{"id":"W4285218787","doi":"10.1007/978-1-0716-2124-0_16","title":"Mining Proteomics Datasets to Uncover Functional Pseudogenes","year":2022,"lang":"en","type":"article","venue":"Methods in molecular biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"Canadian Institutes of Health Research","keywords":"Pseudogene; Computational biology; Computer science; Proteomics; Biology; Genetics; Gene; Genome","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":[0.001586519,0.0001998547,0.0002136217,0.0001785868,0.000139042,0.00001449779,0.000418641,0.0001338868,0.0001605568],"category_scores_gemma":[0.0006966852,0.0002131873,0.00008212862,0.0002958406,0.00006133827,0.000002567816,0.001048869,0.0002676023,0.000008820448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005072961,"about_ca_system_score_gemma":0.0001004266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002090217,"about_ca_topic_score_gemma":0.000009586117,"domain_scores_codex":[0.9976157,0.00106596,0.0003609596,0.0004609882,0.0001299439,0.0003664663],"domain_scores_gemma":[0.9991678,0.0000531017,0.0001142562,0.0005524312,0.00003175738,0.00008063956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001202811,0.00004578045,0.00569727,0.00001066081,0.00003720366,0.000008706319,0.00006173833,0.01563038,0.9708113,0.0006823274,0.001691078,0.005203268],"study_design_scores_gemma":[0.00108296,0.001127382,0.001102106,0.000007007463,0.00002331485,0.0001998865,0.0002186489,0.002985045,0.4261747,0.001052233,0.5653188,0.0007079373],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.144485,0.0001890166,0.8533792,0.0002934636,0.0004373166,0.000363596,0.0001577168,0.00001730449,0.000677439],"genre_scores_gemma":[0.01127408,0.00000672993,0.9831546,0.003185317,0.00008894109,0.0002767035,0.001761728,0.00003528328,0.0002166466],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5636277,"threshold_uncertainty_score":0.8693524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02048432241387272,"score_gpt":0.3699581426326024,"score_spread":0.3494738202187297,"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."}}