{"id":"W4296682879","doi":"10.1016/j.mex.2022.101846","title":"Computational curation and analysis of publicly available protein sequence data from a single protein family","year":2022,"lang":"en","type":"article","venue":"MethodsX","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Reuse; Domain (mathematical analysis); Information retrieval; Sequence (biology); Public domain; Parsing; Data curation; Data mining; Download; Biological database; Data science; Biological data; Protein sequencing; Bioinformatics; World Wide Web; Peptide sequence; Artificial intelligence; Biology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004958437,0.00007904747,0.0001589736,0.000061538,0.0001126117,0.00001872397,0.0002159211,0.00002805521,0.00005031277],"category_scores_gemma":[0.00009946068,0.0000821003,0.00003482536,0.0002374231,0.00006483046,0.000002516608,0.0004281235,0.00004577142,5.467874e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009710426,"about_ca_system_score_gemma":0.00006182613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004139401,"about_ca_topic_score_gemma":0.00003651783,"domain_scores_codex":[0.9989978,0.0002248259,0.0001807192,0.0003731602,0.0001287205,0.00009477981],"domain_scores_gemma":[0.9993814,0.00002610008,0.0001150968,0.0003836718,0.00006746503,0.00002623631],"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":[0.00002885808,0.00004432585,0.002323729,0.000005191788,0.0003592599,4.516145e-7,0.00006558903,0.001533816,0.992928,0.00006967661,0.000129336,0.002511786],"study_design_scores_gemma":[0.002212874,0.001771899,0.07630063,0.00002175864,0.001502823,0.000007837252,0.001427893,0.24762,0.5129517,0.008962608,0.1459199,0.001300007],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9499451,0.00138758,0.04709969,0.00008820037,0.00002226764,0.0002346935,0.001009733,0.000002330824,0.0002103827],"genre_scores_gemma":[0.7651122,0.000008557264,0.2332792,0.00006493735,0.00002288529,0.00005833774,0.001246903,0.000007280462,0.000199705],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4799763,"threshold_uncertainty_score":0.3347953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1192834641721087,"score_gpt":0.3252766679347823,"score_spread":0.2059932037626736,"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."}}