{"id":"W4282011047","doi":"10.1186/s13059-022-02690-2","title":"Virtual ChIP-seq: predicting transcription factor binding by learning from the transcriptome","year":2022,"lang":"en","type":"article","venue":"Genome biology","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; Vector Institute; Princess Margaret Cancer Centre; University of Toronto","funders":"Banff International Research Station for Mathematical Innovation and Discovery; University of Toronto; Canadian Cancer Society","keywords":"Biology; Computational biology; Transcription factor; DNA binding site; Sequence (biology); Binding site; Genetics; Chromatin; Sequence motif; Transcriptome; Gene; Gene expression; Promoter","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002267704,0.0001924727,0.0001708921,0.00003291477,0.0006147008,0.00002693638,0.0004387874,0.0001385505,0.0003204489],"category_scores_gemma":[0.00002130337,0.000168862,0.0001297308,0.00008090159,0.00008303024,0.000003172986,0.0001521377,0.0003511444,0.00001306305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005205502,"about_ca_system_score_gemma":0.00004738124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009030307,"about_ca_topic_score_gemma":0.00002161157,"domain_scores_codex":[0.9985531,0.0002634491,0.0002706375,0.0004499485,0.00009903541,0.0003638239],"domain_scores_gemma":[0.9995126,0.00003001791,0.0001204972,0.0002562608,0.00002001423,0.00006057177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004632629,0.00002829554,0.007926641,0.000002011149,0.00008442639,6.552502e-7,0.0006782393,0.0006665304,0.9890693,0.00005271757,0.000132648,0.001312183],"study_design_scores_gemma":[0.00434234,0.005418791,0.05137343,0.00001115565,0.0001898572,0.00007886923,0.01117678,0.004926518,0.06208557,0.0005782166,0.8578444,0.001974114],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993775,0.001526042,0.002535062,0.000246476,0.0005424355,0.0001971229,0.001008666,0.00003180753,0.0001374237],"genre_scores_gemma":[0.9947706,0.0001880108,0.00008007709,0.0003037681,0.0002930802,0.00005861945,0.003775415,0.00003667959,0.0004937143],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9269838,"threshold_uncertainty_score":0.6885991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009674003886454572,"score_gpt":0.2073851014318302,"score_spread":0.1977110975453756,"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."}}