{"meta":{"query_hash":"2a78974ab50e","filters":{"venue":"NAR Genomics and Bioinformatics"},"cohort_total":54,"direct_labels_cover":0,"predictions_cover":54,"exported":54,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/2a78974ab50e","api":"https://metacan.xera.ac/api/v1/cohort?venue=NAR+Genomics+and+Bioinformatics"},"results":[{"id":"W2964367788","doi":"10.1093/nargab/lqz003","title":"Open chromatin structure in PolyQ disease-related genes: a potential mechanism for CAG repeat expansion in the normal human population","year":2019,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation; Israel Science Foundation","keywords":"Chromatin; Gene; Biology; Epigenetics; Genetics; Genome; ChIA-PET; Population; Chromatin remodeling","score_opus":0.00761182982789455,"score_gpt":0.2540048161247481,"score_spread":0.24639298629685358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964367788","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99836236,0.00012845783,0.00020086617,0.00011412635,0.000049604605,0.0010075606,0.00006587157,0.0000028042232,0.00006835131],"genre_scores_gemma":[0.9972115,0.00011151303,0.0016013815,0.00018660502,0.000038250062,0.00001758174,0.0006830694,0.000011748582,0.00013830654],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991199,0.00003327834,0.00034051778,0.00015683153,0.00011489077,0.00023458466],"domain_scores_gemma":[0.9995513,0.0000074553145,0.00010045366,0.0002506781,0.000032484564,0.000057651057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003119403,0.00012008287,0.00013477323,0.000071789305,0.00012193447,0.000118582466,0.00029134256,0.00012674431,0.000007237966],"category_scores_gemma":[0.000020330252,0.000088502864,0.000042648353,0.00007368912,0.000017955177,0.000023414652,0.00019083517,0.00009652572,0.0000015273889],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028226178,0.000051069488,0.006973095,0.00019934775,0.000026848818,0.000004980589,0.0008978452,0.000811689,0.98203504,0.0016483235,0.00010542118,0.0069640707],"study_design_scores_gemma":[0.017479274,0.0028563223,0.17526384,0.00033711724,0.00010001721,0.00015994046,0.010624101,0.7085329,0.0694909,0.01144683,0.0017849923,0.0019237207],"about_ca_topic_score_codex":0.0002116973,"about_ca_topic_score_gemma":0.00030062717,"teacher_disagreement_score":0.91254413,"about_ca_system_score_codex":0.000027983098,"about_ca_system_score_gemma":0.000055634122,"threshold_uncertainty_score":0.36090422},"labels":[],"label_agreement":null},{"id":"W3001111520","doi":"10.1093/nargab/lqaa002","title":"Bayesian correlation is a robust gene similarity measure for single-cell RNA-seq data","year":2020,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"University of Bern; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Similarity (geometry); Bayesian probability; Correlation; Pearson product-moment correlation coefficient; Mathematics; Artificial intelligence; RNA-Seq; Similarity measure; Pattern recognition (psychology); Computational biology; Computer science; Gene; Statistics; Biology; Gene expression; Transcriptome; Genetics","score_opus":0.059689052934759304,"score_gpt":0.22642125919351536,"score_spread":0.16673220625875607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001111520","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19469406,0.0012585166,0.7971661,0.00169213,0.00037256646,0.0009540027,0.0019668902,0.000045775185,0.001849982],"genre_scores_gemma":[0.8793997,0.00065150554,0.11187948,0.004312526,0.0005782457,0.000008865947,0.003006019,0.00005949318,0.000104153914],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884623,0.000015398473,0.000416419,0.00032501522,0.00013251025,0.00026441534],"domain_scores_gemma":[0.9990831,0.000016638614,0.00016569556,0.0004371335,0.000110338784,0.00018706376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021034676,0.00022476148,0.00021692432,0.000028247101,0.00017386752,0.00010738126,0.00035414213,0.00027448253,0.000007250058],"category_scores_gemma":[0.00006507085,0.00021933614,0.00008265318,0.000076407225,0.00006201374,0.00002264227,0.00018161468,0.00012879576,0.000005066565],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056699244,0.00022679933,0.0012896135,0.0005913738,0.00017020441,0.0000023365717,0.0020483455,0.0015682807,0.9480886,0.000040664785,0.015075731,0.03033108],"study_design_scores_gemma":[0.0025128464,0.0010512102,0.00003918904,0.000019059336,0.0001620592,0.000020583193,0.00037251017,0.7468775,0.1655339,0.000058875044,0.082685016,0.0006672412],"about_ca_topic_score_codex":0.0000089073465,"about_ca_topic_score_gemma":0.000016335942,"teacher_disagreement_score":0.7825547,"about_ca_system_score_codex":0.00001908356,"about_ca_system_score_gemma":0.000108613,"threshold_uncertainty_score":0.8944268},"labels":[],"label_agreement":null},{"id":"W3016947700","doi":"10.1093/nargab/lqaa024","title":"A minimum reporting standard for multiple sequence alignments","year":2020,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Commonwealth Scientific and Industrial Research Organisation","keywords":"Completeness (order theory); Sequence (biology); Transparency (behavior); nobody; Computer science; Simple (philosophy); Data mining; Mathematics; Biology; Computer security; Genetics","score_opus":0.04466610776664429,"score_gpt":0.2708863985655486,"score_spread":0.2262202907989043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016947700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98956317,0.00058906304,0.008198183,0.00045454229,0.00009824052,0.00043517526,0.0003068528,0.0000060026487,0.0003487511],"genre_scores_gemma":[0.94341743,0.0006636926,0.054308157,0.001253177,0.00019279873,0.000021351772,0.00008412558,0.00001924697,0.000040006886],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988943,0.0000063443667,0.00059131376,0.00019819807,0.0000801036,0.00022977957],"domain_scores_gemma":[0.9992102,0.000016602458,0.00041484096,0.00015263866,0.000082877996,0.00012284989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021270242,0.00015278911,0.000201356,0.0000151583745,0.0001465586,0.000045815756,0.000111711895,0.00008829702,0.0000012135188],"category_scores_gemma":[0.00027445628,0.00014087197,0.00007830057,0.000036586356,0.000055591092,0.00000172292,0.0001604439,0.0000419805,0.0000019724578],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034290302,0.00002176551,0.00905928,0.00028707724,0.00021817205,0.0000025943652,0.0023048294,0.0002007871,0.95807236,0.00011171976,0.003915299,0.025463235],"study_design_scores_gemma":[0.004236371,0.0027544964,0.0014065723,0.00003487189,0.00013552516,0.00006219574,0.003865041,0.06669134,0.23079932,0.00046718802,0.6883497,0.0011973431],"about_ca_topic_score_codex":0.0000026717676,"about_ca_topic_score_gemma":0.0000039186452,"teacher_disagreement_score":0.72727305,"about_ca_system_score_codex":0.000013184657,"about_ca_system_score_gemma":0.00006973864,"threshold_uncertainty_score":0.57445925},"labels":[],"label_agreement":null},{"id":"W3032790130","doi":"10.1093/nargab/lqaa035","title":"Where are G-quadruplexes located in the human transcriptome?","year":2020,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Université de Sherbrooke","keywords":"Transcriptome; Computational biology; Non-coding RNA; Biology; RNA splicing; Alternative splicing; RNA; Untranslated region; G-quadruplex; Nucleic acid structure; Gene; RNA-Seq; microRNA; Genetics; Gene expression; Messenger RNA; DNA","score_opus":0.017109350249607753,"score_gpt":0.22700013400142757,"score_spread":0.20989078375181983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032790130","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99411666,0.001310582,0.0017929152,0.0017133428,0.00003248709,0.00029207868,0.000039083057,0.000009767176,0.0006930889],"genre_scores_gemma":[0.99522156,0.0012992193,0.001519534,0.0017609143,0.00009724507,0.0000113168635,0.00004636641,0.000012352346,0.000031510703],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993388,0.00003134314,0.0002493599,0.00012238906,0.000089663794,0.00016842445],"domain_scores_gemma":[0.99966115,0.0000067338883,0.00008390029,0.00016600214,0.000021704429,0.000060517035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019325555,0.00012958623,0.00012958044,0.000022304346,0.000099762656,0.00006302826,0.00022564887,0.00012041218,0.000010445894],"category_scores_gemma":[0.000014108077,0.00009317725,0.000048181606,0.000075382806,0.000037604867,0.000005929218,0.000041400235,0.000086919434,0.0000078550465],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073103096,0.00005376299,0.002342903,0.0003869095,0.000051182877,0.0000073615174,0.0053940895,0.000056412337,0.97677886,0.0007935062,0.0023886207,0.011673271],"study_design_scores_gemma":[0.0036344419,0.0017913701,0.0062594353,0.00018173941,0.00010725574,0.000097021264,0.031546798,0.008754714,0.43998724,0.00077129324,0.5052656,0.0016031039],"about_ca_topic_score_codex":0.00000798911,"about_ca_topic_score_gemma":0.000036079226,"teacher_disagreement_score":0.5367916,"about_ca_system_score_codex":0.0000052671703,"about_ca_system_score_gemma":0.000021169586,"threshold_uncertainty_score":0.3799658},"labels":[],"label_agreement":null},{"id":"W3037354611","doi":"10.1093/nargab/lqaa043","title":"Factorial study of the RNA-seq computational workflow identifies biases as technical gene signatures","year":2020,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Modularity (biology); RNA-Seq; Pipeline (software); Computational biology; Computer science; Workflow; RNA; Modular design; Software; Gene; Biology; Genetics; Transcriptome; Gene expression; Database; Programming language","score_opus":0.019293357317551538,"score_gpt":0.24295756390417217,"score_spread":0.22366420658662062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037354611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99806046,0.0006344064,0.00029249105,0.00017381886,0.00022861543,0.00034511997,0.00008074287,0.0000039220977,0.00018043198],"genre_scores_gemma":[0.99657375,0.00024255653,0.0025241706,0.00036437335,0.00023511688,0.0000060167636,0.00002588211,0.0000113270835,0.000016838832],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99915206,0.000023919249,0.00036193646,0.0001580695,0.00016568233,0.00013834535],"domain_scores_gemma":[0.99946165,0.000033645672,0.00016787501,0.00018195252,0.000088898654,0.00006597465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009318686,0.00015204173,0.00018451146,0.000021234642,0.0001510695,0.000042101638,0.00023909457,0.00010637369,0.0000034616876],"category_scores_gemma":[0.00010714158,0.00010972106,0.00007977031,0.00008685623,0.00010845727,0.0000018734553,0.00037764813,0.00009553749,0.0000019943573],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040112005,0.00037432302,0.007692194,0.000119460165,0.0006074055,0.0000028071374,0.0070787757,0.022657758,0.9493709,0.00024355036,0.004218216,0.007233486],"study_design_scores_gemma":[0.018567923,0.015353942,0.16148783,0.00016469308,0.0012558897,0.00015129936,0.0291735,0.045179363,0.6532864,0.0074002044,0.06363356,0.004345412],"about_ca_topic_score_codex":0.000014164237,"about_ca_topic_score_gemma":0.000019111212,"teacher_disagreement_score":0.29608452,"about_ca_system_score_codex":0.0000075295497,"about_ca_system_score_gemma":0.00007130846,"threshold_uncertainty_score":0.4474295},"labels":[],"label_agreement":null},{"id":"W3038449881","doi":"10.1093/nargab/lqaa046","title":"On the prediction of DNA-binding preferences of C2H2-ZF domains using structural models: application on human CTCF","year":2020,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"European Regional Development Fund; Ministerio de Ciencia e Innovación","keywords":"Zinc finger; CTCF; DNA; Transcription factor; Computational biology; Binding site; Biology; DNA-binding protein; Chromatin; Genetics; Gene","score_opus":0.04841538685684868,"score_gpt":0.24961517097100394,"score_spread":0.20119978411415526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038449881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99171126,0.000031868236,0.007353695,0.000050939256,0.000024294799,0.00025723706,0.00010605492,0.000004005415,0.00046064483],"genre_scores_gemma":[0.9968095,0.00007794092,0.0029171063,0.000082561455,0.000048251346,0.000004639796,0.00004920793,0.0000071112318,0.0000036812899],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994147,0.000018998544,0.00027343538,0.000098432916,0.000107821295,0.00008664189],"domain_scores_gemma":[0.999529,0.00001528464,0.00023187297,0.00015412497,0.00003532717,0.00003436852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000119787794,0.00009659462,0.00011492643,0.000024161123,0.00010369709,0.000014667384,0.00012568645,0.00009457122,0.0000028797735],"category_scores_gemma":[0.000017252341,0.00006691779,0.000041971634,0.00004401351,0.000050124487,0.0000068595245,0.000048690035,0.000049413804,6.008881e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055377004,0.000008398561,0.000043685577,0.00006542575,0.000030436713,2.9854547e-8,0.00057159935,0.0009022821,0.9890482,0.0058762506,0.00001891926,0.0033794323],"study_design_scores_gemma":[0.0002443378,0.0006405478,0.00005441788,0.00003117851,0.000025577861,0.000001852384,0.00066232757,0.101881646,0.89281404,0.0033882712,0.0001531374,0.00010268851],"about_ca_topic_score_codex":0.0000045444067,"about_ca_topic_score_gemma":0.0000011908496,"teacher_disagreement_score":0.100979365,"about_ca_system_score_codex":0.000008625849,"about_ca_system_score_gemma":0.00002237644,"threshold_uncertainty_score":0.27288282},"labels":[],"label_agreement":null},{"id":"W3089247545","doi":"10.1093/nargab/lqaa066","title":"The expression of long non-coding RNAs is associated with H3Ac and H3K4me2 changes regulated by the HDA6-LDL1/2 histone modification complex in <i>Arabidopsis</i>","year":2020,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Agriculture and Agri-Food Canada","funders":"Agriculture and Agri-Food Canada; National Taiwan University; Ministry of Science and Technology of the People's Republic of China","keywords":"Biology; Long non-coding RNA; Arabidopsis; Histone; Histone deacetylase; Regulation of gene expression; Genetics; RNA splicing; Transcription factor; Gene expression; Alternative splicing; Gene; RNA; Cell biology; Messenger RNA; Mutant","score_opus":0.01933077866174409,"score_gpt":0.253167448844162,"score_spread":0.23383667018241788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089247545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97774184,0.0023463578,0.015574619,0.0031897163,0.000034833873,0.00076376944,0.00012723597,0.000010406892,0.00021119857],"genre_scores_gemma":[0.99575526,0.0029120627,0.00044571504,0.00058892515,0.00002311156,0.000014462866,0.00017325522,0.000018148237,0.00006903797],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991521,0.000038397484,0.00026523994,0.00016192242,0.00017732187,0.00020499997],"domain_scores_gemma":[0.9993853,0.00002771392,0.00020560372,0.00021907676,0.000091888665,0.00007043603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029276672,0.00013507571,0.00015607123,0.000028759501,0.00017863755,0.000052547526,0.00018104416,0.00014056309,0.0000021524731],"category_scores_gemma":[0.000049305872,0.00008699091,0.000025445044,0.00015566585,0.00015693829,0.000007395352,0.00015233284,0.00014807218,5.070677e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014966087,0.000016967615,0.000027342909,0.000047824265,0.000042309373,7.7353224e-7,0.0012278837,0.00007758209,0.98895615,0.000012703165,0.002279883,0.007160932],"study_design_scores_gemma":[0.0012064909,0.00038903434,0.00041627887,0.00005898449,0.000028068926,0.000011823684,0.0008895661,0.056849815,0.9333024,0.000016885106,0.0066282838,0.00020237552],"about_ca_topic_score_codex":0.000019494673,"about_ca_topic_score_gemma":0.00004621494,"teacher_disagreement_score":0.056772232,"about_ca_system_score_codex":0.00003597192,"about_ca_system_score_gemma":0.00005388422,"threshold_uncertainty_score":0.35473865},"labels":[],"label_agreement":null},{"id":"W3097162993","doi":"10.1093/nargab/lqaa086","title":"aliFreeFoldMulti: