{"id":"W4404281816","doi":"10.1101/2024.11.11.619379","title":"Cross-platform DNA motif discovery and benchmarking to explore binding specificities of poorly studied human transcription factors","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Children's Hospital; University of British Columbia; Occupational Cancer Research Centre","funders":"Canadian Institutes of Health Research; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Motif (music); Benchmarking; Computational biology; Sequence motif; Transcription factor; DNA; DNA binding site; Genetics; Biology; Gene; Business; Promoter; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01022121,0.001161613,0.001152122,0.001995951,0.0005536093,0.0008145498,0.001622762,0.0009490977,0.001326831],"category_scores_gemma":[0.01993641,0.0004176873,0.001232315,0.001968605,0.0006780137,0.0009215012,0.001923131,0.001097157,0.000805505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005888669,"about_ca_system_score_gemma":0.0008575746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001985601,"about_ca_topic_score_gemma":0.002777656,"domain_scores_codex":[0.9946399,0.001829936,0.0005703166,0.001528747,0.001103892,0.0003272043],"domain_scores_gemma":[0.9899281,0.006098079,0.0005073779,0.002010865,0.001170428,0.0002852832],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.006107931,0.001802814,0.09595162,0.005300543,0.001847206,0.0008248126,0.001051137,0.2003483,0.4655961,0.005167067,0.0115356,0.2044669],"study_design_scores_gemma":[0.0003519193,0.002781879,0.04502969,0.0001443174,0.0003696558,0.0007774899,0.0004255889,0.5748132,0.356385,0.00497424,0.01373384,0.000213209],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9036676,0.001499874,0.07907036,0.0001154275,0.00009811855,0.0002498506,0.006384544,0.007259788,0.001654452],"genre_scores_gemma":[0.7961736,0.0004900984,0.1711779,0.0002351307,0.00002543845,0.0006385014,0.02906677,0.00130229,0.0008902228],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01022121,"threshold_uncertainty_score":0.05405557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02670135023359036,"score_gpt":0.2485481827943868,"score_spread":0.2218468325607965,"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."}}