{"id":"W4415937939","doi":"10.1101/2025.11.04.686393","title":"Harnessing Interpretable Deep Learning to Predict Resistance in <i>Klebsiella pneumoniae</i>","year":2025,"lang":"","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"FPInnovations","funders":"Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Deep learning; Meropenem; Antibiotic resistance; Inference; Profiling (computer programming); ORFS; False positive paradox; Mechanism (biology)","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":[0.0006319116,0.0008292419,0.0004114027,0.0004418167,0.0001826318,0.0007657481,0.0006590592,0.0007996084,0.001134514],"category_scores_gemma":[0.00163514,0.0002674015,0.0005472445,0.0002366271,0.0003928448,0.000628548,0.000661762,0.001164754,0.0002936748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007844268,"about_ca_system_score_gemma":0.0008990146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008157071,"about_ca_topic_score_gemma":0.006825839,"domain_scores_codex":[0.9998353,0.00004486361,0.000008440756,0.00004330749,0.00003515339,0.00003297037],"domain_scores_gemma":[0.9995188,0.0002322001,0.00005615385,0.00004450998,0.0001104333,0.00003802445],"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":[0.000219591,0.0001740655,0.007804005,0.00008245576,0.00008899489,0.0001259056,0.00003956614,0.9115437,0.01445281,0.001469899,0.001951456,0.06204752],"study_design_scores_gemma":[0.000003056269,0.00001804895,0.0002343053,0.000003224227,0.000005208596,0.000004500971,0.000002546323,0.9974885,0.00135811,0.0007763111,0.0001037237,0.000002495382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6442221,0.001553283,0.3406971,0.002423279,0.000196541,0.00007410983,0.001046184,0.004889642,0.004897852],"genre_scores_gemma":[0.9695976,0.0002009658,0.0279122,0.0002337081,0.00003699555,0.00003056728,0.0006816257,0.00004497957,0.001261459],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008157071,"threshold_uncertainty_score":0.0162192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004704489044187024,"score_gpt":0.2194177016508908,"score_spread":0.2147132126067037,"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."}}