alignment-free method to predict secondary structures of multiple RNA homologs","year":2020,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"RNA; Sequence (biology); Multiple sequence alignment; Set (abstract data type); Structural alignment; Algorithm; Computer science; Nucleic acid structure; Protein secondary structure; Sequence alignment; Nucleic acid secondary structure; Computational biology; Mathematics; Biology; Genetics; Peptide sequence","score_opus":0.012136323943378734,"score_gpt":0.22952791334956302,"score_spread":0.21739158940618428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097162993","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8099552,0.0009870756,0.18449831,0.0009686768,0.0001748445,0.00089232123,0.0009832418,0.00002880493,0.0015115511],"genre_scores_gemma":[0.5307975,0.00027309838,0.46642205,0.0021327562,0.00017661507,0.000015143597,0.00010073247,0.000028011433,0.00005410049],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99900585,0.000039545324,0.00040572564,0.00020025183,0.00013525708,0.00021333882],"domain_scores_gemma":[0.99919343,0.000026918897,0.00016333823,0.0003592446,0.000053292693,0.00020379318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023359287,0.00018595046,0.00024614297,0.000040043604,0.00006798105,0.000027277141,0.0003584633,0.00017768088,0.000022021792],"category_scores_gemma":[0.00014606296,0.0001619181,0.000083692285,0.00006470382,0.000043821346,0.0000073058313,0.00038682908,0.00007444627,0.0000048137285],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014595686,0.000014296125,0.00016237487,0.00013690263,0.00009704789,0.0000012023471,0.00077148527,0.000112049376,0.93768936,0.0002045143,0.0026549823,0.058009833],"study_design_scores_gemma":[0.00090020086,0.00070201507,0.00021591599,0.000010658691,0.000033743177,0.000014433796,0.0005062608,0.0034431345,0.95383984,0.00044237837,0.039636344,0.0002550949],"about_ca_topic_score_codex":0.000014138845,"about_ca_topic_score_gemma":0.0000044482354,"teacher_disagreement_score":0.28192374,"about_ca_system_score_codex":0.000008750783,"about_ca_system_score_gemma":0.00006583856,"threshold_uncertainty_score":0.66028285},"labels":[],"label_agreement":null},{"id":"W3110037558","doi":"10.1093/nargab/lqaa098","title":"TOUCAN: a framework for fungal biosynthetic gene cluster discovery","year":2020,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Microbial Natural Products and Biosynthesis","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Université du Québec à Montréal","keywords":"Biology; Computational biology; Scope (computer science); Computer science","score_opus":0.020215865460523626,"score_gpt":0.23932528590337646,"score_spread":0.21910942044285284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110037558","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9370061,0.0011215388,0.022107918,0.03694769,0.0003488349,0.0014972516,0.0005052956,0.000074558804,0.0003908097],"genre_scores_gemma":[0.75327957,0.00073786895,0.2304297,0.014312485,0.0008647388,0.000002528094,0.000058037953,0.00003192806,0.00028313434],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991142,0.000006621503,0.0003487145,0.00017797436,0.00010172433,0.00025074463],"domain_scores_gemma":[0.99939626,0.00007609214,0.00010879714,0.00017573708,0.00006125811,0.00018182256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012543253,0.00017487557,0.0003037911,0.0000442158,0.00010689995,0.00010468031,0.00008695835,0.00016079872,0.000024149003],"category_scores_gemma":[0.00021321978,0.00012271435,0.00011336893,0.00010600252,0.00006515248,0.00012611061,0.000085725085,0.00017149071,0.000020697837],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006765617,0.00053218723,0.0012151027,0.009913179,0.001203291,0.000042865657,0.015430565,0.000046397516,0.493205,0.013992727,0.051629294,0.40602374],"study_design_scores_gemma":[0.004382943,0.0027332413,0.0005266552,0.0003941217,0.0007950053,0.00045099147,0.0020850566,0.06184226,0.36642045,0.0018074036,0.5571312,0.001430706],"about_ca_topic_score_codex":0.0000025420497,"about_ca_topic_score_gemma":7.9315106e-7,"teacher_disagreement_score":0.50550187,"about_ca_system_score_codex":0.000033354892,"about_ca_system_score_gemma":0.00007321173,"threshold_uncertainty_score":0.5004146},"labels":[],"label_agreement":null},{"id":"W3129861733","doi":"10.1093/nargab/lqab011","title":"Single-cell mapper (scMappR): using scRNA-seq to infer the cell-type specificities of differentially expressed genes","year":2021,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; SickKids Foundation; University Health Network; Canadian Institute for Advanced Research; Vector Institute","funders":"Canadian Institutes of Health Research; Hospital for Sick Children; Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Research, Innovation and Science","keywords":"RNA-Seq; RNA; Biology; Cell type; Computational biology; Gene expression; Gene; Population; Cell; Genetics; Transcriptome","score_opus":0.025780475905938335,"score_gpt":0.21534810033163332,"score_spread":0.18956762442569497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129861733","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9885974,0.0014746356,0.007716518,0.00007481009,0.00033894024,0.00019080532,0.000074889846,0.000007797022,0.0015242068],"genre_scores_gemma":[0.97323984,0.0014214204,0.023805525,0.0004890875,0.0002340743,0.000002682481,0.00012151329,0.0000358655,0.00065000675],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988781,0.00003163853,0.00046554502,0.00019773107,0.00015695272,0.0002699835],"domain_scores_gemma":[0.9991347,0.000020635762,0.00014703728,0.0003905957,0.00020864795,0.00009836639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012270009,0.00022291367,0.00024291757,0.000051198156,0.00014994455,0.00011328644,0.00022213606,0.00016962226,0.000022245107],"category_scores_gemma":[0.000017935843,0.00017455945,0.00010580248,0.00011971008,0.00010976597,0.000009550622,0.00020180938,0.00010089193,0.000004932998],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007152117,0.000105542764,0.0005265069,0.00013939494,0.00003504162,0.0000014408108,0.0008570526,0.0003809005,0.99494404,0.000031667787,0.00032057302,0.0025863503],"study_design_scores_gemma":[0.0005132701,0.00020538217,0.00012296616,0.00002277848,0.000048464877,0.000012809515,0.0015036794,0.0028931762,0.96342283,0.00003282783,0.03094761,0.00027418172],"about_ca_topic_score_codex":0.00001709937,"about_ca_topic_score_gemma":0.000019688356,"teacher_disagreement_score":0.031521153,"about_ca_system_score_codex":0.00001791009,"about_ca_system_score_gemma":0.00014547273,"threshold_uncertainty_score":0.71183276},"labels":[],"label_agreement":null},{"id":"W3158542203","doi":"10.1093/nargab/lqab035","title":"Wavelet Screening identifies regions highly enriched for differentially methylated loci for orofacial clefts","year":2021,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Cleft Lip and Palate Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Norges Forskningsråd; Réseau de cancérologie Rossy","keywords":"DNA methylation; Computational biology; Epigenetics; Differentially methylated regions; Biology; Methylation; Genetics; Bioinformatics; Computer science; Gene; Gene expression","score_opus":0.026889180161575744,"score_gpt":0.28434592654648333,"score_spread":0.25745674638490756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158542203","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83625114,0.0004638586,0.16120447,0.00055383804,0.0002174666,0.0006353813,0.0004136362,0.000018030965,0.00024216926],"genre_scores_gemma":[0.9124071,0.003229552,0.075929776,0.0005380159,0.00064975943,0.00008153359,0.004533893,0.00006534798,0.002565052],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99891686,0.00002290812,0.00036791732,0.00022184558,0.000116368676,0.0003541253],"domain_scores_gemma":[0.99916476,0.000060680704,0.000112157686,0.0002468035,0.00029528193,0.00012032068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027909823,0.00017170883,0.00022071257,0.00005665054,0.00029950865,0.00015334808,0.00014293699,0.0002310266,0.0000065225854],"category_scores_gemma":[0.00013423713,0.00016141069,0.0001628923,0.00008311485,0.000067199675,0.0000099201725,0.00016300405,0.00008666944,0.000002183537],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042428912,0.0000742783,0.00049756654,0.0005381499,0.00049697404,0.0000032552246,0.0008451161,0.00003815248,0.94309735,0.0012580802,0.009120217,0.043606583],"study_design_scores_gemma":[0.00868538,0.0011726422,0.004789487,0.00006999141,0.00035887706,0.000099416684,0.0027845458,0.056359824,0.41996777,0.0038146703,0.50027305,0.0016243638],"about_ca_topic_score_codex":0.0000058626333,"about_ca_topic_score_gemma":0.000048053455,"teacher_disagreement_score":0.5231296,"about_ca_system_score_codex":0.000013928579,"about_ca_system_score_gemma":0.00014226385,"threshold_uncertainty_score":0.6582137},"labels":[],"label_agreement":null},{"id":"W3158876629","doi":"10.1093/nargab/lqab027","title":"On the use of direct-coupling analysis with a reduced alphabet of amino acids combined with super-secondary structure motifs for protein fold prediction","year":2021,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"Instituto de Salud Carlos III; Ministerio de Economía y Competitividad; Generalitat de Catalunya","keywords":"Protein secondary structure; Protein folding; Sequence (biology); Protein structure prediction; Protein structure; Structural motif; Alphabet; Computational biology; Protein sequencing; Amino acid; Chemistry; Biological system; Peptide sequence; Crystallography; Biology; Biochemistry","score_opus":0.008394857317764562,"score_gpt":0.19393503414601293,"score_spread":0.18554017682824836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158876629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98856616,0.00009774276,0.009825756,0.000043008386,0.000021513686,0.00053409603,0.00087044423,0.0000047401877,0.00003653233],"genre_scores_gemma":[0.97535515,0.00005035595,0.02380625,0.000075652744,0.000021597189,0.00001751972,0.0006093847,0.000014529119,0.000049590202],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992337,0.000014503915,0.0003175089,0.00016389866,0.00012411416,0.00014623627],"domain_scores_gemma":[0.9991338,0.000030873896,0.00021985355,0.00036071433,0.0002180072,0.00003674621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000107525324,0.00016436975,0.0002830132,0.00006229619,0.00009515691,0.000035837333,0.00009767715,0.00013975045,0.000004006395],"category_scores_gemma":[0.00005010813,0.000100811914,0.00008443888,0.00020316581,0.00010091396,0.000012139452,0.000052739248,0.00010296734,3.969766e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001884175,0.00008852341,0.0030406804,0.0004943596,0.0022922435,0.0000016477638,0.0007743719,0.010285837,0.97716475,0.0010770812,0.0000968363,0.0027994805],"study_design_scores_gemma":[0.001910944,0.002913116,0.002126418,0.00008005489,0.0007003131,0.000017451152,0.0005546802,0.15266329,0.8377107,0.00026065396,0.0007439028,0.00031849105],"about_ca_topic_score_codex":0.0000065726244,"about_ca_topic_score_gemma":0.00005846303,"teacher_disagreement_score":0.14237747,"about_ca_system_score_codex":0.000012193922,"about_ca_system_score_gemma":0.00014290764,"threshold_uncertainty_score":0.41109905},"labels":[],"label_agreement":null},{"id":"W3164889407","doi":"10.1093/nargab/lqab037","title":"Detection of homozygous and hemizygous complete or partial exon deletions by whole-exome sequencing","year":2021,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Research Resources; National Institutes of Health; Fonds de Recherche en Santé Respiratoire; Hospital for Sick Children; Institut National de la Santé et de la Recherche Médicale; SCOR Corporate Foundation for Science; Institut des maladies génétiques Imagine; St. Giles Foundation; Université de Paris; Rockefeller University; Yale University; National Center for Advancing Translational Sciences; National Human Genome Research Institute; Agence Nationale de la Recherche; National Institute of Allergy and Infectious Diseases; Howard Hughes Medical Institute","keywords":"Exome sequencing; Exon; Genetics; Biology; Computational biology; Exome; Copy-number variation; Gene; Mutation; Genome","score_opus":0.012977036308436845,"score_gpt":0.20678007204484916,"score_spread":0.1938030357364123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164889407","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9910771,0.0009060445,0.007189871,0.00006743935,0.000072814946,0.00010500139,0.0003413194,0.000007667777,0.00023274521],"genre_scores_gemma":[0.9927703,0.0011616249,0.0052735326,0.00013728584,0.00006956229,0.000007203274,0.00026990578,0.00001160757,0.0002989442],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992536,0.00001901268,0.00034498336,0.00013904808,0.000071705654,0.00017170083],"domain_scores_gemma":[0.99951077,0.000013173878,0.00013334992,0.00017249642,0.00009810007,0.00007212194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010256278,0.00012704838,0.00016455984,0.00003063525,0.00016057034,0.00005161333,0.000058385613,0.000120041004,0.000009224273],"category_scores_gemma":[0.000026526377,0.00011568094,0.000042305735,0.00006581244,0.00008306733,0.000010997405,0.00011254081,0.00006502837,0.0000020934444],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050090424,0.000029180372,0.00019340601,0.00014307341,0.000068397334,0.0000045032484,0.0007053027,0.00007087647,0.99190307,0.00009833416,0.00021433386,0.0065194555],"study_design_scores_gemma":[0.0018881756,0.0008603061,0.0004925348,0.000046509347,0.00013501084,0.0016259043,0.0075671296,0.01555801,0.8319003,0.00017554815,0.13908124,0.00066934363],"about_ca_topic_score_codex":0.00002675683,"about_ca_topic_score_gemma":0.00005906836,"teacher_disagreement_score":0.16000277,"about_ca_system_score_codex":0.000025259635,"about_ca_system_score_gemma":0.0001194606,"threshold_uncertainty_score":0.47173318},"labels":[],"label_agreement":null},{"id":"W3172664492","doi":"10.1093/nargab/lqab042","title":"Retracted and Replaced: Known sequence features can explain half of all human gene ends","year":2021,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":true,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Polyadenylation; Gene; Coding region; Genetics; Biology; Sequence (biology); Computational biology; Primary transcript; Context (archaeology); Regulatory sequence; Messenger RNA; Gene expression; Alternative