{"id":"W4388774247","doi":"10.1101/2023.11.14.566903","title":"DeepMRG: a multi-label deep learning classifier for predicting bacterial metal resistance genes","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bacterial biofilms and quorum sensing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; Chinese Academy of Sciences","keywords":"Classifier (UML); Antibiotic resistance; Computer science; Machine learning; Artificial intelligence; Cutoff; Metagenomics; Source code; Data mining; Computational biology; Antibiotics; Gene; Biology; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001016559,0.001821411,0.001080442,0.001537061,0.0004690056,0.001067644,0.001914163,0.002330917,0.002088899],"category_scores_gemma":[0.00190107,0.0003933087,0.001116876,0.0008840136,0.0003675363,0.001025808,0.001219342,0.002084514,0.001400979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001206461,"about_ca_system_score_gemma":0.001125565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008190559,"about_ca_topic_score_gemma":0.009733162,"domain_scores_codex":[0.9992656,0.0001391081,0.00004925219,0.0002620887,0.0001700057,0.0001140513],"domain_scores_gemma":[0.9990792,0.0003433196,0.0001273446,0.00008505865,0.0002952704,0.00006986212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001057931,0.001050893,0.02984477,0.0005916635,0.0003262105,0.0004537993,0.000130901,0.2430436,0.05808103,0.00285484,0.03335678,0.6292076],"study_design_scores_gemma":[0.00001551157,0.00007167666,0.0008540138,0.0000210432,0.00002107517,0.00002879184,0.00001850176,0.9895881,0.006445255,0.001475405,0.001445113,0.00001552749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3551449,0.007825491,0.5901906,0.002889788,0.0008276439,0.0003492373,0.009889862,0.02505055,0.007831949],"genre_scores_gemma":[0.722027,0.001100888,0.249725,0.001801464,0.0001993877,0.0002954235,0.01521435,0.0002661647,0.009370274],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008190559,"threshold_uncertainty_score":0.01628578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02647085069410691,"score_gpt":0.2437040203545695,"score_spread":0.2172331696604626,"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."}}