{"id":"W2101456936","doi":"10.1093/bioinformatics/btn645","title":"Predicting the binding preference of transcription factors to individual DNA <i>k</i>-mers","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Howard Hughes Medical Institute","keywords":"Inference; Computational biology; Biology; Transcription factor; DNA; DNA sequencing; DNA binding site; Preference; Gene; Genetics; Mechanism (biology); Computer science; Gene expression; Artificial intelligence; Mathematics; Promoter","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000130524,0.0001141817,0.0001026203,0.00004028247,0.0001388646,0.00001515004,0.0002668356,0.00008497406,0.000004182077],"category_scores_gemma":[0.00004225588,0.00008340712,0.00006547379,0.0000968688,0.0000628833,0.000007173428,0.00007737221,0.00006413823,0.000004838846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001019086,"about_ca_system_score_gemma":0.00005905535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001024312,"about_ca_topic_score_gemma":0.00001218138,"domain_scores_codex":[0.9992467,0.0000136561,0.0003101575,0.00008808861,0.0001667953,0.0001745673],"domain_scores_gemma":[0.9995186,0.00001159442,0.0001347317,0.0002297133,0.00004696847,0.00005841684],"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":[0.00005691711,0.00009973968,0.1028965,0.0002223791,0.0002155375,7.913409e-7,0.02172223,0.002020924,0.8681486,0.0002057196,0.001755402,0.002655263],"study_design_scores_gemma":[0.001467276,0.001459946,0.1655304,0.0001319723,0.0001540567,0.00008649082,0.01350661,0.0148369,0.7922748,0.00005113617,0.009498826,0.001001548],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966033,0.00002915487,0.002135507,0.00002748998,0.0001273626,0.0001906159,0.000126651,0.000009681033,0.0007502077],"genre_scores_gemma":[0.9965827,0.00008104159,0.002956528,0.00008399079,0.0000360433,0.000005739427,0.0001503788,0.00001000199,0.00009359184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07587378,"threshold_uncertainty_score":0.3401243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02841896909652167,"score_gpt":0.2170266167777433,"score_spread":0.1886076476812216,"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."}}