{"id":"W4399993795","doi":"10.1101/2024.06.20.599829","title":"Predicting biological activity from biosynthetic gene clusters using neural networks","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Gene; Computational biology; Artificial neural network; Biology; Computer science; Genetics; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005309178,0.0008275956,0.0004191422,0.002420991,0.0002234285,0.0006548517,0.0004672194,0.0006145369,0.001253789],"category_scores_gemma":[0.001497841,0.000199325,0.0006040403,0.001442058,0.0001695929,0.0005007304,0.0003396132,0.0005157283,0.0003306419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000882611,"about_ca_system_score_gemma":0.0004282231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008442785,"about_ca_topic_score_gemma":0.007560905,"domain_scores_codex":[0.9997723,0.00004956306,0.00001285518,0.00009658882,0.00004417332,0.00002451797],"domain_scores_gemma":[0.9991962,0.0005365949,0.00008697656,0.00002982694,0.0001167123,0.00003372662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007533455,0.0007297624,0.04944471,0.0002649974,0.0001809073,0.0001372478,0.00004080338,0.754495,0.02371362,0.0008957477,0.002343286,0.1670006],"study_design_scores_gemma":[0.000004580224,0.00002369576,0.001675363,0.000003632646,0.000007950621,0.00000654427,0.000006715404,0.9955084,0.002178553,0.0004284597,0.0001524788,0.000003591362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8297718,0.001016575,0.1567404,0.0004501934,0.00005502467,0.0001684498,0.006032487,0.002591617,0.003173551],"genre_scores_gemma":[0.9121633,0.0002834612,0.08066223,0.00007857251,0.00002527281,0.0001162858,0.005448635,0.00003986656,0.001182477],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008442785,"threshold_uncertainty_score":0.01678729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01588516454159353,"score_gpt":0.2203851898149495,"score_spread":0.204500025273356,"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."}}