{"id":"W4360812610","doi":"10.1021/acs.jproteome.3c00054","title":"OpenCustomDB: Integration of Unannotated Open Reading Frames and Genetic Variants to Generate More Comprehensive Customized Protein Databases","year":2023,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Research in Immunology and Cancer; Université de Montréal; PROTEO; Université de Sherbrooke","funders":"Université de Montréal; Canada Research Chairs; Fonds de Recherche du Québec - Santé; Cole Foundation; Ministère de l'Économie, de la Science et de l'Innovation - Québec; Leukemia and Lymphoma Society of Canada; Canadian Cancer Society; Canadian Institutes of Health Research; Leukemia and Lymphoma Society","keywords":"Proteomics; Computational biology; Open reading frame; Proteogenomics; Biology; Protein sequencing; Genome; Genomics; Database; Genetics; Computer science; Peptide sequence; Gene","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":[0.001089105,0.0001493625,0.0004082899,0.0004423628,0.0002087035,0.0001377926,0.0007407687,0.00008693648,0.00009378386],"category_scores_gemma":[0.0006522128,0.00012332,0.00004844944,0.001015583,0.0001383839,0.0003186399,0.0007627899,0.0006541663,0.00001336576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001021112,"about_ca_system_score_gemma":0.0002389169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002183708,"about_ca_topic_score_gemma":0.000005761378,"domain_scores_codex":[0.9980134,0.0001420985,0.0006612545,0.0002905158,0.0005511594,0.0003415818],"domain_scores_gemma":[0.9976082,0.0001773457,0.0003714853,0.0004093053,0.001236771,0.0001969185],"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":[0.0003858396,0.00005299485,0.0001025935,0.0001293784,0.00003628571,0.00004812013,0.0002159999,0.0001594574,0.9927798,0.0004965909,0.0007294128,0.004863522],"study_design_scores_gemma":[0.0009660588,0.000165031,0.0006681075,0.0008376411,0.00001247903,0.00005723667,0.0006802662,0.002178375,0.9893759,0.003243072,0.001656275,0.0001595113],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9812145,0.00009205576,0.01537784,0.001105016,0.00001188384,0.001844839,0.00008513013,0.00003002344,0.0002387604],"genre_scores_gemma":[0.6530677,0.0003855032,0.3443083,0.00002710216,0.0001190856,0.0007675018,0.00003246026,0.00005232187,0.001239963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3289305,"threshold_uncertainty_score":0.5028844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1457079027742497,"score_gpt":0.4535127458057859,"score_spread":0.3078048430315362,"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."}}