{"id":"W4308715575","doi":"10.21203/rs.3.rs-2239137/v1","title":"Graph-Based Active Machine Learning Method for Diverse and Novel Antimicrobial Peptides Generation and Selection","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Genentech; Institut de Valorisation des Données","keywords":"Novelty; Computer science; Antimicrobial peptides; Machine learning; Graph; Artificial intelligence; Selection (genetic algorithm); Scalability; Antimicrobial; Biology; Theoretical computer science; Microbiology","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":[0.0009742497,0.0001767865,0.0001862815,0.0001925982,0.0005817653,0.0001360157,0.000116611,0.0002048515,0.0000107422],"category_scores_gemma":[0.0002183026,0.000174481,0.00008819549,0.0001039902,0.00004999125,0.000007661723,0.0007164365,0.0005884903,2.10354e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003998323,"about_ca_system_score_gemma":0.0001342845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002521929,"about_ca_topic_score_gemma":0.00008214085,"domain_scores_codex":[0.9987579,0.0001984054,0.0001751451,0.0004192695,0.0001854595,0.0002638104],"domain_scores_gemma":[0.9993889,0.00005568672,0.0001021403,0.0001453993,0.0002495702,0.00005831989],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000571719,0.0001209559,0.001882489,0.001093087,0.0001933726,4.733709e-7,0.0003279235,0.01344747,0.9706243,0.0001388176,0.001049307,0.01055013],"study_design_scores_gemma":[0.003567436,0.002416564,0.005130869,0.0001333622,0.0001087683,0.00002777702,0.001894101,0.6738027,0.2864446,0.0001851304,0.02545687,0.0008318639],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8906426,0.0006988265,0.1063173,0.0002475245,0.00008262118,0.001424739,0.0004787414,0.00001875751,0.00008889069],"genre_scores_gemma":[0.9591649,0.0008178386,0.03459556,0.00004275828,0.0002596523,0.0003184617,0.004463257,0.00004344506,0.0002941626],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6841797,"threshold_uncertainty_score":0.7115129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06683693460630268,"score_gpt":0.3695762068648638,"score_spread":0.3027392722585611,"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."}}