{"id":"W4392844094","doi":"10.1093/nargab/lqae005","title":"Functional domain annotation by structural similarity","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Annotation; Computational biology; Structural similarity; In silico; Protein domain; Domain (mathematical analysis); Similarity (geometry); Structural alignment; Sequence alignment; Proteome; UniProt; Biology; Sequence (biology); Protein sequencing; Benchmark (surveying); Computer science; Bioinformatics; Genetics; Peptide sequence; Artificial intelligence; Geography","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":[0.0001240809,0.0001366403,0.00009596797,0.0000331078,0.0001368141,0.0001010268,0.00006290289,0.0001029455,0.000008957792],"category_scores_gemma":[0.000008404623,0.0001183947,0.00005125804,0.00005139911,0.00006901922,0.00000281225,0.00008944294,0.00007163046,0.000008939202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001659628,"about_ca_system_score_gemma":0.00004992689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004626226,"about_ca_topic_score_gemma":0.00000609886,"domain_scores_codex":[0.9993743,0.000009118638,0.0002129109,0.0001597689,0.00008081996,0.0001630992],"domain_scores_gemma":[0.9997356,0.00001033474,0.00003837921,0.0001181725,0.00003904564,0.00005846352],"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":[0.0001108648,0.00002850975,0.002288661,0.0003228757,0.0004314052,0.000003333718,0.001752411,0.0002585745,0.8467063,0.003203998,0.07677342,0.0681197],"study_design_scores_gemma":[0.001047937,0.0005647213,0.009281103,0.00002698504,0.00008542697,0.0001408026,0.001395966,0.02974894,0.03026578,0.005683051,0.9208325,0.0009268547],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9897022,0.005393073,0.003058172,0.0002952211,0.0003444497,0.0001283699,0.0002473589,0.000008429623,0.0008227013],"genre_scores_gemma":[0.9894115,0.001330721,0.007957944,0.0003786612,0.0002442732,0.000007161283,0.00036528,0.0000165605,0.0002879389],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.844059,"threshold_uncertainty_score":0.4827995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007423367596102924,"score_gpt":0.2145816978091313,"score_spread":0.2071583302130283,"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."}}