{"id":"W4414717304","doi":"10.1101/2025.09.30.679566","title":"Identification and characterization of bacterial repeat-in-toxin adhesins using long-read genome analysis","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Queen's University","funders":"Canadian Glycomics Network; Natural Sciences and Engineering Research Council of Canada","keywords":"Bacterial adhesin; Genome; Bacteria; Bacterial genetics; DNA; Function (biology); Escherichia coli; Host (biology)","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":[0.0006099944,0.000549908,0.0005520299,0.001711938,0.0004041625,0.001141665,0.0005188076,0.0005227587,0.001269563],"category_scores_gemma":[0.001496163,0.0002114579,0.001212124,0.002153891,0.0002316411,0.0003891212,0.0005276672,0.000566621,0.001142467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002918043,"about_ca_system_score_gemma":0.0003920808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00147596,"about_ca_topic_score_gemma":0.001884544,"domain_scores_codex":[0.9995403,0.00006124792,0.00005333098,0.0001510729,0.0001312116,0.00006278809],"domain_scores_gemma":[0.9989078,0.0002978316,0.0003395623,0.00008114086,0.0002240747,0.0001495053],"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":[0.0004570648,0.0002556673,0.02777199,0.0003608066,0.0001471852,0.0004655076,0.0002458092,0.001188702,0.951363,0.0001999212,0.0002909879,0.01725329],"study_design_scores_gemma":[0.00007718681,0.001352694,0.6125963,0.0001521535,0.0007945628,0.002973522,0.0008981189,0.0362085,0.3327112,0.0007855523,0.01129681,0.0001535207],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9464502,0.0008577141,0.03604883,0.0001264925,0.00003244053,0.0002359278,0.01483676,0.0004243265,0.0009872407],"genre_scores_gemma":[0.8605107,0.00059583,0.08305292,0.0001476586,0.00003928925,0.0002216442,0.05345385,0.000294782,0.001683327],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001711938,"threshold_uncertainty_score":0.004247069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00826467601069353,"score_gpt":0.2341864144382199,"score_spread":0.2259217384275264,"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."}}