splicing","score_opus":0.018737581049586446,"score_gpt":0.2740747268087642,"score_spread":0.25533714575917776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172664492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9974933,0.0011450959,0.00009500977,0.0003085496,0.000028319319,0.00009169768,0.000084784544,0.000005131177,0.0007480801],"genre_scores_gemma":[0.9854097,0.0025967583,0.009781806,0.00034073938,0.000098055025,0.0000036817155,0.00045701952,0.000014753727,0.0012975272],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991982,0.000023879858,0.0002709099,0.00016328665,0.000118958764,0.00022475596],"domain_scores_gemma":[0.999374,0.000012480512,0.00010548526,0.0002681094,0.000112510155,0.00012744142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023583874,0.00012343108,0.00016217126,0.000045066845,0.00010277598,0.000053489563,0.00009819498,0.00017654743,0.0000055380624],"category_scores_gemma":[0.00007435699,0.00011225051,0.00003945509,0.00006430062,0.00009811106,0.0000071110117,0.00016621864,0.00014196715,4.902519e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027088772,0.000015080243,0.00032893117,0.00008411638,0.00004786637,0.000011029679,0.0002869562,0.000005430581,0.99388653,0.0001411798,0.00081294344,0.0043528643],"study_design_scores_gemma":[0.000700645,0.00035769012,0.0013443079,0.000029159972,0.000022486587,0.00033238277,0.0006825298,0.0012553137,0.9704661,0.00006841301,0.024486346,0.0002546259],"about_ca_topic_score_codex":0.0000750508,"about_ca_topic_score_gemma":0.0001458718,"teacher_disagreement_score":0.023673402,"about_ca_system_score_codex":0.000016269241,"about_ca_system_score_gemma":0.00011092654,"threshold_uncertainty_score":0.4577443},"labels":[],"label_agreement":null},{"id":"W3217246491","doi":"10.1093/nargab/lqab105","title":"RNA-Scoop: interactive visualization of transcripts in single-cell transcriptomes","year":2021,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Canada's Michael Smith Genome Sciences Centre; Genome Canada","keywords":"Transcriptome; RNA; Computational biology; Visualization; Biology; Cell; Single-cell analysis; Computer science; Genetics; Gene expression; Gene; Data mining","score_opus":0.013069874968820455,"score_gpt":0.228204744840605,"score_spread":0.21513486987178454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217246491","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9844031,0.0012836488,0.010951866,0.000053067586,0.00021709116,0.00016188384,0.000059151862,0.0000080402115,0.0028621762],"genre_scores_gemma":[0.993282,0.0015132249,0.0045028594,0.00026998974,0.00004745847,0.0000038501194,0.00021498019,0.000022554688,0.00014304124],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99892515,0.000035059216,0.0005224615,0.00019189178,0.000113404094,0.00021203917],"domain_scores_gemma":[0.99946904,0.000014977602,0.00012900322,0.0001877388,0.00012936523,0.00006988895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013242928,0.00018085918,0.00025066413,0.00009438066,0.000043524826,0.00004052901,0.00011235496,0.00018301976,0.000010417592],"category_scores_gemma":[0.000024351826,0.00018388059,0.00009658774,0.00016482388,0.00007660336,0.000019272977,0.00003197186,0.000098484656,0.0000014865576],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012055727,0.00025584566,0.0013691823,0.00021565505,0.00003251334,0.0000031995046,0.00213214,0.00007845152,0.98874754,0.00009460849,0.000066932735,0.00688337],"study_design_scores_gemma":[0.0017199775,0.000378849,0.000721767,0.000058651327,0.000034802542,0.000021234147,0.0014296486,0.003641653,0.98332393,0.000055182787,0.008320272,0.00029404555],"about_ca_topic_score_codex":0.000017265867,"about_ca_topic_score_gemma":0.00009225534,"teacher_disagreement_score":0.008878967,"about_ca_system_score_codex":0.000025870311,"about_ca_system_score_gemma":0.0001116441,"threshold_uncertainty_score":0.7498433},"labels":[],"label_agreement":null},{"id":"W4206004774","doi":"10.1093/nargab/lqab122","title":"A comparison on predicting functional impact of genomic variants","year":2022,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Key Research and Development Program of China","keywords":"Single-nucleotide polymorphism; Missense mutation; Genomics; Human genome; Functional genomics; SNP","score_opus":0.014672094106870068,"score_gpt":0.2587007337804651,"score_spread":0.24402863967359503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206004774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99759775,0.0003788065,0.00023892778,0.000016608432,0.00014000514,0.000161874,0.0004766779,0.0000058909977,0.0009834771],"genre_scores_gemma":[0.99837375,0.000107202955,0.0008446917,0.000117238,0.000087844644,0.000009702485,0.0003635516,0.000015037043,0.000080967075],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991868,0.000021595977,0.00034190132,0.00014299463,0.00012783335,0.0001788821],"domain_scores_gemma":[0.9994465,0.0000128461725,0.00021150525,0.00020417011,0.000040330004,0.000084656946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000179576,0.00013555265,0.00016825827,0.00007375262,0.0002271228,0.00002239201,0.00013026372,0.00005264839,0.000074460026],"category_scores_gemma":[0.000015364354,0.00012288237,0.00012878928,0.00005223996,0.0000423073,0.0000034707828,0.00025432892,0.00010353881,0.000005053489],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029658815,0.001431263,0.16765754,0.00028880456,0.0014543846,0.0000136534645,0.003129795,0.111066066,0.66088617,0.0010531177,0.023738246,0.026315095],"study_design_scores_gemma":[0.008230046,0.0148491915,0.55197257,0.000043103275,0.00034934308,0.0006890295,0.0063936445,0.34244472,0.012200466,0.0004912027,0.060165696,0.0021710212],"about_ca_topic_score_codex":0.000015492356,"about_ca_topic_score_gemma":0.0000015015017,"teacher_disagreement_score":0.6486857,"about_ca_system_score_codex":0.000055758872,"about_ca_system_score_gemma":0.00018179497,"threshold_uncertainty_score":0.50109977},"labels":[],"label_agreement":null},{"id":"W4206771039","doi":"10.1093/nargab/lqab123","title":"FILER: a framework for harmonizing and querying large-scale functional genomics knowledge","year":2022,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Weston Brain Institute","keywords":"Scale (ratio); Genomics; Computer science; Functional genomics; Data science; Computational biology; Biology; Genome; Geography; Genetics; Cartography; Gene","score_opus":0.02949434952622089,"score_gpt":0.25344907683266604,"score_spread":0.22395472730644517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206771039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7343967,0.0048239185,0.2573004,0.0006148286,0.00068471645,0.0006641831,0.00050071825,0.000028449856,0.0009861079],"genre_scores_gemma":[0.8398544,0.0027455722,0.15165678,0.0025888877,0.00066801015,0.00033009332,0.0010438584,0.000067714405,0.0010446624],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99927557,0.000017319147,0.00023966053,0.0001931835,0.0000735645,0.00020073005],"domain_scores_gemma":[0.99954784,0.000021251655,0.00012331488,0.00017663065,0.000049467555,0.000081470534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002599908,0.00012338469,0.0001141276,0.000058661095,0.00052797305,0.000057826684,0.000094545954,0.00009720494,0.000020399488],"category_scores_gemma":[0.000022749195,0.00012664178,0.000053756456,0.000065208085,0.00003450305,0.0000070389583,0.00026618966,0.00012205577,0.00000171117],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011209722,0.00048346046,0.0030102,0.00079297414,0.00033415013,0.000001183369,0.015309011,0.0014023591,0.69012576,0.013678107,0.100150764,0.17359108],"study_design_scores_gemma":[0.00092108245,0.00022756612,0.0004949517,0.000010749883,0.000028696995,0.000030293639,0.0045793247,0.038468417,0.008711496,0.0011116321,0.94511205,0.00030375773],"about_ca_topic_score_codex":9.186356e-7,"about_ca_topic_score_gemma":0.0000039121824,"teacher_disagreement_score":0.8449613,"about_ca_system_score_codex":0.00004422739,"about_ca_system_score_gemma":0.000108812856,"threshold_uncertainty_score":0.5164302},"labels":[],"label_agreement":null},{"id":"W4211146659","doi":"10.1093/nargab/lqab125","title":"An improved molecular inversion probe based targeted sequencing approach for low variant allele frequency","year":2022,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"Rising Tide Foundation; Applebaum Foundation; Princess Margaret Cancer Foundation","keywords":"Allele frequency; Allele; Genetics; Inversion (geology); Computational biology; Biology; Paleontology; Gene","score_opus":0.007255798986068817,"score_gpt":0.20408456254668625,"score_spread":0.19682876356061743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211146659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5102364,0.00083455635,0.48548532,0.00014900572,0.0002210689,0.001573757,0.0010043815,0.000034364224,0.0004611577],"genre_scores_gemma":[0.63217103,0.00011938064,0.361926,0.0019136751,0.00012348322,0.0001783811,0.0034914368,0.00005060981,0.000026003907],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877715,0.000032309177,0.00038238073,0.000321181,0.00013454,0.0003524089],"domain_scores_gemma":[0.9990939,0.00001460159,0.00020052206,0.00042512867,0.000101647274,0.0001642348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038708502,0.00022678572,0.00020223281,0.00008236592,0.0003844125,0.000084969586,0.00028699287,0.00013229287,0.000011097582],"category_scores_gemma":[0.000043304946,0.00023860944,0.000106120926,0.0001006206,0.00005380197,0.000012284104,0.00019823348,0.00013930585,6.015651e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019699153,0.00016270706,0.00009154027,0.00022725515,0.00007628889,0.0000045180195,0.00045673095,0.017126892,0.97696716,0.0007690901,0.00080893736,0.0031118698],"study_design_scores_gemma":[0.0018995889,0.0015615851,0.000016330374,0.0000043954515,0.000058551144,0.000031380732,0.0010717841,0.92152214,0.06439956,0.00053021684,0.008353868,0.0005505928],"about_ca_topic_score_codex":0.000044367203,"about_ca_topic_score_gemma":0.000007676655,"teacher_disagreement_score":0.9125676,"about_ca_system_score_codex":0.0001482345,"about_ca_system_score_gemma":0.00047165173,"threshold_uncertainty_score":0.97302103},"labels":[],"label_agreement":null},{"id":"W4214852607","doi":"10.1093/nargab/lqac010","title":"G-quadruplex occurrence and conservation: more than just a question of guanine–cytosine content","year":2022,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"DNA and Nucleic Acid Chemistry","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Guanine; Cytosine; G-quadruplex; Content (measure theory); Chemistry; DNA; Mathematics; Biochemistry; Gene; Mathematical analysis","score_opus":0.020899956561881126,"score_gpt":0.2418839903462985,"score_spread":0.2209840337844174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214852607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9979165,0.00071878236,0.00028189382,0.00039341897,0.000058644542,0.00010913678,0.0002649784,0.000006088749,0.00025055668],"genre_scores_gemma":[0.99597114,0.00058705045,0.0024544504,0.000391544,0.000038416714,0.000009027929,0.00039671324,0.0000065352297,0.0001451068],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99940324,0.000010775596,0.0002607122,0.00011257515,0.00010014642,0.00011257545],"domain_scores_gemma":[0.99956244,0.00000727132,0.00016021663,0.00015421755,0.000060748956,0.000055109853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015352717,0.00010485871,0.00012421342,0.000023363602,0.00012140278,0.000017052253,0.0000947613,0.000058805752,0.000012407764],"category_scores_gemma":[0.000024280545,0.00010130298,0.000030436857,0.00005044604,0.00011319396,0.000006103194,0.00021619853,0.00007456717,4.5760456e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033398095,0.00014707001,0.02006092,0.00051350915,0.00012189079,0.0000036461283,0.0017803237,0.00008101481,0.9516412,0.0006477706,0.009308203,0.015360473],"study_design_scores_gemma":[0.006164173,0.0024324195,0.01982961,0.00010724765,0.00026437594,0.00084626133,0.02481801,0.04999952,0.5608061,0.0001989304,0.3328307,0.0017026576],"about_ca_topic_score_codex":0.000017100618,"about_ca_topic_score_gemma":0.0000026798175,"teacher_disagreement_score":0.3908351,"about_ca_system_score_codex":0.000013564633,"about_ca_system_score_gemma":0.0000518116,"threshold_uncertainty_score":0.41310158},"labels":[],"label_agreement":null},{"id":"W4220964301","doi":"10.1093/nargab/lqac018","title":"Data-driven identification of inherent features of eukaryotic stress-responsive genes","year":2022,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; National Institutes of Health; Boehringer Ingelheim Fonds","keywords":"Gene; Computational biology; Biology; Saccharomyces cerevisiae; Yeast; Gene expression; Genetics","score_opus":0.020233198738345302,"score_gpt":0.2752859193507044,"score_spread":0.2550527206123591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220964301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99653757,0.0013343736,0.0004858712,0.00004843671,0.000049179744,0.00018527311,0.0012766334,0.0000022837858,0.00008037517],"genre_scores_gemma":[0.9955505,0.001151115,0.0019868806,0.00003281546,0.000030093079,0.0000068717795,0.00096386945,0.000008445398,0.0002694133],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992034,0.000035686924,0.00034846817,0.000118188684,0.0001710901,0.00012317927],"domain_scores_gemma":[0.99921376,0.000015684112,0.0002339162,0.0004120163,0.0000801763,0.00004443952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027989128,0.000077206096,0.00012603517,0.00007016124,0.00009690121,0.00001592937,0.00032925958,0.000040187108,0.0000078360135],"category_scores_gemma":[0.000049069055,0.00007137768,0.000033580578,0.0000730995,0.000071175244,0.000007876406,0.0006350122,0.00007493375,6.0900965e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018433797,0.0000733666,0.0029176106,0.00020840438,0.00010516788,0.0000010607821,0.00032327615,0.0016666007,0.97070944,0.0001435353,0.0011678286,0.022499382],"study_design_scores_gemma":[0.0020308532,0.0018374621,0.036007654,0.00004259186,0.00012214454,0.00008502517,0.010750932,0.10300454,0.8282084,0.00012848827,0.017174017,0.0006079052],"about_ca_topic_score_codex":0.000019269068,"about_ca_topic_score_gemma":0.000017415205,"teacher_disagreement_score":0.14250104,"about_ca_system_score_codex":0.00001268631,"about_ca_system_score_gemma":0.00010706804,"threshold_uncertainty_score":0.29106975},"labels":[],"label_agreement":null},{"id":"W4221050649","doi":"10.1093/nargab/lqac026","title":"Construction of a chromosome-level Japanese stickleback species genome using ultra-dense linkage analysis with single-cell sperm sequencing","year":2022,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; Japan Society for the Promotion of Science; Research Organization of Information and Systems","keywords":"Genome; Biology; Genetics; Linkage (software); Contig; Genetic linkage; Genotyping; Genomics; Chromosome; Sperm; Computational biology; Stickleback; Genotype; Gene; Fish <Actinopterygii>","score_opus":0.025442406299582006,"score_gpt":0.20445496936941632,"score_spread":0.17901256306983432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221050649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99606705,0.0007831628,0.0014197073,0.000014412208,0.00007332363,0.00022373555,0.00056333246,0.0000037789573,0.00085148413],"genre_scores_gemma":[0.967439,0.0004893676,0.03162498,0.000071399554,0.00007777801,0.0000055690307,0.00014820458,0.000021386373,0.00012230898],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987998,0.00003192962,0.00047431028,0.00023799497,0.00018863374,0.0002673271],"domain_scores_gemma":[0.9991014,0.000019164669,0.00036460714,0.0003140388,0.00011957374,0.000081210856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020579612,0.00022947679,0.0003571156,0.00016732863,0.00029527515,0.000042212945,0.0001668495,0.000078748075,0.000023742776],"category_scores_gemma":[0.000011725364,0.00021248143,0.00012436914,0.00032049278,0.00021720689,0.0000037471748,0.00020588496,0.00011475839,7.39892e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007555017,0.000048976486,0.002274493,0.00010354768,0.0004929789,0.0000033207673,0.0027318571,0.010836962,0.9831325,0.000020913234,0.0000062927743,0.0002726019],"study_design_scores_gemma":[0.00749285,0.007092036,0.012646748,0.00006528066,0.005200095,0.0017456083,0.13929729,0.06492877,0.74007744,0.00017227244,0.017318,0.003963596],"about_ca_topic_score_codex":0.000037067515,"about_ca_topic_score_gemma":0.00002718053,"teacher_disagreement_score":0.24305506,"about_ca_system_score_codex":0.00009819934,"about_ca_system_score_gemma":0.00014014532,"threshold_uncertainty_score":0.86647415},"labels":[],"label_agreement":null},{"id":"W4289712796","doi":"10.1093/nargab/lqac057","title":"Mining bacterial NGS data vastly expands the complete genomes of temperate phages","year":2022,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Simon Fraser University; University of British Columbia","funders":"National Institutes of Health; National Key Research and Development Program of China; Hebei Provincial Key Research Projects; U.S. National Library of Medicine; National Natural Science Foundation of China","keywords":"Bacterial genome size; Genome; Temperate climate; Biology; Computational biology; Evolutionary biology; Data science; Computer science; Genetics; Ecology; Gene","score_opus":0.03181369653655028,"score_gpt":0.23701824864955845,"score_spread":0.20520455211300817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289712796","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9974068,0.00006407665,0.00007416951,0.0002349149,0.00025471134,0.00014701717,0.00071321847,0.0000086515265,0.0010964843],"genre_scores_gemma":[0.99224615,0.000261908,0.0064477604,0.0003756626,0.000059414986,0.000006776918,0.0002663664,0.000011284996,0.0003246505],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992994,0.000023751209,0.00030515375,0.000114424365,0.00010294385,0.00015432455],"domain_scores_gemma":[0.9994037,0.000035913083,0.00017141175,0.00034529937,0.0000057398765,0.000037920192],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00027932762,0.00009693257,0.0001296221,0.000022405538,0.0004361524,0.00007398361,0.00043879228,0.000020357678,0.0013057191],"category_scores_gemma":[0.000005558555,0.00007207266,0.000030814477,0.00008631877,0.00012402258,0.00023238747,0.0013421035,0.00010494552,0.000020077145],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007717228,0.00008657646,0.00090874796,0.000041294115,0.00008348624,0.0000021600254,0.012356972,0.00039698856,0.91713405,0.000037510486,0.011007614,0.057867423],"study_design_scores_gemma":[0.0008212293,0.00028760696,0.011881781,0.000009754047,0.00007917752,0.00016246803,0.009766753,0.036861915,0.003122355,0.000025299327,0.9366094,0.00037228654],"about_ca_topic_score_codex":0.00008741548,"about_ca_topic_score_gemma":0.00002778544,"teacher_disagreement_score":0.9256018,"about_ca_system_score_codex":0.00004780725,"about_ca_system_score_gemma":0.000016630062,"threshold_uncertainty_score":0.9996072},"labels":[],"label_agreement":null},{"id":"W4292615690","doi":"10.1093/nargab/lqac058","title":"A computational approach to rapidly design peptides that detect SARS-CoV-2 surface protein S","year":2022,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada; Ottawa Hospital; University of Regina; Carleton University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Computational biology; Pandemic; Peptide; Coronavirus; Surface plasmon resonance; Biology; Virology; Computer science; Medicine; Biochemistry; Disease; Nanotechnology; Infectious disease (medical specialty); Pathology; Materials science","score_opus":0.06575502002795491,"score_gpt":0.30127007006995987,"score_spread":0.23551505004200496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292615690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9438411,0.00027243237,0.05116668,0.00024546706,0.000043648164,0.0017944406,0.00005073915,0.00006305819,0.002522411],"genre_scores_gemma":[0.6594419,0.00000896282,0.3123108,0.027914448,0.000062205596,0.0001327824,0.0000309134,0.00004356097,0.000054426982],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984398,0.000061151986,0.00035953906,0.00021037033,0.0005566064,0.00037256704],"domain_scores_gemma":[0.9993864,0.00010204296,0.0001032283,0.00024349004,0.00009214795,0.000072631636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008270679,0.00019885784,0.00029652668,0.00019587064,0.0003439202,0.00010790002,0.00020742332,0.00006961132,0.0000039113716],"category_scores_gemma":[0.00007023427,0.00017730088,0.00008383995,0.0003308381,0.00007265033,0.00009691171,0.00028895846,0.0003193078,0.00003776175],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058598206,0.0016488435,0.0051162606,0.0038211602,0.0010262096,0.00013518793,0.03461766,0.015575637,0.80546236,0.001939818,0.027966002,0.09683103],"study_design_scores_gemma":[0.003470935,0.0018836523,0.0002875887,0.00005443679,0.00007052117,0.00044870548,0.0037673668,0.68555236,0.16959265,0.00088254164,0.1333174,0.00067185075],"about_ca_topic_score_codex":0.00004425444,"about_ca_topic_score_gemma":0.00000261613,"teacher_disagreement_score":0.6699767,"about_ca_system_score_codex":0.00021799907,"about_ca_system_score_gemma":0.00057003985,"threshold_uncertainty_score":0.723012},"labels":[],"label_agreement":null},{"id":"W4310786235","doi":"10.1093/nargab/lqac092","title":"PBSIM3: a simulator for all types of PacBio and ONT long reads","year":2022,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; Japan Society for the Promotion of Science","keywords":"Computer science; Nanopore sequencing; High fidelity; Fidelity; Throughput; DNA sequencing; Operating system; Engineering; Wireless; Telecommunications","score_opus":0.010942076505552106,"score_gpt":0.23069063892170819,"score_spread":0.2197485624161561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310786235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9955359,0.002903262,0.00059401203,0.0000874671,0.00008986152,0.0002932575,0.00028346584,0.0000019971865,0.0002107479],"genre_scores_gemma":[0.99226046,0.0011822076,0.005990548,0.00029072198,0.000054386197,0.00002063138,0.00007318408,0.000013887585,0.00011394983],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993767,0.000009986746,0.00025580192,0.00013018705,0.00006550111,0.0001618233],"domain_scores_gemma":[0.9995914,0.000020923684,0.00012579151,0.0001594577,0.00004917385,0.000053258325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019396831,0.00011768936,0.00016839373,0.00003508116,0.00014468851,0.00001594242,0.00009250332,0.000054335564,0.0000031545503],"category_scores_gemma":[0.000018669572,0.00011024895,0.000052370968,0.000030108255,0.000064639295,0.0000010788553,0.00028934985,0.000045350764,2.6919403e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014795664,0.0004292693,0.037882503,0.0014897054,0.001973802,0.0000045381066,0.011389907,0.008140444,0.8237277,0.0034295341,0.00621766,0.10383532],"study_design_scores_gemma":[0.0055555273,0.005947318,0.01302777,0.0000249909,0.00041421,0.00013763912,0.0056454404,0.064659104,0.07997321,0.0017239695,0.8213864,0.0015044392],"about_ca_topic_score_codex":0.000009415555,"about_ca_topic_score_gemma":0.000013036531,"teacher_disagreement_score":0.81516874,"about_ca_system_score_codex":0.00001175616,"about_ca_system_score_gemma":0.00004542494,"threshold_uncertainty_score":0.44958216},"labels":[],"label_agreement":null},{"id":"W4317624614","doi":"10.1093/nargab/lqad006","title":"Model-driven experimental design workflow expands understanding of regulatory role of Nac in <i>Escherichia coli</i>","year":2023,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Institutes of Health; Ministry of Science and ICT, South Korea; Novo Nordisk Fonden; National Institute of General Medical Sciences; Danmarks Tekniske Universitet; Novo Nordisk; National Research Foundation of Korea; Ulsan National Institute of Science and Technology; National Research Foundation","keywords":"Escherichia coli; Workflow; Computer science; Computational biology; Business; Chemistry; Biochemical engineering; Process management; Biology; Engineering; Biochemistry; Gene; Database","score_opus":0.0216666012447547,"score_gpt":0.22283707848553883,"score_spread":0.20117047724078413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317624614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99146825,0.0005673154,0.007635908,0.000010153597,0.00006204885,0.00013413366,0.000017632845,0.000008815719,0.00009571283],"genre_scores_gemma":[0.97901666,0.00074622774,0.020111086,0.00001398689,0.000036337413,0.0000037471495,0.000028039054,0.000010911561,0.000033001066],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994096,0.0000101899395,0.0002818981,0.00009994896,0.000066249326,0.00013211057],"domain_scores_gemma":[0.9997012,0.0000032203202,0.000094929106,0.00014719983,0.00002060006,0.000032833235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020448299,0.00009631567,0.00015096631,0.00008163076,0.000027050522,0.000006863963,0.00008503821,0.00010323042,7.899211e-7],"category_scores_gemma":[0.00001003097,0.000093156494,0.000036777023,0.00014400521,0.00005534708,0.0000057786096,0.00006863567,0.000045626217,5.2027167e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047745707,0.000020454423,0.00008082165,0.000046873567,0.000016421895,1.0462452e-7,0.0007947482,0.021023348,0.97688544,0.00014216577,0.000121869,0.0008200043],"study_design_scores_gemma":[0.0003737224,0.00011198965,0.000105751766,0.000025232172,0.0000075822963,0.000002129871,0.0010834824,0.1458098,0.8518782,0.000104249804,0.00038006788,0.00011775687],"about_ca_topic_score_codex":0.0000038118803,"about_ca_topic_score_gemma":0.0000014331149,"teacher_disagreement_score":0.12500721,"about_ca_system_score_codex":0.000024578756,"about_ca_system_score_gemma":0.000044172142,"threshold_uncertainty_score":0.37988117},"labels":[],"label_agreement":null},{"id":"W4317743512","doi":"10.1093/nargab/lqad003","title":"Differential Expression Enrichment Tool (DEET): an interactive atlas of human differential gene expression","year":2023,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; SickKids Foundation; University of Toronto","funders":"National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Centre for Applied Genomics; Genome Canada","keywords":"Computational biology; Expression (computer science); Pipeline (software); Gene expression; Gene; Computer science; Differential (mechanical device); Biology; Gene expression profiling; DEET; Information retrieval; Data mining; Genetics","score_opus":0.009721680046971246,"score_gpt":0.24657784619213813,"score_spread":0.23685616614516689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317743512","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98959094,0.00005851988,0.009232264,0.000015755684,0.0003022024,0.0003372667,0.00012551344,0.000029296916,0.0003082129],"genre_scores_gemma":[0.99249274,0.0004864483,0.0050563063,0.00005549724,0.00031126008,0.000017976134,0.0013557263,0.000030002353,0.00019404416],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99841976,0.000034733777,0.0007158102,0.00024939163,0.0002126412,0.00036767902],"domain_scores_gemma":[0.99890685,0.000016355774,0.00037449857,0.00046795222,0.000083814084,0.0001505508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015788885,0.00029208395,0.00031498066,0.00013125346,0.00022668755,0.00008692497,0.00028736328,0.0002808159,0.000039591752],"category_scores_gemma":[0.000012229116,0.00024346066,0.00012584383,0.00009808125,0.00010310128,0.000030997882,0.00055369997,0.00016433517,0.000012384344],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013806652,0.0000880434,0.00027684888,0.0000987852,0.000052500272,0.0000010511621,0.0011239636,0.0000884308,0.98859286,0.00006934321,0.0015004686,0.007969625],"study_design_scores_gemma":[0.0019825082,0.0010517023,0.001921365,0.0000927022,0.00005957377,0.000018064937,0.0015045987,0.034992296,0.95381516,0.0003769824,0.0035338583,0.000651206],"about_ca_topic_score_codex":0.000006351647,"about_ca_topic_score_gemma":0.000004141311,"teacher_disagreement_score":0.034903865,"about_ca_system_score_codex":0.000024885805,"about_ca_system_score_gemma":0.000044606826,"threshold_uncertainty_score":0.99280375},"labels":[],"label_agreement":null},{"id":"W4323076270","doi":"10.1093/nargab/lqad017","title":"BaM-seq and TBaM-seq, highly multiplexed and targeted RNA-seq protocols for rapid, low-cost library generation from bacterial samples","year":2023,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Howard Hughes Medical Institute; National Institutes of Health; National Science Foundation","keywords":"RNA-Seq; Computational biology; DNA sequencing; Transcriptome; RNA; Genomic library; Deep sequencing; Biology; Computer science; Gene; Gene expression; Genetics; Genome; Base sequence","score_opus":0.027829999735565897,"score_gpt":0.2409403088289274,"score_spread":0.21311030909336148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323076270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99188495,0.00061274733,0.00037000474,0.00032090518,0.00021820617,0.004482165,0.0020292695,0.000021201691,0.000060540842],"genre_scores_gemma":[0.8414009,0.014849014,0.12430227,0.0012936617,0.0028016213,0.003822669,0.010766487,0.00018636594,0.000576978],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99875057,0.000025484973,0.00047226337,0.00033472767,0.00008613055,0.00033082656],"domain_scores_gemma":[0.99931204,0.000052013947,0.0001831284,0.0002502432,0.000060057493,0.00014251724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001828727,0.0002874359,0.0003049727,0.000073142575,0.00028481366,0.00022255204,0.00013138707,0.00023382061,0.0000071113104],"category_scores_gemma":[0.000052431507,0.00024000797,0.00006684857,0.00007621268,0.00012114197,0.000013453849,0.00031040388,0.00006904761,0.0000034513896],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025414754,0.00002607645,0.0013764577,0.0001347614,0.00014836485,8.272267e-7,0.00066805945,0.000044409688,0.96129155,0.000104933955,0.004449815,0.031500567],"study_design_scores_gemma":[0.007747516,0.0011403717,0.023045106,0.00007040171,0.000141917,0.000017523298,0.0008438376,0.051816177,0.46567675,0.0012126449,0.44680902,0.0014787378],"about_ca_topic_score_codex":0.00001869863,"about_ca_topic_score_gemma":0.000020344354,"teacher_disagreement_score":0.49561483,"about_ca_system_score_codex":0.000009812952,"about_ca_system_score_gemma":0.000082237726,"threshold_uncertainty_score":0.9787241},"labels":[],"label_agreement":null},{"id":"W4362562485","doi":"10.1093/nargab/lqad031","title":"Known