{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002699558,0.002196536,0.001826424,0.00483339,0.001008702,0.003187316,0.003039928,0.0009991779,0.01089662],"category_scores_gemma":[0.003920765,0.001157846,0.001246917,0.004705076,0.000549153,0.002876282,0.003249138,0.001349823,0.006740238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009031761,"about_ca_system_score_gemma":0.00176713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00146383,"about_ca_topic_score_gemma":0.001829509,"domain_scores_codex":[0.9988253,0.0001205067,0.0002081726,0.0004733631,0.0002620054,0.00011073],"domain_scores_gemma":[0.9983364,0.0004931028,0.000303784,0.0003882938,0.0002444931,0.00023395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.01257842,0.001418682,0.02803501,0.007722467,0.002045061,0.004172373,0.001911399,0.008911791,0.205639,0.01855497,0.3848014,0.3242095],"study_design_scores_gemma":[0.002377836,0.001298686,0.02771147,0.0007062578,0.0008760135,0.005345996,0.001186548,0.09156726,0.2795351,0.03516493,0.553502,0.0007278236],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.109665,0.003800965,0.2944956,0.00102094,0.000808116,0.001111381,0.3260897,0.2519669,0.0110414],"genre_scores_gemma":[0.1216316,0.001741108,0.2478995,0.0005562106,0.0001923933,0.001287249,0.6081619,0.01525436,0.003275685],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01089662,"threshold_uncertainty_score":0.03645283,"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."}}