{"id":"W2950259236","doi":"10.48550/arxiv.q-bio/0603011","title":"PFMFind: a system for discovery of peptide homology and function","year":2006,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Python (programming language); Computer science; Plug-in; Homology (biology); Computational biology; Data mining; Programming language; Theoretical computer science; Artificial intelligence; Information retrieval; Biology; Amino acid; Genetics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001361221,0.0001845198,0.000246016,0.00008679499,0.00005421766,0.00001917395,0.0001962263,0.0003625189,0.000001135437],"category_scores_gemma":[0.00003389666,0.0002052126,0.0001384169,0.00005081485,0.0001214478,0.000005968311,0.0004287309,0.0001650886,0.000001412623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003288559,"about_ca_system_score_gemma":0.00007232062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001338405,"about_ca_topic_score_gemma":0.00007294607,"domain_scores_codex":[0.9991865,0.00005156171,0.0001917594,0.0003786265,0.00002999744,0.0001615868],"domain_scores_gemma":[0.9991577,0.00002637511,0.0002943307,0.0004057623,0.00008054384,0.00003530091],"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":[0.004066427,0.0004988129,0.1466528,0.01489646,0.002203603,0.0001352023,0.0003392737,0.6275047,0.05286159,0.1370793,0.01166246,0.002099391],"study_design_scores_gemma":[0.02383383,0.01051741,0.1453891,0.002733046,0.00664769,0.0003817999,0.003495475,0.6064121,0.07175419,0.03440759,0.08531962,0.0091081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.796115,0.00008730807,0.201152,0.000006706057,0.0002094327,0.0002618992,0.00008375031,0.00001780853,0.002066088],"genre_scores_gemma":[0.995674,0.00004330681,0.0008826181,0.00001748917,0.0001014769,0.000002047214,0.0004486367,0.00001820777,0.002812292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2002693,"threshold_uncertainty_score":0.8368327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01980607468470608,"score_gpt":0.1765235841290318,"score_spread":0.1567175094443257,"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."}}