{"id":"W4390810936","doi":"10.1101/2024.01.12.574168","title":"Benchmarking computational tools for de novo motif discovery","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":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Cancer Research","funders":"Stiftelsen för Strategisk Forskning; Volkswagen Foundation; Cancer Research UK","keywords":"Benchmarking; Motif (music); Computational biology; Computer science; Drug discovery; Sequence motif; Bioinformatics; Biology; Business; Genetics; Philosophy; Gene","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":[0.008068588,0.002474501,0.001662491,0.004303803,0.000878895,0.002555124,0.005469677,0.001820182,0.003987942],"category_scores_gemma":[0.02278134,0.0007054695,0.001997826,0.004087819,0.0008938297,0.002515106,0.002225222,0.001906391,0.002005185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001265317,"about_ca_system_score_gemma":0.002393801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001906252,"about_ca_topic_score_gemma":0.002213321,"domain_scores_codex":[0.9945661,0.001583249,0.0008076573,0.001347969,0.001363614,0.0003315049],"domain_scores_gemma":[0.9853961,0.01012321,0.0008239776,0.001725782,0.001536956,0.0003939971],"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":[0.002618005,0.001279829,0.02195748,0.006328524,0.002220716,0.001040122,0.00042646,0.4882579,0.02657859,0.02548694,0.02445335,0.3993521],"study_design_scores_gemma":[0.0002885583,0.0003173751,0.001419446,0.0001703491,0.0001426667,0.0003946351,0.0001086387,0.946108,0.02416501,0.01297647,0.01383823,0.00007065641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1780799,0.006476619,0.7318668,0.0007145259,0.0004006581,0.0006332785,0.009017156,0.0644815,0.008329506],"genre_scores_gemma":[0.2064364,0.001645472,0.768732,0.0002570788,0.00006554188,0.0007838806,0.01902163,0.002295551,0.0007624771],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008068588,"threshold_uncertainty_score":0.04267132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01021085123719515,"score_gpt":0.2231773296661048,"score_spread":0.2129664784289096,"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."}}