{"id":"W4416285480","doi":"10.1101/2025.11.16.688692","title":"Inferring binding specificities of human transcription factors with the wisdom of crowds","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"","keywords":"Benchmarking; Motif (music); Deep learning; DNA binding site; Transcription factor; Transcription (linguistics)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007939222,0.001012748,0.001295312,0.001702919,0.001038097,0.002720844,0.001916187,0.002323404,0.00222505],"category_scores_gemma":[0.03195804,0.0007727123,0.001441307,0.001811759,0.002081006,0.002735316,0.002258598,0.002464627,0.0009315241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002036549,"about_ca_system_score_gemma":0.002177119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008968257,"about_ca_topic_score_gemma":0.008276974,"domain_scores_codex":[0.9948912,0.002558528,0.0001766889,0.001276017,0.0009045761,0.0001930461],"domain_scores_gemma":[0.9831181,0.01275391,0.0006325568,0.002413599,0.0006795258,0.0004023774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007014375,0.0001667138,0.02346133,0.0005429646,0.0003396261,0.0002147454,0.0007175685,0.772648,0.004262946,0.06641084,0.01752543,0.1130083],"study_design_scores_gemma":[0.00004386312,0.00002459752,0.001598143,0.00004584653,0.00001822801,0.00004166539,0.0001569256,0.8225796,0.001953454,0.1678839,0.005624535,0.00002925812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2857747,0.00237367,0.6842085,0.004584039,0.0002902755,0.0001592695,0.008309276,0.002770827,0.01152951],"genre_scores_gemma":[0.8302711,0.0007033494,0.1583271,0.0008747329,0.0001434757,0.000154901,0.006533025,0.0003837245,0.002608583],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008968257,"threshold_uncertainty_score":0.04198712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0117728492834513,"score_gpt":0.2121731528702013,"score_spread":0.20040030358675,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}