sequence features explain half of all human gene ends","year":2022,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; University of Toronto","funders":"Canadian Institutes of Health Research; University of Toronto","keywords":"Polyadenylation; Gene; Biology; Genetics; Coding region; Computational biology; Sequence (biology); Primary transcript; Context (archaeology); RNA; Messenger RNA; Alternative splicing","score_opus":0.020650263060473267,"score_gpt":0.2755685505550601,"score_spread":0.2549182874945868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362562485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9974541,0.00072308973,0.00019704552,0.0001520417,0.00004229538,0.00013478217,0.00011600837,0.0000054930424,0.0011751191],"genre_scores_gemma":[0.99233085,0.00047090353,0.0051190834,0.00032238264,0.00008258912,0.000015001692,0.00035597009,0.000013935631,0.0012892826],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99920535,0.000026414446,0.00025095948,0.0001229194,0.00016364585,0.00023073828],"domain_scores_gemma":[0.9995179,0.000007778409,0.00010901077,0.00023719143,0.000041156716,0.000086919244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003086326,0.00010838017,0.00012996116,0.000064369,0.00021592513,0.000026543068,0.00022054142,0.000060630537,0.00002002705],"category_scores_gemma":[0.000017331631,0.00010150906,0.00005668381,0.000063388354,0.00007351683,0.000005333718,0.0003777274,0.00013161874,0.0000012959384],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038184335,0.000026059353,0.00013732692,0.00004345999,0.000041840223,0.000004042631,0.00034838807,0.00013168278,0.9913236,0.00033743843,0.0018349893,0.0057330173],"study_design_scores_gemma":[0.0015145169,0.0020079687,0.00061811873,0.0000133273315,0.000034737335,0.0003785792,0.002675666,0.007453121,0.7056831,0.00024206343,0.2787909,0.00058791984],"about_ca_topic_score_codex":0.00006183576,"about_ca_topic_score_gemma":0.000016451202,"teacher_disagreement_score":0.28564048,"about_ca_system_score_codex":0.00002646016,"about_ca_system_score_gemma":0.000071713745,"threshold_uncertainty_score":0.41394195},"labels":[],"label_agreement":null},{"id":"W4366818125","doi":"10.1093/nargab/lqad038","title":"SUP: a probabilistic framework to propagate genome sequence uncertainty, with applications","year":2023,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Western University","keywords":"Resampling; Computer science; Propagation of uncertainty; Probabilistic logic; Sequence (biology); Representation (politics); Variance (accounting); Algorithm; Data mining; Artificial intelligence; Biology","score_opus":0.015766099384214038,"score_gpt":0.2448559491589844,"score_spread":0.22908984977477037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366818125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877435,0.0003003085,0.009359669,0.00046089658,0.000052327214,0.0012090494,0.00029603194,0.000025603755,0.0005525929],"genre_scores_gemma":[0.94495595,0.0020943924,0.05055433,0.00090777397,0.00024995537,0.0003935381,0.00030850476,0.000049021473,0.00048652958],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990121,0.000010757143,0.00026708897,0.0002612501,0.000111267116,0.00033754148],"domain_scores_gemma":[0.99926436,0.000020580865,0.00008122452,0.0003704992,0.0001110745,0.00015227804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018452217,0.00019706694,0.00017297264,0.0000736495,0.00021053937,0.00006874185,0.00020765357,0.00010626234,0.000002311855],"category_scores_gemma":[0.000027773198,0.00015890124,0.000037510606,0.00028395638,0.000115816394,0.000001707993,0.00020023291,0.000084006824,0.00005468295],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074466056,0.00028827324,0.0068504107,0.0017307482,0.0011138578,0.000024030069,0.014350432,0.14487585,0.71011555,0.017451977,0.0034749273,0.0989793],"study_design_scores_gemma":[0.0014516626,0.0027402127,0.0064673657,0.00010627828,0.0001769657,0.0001658731,0.0034519173,0.030060884,0.004274028,0.009587438,0.9393823,0.002135035],"about_ca_topic_score_codex":0.0000073321767,"about_ca_topic_score_gemma":0.000018594901,"teacher_disagreement_score":0.9359074,"about_ca_system_score_codex":0.000023777939,"about_ca_system_score_gemma":0.00009932439,"threshold_uncertainty_score":0.64798045},"labels":[],"label_agreement":null},{"id":"W4378713713","doi":"10.1093/nargab/lqad052","title":"Refining the genomic determinants underlying escape from X-chromosome inactivation","year":2022,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genetic and Clinical Aspects of Sex Determination and Chromosomal Abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"X-inactivation; Biology; Genetics; Gene; Transgene; X chromosome; Transcription (linguistics); Transcription factor; Phenotype; Chromosome; Context (archaeology)","score_opus":0.022748884197983422,"score_gpt":0.25523385560712253,"score_spread":0.2324849714091391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378713713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.997607,0.00042784345,0.00022188597,0.0002868027,0.00017797106,0.00010767189,0.00007983587,0.000011414401,0.001079585],"genre_scores_gemma":[0.9963077,0.00027691858,0.0014068024,0.0011891541,0.00011471472,0.000023530229,0.0001419306,0.000015191046,0.00052407326],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905664,0.000043481967,0.00037215557,0.00017445337,0.00015515205,0.00019814502],"domain_scores_gemma":[0.9994312,0.000040248153,0.0001941372,0.00024118734,0.00003251785,0.000060703373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023311104,0.00014294639,0.00013684343,0.00003111534,0.00062387635,0.00007917364,0.00024460777,0.0000697659,0.00007055928],"category_scores_gemma":[0.000024354902,0.00011438162,0.00006319468,0.000060080725,0.00008939668,0.000010247843,0.00040033166,0.00015644082,0.000008591762],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005218573,0.0003364911,0.018815417,0.00015806471,0.0003823954,0.000020025052,0.0074127014,0.0014559036,0.46864125,0.0011038223,0.0034514344,0.49770063],"study_design_scores_gemma":[0.0054042335,0.0038640792,0.077918105,0.00005932728,0.0002536098,0.00047190482,0.058586303,0.060414147,0.060760096,0.003795194,0.72600055,0.0024724384],"about_ca_topic_score_codex":0.000034740402,"about_ca_topic_score_gemma":0.00002218595,"teacher_disagreement_score":0.72254914,"about_ca_system_score_codex":0.00003425895,"about_ca_system_score_gemma":0.00006793106,"threshold_uncertainty_score":0.47984156},"labels":[],"label_agreement":null},{"id":"W4383216982","doi":"10.1093/nargab/lqad065","title":"GCPBayes pipeline: a tool for exploring pleiotropy at the gene level","year":2023,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genetic Mapping and Diversity in Plants and Animals","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Ligue Contre le Cancer; Ovarian Cancer Research Fund; National Institutes of Health; Cancer Research UK; Government of Canada; Institut National de la Santé et de la Recherche Médicale; Fondation du cancer du sein du Québec; Canadian Institutes of Health Research; Gray Foundation; Genome Canada; European Commission; Breast Cancer Research Foundation","keywords":"Pleiotropy; Pipeline (software); Context (archaeology); Computer science; Set (abstract data type); Genome-wide association study; Computational biology; Gene; Genome; Data mining; Biology; Phenotype; Genetics; Single-nucleotide polymorphism","score_opus":0.061373062267999635,"score_gpt":0.24300302344086586,"score_spread":0.18162996117286623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383216982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942534,0.00028325096,0.0037991172,0.00041723906,0.00017510846,0.00023479498,0.00054469594,0.000018922005,0.00027349542],"genre_scores_gemma":[0.9223756,0.01670451,0.033857737,0.0023176966,0.001289864,0.00013054753,0.0023690136,0.00006186706,0.020893153],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993419,0.000006997463,0.00019842398,0.00013297988,0.000081156046,0.00023854681],"domain_scores_gemma":[0.99962425,0.000025697433,0.00006810124,0.00018420952,0.000047613255,0.000050127088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023811842,0.00012130359,0.00010682977,0.000034499266,0.0003478623,0.000059658807,0.00013906037,0.000075657095,0.0000060663424],"category_scores_gemma":[0.000043197164,0.00008657426,0.000072736075,0.00005806001,0.00004992407,0.000004592513,0.00023938871,0.000038804974,0.000031040814],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006437285,0.000075601354,0.0046208636,0.0005576327,0.00034429075,0.000006825036,0.0036610581,0.0012745531,0.49387875,0.0009823637,0.3598231,0.13413124],"study_design_scores_gemma":[0.0012922876,0.00041226775,0.0028037254,0.000019991396,0.00006215376,0.00005070993,0.0019273551,0.025771437,0.065019056,0.00017551772,0.90196383,0.0005016461],"about_ca_topic_score_codex":0.0000045629963,"about_ca_topic_score_gemma":0.000007933807,"teacher_disagreement_score":0.5421407,"about_ca_system_score_codex":0.000009303641,"about_ca_system_score_gemma":0.000031470172,"threshold_uncertainty_score":0.3530396},"labels":[],"label_agreement":null},{"id":"W4391994538","doi":"10.1093/nargab/lqae018","title":"CDBProm: the Comprehensive Directory of Bacterial Promoters","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Izaak Walton Killam Health Centre; Dalhousie University","funders":"Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México; Research Nova Scotia; Universidad Nacional Autónoma de México; Dalhousie Medical Research Foundation; Dalhousie University; Canadian Institutes of Health Research; Li Ka Shing Foundation","keywords":"Promoter; Genome; Bacterial genome size; Biology; Computational biology; Genetics; Gene; Bacterial artificial chromosome; DNA sequencing; In silico; Directory; Computer science; Gene expression","score_opus":0.013056275883971543,"score_gpt":0.23510266022786458,"score_spread":0.22204638434389304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391994538","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99186933,0.006272159,0.000164998,0.00012955762,0.0003942292,0.00020027025,0.00008818886,0.0000043203263,0.000876934],"genre_scores_gemma":[0.993361,0.0035305673,0.002549842,0.00012968347,0.00021638712,0.00000781871,0.000043034237,0.000015538753,0.0001461096],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994423,0.000013496357,0.00023231126,0.00011561617,0.00006292976,0.00013339201],"domain_scores_gemma":[0.9996601,0.000020307987,0.000056295357,0.00018279045,0.00004665464,0.00003387392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011072079,0.00011941665,0.00012497052,0.000028817563,0.000075612064,0.0000462332,0.00011435793,0.00006584923,0.000005028532],"category_scores_gemma":[0.000009138992,0.0000797762,0.000065705804,0.000047492,0.0001463366,0.0000012395151,0.0001452854,0.000056115754,0.0000036918282],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051232313,0.000019285102,0.00020609023,0.0002942218,0.00028829658,0.0000011923867,0.002057753,0.000035491576,0.9592586,0.00045708552,0.0035983943,0.03373235],"study_design_scores_gemma":[0.0004890012,0.0005241609,0.003595556,0.000053635486,0.00010765573,0.000058416626,0.0013044542,0.005139802,0.089622386,0.00032811458,0.8983644,0.00041238609],"about_ca_topic_score_codex":0.000005675889,"about_ca_topic_score_gemma":0.000004160218,"teacher_disagreement_score":0.89476603,"about_ca_system_score_codex":0.00000743691,"about_ca_system_score_gemma":0.000059567697,"threshold_uncertainty_score":0.3253179},"labels":[],"label_agreement":null},{"id":"W4392844094","doi":"10.1093/nargab/lqae005","title":"Functional domain annotation by structural similarity","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Annotation; Computational biology; Structural similarity; In silico; Protein domain; Domain (mathematical analysis); Similarity (geometry); Structural alignment; Sequence alignment; Proteome; UniProt; Biology; Sequence (biology); Protein sequencing; Benchmark (surveying); Computer science; Bioinformatics; Genetics; Peptide sequence; Artificial intelligence; Geography","score_opus":0.007423367596102924,"score_gpt":0.21458169780913128,"score_spread":0.20715833021302835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392844094","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897022,0.0053930734,0.0030581718,0.00029522114,0.00034444968,0.0001283699,0.00024735893,0.000008429623,0.00082270126],"genre_scores_gemma":[0.9894115,0.0013307211,0.007957944,0.00037866118,0.00024427316,0.0000071612826,0.00036527996,0.0000165605,0.00028793892],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993743,0.0000091186375,0.00021291095,0.00015976887,0.00008081996,0.00016309922],"domain_scores_gemma":[0.9997356,0.0000103347365,0.00003837921,0.000118172524,0.00003904564,0.00005846352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012408094,0.00013664034,0.000095967975,0.000033107797,0.00013681414,0.00010102681,0.00006290289,0.000102945465,0.000008957792],"category_scores_gemma":[0.000008404623,0.00011839468,0.00005125804,0.00005139911,0.00006901922,0.0000028122497,0.00008944294,0.00007163046,0.000008939202],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110864756,0.000028509754,0.002288661,0.00032287574,0.00043140523,0.000003333718,0.0017524112,0.0002585745,0.8467063,0.003203998,0.07677342,0.068119705],"study_design_scores_gemma":[0.0010479371,0.0005647213,0.009281103,0.000026985044,0.000085426975,0.00014080261,0.0013959656,0.029748939,0.030265778,0.0056830514,0.92083246,0.00092685473],"about_ca_topic_score_codex":0.000004626226,"about_ca_topic_score_gemma":0.0000060988596,"teacher_disagreement_score":0.844059,"about_ca_system_score_codex":0.000016596276,"about_ca_system_score_gemma":0.000049926886,"threshold_uncertainty_score":0.4827995},"labels":[],"label_agreement":null},{"id":"W4399154467","doi":"10.1093/nargab/lqae060","title":"G-quadruplex propensity in <i>H. neanderthalensis</i>, <i>H. sapiens</i> and Denisovans mitochondrial genomes","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Vermont Agency of Natural Resources; Institut National Du Cancer; Grantová Agentura České Republiky; Agence Nationale de la Recherche; CNIB","keywords":"Homo sapiens; Mitochondrial DNA; Genome; Genetics; Biology; DNA; Evolutionary biology; Gene; Geography","score_opus":0.011667398392851707,"score_gpt":0.21640499014123454,"score_spread":0.20473759174838282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399154467","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98612833,0.009491279,0.0023550438,0.00027384222,0.00031762858,0.00046913532,0.000050562056,0.000024835263,0.00088935153],"genre_scores_gemma":[0.9606297,0.011554004,0.02610286,0.0007118172,0.0003634345,0.000025745312,0.00008626381,0.00004696719,0.00047917885],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989807,0.000028049253,0.0003384548,0.00027444868,0.00010418907,0.00027414708],"domain_scores_gemma":[0.99957466,0.000021493304,0.000053255473,0.00021723291,0.000029847788,0.00010351018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024177947,0.00020857019,0.00021536933,0.000087793305,0.00009669692,0.00017597232,0.00010879873,0.00016721619,0.0000072219364],"category_scores_gemma":[0.000024438032,0.0001772914,0.000057533944,0.000088660636,0.00008999521,0.000017466391,0.00016719388,0.000110765766,0.000011148908],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001894162,0.00004683205,0.0010671968,0.00048478704,0.00011341173,0.000041040883,0.0015482911,0.000024614726,0.8372644,0.00092611776,0.0014886032,0.15680528],"study_design_scores_gemma":[0.0025415681,0.0011130306,0.001251718,0.00026781313,0.00014646244,0.0010212333,0.0015363581,0.018089697,0.39020213,0.0023209862,0.5797258,0.0017832216],"about_ca_topic_score_codex":0.000014334088,"about_ca_topic_score_gemma":0.00005656988,"teacher_disagreement_score":0.5782372,"about_ca_system_score_codex":0.000017148348,"about_ca_system_score_gemma":0.00008733697,"threshold_uncertainty_score":0.72297335},"labels":[],"label_agreement":null},{"id":"W4399656493","doi":"10.1093/nargab/lqae068","title":"Structure-based