{"id":"W2014097763","doi":"10.1186/1471-2105-13-264","title":"Sifting through genomes with iterative-sequence clustering produces a large, phylogenetically diverse protein-family resource","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Joint Genome Institute; Gordon and Betty Moore Foundation; U.S. Department of Energy; National Science Foundation","keywords":"Genome; Computational biology; Cluster analysis; Identification (biology); Protein family; Phylogenetic tree; Computer science; Biology; Genomics; Comparative genomics; Sequence alignment; Genetics; Gene; Machine learning; Peptide sequence","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":[0.0002838097,0.0002893923,0.0002222962,0.00003461654,0.0002775018,0.00006662044,0.0002573711,0.00011266,0.000005585868],"category_scores_gemma":[0.00006985082,0.0002275719,0.00007310915,0.0001239335,0.0001489572,0.00001097571,0.0003908035,0.0001030247,0.00002125792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001910904,"about_ca_system_score_gemma":0.00007914575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005274251,"about_ca_topic_score_gemma":0.00002611298,"domain_scores_codex":[0.9985134,0.00004575152,0.0003643689,0.0002437903,0.0002082233,0.0006244658],"domain_scores_gemma":[0.9991305,0.00001933106,0.0001921206,0.0004308121,0.0001125162,0.0001146479],"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":[0.0006367836,0.0005207459,0.1324689,0.001221969,0.0006763532,0.00000641788,0.02138049,0.003717021,0.8244696,0.0013549,0.001349006,0.01219781],"study_design_scores_gemma":[0.006431536,0.003662719,0.06410315,0.0005683496,0.0003863838,0.0002481015,0.03088383,0.02105108,0.2533237,0.0002085799,0.6146103,0.004522258],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9531172,0.002765698,0.036941,0.00004329297,0.0001052816,0.000730585,0.00007206253,0.00001853938,0.006206335],"genre_scores_gemma":[0.7873139,0.000116267,0.2114571,0.0003821834,0.0003321368,0.0000624208,0.00004768927,0.00003088177,0.0002573551],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6132613,"threshold_uncertainty_score":0.9280112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03413198597559645,"score_gpt":0.2570171978229868,"score_spread":0.2228852118473903,"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."}}