],"category_scores_gemma":[0.00002158156,0.0001912702,0.00007084332,0.0001088528,0.00004989114,0.00001791621,0.00005706149,0.0000572389,0.000008668319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005314536,"about_ca_system_score_gemma":0.0001158941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009012992,"about_ca_topic_score_gemma":0.00005792038,"domain_scores_codex":[0.9989371,0.00001145375,0.0003734564,0.0002661882,0.0001157442,0.0002960027],"domain_scores_gemma":[0.9994069,0.00001877969,0.0001143025,0.0002809017,0.00009993196,0.00007912492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002985649,0.00007315484,0.0009404434,0.001458185,0.0002902249,0.000007201894,0.001370299,0.0730907,0.8631619,0.0005522884,0.0005150734,0.05824192],"study_design_scores_gemma":[0.001438096,0.001317342,0.001790658,0.0001677044,0.0001447618,0.00007244616,0.001033223,0.5314842,0.04279692,0.000866928,0.4176296,0.001258132],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9116266,0.005642364,0.08017319,0.00006854038,0.0003818328,0.0007597925,0.0006686833,0.0001081812,0.0005708208],"genre_scores_gemma":[0.967472,0.0008364073,0.02931865,0.0001849675,0.0003449981,0.0000645148,0.001504111,0.00004718292,0.0002271847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.820365,"threshold_uncertainty_score":0.7799773,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0465884028724005,"gpt":0.3316644022699577,"spread":0.2850759993975572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003581852,0.0002756298,0.0002731467,0.0001263199,0.0001053564,0.00008387674,0.001052962,0.0001729241,0.00001715308],"category_scores_gemma":[0.00003652987,0.0002399758,0.0001103031,0.00007290462,0.00005167871,0.00002812216,0.001360654,0.0002531765,0.000001575479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008252482,"about_ca_system_score_gemma":0.0002515874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001233345,"about_ca_topic_score_gemma":0.00007969551,"domain_scores_codex":[0.9982271,0.00004952718,0.0006267112,0.0005351699,0.0002872216,0.0002743379],"domain_scores_gemma":[0.9981394,0.00001620756,0.0004198437,0.001322605,0.00004029101,0.0000616183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004028453,0.003596269,0.02536051,0.01474551,0.0005447923,0.00001494536,0.008230117,0.1162713,0.2759228,0.0008149496,0.06009611,0.4903743],"study_design_scores_gemma":[0.001668443,0.0002494382,0.002645312,0.0003746084,0.0000420181,0.000003910487,0.002056064,0.06894666,0.01527482,0.0001099159,0.9078351,0.0007937102],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7839659,0.01300894,0.189294,0.0006073043,0.004395256,0.002939725,0.004637828,0.00005365793,0.001097361],"genre_scores_gemma":[0.9640079,0.005645981,0.007153627,0.0003282825,0.0002790047,0.0006651041,0.02127806,0.00005041745,0.0005916886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.847739,"threshold_uncertainty_score":0.9785931,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01568206321207271,"gpt":0.2369625222065186,"spread":0.2212804589944458,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009798821,0.0001340453,0.0001533019,0.00004115763,0.00008309432,0.0001098373,0.0001770584,0.00004899124,0.0001232544],"category_scores_gemma":[0.0000238002,0.00005499696,0.00005526851,0.0003788525,0.00002516147,0.0003210023,0.00003845382,0.00008606176,0.0001388826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002337598,"about_ca_system_score_gemma":0.00001386924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005110774,"about_ca_topic_score_gemma":0.00143703,"domain_scores_codex":[0.9990702,0.00001152572,0.0003371917,0.0001591455,0.000169565,0.0002523234],"domain_scores_gemma":[0.9997103,0.00009032661,0.00003589065,0.00005189517,0.0000198485,0.00009172476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005244639,0.00007476565,0.008377604,0.0001715034,0.00001463478,0.00009786497,0.002004018,0.000112372,0.04591192,0.0003376038,0.000588601,0.9422567],"study_design_scores_gemma":[0.000290171,0.0005406975,0.3444285,0.0006727593,0.00002248004,0.0001342737,0.001556277,0.00981361,0.004889619,0.0006710503,0.6362251,0.0007554191],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941925,0.0006010099,0.0002461173,0.00178782,0.0003473146,0.0002711653,0.000493377,0.0001106746,0.001950047],"genre_scores_gemma":[0.9967427,0.0005445824,0.001533297,0.0002813912,0.0002613245,0.00003999158,0.0001911815,0.000001240708,0.0004043505],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9415013,"threshold_uncertainty_score":0.2242711,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01610781482344448,"gpt":0.3134939633144855,"spread":0.297386148491041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000438276,0.0001458524,0.0001252721,0.00007544496,0.000223322,0.00004268316,0.0001586697,0.00005337482,0.0002463036],"category_scores_gemma":[0.0003051904,0.0001415483,0.00004070235,0.0003881616,0.00008777619,0.001356188,0.00009901413,0.0000689154,0.001666117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002430484,"about_ca_system_score_gemma":0.00001824077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002089124,"about_ca_topic_score_gemma":0.00005304363,"domain_scores_codex":[0.9987522,0.00003303797,0.0003686532,0.000229593,0.0002994099,0.0003170422],"domain_scores_gemma":[0.9991323,0.0002785465,0.0002575584,0.0002291774,0.00001022668,0.0000922145],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002375427,0.0002471295,0.04913094,0.0005111633,0.00003679261,0.00000622367,0.002954195,0.1935981,0.000941663,0.0009154217,0.02962784,0.721793],"study_design_scores_gemma":[0.0005403103,0.0001022494,0.01293701,0.00004384285,0.00001364893,0.000001137535,0.0005344934,0.7970034,0.0008500154,0.0005554371,0.1872023,0.0002161545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0445447,0.00004018356,0.9436131,0.0003384078,0.0007619182,0.001833373,0.001025644,0.0003241929,0.007518499],"genre_scores_gemma":[0.921429,0.0004073252,0.0638902,0.003230774,0.0001650606,0.0004535152,0.009966822,0.00007687441,0.0003804593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8797229,"threshold_uncertainty_score":0.9991112,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}