learning to predict and model protein–DNA interactions and transcription-factor co-operativity in <i>cis</i>-regulatory elements","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"Agencia Estatal de Investigación; Ministerio de Ciencia e Innovación; Generalitat de Catalunya; Human Frontier Science Program","keywords":"Transcription factor; DNA; Computational biology; Transcription (linguistics); Genetics; Biology; Gene","score_opus":0.009518222244531825,"score_gpt":0.2376803225427711,"score_spread":0.22816210029823927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399656493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842872,0.00051774114,0.014336846,0.00010572059,0.000048392856,0.00045718625,0.00017089747,0.000013485345,0.00006254443],"genre_scores_gemma":[0.984235,0.00018840369,0.01518431,0.00015762138,0.000037075668,0.000024620827,0.000057943227,0.000015647718,0.00009935999],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99928844,0.000024617444,0.00025504324,0.0001892119,0.00008364513,0.00015907174],"domain_scores_gemma":[0.99972796,0.000009338351,0.00003866473,0.00010680622,0.00001986497,0.00009736467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016049141,0.00015369334,0.00013094945,0.000089065456,0.00010500193,0.00013222986,0.0000516494,0.00010454432,0.000008231008],"category_scores_gemma":[0.00001687442,0.0001363767,0.000026143487,0.000044373326,0.00003650101,0.00002207771,0.000038197082,0.000119393924,0.0000011604628],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055847915,0.00001098373,0.0002733296,0.00015771389,0.000024807165,7.24963e-7,0.00069184694,0.0004737445,0.9702142,0.00007458242,0.000037694845,0.02798454],"study_design_scores_gemma":[0.000733742,0.00051011145,0.00063681445,0.0001547301,0.000028705666,0.000019406018,0.00034086607,0.2895376,0.68946576,0.0002747208,0.017859671,0.00043784987],"about_ca_topic_score_codex":0.0000045818792,"about_ca_topic_score_gemma":0.000033707267,"teacher_disagreement_score":0.28906387,"about_ca_system_score_codex":0.000021122898,"about_ca_system_score_gemma":0.00007167393,"threshold_uncertainty_score":0.55612797},"labels":[],"label_agreement":null},{"id":"W4400562029","doi":"10.1093/nargab/lqae079","title":"Optimizing hybrid ensemble feature selection strategies for transcriptomic biomarker discovery in complex diseases","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Feature selection; Robustness (evolution); Computer science; Biomarker discovery; Feature (linguistics); Data mining; Machine learning; Artificial intelligence; Computational biology; Biology; Gene","score_opus":0.01872548788231583,"score_gpt":0.2641647738759884,"score_spread":0.2454392859936726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400562029","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8245448,0.009163351,0.16359802,0.0005460769,0.0003453537,0.0006103717,0.0003321086,0.000041562507,0.0008183926],"genre_scores_gemma":[0.9902861,0.0018457881,0.006723052,0.00016907124,0.00009491441,0.000036179255,0.00054086646,0.000017066008,0.00028692355],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99941444,0.000010681858,0.00018810797,0.00017290992,0.00005487983,0.00015900597],"domain_scores_gemma":[0.9997817,0.000008514221,0.00003971245,0.000099847304,0.000025697122,0.000044480854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008140791,0.0001247644,0.00010486804,0.00009097573,0.00007312059,0.0002574954,0.000068416884,0.00008005061,0.0000024372423],"category_scores_gemma":[0.0000053621143,0.00010836558,0.0000655488,0.000081732105,0.000033015163,0.000032877037,0.00002262371,0.00005703908,0.0000010275828],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018459279,0.00003214569,0.00011173195,0.00037039642,0.000051246567,7.813145e-7,0.00043030796,0.00045599995,0.93174577,0.000702358,0.018876575,0.0470381],"study_design_scores_gemma":[0.0014816646,0.00034028964,0.0022230302,0.00012188729,0.00008746423,0.000051898358,0.0029943893,0.41695952,0.06208326,0.0012282918,0.5117786,0.00064971263],"about_ca_topic_score_codex":0.0000027384988,"about_ca_topic_score_gemma":0.000021097936,"teacher_disagreement_score":0.8696625,"about_ca_system_score_codex":0.000031080726,"about_ca_system_score_gemma":0.00013817492,"threshold_uncertainty_score":0.441902},"labels":[],"label_agreement":null},{"id":"W4400738267","doi":"10.1093/nargab/lqae084","title":"<b> s </b>CIRCLE—An interactive visual exploration tool for single cell RNA-Seq data","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Bayerisches Staatsministerium für Wissenschaft und Kunst","keywords":"Metadata; Visualization; Computer science; Data visualization; Focus (optics); RNA-Seq; Software; Interactive visualization; Dimensionality reduction; Data mining; Gene; Artificial intelligence; World Wide Web; Transcriptome; Gene expression; Biology; Programming language","score_opus":0.03484221898688085,"score_gpt":0.2773704812826971,"score_spread":0.24252826229581625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400738267","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8242715,0.0008951989,0.17176588,0.00013426537,0.00081896374,0.0005556175,0.0006206239,0.000052871434,0.0008850771],"genre_scores_gemma":[0.975026,0.0006501449,0.020131776,0.00032166843,0.0005121899,0.00001640093,0.0031244329,0.000043603828,0.00017374611],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990881,0.000014123757,0.00032769568,0.00028048968,0.00008309377,0.00020647411],"domain_scores_gemma":[0.9994286,0.00002485257,0.00006996319,0.00033481896,0.00006685102,0.00007491617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022477686,0.00016528866,0.00013724358,0.000056158926,0.00010941359,0.00027883638,0.00022614759,0.00015478679,0.000003591973],"category_scores_gemma":[0.000026159032,0.00016134689,0.000055225955,0.0000549259,0.000046840083,0.00008498605,0.00013000226,0.0000921676,0.00000952068],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017216249,0.00015327225,0.000021884212,0.000301914,0.000061078936,0.0000015960977,0.0011420564,0.000057567628,0.8472745,0.000064662796,0.0012653278,0.14948398],"study_design_scores_gemma":[0.001156982,0.0018596194,0.000021755635,0.00006239024,0.00012328396,0.000032436055,0.0015717644,0.40957898,0.44423655,0.00032142733,0.1403437,0.00069111056],"about_ca_topic_score_codex":0.000009191744,"about_ca_topic_score_gemma":0.00002213885,"teacher_disagreement_score":0.40952143,"about_ca_system_score_codex":0.000026626438,"about_ca_system_score_gemma":0.00009395327,"threshold_uncertainty_score":0.6579535},"labels":[],"label_agreement":null},{"id":"W4401385491","doi":"10.1093/nargab/lqae098","title":"Evaluating cell type deconvolution in FFPE breast tissue: application to benign breast disease","year":2024,"lang":"en","type":"review","venue":"NAR Genomics and Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute; National Institutes of Health; Mayo Clinic","keywords":"Deconvolution; Transcriptome; Computational biology; Cell type; RNA; Computer science; Cell; Pattern recognition (psychology); Artificial intelligence; Biology; Gene expression; Gene; Algorithm; Genetics","score_opus":0.030019536453562142,"score_gpt":0.3274310347500039,"score_spread":0.29741149829644176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401385491","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050948854,0.9904845,0.0017443298,0.00004162067,0.00035650854,0.0012942232,0.00072664884,0.000023284214,0.00023400995],"genre_scores_gemma":[0.0021151076,0.9917395,0.0036028328,0.00010055003,0.00033516815,0.00006158047,0.0017440105,0.000069415386,0.00023180053],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99841464,0.000038743205,0.0007103063,0.0003900776,0.00014477207,0.00030148847],"domain_scores_gemma":[0.99910885,0.000012167084,0.00018738095,0.00038616388,0.00008424475,0.000221196],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000332834,0.00038877077,0.000524454,0.00017449343,0.00007791628,0.00011399029,0.00023870659,0.00034660386,0.000004708066],"category_scores_gemma":[0.000015629208,0.00034192204,0.00014012965,0.00025951306,0.00003776542,0.000008721546,0.00016202826,0.00022141986,0.00010669944],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045086483,0.000056319474,0.000017263037,0.007694665,0.00004197945,0.0000020267298,0.00013425369,0.00007965664,0.0011745394,0.000023573868,0.00033459434,0.990396],"study_design_scores_gemma":[0.0003869186,0.0002764431,0.00003897206,0.001634841,0.0006910455,0.0001245922,0.000063187494,0.014490576,0.00006993916,0.00004791445,0.98130745,0.00086813065],"about_ca_topic_score_codex":0.000022305818,"about_ca_topic_score_gemma":0.000031828422,"teacher_disagreement_score":0.98952794,"about_ca_system_score_codex":0.00011008265,"about_ca_system_score_gemma":0.0003560603,"threshold_uncertainty_score":0.99990326},"labels":[],"label_agreement":null},{"id":"W4402853960","doi":"10.1093/nargab/lqae122","title":"eQTL-Detect: nextflow-based pipeline for eQTL detection in modular format with sharable and parallelizable scripts","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genetic Mapping and Diversity in Plants and Animals","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Agriculture and Agri-Food Canada","funders":"European Commission","keywords":"Pipeline (software); Expression quantitative trait loci; Computer science; Workflow; Modular design; Scripting language; Parallelizable manifold; Orchestration; Data mining; Database; Programming language; Biology; Gene","score_opus":0.00964774568446424,"score_gpt":0.20494182402514696,"score_spread":0.19529407834068271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402853960","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9008753,0.0033294803,0.09429408,0.00015819515,0.00013022816,0.00046067924,0.00018355326,0.000027369086,0.0005411451],"genre_scores_gemma":[0.982522,0.0014400989,0.015143452,0.000311511,0.000078566096,0.00001614464,0.00014582742,0.00001481731,0.00032755802],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929667,0.000006889408,0.00021286703,0.00018056252,0.00007048504,0.00023251111],"domain_scores_gemma":[0.9997122,0.000012645878,0.000044293683,0.000114911556,0.000041975753,0.00007393675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020462999,0.00015131953,0.00014393199,0.0000861631,0.00012638823,0.00015264133,0.00006822429,0.00012616768,0.0000031126],"category_scores_gemma":[0.000013382715,0.0001223544,0.00003641909,0.00006856238,0.00004227983,0.000015245547,0.000048956335,0.00006911947,0.0000025358838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029266933,0.00027831382,0.0019505229,0.0076136803,0.0004324548,0.000043701562,0.0030348962,0.023038832,0.5293873,0.00069313124,0.0151996175,0.41540083],"study_design_scores_gemma":[0.0013856988,0.0006616242,0.00013830929,0.000109332716,0.000042814474,0.000049486018,0.00048331567,0.8234244,0.0229672,0.00017484989,0.15022881,0.00033417263],"about_ca_topic_score_codex":0.000023786199,"about_ca_topic_score_gemma":0.000057254718,"teacher_disagreement_score":0.80038553,"about_ca_system_score_codex":0.000012751954,"about_ca_system_score_gemma":0.000053118158,"threshold_uncertainty_score":0.49894676},"labels":[],"label_agreement":null},{"id":"W4404333429","doi":"10.1093/nargab/lqae145","title":"Refining SARS-CoV-2 intra-host variation by leveraging large-scale sequencing data","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Montreal Heart Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données; Canada Foundation for Innovation","keywords":"Workflow; Computational biology; Host (biology); DNA sequencing; Computer science; Cluster analysis; Visualization; Biology; Data mining; Genetics; Artificial intelligence; DNA; Database","score_opus":0.06431370519734829,"score_gpt":0.3304385491763903,"score_spread":0.266124843979042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404333429","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96337336,0.0024254848,0.026944771,0.00079249835,0.00037687272,0.00032226066,0.0004453265,0.0001759984,0.0051434245],"genre_scores_gemma":[0.8372538,0.00064486545,0.07744149,0.082034394,0.0010680996,0.000027443582,0.0011707131,0.00017449449,0.00018468077],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852765,0.000016609496,0.00047017756,0.0002766224,0.00030862453,0.00040029065],"domain_scores_gemma":[0.99922043,0.00008575957,0.000073830386,0.00051057246,0.00006815726,0.00004127293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009824208,0.00018274458,0.00025061035,0.00019026342,0.00017323293,0.00032211945,0.00022784482,0.00014481456,0.000004410714],"category_scores_gemma":[0.00008597637,0.00015796794,0.000044331315,0.00028539074,0.0000474885,0.0004451659,0.00031894867,0.00039230648,0.000084135485],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011250153,0.000070022565,0.0017741595,0.0019063912,0.0002626949,0.00007404178,0.019000784,0.0000019162094,0.8972982,0.0004341234,0.015165137,0.0639],"study_design_scores_gemma":[0.0006400109,0.00009666858,0.00007720057,0.00019817884,0.00007656134,0.00012466828,0.0013653284,0.5161564,0.039719436,0.00006422629,0.44126177,0.00021957417],"about_ca_topic_score_codex":0.00013023824,"about_ca_topic_score_gemma":0.00003396641,"teacher_disagreement_score":0.8575788,"about_ca_system_score_codex":0.00026335742,"about_ca_system_score_gemma":0.0004226823,"threshold_uncertainty_score":0.6441746},"labels":[],"label_agreement":null},{"id":"W4405282922","doi":"10.1093/nargab/lqae161","title":"Water-mediated ribonucleotide–amino acid pairs and higher-order structures at the RNA–protein interface: analysis of the crystal structure database and a topological classification","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interface (matter); Topology (electrical circuits); Amino acid; Database; Order (exchange); Ribonucleotide; Computer science; Crystal structure; RNA; Computational biology; Data mining; Biology; Chemistry; Crystallography; Mathematics; Biochemistry; Nucleotide; Combinatorics; Operating