{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002119211,0.00119591,0.001176286,0.00326336,0.001170132,0.001319622,0.001484523,0.0006599683,0.004425898],"category_scores_gemma":[0.004235982,0.0006847852,0.002296975,0.005029373,0.0005425277,0.001473412,0.001585791,0.001065791,0.003492469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00143976,"about_ca_system_score_gemma":0.002599523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005704893,"about_ca_topic_score_gemma":0.009217832,"domain_scores_codex":[0.9989805,0.0001792251,0.00007572335,0.0003347284,0.000319535,0.0001102979],"domain_scores_gemma":[0.9980627,0.0006422387,0.0002065737,0.0004767778,0.0004817906,0.0001300488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002065916,0.0007034196,0.05814648,0.002024526,0.001375156,0.001198774,0.001165247,0.1053927,0.2165007,0.0171391,0.06697071,0.5273173],"study_design_scores_gemma":[0.0003400337,0.0005026491,0.03194654,0.0002072697,0.0005271041,0.001503204,0.0007213734,0.7321458,0.1196679,0.0411512,0.07104599,0.0002409905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.232224,0.000692133,0.7035944,0.0006165892,0.0001142784,0.0004091356,0.01690587,0.04145083,0.00399278],"genre_scores_gemma":[0.1587212,0.0003589824,0.8035308,0.0001806203,0.00001833533,0.0003042719,0.03353556,0.002480749,0.0008694368],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005704893,"threshold_uncertainty_score":0.01480615,"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."}}