{"id":"W4298148300","doi":"10.1016/j.gpb.2022.09.008","title":"Newfound Coding Potential of Transcripts Unveils Missing Members of Human Protein Communities","year":2022,"lang":"en","type":"article","venue":"Genomics Proteomics & Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"PROTEO; Université de Sherbrooke","funders":"Canadian Institutes of Health Research; Fonds de Recherche du Québec - Santé; Compute Canada; Centre Hospitalier Universitaire de Québec; Université de Sherbrooke","keywords":"Proteogenomics; Pseudogene; ENCODE; Computational biology; Open reading frame; Gene; Biology; Human genome; Genetics; Genome; Genomics; Peptide sequence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008463228,0.0003028146,0.0004560467,0.000224266,0.0005344132,0.00005409801,0.0007729799,0.000178089,0.00005123566],"category_scores_gemma":[0.00001228895,0.0003432413,0.0002579107,0.0002140901,0.0003017387,0.00002388797,0.0005701085,0.0003748305,0.000001405062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009635097,"about_ca_system_score_gemma":0.0002896469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001211683,"about_ca_topic_score_gemma":0.00003528964,"domain_scores_codex":[0.997694,0.000093098,0.001309973,0.0001492678,0.000317265,0.0004363903],"domain_scores_gemma":[0.9980839,0.00001161575,0.0009490328,0.0007036969,0.0001428777,0.0001088855],"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":[0.0002166231,0.0001272129,0.00008599523,0.0005047574,0.0002042581,0.000001047256,0.004527352,0.01058586,0.9778261,0.002454822,0.0003135141,0.003152416],"study_design_scores_gemma":[0.006243686,0.00356535,0.0001647128,0.0002426794,0.0003107384,0.0002038238,0.03385063,0.1593959,0.7675768,0.005973682,0.02035913,0.002112925],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9628837,0.0002192423,0.03281166,0.00007490732,0.0002182109,0.001197501,0.0003815465,0.00001741073,0.002195825],"genre_scores_gemma":[0.9579523,0.00006681322,0.04088661,0.0001517457,0.00008048934,0.00006333391,0.0006225317,0.00004713317,0.0001290735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2102494,"threshold_uncertainty_score":0.999902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01459719515072576,"score_gpt":0.2300191319180293,"score_spread":0.2154219367673036,"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."}}