{"id":"W4322756984","doi":"10.20944/preprints202303.0048.v1","title":"A Deep Learning Method for Predicting the Minimum Inhibitory Concentration of Antimicrobial Peptides against Escherichia coli using Multi-Branch-CNN and Attention","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Antimicrobial Peptides and Activities","field":"Immunology and Microbiology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Infection and Immunity; University of Ottawa","funders":"Universidade de Macau; Government of Canada","keywords":"Escherichia coli; Minimum bactericidal concentration; Minimum inhibitory concentration; Antimicrobial peptides; Antimicrobial; Potency; Artificial intelligence; Correlation coefficient; Mean squared error; Support vector machine; Machine learning; Computer science; Computational biology; Biology; Mathematics; Microbiology; Biochemistry; Statistics; In vitro","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001230087,0.0004003622,0.0006597029,0.0001056702,0.0005429403,0.00003960959,0.000301565,0.0006265567,0.00001784268],"category_scores_gemma":[0.0004615675,0.0003681583,0.0003150527,0.0001045031,0.0004794524,0.0001438997,0.0007948495,0.001034808,0.00003265176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009227797,"about_ca_system_score_gemma":0.0001389076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007239764,"about_ca_topic_score_gemma":0.00004965806,"domain_scores_codex":[0.9973205,0.0005980138,0.0007555801,0.0008048042,0.00006222636,0.0004588563],"domain_scores_gemma":[0.9978779,0.0004886557,0.0009471432,0.0003925973,0.000265031,0.00002868137],"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":[0.0001773478,0.00008287495,0.07054643,0.000486972,0.0004078997,9.08454e-7,0.002354543,0.006025955,0.9194915,0.00003733438,0.00003979704,0.0003484681],"study_design_scores_gemma":[0.001960202,0.00005487136,0.05456372,0.001227223,0.0004563105,0.00001422671,0.003118255,0.01584879,0.9217153,0.0001236862,0.000298735,0.0006186925],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9696704,0.0003689367,0.02666393,0.00013952,0.001587811,0.001287992,0.00007386633,0.0001541869,0.00005334095],"genre_scores_gemma":[0.9948296,0.0003019892,0.003328023,0.00008229377,0.0001963347,0.00007660989,0.000242017,0.00007279051,0.0008703322],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0251592,"threshold_uncertainty_score":0.999877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08686529112486574,"score_gpt":0.33046792609646,"score_spread":0.2436026349715942,"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."}}