{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005553974,0.001898099,0.001748976,0.006518882,0.003113626,0.003561475,0.002862138,0.0008494493,0.009715961],"category_scores_gemma":[0.01654648,0.001053723,0.003339831,0.007177558,0.0008439316,0.002433328,0.003153152,0.003149099,0.01169379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001832702,"about_ca_system_score_gemma":0.007427431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004818525,"about_ca_topic_score_gemma":0.01365471,"domain_scores_codex":[0.9969769,0.0006546091,0.0004900019,0.0007397182,0.0009639825,0.0001748839],"domain_scores_gemma":[0.9935486,0.001986684,0.0006088314,0.002271906,0.001307675,0.0002763423],"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":[0.000951699,0.0006881952,0.01740946,0.007790669,0.001084581,0.001883443,0.001812502,0.01373733,0.1218132,0.02735845,0.4312448,0.3742256],"study_design_scores_gemma":[0.0002288253,0.0002624644,0.02103677,0.001362556,0.0004209882,0.001650127,0.001222896,0.08698098,0.09375733,0.04351001,0.7492694,0.0002976528],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04253149,0.001801922,0.5836825,0.002674723,0.0008172215,0.001999523,0.2821118,0.07170992,0.01267084],"genre_scores_gemma":[0.01864146,0.001270372,0.6550202,0.0003683094,0.0001025664,0.001479312,0.3163686,0.003907904,0.002841251],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009715961,"threshold_uncertainty_score":0.03250319,"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."}}