system; Gene","score_opus":0.0112042506949473,"score_gpt":0.2291308502527272,"score_spread":0.2179265995577799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405282922","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99547726,0.0019662448,0.001013487,0.00063492503,0.000083525534,0.0002673589,0.00047401685,0.000007797324,0.000075398544],"genre_scores_gemma":[0.99758416,0.00055356696,0.0013501707,0.00014680829,0.00003701705,0.0000061226287,0.00019506118,0.000009813472,0.000117297845],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999204,0.000053059368,0.00027999532,0.00019571681,0.00011086467,0.00015641275],"domain_scores_gemma":[0.99949926,0.000020954927,0.00009138692,0.0002976422,0.00003839588,0.000052357715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021433516,0.00016146831,0.00017265572,0.000054599932,0.0001853148,0.00009121328,0.00014682394,0.00016962264,0.000043192882],"category_scores_gemma":[0.00003543725,0.000077282624,0.000059241724,0.00012954252,0.0002915308,0.0000139704525,0.0003497309,0.00010778462,5.850803e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041565665,0.000004520067,0.00013200469,0.00008281651,0.00020706236,4.2610935e-7,0.00035149526,0.000011298651,0.99328023,0.0007557891,0.00006920066,0.0050635897],"study_design_scores_gemma":[0.00029085047,0.00018763656,0.0042396183,0.000028493076,0.0004454454,0.000027336171,0.00075437,0.012448665,0.95675105,0.0006737652,0.023877412,0.00027535507],"about_ca_topic_score_codex":0.000010807989,"about_ca_topic_score_gemma":0.000037790996,"teacher_disagreement_score":0.036529176,"about_ca_system_score_codex":0.000013933488,"about_ca_system_score_gemma":0.000023733344,"threshold_uncertainty_score":0.3151494},"labels":[],"label_agreement":null},{"id":"W4405620286","doi":"10.1093/nargab/lqae176","title":"SARS-CoV-2 Illumina GeNome Assembly Line (SIGNAL), a Snakemate workflow for rapid and bulk analysis of Illumina sequencing of SARS-CoV-2 genomes","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; Canada Research Chairs; Vector Institute; University of Saskatchewan; University of Manitoba; Public Health Agency of Canada; University Health Network; Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto; Dalhousie University; Perimeter Institute; McMaster University","funders":"Genome Canada; Canadian Institutes of Health Research; Michael G. DeGroote Institute for Infectious Disease Research, McMaster University; University of Toronto; Natural Sciences and Engineering Research Council of Canada; McMaster University","keywords":"Workflow; Illumina dye sequencing; Whole genome sequencing; DNA sequencing; Genome; Personal genomics; Computer science; Computational biology; Biology; Genetics; Database; DNA; Gene","score_opus":0.057473568328843525,"score_gpt":0.3294186607319,"score_spread":0.2719450924030565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405620286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9833161,0.009186061,0.0051337285,0.00018092705,0.00009193106,0.0009953988,0.00041145392,0.000057758654,0.0006266124],"genre_scores_gemma":[0.9727031,0.0017299822,0.02140032,0.0037126925,0.00017133646,0.000046599598,0.00012041672,0.00008136696,0.00003419271],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9971041,0.00003267539,0.0013630007,0.00041200727,0.0004814912,0.00060671545],"domain_scores_gemma":[0.9983352,0.00031122967,0.0003688562,0.0005211589,0.0003945479,0.00006900774],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001254238,0.00042394514,0.0012896764,0.0013851591,0.0001351807,0.00013979191,0.00025211426,0.0002937357,0.0000039058064],"category_scores_gemma":[0.00009795978,0.00035369748,0.00045224736,0.0013546966,0.0003877228,0.00023641883,0.00021306069,0.00029413457,0.0000076076444],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003425542,0.000082802195,0.0003618274,0.0044141426,0.002338421,0.000032979948,0.006105578,0.000016116806,0.94279,0.00022555965,0.000113489135,0.04317653],"study_design_scores_gemma":[0.0013679898,0.0010650386,0.00019253136,0.00031991475,0.0023134698,0.00009250381,0.0014634313,0.3454148,0.61337954,0.00018775814,0.033741705,0.00046133978],"about_ca_topic_score_codex":0.000093724644,"about_ca_topic_score_gemma":0.000058127727,"teacher_disagreement_score":0.34539866,"about_ca_system_score_codex":0.00023239825,"about_ca_system_score_gemma":0.00054388493,"threshold_uncertainty_score":0.9998915},"labels":[],"label_agreement":null},{"id":"W4408163552","doi":"10.1093/nargab/lqaf011","title":"iModEst: disentangling -omic impacts on gene expression variation across genes and tissues","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; SickKids Foundation; Vector Institute; University of Toronto","funders":"","keywords":"Gene; Biology; Variation (astronomy); Genetics; Gene expression; Computational biology; Genetic variation; Evolutionary biology","score_opus":0.00522141975189719,"score_gpt":0.24582336438267025,"score_spread":0.24060194463077306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408163552","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9934864,0.0015127785,0.004092642,0.00011789609,0.00015496869,0.00020652388,0.000102391,0.000012584975,0.00031382538],"genre_scores_gemma":[0.9788591,0.0054009594,0.014874078,0.00040123376,0.00010213361,0.0000074420554,0.00018990377,0.000018500674,0.00014663566],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991303,0.0000143251245,0.00031863427,0.00021197258,0.000076369186,0.00024840565],"domain_scores_gemma":[0.999458,0.000015300362,0.00013384565,0.00026112158,0.000045945562,0.00008574945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018299012,0.00019542094,0.00016896185,0.000052570394,0.00023949024,0.00014035095,0.000116205716,0.00017970007,0.0000013817961],"category_scores_gemma":[0.00002461716,0.00017550161,0.000042831445,0.000055231605,0.000058945563,0.000010663257,0.00022926352,0.0000772094,0.0000027390784],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001407961,0.00006607536,0.004058395,0.0002382506,0.00009092843,0.0000019668778,0.0015236489,0.000813022,0.9618694,0.000454392,0.00035074138,0.030392393],"study_design_scores_gemma":[0.0035766677,0.0008069553,0.015559247,0.00024911657,0.00012092969,0.00007628588,0.002454267,0.21289743,0.74188566,0.0016402856,0.019477906,0.0012552576],"about_ca_topic_score_codex":0.000008142263,"about_ca_topic_score_gemma":0.000013204313,"teacher_disagreement_score":0.21998374,"about_ca_system_score_codex":0.0000341158,"about_ca_system_score_gemma":0.000053444917,"threshold_uncertainty_score":0.71567476},"labels":[],"label_agreement":null},{"id":"W4408249210","doi":"10.1093/nargab/lqaf016","title":"BacTermFinder: a comprehensive and general bacterial terminator finder using a CNN ensemble","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Terminator (solar); False positive paradox; Computer science; Bacterial transcription; Bacterial genome size; Convolutional neural network; Artificial intelligence; Computational biology; Bacterial protein; Machine learning; Biology; Data mining; RNA; Genome; Gene; Genetics; RNA polymerase; Physics","score_opus":0.012491023769565504,"score_gpt":0.2440232268859487,"score_spread":0.2315322031163832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408249210","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99692565,0.0012243675,0.0005960703,0.000072526054,0.00024900804,0.00022203874,0.00005486259,0.0000035415892,0.00065195706],"genre_scores_gemma":[0.9747844,0.0019127002,0.02181187,0.00088220945,0.00018497814,0.000007761992,0.000049784492,0.000017723974,0.00034861398],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991635,0.000017217128,0.00030330825,0.00021102351,0.000055188604,0.00024973004],"domain_scores_gemma":[0.999528,0.000014113013,0.00009865446,0.00020879228,0.000075891,0.00007454213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007776398,0.0002096111,0.0002285163,0.00006878284,0.00020371677,0.00009234568,0.00009778196,0.00016323278,0.0000030478247],"category_scores_gemma":[0.000012516307,0.00019534603,0.000054084343,0.00005238589,0.00012271153,0.0000028557577,0.00033772326,0.00007064141,0.000001332739],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010486401,0.000029436835,0.002809378,0.00015242925,0.00020693254,0.0000019791182,0.00047286472,0.0000372805,0.9746245,0.0002815092,0.0007525706,0.020526236],"study_design_scores_gemma":[0.0087364465,0.0012103172,0.06364343,0.00016610126,0.0005285835,0.00038178853,0.0031289742,0.057797156,0.22615333,0.001810291,0.63389754,0.0025460287],"about_ca_topic_score_codex":0.000015446569,"about_ca_topic_score_gemma":0.000009802726,"teacher_disagreement_score":0.7484712,"about_ca_system_score_codex":0.000018426626,"about_ca_system_score_gemma":0.00010637812,"threshold_uncertainty_score":0.796598},"labels":[],"label_agreement":null},{"id":"W4409905545","doi":"10.1093/nargab/lqaf048","title":"Discovering governing equations of biological systems through representation learning and sparse model discovery","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Computer science; Identification (biology); Representation (politics); Gene regulatory network; Artificial intelligence; Machine learning; Dynamical systems theory; Biological network; Complex system; Biological data; Nonlinear system; PageRank; Systems biology; Key (lock); Theoretical computer science; Deep learning; Data mining; Computational biology; Gene; Biology; Bioinformatics; Gene expression","score_opus":0.02124096170560071,"score_gpt":0.26378734613985466,"score_spread":0.24254638443425394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409905545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7858101,0.0014712702,0.21196117,0.000021902726,0.000038171467,0.00010060963,0.000018228448,0.0000047751782,0.00057375594],"genre_scores_gemma":[0.99075776,0.0027791387,0.0059416234,0.000024671808,0.00003181415,0.0000049864143,0.00011171311,0.0000059027757,0.0003423638],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931586,0.000024590341,0.0003226799,0.00014507554,0.00006829643,0.00012349848],"domain_scores_gemma":[0.9995976,0.000026003594,0.00017235501,0.00013944371,0.000039184804,0.000025382462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015484319,0.000106146406,0.00017397021,0.00003909052,0.00011506806,0.0000658988,0.00006129714,0.00010432507,3.9885234e-7],"category_scores_gemma":[0.00006327251,0.000092672315,0.000051083825,0.00009479669,0.00008016852,0.000020627856,0.00017915375,0.00006810781,3.8013664e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101517515,0.0000504393,0.038678605,0.00036690768,0.00044619653,6.362888e-7,0.001228286,0.7352794,0.21004441,0.0077687968,0.0002232499,0.0058115725],"study_design_scores_gemma":[0.00032433023,0.00007481765,0.00062599976,0.000040446186,0.000072115676,0.0000038431144,0.002067787,0.98866695,0.005973592,0.00019448929,0.0017964449,0.0001592015],"about_ca_topic_score_codex":0.00001978892,"about_ca_topic_score_gemma":0.000006792376,"teacher_disagreement_score":0.25338754,"about_ca_system_score_codex":0.000016422584,"about_ca_system_score_gemma":0.000051409348,"threshold_uncertainty_score":0.37790674},"labels":[],"label_agreement":null},{"id":"W4411754998","doi":"10.1093/nargab/lqaf087","title":"MOLGENIS VIP: an end-to-end DNA variant interpretation pipeline for research and diagnostics configurable to support rapid implementation of new methods","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Scalability; Pipeline (software); Computer science; Data science; DNA sequencing; Genome; Variety (cybernetics); Software; Protocol (science); Computational biology; Data mining; Biology; Medicine; Artificial intelligence; Genetics; Database; Gene","score_opus":0.04216451958384585,"score_gpt":0.39957096283162724,"score_spread":0.35740644324778137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411754998","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7813899,0.0008893271,0.21464682,0.00062388816,0.00024655156,0.0012382152,0.00044920688,0.0000036803688,0.00051239715],"genre_scores_gemma":[0.7248366,0.0026489052,0.27079356,0.00085776934,0.0001158703,0.000064154985,0.00028723208,0.000021342055,0.0003745793],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988933,0.000038206963,0.0004906295,0.00022302989,0.000091359034,0.00026347948],"domain_scores_gemma":[0.99911153,0.00010736418,0.00010038901,0.00023573443,0.0002883198,0.0001566723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009796494,0.0001465238,0.00022648151,0.00016417887,0.00014242095,0.00006401438,0.00014188793,0.000098438075,0.000009881399],"category_scores_gemma":[0.0001482685,0.00014100337,0.00003733937,0.0001351715,0.00006114475,0.000004443714,0.00020738164,0.000054802164,9.726253e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023467082,0.00004189177,0.00028006296,0.00015582266,0.00013158198,2.9362695e-7,0.0035628416,0.00006749311,0.45440942,0.0010304771,0.0052464856,0.534839],"study_design_scores_gemma":[0.0024118444,0.0056290566,0.0035777749,0.00004613729,0.00017240808,0.000015278905,0.009866436,0.011094699,0.7267193,0.0034079575,0.23651424,0.00054485217],"about_ca_topic_score_codex":0.00008162114,"about_ca_topic_score_gemma":0.00010363499,"teacher_disagreement_score":0.5342941,"about_ca_system_score_codex":0.000022084907,"about_ca_system_score_gemma":0.00022589,"threshold_uncertainty_score":0.57499504},"labels":[],"label_agreement":null},{"id":"W4412492594","doi":"10.1093/nargab/lqaf099","title":"Modeling RNA duplex dynamics with Gibbs sampling enhances base-pair prediction accuracy and reveals structural activity profiles","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Research in Immunology and Cancer","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Google","keywords":"RNA; Base pair; Duplex (building); Nucleic acid secondary structure; Nucleic acid structure; Biological system; Statistical physics; Algorithm; Computational biology; Computer science; Physics; Biology; Genetics; DNA","score_opus":0.011571702968631912,"score_gpt":0.24118674235263773,"score_spread":0.22961503938400582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412492594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89075494,0.00038938734,0.10805161,0.00011945233,0.0000762624,0.00032711262,0.000102127866,0.00001741139,0.00016167527],"genre_scores_gemma":[0.9563514,0.00077983725,0.04248518,0.000101632264,0.000063980726,0.000016821179,0.00009360646,0.000012416594,0.00009509536],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992129,0.000023043915,0.0002586404,0.00020892818,0.00009177162,0.00020468884],"domain_scores_gemma":[0.99951416,0.000026183996,0.00012081679,0.00020774594,0.00006912417,0.00006196529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023220057,0.00018909018,0.0001831682,0.000059569935,0.000246774,0.00010817969,0.00010250752,0.00016367121,0.0000020201328],"category_scores_gemma":[0.00005562122,0.00015073863,0.000034655317,0.000064980515,0.000058860533,0.00002813679,0.00011152944,0.000095420204,4.574124e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033715196,0.000019540856,0.0011039914,0.00049353525,0.00015347356,6.792883e-7,0.0003077891,0.0026243622,0.86425465,0.00075313874,0.00003897495,0.12991272],"study_design_scores_gemma":[0.0005152009,0.0002700121,0.00045541083,0.00011717495,0.0000594348,0.000021758067,0.0006501004,0.7684335,0.22816335,0.00064408564,0.00036888337,0.00030105194],"about_ca_topic_score_codex":0.000017862083,"about_ca_topic_score_gemma":0.000022618382,"teacher_disagreement_score":0.7658092,"about_ca_system_score_codex":0.000027600168,"about_ca_system_score_gemma":0.00008678288,"threshold_uncertainty_score":0.6146943},"labels":[],"label_agreement":null},{"id":"W4413342468","doi":"10.1093/nargab/lqaf108","title":"Explicit Scale Simulation for analysis of RNA-sequencing count data with