{"id":"W6976891677","doi":"10.60692/7xw3a-a8768","title":"AMP-RNNpro: a two-stage approach for identification of antimicrobials using probabilistic features","year":2024,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Antimicrobial Peptides and Activities","field":"Immunology and Microbiology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Probabilistic logic; Identification (biology); Encoding (memory); Feature (linguistics); Artificial neural network; Antimicrobial peptides; Multi-label classification; Statistical model","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":[0.001123775,0.001189164,0.0008378653,0.0009768876,0.0003903971,0.0006779046,0.001501721,0.001099505,0.001391925],"category_scores_gemma":[0.002034599,0.0005124081,0.001284842,0.0003449786,0.000372922,0.001223805,0.001051526,0.001103962,0.0005433083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006407257,"about_ca_system_score_gemma":0.0009294899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004336663,"about_ca_topic_score_gemma":0.003982164,"domain_scores_codex":[0.9994574,0.0001393598,0.00003675725,0.0001575113,0.0001504484,0.00005846419],"domain_scores_gemma":[0.9993396,0.0002739761,0.00009949879,0.00006230905,0.0001800496,0.00004456226],"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":[0.0003459447,0.0002465806,0.005740399,0.0001251299,0.0001977891,0.0002846704,0.00006516574,0.8228474,0.01740259,0.004938955,0.001656334,0.146149],"study_design_scores_gemma":[0.000002342646,0.00002531069,0.0001222152,0.000001997264,0.000006075968,0.00001438721,0.000002671169,0.9980434,0.001038296,0.0006196755,0.0001195046,0.000004012995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07187045,0.0004987093,0.9224052,0.0003644472,0.00006157711,0.0001113858,0.0002619541,0.002389541,0.002036847],"genre_scores_gemma":[0.7791707,0.0002286099,0.2166225,0.0002241046,0.00007279678,0.0001864294,0.0006082306,0.0001099769,0.002776629],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004336663,"threshold_uncertainty_score":0.008622825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04343721965465173,"score_gpt":0.2522834251660045,"score_spread":0.2088462055113528,"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."}}