{"id":"W4413396779","doi":"10.1093/bioinformatics/btaf460","title":"PDP-Miner: an AI/ML tool to detect prophage tail proteins with depolymerase domains across thousands of bacterial genomes","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Prophage; Genome; Bacteriophage; Bacterial genome size; Source code; Computational biology; Computer science; Biology; Software; Gene; Genetics; Programming language; Escherichia coli","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003462696,0.0003424939,0.0003531526,0.0001208962,0.0001868465,0.000128809,0.0004931689,0.0002349581,0.00002280038],"category_scores_gemma":[0.0001598003,0.0002698565,0.00009755426,0.0003243437,0.0001493812,0.00004167617,0.0003183056,0.0001829813,0.00001428889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002989682,"about_ca_system_score_gemma":0.0002908741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002023022,"about_ca_topic_score_gemma":0.000100349,"domain_scores_codex":[0.9981887,0.00004635771,0.0007591648,0.0002239009,0.0002865494,0.0004952757],"domain_scores_gemma":[0.9984945,0.00001486161,0.0003042576,0.0008646052,0.0001731546,0.0001486198],"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":[0.003400485,0.0004535567,0.009106941,0.003512337,0.0005887993,0.00001846897,0.007914715,0.002616417,0.7974615,0.0005328058,0.004085357,0.1703087],"study_design_scores_gemma":[0.003997643,0.004278224,0.002683213,0.0002343446,0.0001140713,0.00007271528,0.001145143,0.008675748,0.9077847,0.00003159653,0.06985818,0.001124447],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.93186,0.0001031165,0.0646424,0.00008107727,0.0001582258,0.001062985,0.0001743981,0.00006242612,0.001855427],"genre_scores_gemma":[0.8302332,0.0000457314,0.1670244,0.0009974455,0.0001940662,0.0001276074,0.0004397442,0.0000491063,0.0008887376],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1691842,"threshold_uncertainty_score":0.9999754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00454705534616463,"score_gpt":0.2597397804878549,"score_spread":0.2551927251416903,"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."}}