ALDEx2","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Computer science; Normalization (sociology); Scale (ratio); Sample size determination; Data mining; Sample (material); Cutoff; False positive paradox; Statistics; Machine learning; Mathematics","score_opus":0.026348781228629416,"score_gpt":0.27803068670699643,"score_spread":0.251681905478367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413342468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.928109,0.000693471,0.06983703,0.00004345024,0.00004109845,0.00030274747,0.00045836816,0.0000020489706,0.00051278924],"genre_scores_gemma":[0.9703379,0.0005888418,0.028413711,0.00017983795,0.000028625249,0.000009487878,0.00036924545,0.0000073921356,0.00006495077],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930286,0.0000057876223,0.00031860982,0.0001743694,0.00006208875,0.00013625102],"domain_scores_gemma":[0.99921054,0.00003554372,0.00015425011,0.0004374147,0.00013254593,0.000029720402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020742007,0.00011672413,0.00022646124,0.00010727158,0.00009446238,0.000025871856,0.0001860705,0.00007604151,8.8536217e-7],"category_scores_gemma":[0.000025156438,0.000096852906,0.000053207288,0.00017524147,0.00005091845,0.0000027152553,0.00018932157,0.000027312446,1.5729664e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001538369,0.00018904464,0.045548093,0.0012433651,0.012221189,7.4392403e-7,0.003879792,0.2710411,0.5727265,0.0020561926,0.0017170986,0.08783855],"study_design_scores_gemma":[0.001495653,0.00033877502,0.004150396,0.000026776506,0.0014515598,0.0000015626471,0.0016674395,0.9449819,0.01930944,0.00011893319,0.02613562,0.00032197317],"about_ca_topic_score_codex":0.00001788556,"about_ca_topic_score_gemma":0.000102948805,"teacher_disagreement_score":0.6739408,"about_ca_system_score_codex":0.000017411588,"about_ca_system_score_gemma":0.00009754094,"threshold_uncertainty_score":0.3949547},"labels":[],"label_agreement":null},{"id":"W4414887972","doi":"10.1093/nargab/lqaf132","title":"VIRUS-MVP: a framework for comprehensive surveillance of viral mutations and their functional impacts","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Viral Infections and Outbreaks Research","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada; University of British Columbia; University of Calgary; Simon Fraser University","funders":"Canadian Institutes of Health Research; Simon Fraser University; Michael Smith Health Research BC; Genome Canada","keywords":"Genomics; Functional genomics; Annotation; Resource (disambiguation); Mutation; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Genome; Modular design","score_opus":0.032538701256875954,"score_gpt":0.3202955777649885,"score_spread":0.28775687650811255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414887972","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9314887,0.0007466684,0.065456346,0.0006408175,0.00010531639,0.0005043299,0.00027721442,0.0000198691,0.0007607546],"genre_scores_gemma":[0.9827673,0.00077787915,0.015796712,0.00042903042,0.000045702567,0.000012298554,0.00007724118,0.0000062144973,0.00008763287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994869,0.0000075828934,0.00024447317,0.00007024897,0.00005773231,0.00013301152],"domain_scores_gemma":[0.9993763,0.0002072442,0.000065983455,0.000093908064,0.00019296838,0.00006360505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011277794,0.00008771023,0.00020145554,0.00013265443,0.00013360268,0.000030565432,0.000023261768,0.00008440701,0.0000066093457],"category_scores_gemma":[0.000071136,0.00006417348,0.000053596654,0.00013105487,0.000117620824,0.000055062003,0.000043853463,0.00011448279,0.0000013755233],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0051025557,0.0012305246,0.062024128,0.012471322,0.003280894,0.0000064033693,0.014530665,0.00069764757,0.178887,0.17492318,0.021524338,0.52532136],"study_design_scores_gemma":[0.010286473,0.0034594575,0.31074008,0.00076785404,0.00025546015,0.00022830557,0.011013901,0.50712603,0.028816653,0.03831022,0.08817405,0.0008214896],"about_ca_topic_score_codex":0.000022129081,"about_ca_topic_score_gemma":0.0000122716765,"teacher_disagreement_score":0.52449983,"about_ca_system_score_codex":0.000029900171,"about_ca_system_score_gemma":0.00011759759,"threshold_uncertainty_score":0.26169184},"labels":[],"label_agreement":null},{"id":"W4416380425","doi":"10.1093/nargab/lqaf148","title":"Genomic islands in <i>Pseudomonas</i> encode modular hotspots of defence and anti-defence systems","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Vibrio bacteria research studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Medical Research Council; Wellcome Trust; UK Research and Innovation; European Molecular Biology Organization","keywords":"Pathogenicity island; Virulence; Lytic cycle; ENCODE; Genomic island; Arms race; Genome","score_opus":0.0066160139177305925,"score_gpt":0.2331474672512933,"score_spread":0.2265314533335627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416380425","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9940524,0.00379029,0.00085780665,0.000055149707,0.00008079394,0.0002800321,0.000077380195,0.0000047315175,0.0008014315],"genre_scores_gemma":[0.98784006,0.009755166,0.0021614465,0.0000870123,0.000024490644,0.0000112424505,0.000022895265,0.000008119974,0.000089542045],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990344,0.000026090924,0.00040561866,0.0001887292,0.00009374545,0.00025141315],"domain_scores_gemma":[0.99948627,0.000024723193,0.00011397724,0.00025022458,0.00007097856,0.00005385332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003058658,0.00015790896,0.0002736124,0.0001259372,0.000072824485,0.00004941166,0.00016909787,0.00012860105,5.787464e-7],"category_scores_gemma":[0.00006274013,0.00014197832,0.000034902685,0.00012582549,0.00017563546,0.000010754224,0.00036077594,0.00008884631,9.941505e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009112137,0.00004318755,0.07279787,0.0007483374,0.000101478065,0.000003416254,0.0008459926,0.00033464227,0.9222896,0.00021619811,0.00029839628,0.002229725],"study_design_scores_gemma":[0.010053861,0.0016257785,0.5097852,0.0011149858,0.00021388801,0.00022175207,0.010980378,0.14478046,0.27741152,0.0007519149,0.04057884,0.0024814713],"about_ca_topic_score_codex":0.000033293934,"about_ca_topic_score_gemma":0.00002251874,"teacher_disagreement_score":0.6448781,"about_ca_system_score_codex":0.0000262177,"about_ca_system_score_gemma":0.00011890063,"threshold_uncertainty_score":0.5789708},"labels":[],"label_agreement":null},{"id":"W4417268800","doi":"10.1093/nargab/lqaf170","title":"<tt>SAFARI</tt> : pangenome alignment of ancient DNA using purine/pyrimidine encodings","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"National Human Genome Research Institute; Novo Nordisk Fonden; Novo Nordisk","keywords":"Spurious relationship; Ancient DNA; Extant taxon; Genome; DNA; Divergence (linguistics)","score_opus":0.012432450812789271,"score_gpt":0.23299770210798124,"score_spread":0.22056525129519197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417268800","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923861,0.0033521887,0.0012408015,0.00010578307,0.00022193999,0.00026570933,0.00008883524,0.000003865971,0.002334795],"genre_scores_gemma":[0.9857775,0.0027537423,0.010643854,0.0005348115,0.00007473002,0.0000058726723,0.000037877744,0.000014849048,0.00015673955],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99888885,0.0000119750575,0.00050264876,0.0002063572,0.00010762292,0.0002825397],"domain_scores_gemma":[0.9993081,0.0000112111575,0.0001961939,0.00030736922,0.000102746,0.000074360476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023354987,0.00021108311,0.00027235592,0.00009881167,0.00015225826,0.000034754226,0.00019216113,0.00012868288,0.00000516249],"category_scores_gemma":[0.000021585987,0.00019437858,0.00009590864,0.00011407134,0.00012472026,0.000002301011,0.0004101328,0.000056664627,0.0000018362703],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048281654,0.000059494938,0.0018638164,0.00018815283,0.00019512512,7.852864e-7,0.0005319791,0.00027175658,0.98919,0.0006469906,0.00051500165,0.006488635],"study_design_scores_gemma":[0.002209206,0.0007897801,0.00979301,0.00010420793,0.00029871313,0.00005350216,0.0027919537,0.011173359,0.69778425,0.000605974,0.27344403,0.00095203664],"about_ca_topic_score_codex":0.000018530713,"about_ca_topic_score_gemma":0.000007917197,"teacher_disagreement_score":0.29140577,"about_ca_system_score_codex":0.000043107517,"about_ca_system_score_gemma":0.00010654329,"threshold_uncertainty_score":0.79265285},"labels":[],"label_agreement":null},{"id":"W4417268808","doi":"10.1093/nargab/lqaf175","title":"Genome sequence assembly and annotation of <i>MATA</i> and <i>MATB</i> strains of <i>Yarrowia lipolytica</i>","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Cancer Institute; Agricultural Research Service; University of Alberta; U.S. Department of Agriculture","keywords":"Genome; Genome project; Whole genome sequencing; Gene; DNA sequencing; Gene Annotation; Sequence assembly; Reference genome; Yeast","score_opus":0.006117237744006283,"score_gpt":0.22040193155462012,"score_spread":0.21428469381061385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417268808","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99533343,0.00201341,0.0019195669,0.000087199915,0.000092539376,0.00014610232,0.000106935695,0.000005909272,0.0002948919],"genre_scores_gemma":[0.98664284,0.004628846,0.00840372,0.00010323721,0.000039378654,0.0000019273725,0.000061709725,0.0000070859674,0.000111244066],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993654,0.00000911228,0.00032727586,0.00013137265,0.000051670188,0.00011519794],"domain_scores_gemma":[0.99959457,0.000004712881,0.00012779677,0.00015835185,0.000073567884,0.000040989915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019431558,0.00011620386,0.00018065888,0.00006592111,0.000041377345,0.000018890158,0.00006201605,0.000106617634,3.7165077e-7],"category_scores_gemma":[0.00003288389,0.00010786811,0.00002505556,0.00009092167,0.00012928376,0.000010762546,0.000081374455,0.00005325363,1.623178e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001765149,0.000013470973,0.0002297789,0.00037256716,0.000033096134,9.367341e-8,0.0001771727,0.00003326299,0.99158067,0.00035144784,0.00006335445,0.007127451],"study_design_scores_gemma":[0.0011155634,0.0004000465,0.0064967703,0.00011246101,0.00012892464,0.00006932044,0.00063783204,0.00345473,0.95823485,0.00016212765,0.028798312,0.0003890766],"about_ca_topic_score_codex":0.000010905498,"about_ca_topic_score_gemma":0.0000038143553,"teacher_disagreement_score":0.03334582,"about_ca_system_score_codex":0.0000050665267,"about_ca_system_score_gemma":0.00004755817,"threshold_uncertainty_score":0.43987337},"labels":[],"label_agreement":null},{"id":"W7117139568","doi":"10.1093/nargab/lqaf189","title":"Life at the extremes: maximally divergent microbes with similar genomic signatures linked to extreme environments","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Western University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Taxonomic rank; Genome; Extreme environment; Metagenomics; Genomics; Biological classification; Adaptation (eye); Phylogenomics; Trait","score_opus":0.01003646980641636,"score_gpt":0.19776717148554032,"score_spread":0.18773070167912395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117139568","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897038,0.0057277405,0.0014365726,0.0012354647,0.00014872447,0.0005771961,0.00010214031,0.0000046588075,0.0010637394],"genre_scores_gemma":[0.97090447,0.008414564,0.01017148,0.0075924103,0.00014560654,0.00004714476,0.000100643374,0.00003865389,0.0025850327],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99885905,0.000022372567,0.00035916653,0.0002970092,0.0001197503,0.00034265488],"domain_scores_gemma":[0.99920714,0.000021415075,0.00011929647,0.00044761278,0.000038550297,0.00016598785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017123292,0.00029456854,0.0002243146,0.00006887913,0.00039633867,0.000070323484,0.0003186696,0.00014385457,0.000010662279],"category_scores_gemma":[0.00003313809,0.00020018463,0.000080197584,0.0000881254,0.00015353046,0.000002050539,0.0007745752,0.00010086425,0.000018797578],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041669162,0.00011446056,0.00565197,0.000092235554,0.0006623861,0.0000026649675,0.0012304074,0.0017786463,0.96618885,0.00012108645,0.014954295,0.008786294],"study_design_scores_gemma":[0.001871366,0.00056392385,0.025365066,0.000035978144,0.00018120161,0.000014500421,0.0011873532,0.0010628165,0.024892155,0.00008615603,0.9440604,0.0006790949],"about_ca_topic_score_codex":0.000012455448,"about_ca_topic_score_gemma":0.000094837436,"teacher_disagreement_score":0.9412967,"about_ca_system_score_codex":0.00005450862,"about_ca_system_score_gemma":0.00011678973,"threshold_uncertainty_score":0.81632924},"labels":[],"label_agreement":null},{"id":"W7117923635","doi":"10.1093/nargab/lqaf208","title":"G-quadruplex structures as modulators of alternative promoter usage","year":2025,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"DNA and Nucleic Acid Chemistry","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Vermont Agency of Natural Resources; Institut National Du Cancer; Agence Nationale de la Recherche; CNIB","keywords":"Promoter; Gene isoform; Gene; Transcription (linguistics); Transcription factor; Regulation of gene expression; DNA; Gene expression","score_opus":0.004621207016402525,"score_gpt":0.23251254045158906,"score_spread":0.22789133343518653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117923635","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99087876,0.00026769337,0.00090554316,0.00005665033,0.000091311485,0.00011791764,0.000039815794,0.000005476766,0.0076368465],"genre_scores_gemma":[0.9935115,0.00032569695,0.005117365,0.00027000447,0.00005209451,0.000002550084,0.000056599754,0.000008415514,0.00065577094],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993815,0.0000066765047,0.0002685959,0.00012660991,0.00007606904,0.00014059355],"domain_scores_gemma":[0.9995459,0.000006014691,0.00011688157,0.00022684468,0.000055812678,0.00004856349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000080772115,0.00013120729,0.00014460985,0.000041289437,0.000051791503,0.000022900183,0.0001593809,0.00013715583,0.000011830329],"category_scores_gemma":[0.000029063784,0.00011261139,0.000056297937,0.000054793432,0.00010814945,0.000005152066,0.00016435963,0.0000665781,0.0000019752667],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014296289,0.00006425211,0.001902239,0.00044767038,0.0003115769,0.0000020552338,0.0008663678,0.00011374996,0.9538018,0.00234384,0.002157184,0.037846304],"study_design_scores_gemma":[0.00060069124,0.00014307562,0.00064736564,0.00002450165,0.000032117874,0.000014083684,0.00041693472,0.0036337748,0.96677965,0.0020747941,0.025429567,0.00020346738],"about_ca_topic_score_codex":0.000008896021,"about_ca_topic_score_gemma":0.0000014134096,"teacher_disagreement_score":0.03764284,"about_ca_system_score_codex":0.000011471288,"about_ca_system_score_gemma":0.00006632734,"threshold_uncertainty_score":0.45921594},"labels":[],"label_agreement":null}]}