{"id":"W2150408357","doi":"10.1093/nar/gkh485","title":"Proteome Analyst: custom predictions with explanations in a web-based tool for high-throughput proteome annotations","year":2004,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Proteome; Gene ontology; Classifier (UML); Naive Bayes classifier; Computer science; Biology; Human proteome project; Bayes' theorem; Function (biology); Machine learning; Protein function; Artificial intelligence; Protein function prediction; Computational biology; Bioinformatics; Gene; Proteomics; Bayesian probability; Genetics; Support vector machine; Gene expression","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":[],"consensus_categories":[],"category_scores_codex":[0.0008465347,0.0001708331,0.0001693168,0.0004340416,0.0003914897,0.00009157749,0.0003412786,0.0001923404,0.00004073354],"category_scores_gemma":[0.0006293913,0.0001512092,0.00006170379,0.0008732136,0.0002333748,0.00002550714,0.00008721816,0.0004403951,0.00003225434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001445369,"about_ca_system_score_gemma":0.000772243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009942389,"about_ca_topic_score_gemma":0.0005369356,"domain_scores_codex":[0.9980994,0.0001251645,0.0003473522,0.0003781134,0.0005262815,0.0005236629],"domain_scores_gemma":[0.998722,0.00005772675,0.00008373173,0.0005417556,0.0004952644,0.00009951926],"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":[0.002728148,0.002746098,0.07065281,0.001203724,0.0006200858,0.00004284921,0.003179441,0.4010558,0.4864552,0.01599839,0.01182242,0.003495006],"study_design_scores_gemma":[0.06670774,0.02463745,0.2441403,0.001400056,0.0002787228,0.0002002112,0.004136654,0.1927365,0.2646157,0.008901021,0.1877462,0.004499414],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9082172,0.00002397863,0.0839904,0.002898463,0.00003922238,0.003003544,0.0002162669,0.00006641921,0.001544542],"genre_scores_gemma":[0.941668,0.00001011313,0.05512609,0.00009123999,0.0001262854,0.001917528,0.000555519,0.00004082147,0.0004644324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2218395,"threshold_uncertainty_score":0.6166131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02065510645228343,"score_gpt":0.3270776948286184,"score_spread":0.306422588376335,"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."}}