{"id":"W3116329593","doi":"10.1101/2020.12.21.423873","title":"Biologically-relevant transfer learning improves transcription factor binding prediction","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Children's Hospital; Canadian Institute for Advanced Research; University of British Columbia","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; University of British Columbia; BC Children's Hospital; Children's Hospital Foundation","keywords":"Transfer of learning; Computer science; Artificial intelligence; Machine learning; Multi-task learning; Deep learning; Task (project management); Training set; Engineering","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":[0.001415454,0.001119825,0.0007094017,0.0004363208,0.0003060852,0.0006188066,0.001281935,0.00141127,0.003361915],"category_scores_gemma":[0.004141734,0.000307683,0.0007542048,0.0004005874,0.0008643253,0.00137068,0.00128823,0.001760918,0.0008324701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009914431,"about_ca_system_score_gemma":0.0007106372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003449674,"about_ca_topic_score_gemma":0.00246718,"domain_scores_codex":[0.9994548,0.0001412176,0.00002168668,0.0002068579,0.0001020066,0.0000734456],"domain_scores_gemma":[0.9989148,0.0005387612,0.00008932073,0.000252559,0.0001186047,0.00008593872],"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":[0.0002240444,0.0002860098,0.003603606,0.0001210336,0.00009551437,0.00009494177,0.00005633279,0.852493,0.04784742,0.001571483,0.001765313,0.0918413],"study_design_scores_gemma":[0.000009391376,0.00004276786,0.0006210294,0.000003413269,0.000007311828,0.00001533386,0.000007117074,0.9831081,0.0132313,0.002713548,0.000233235,0.000007426767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4847328,0.0007382488,0.5007025,0.0009143373,0.0001292057,0.00007779683,0.0004347177,0.007180666,0.005089687],"genre_scores_gemma":[0.9620317,0.00009285523,0.03532056,0.0001796026,0.00003122627,0.00004332454,0.0004155617,0.0002186716,0.001666557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003449674,"threshold_uncertainty_score":0.01124674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01207171857835334,"score_gpt":0.2011223397208332,"score_spread":0.1890506211424799,"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."}}