{"id":"W2121776973","doi":"10.1186/1471-2105-15-148","title":"Improvement of domain-level ortholog clustering by optimizing domain-specific sum-of-pairs score","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute for Basic Biology; National Bioscience Database Center; Institute of Genetics; Research Organization of Information and Systems","keywords":"Cluster analysis; Pipeline (software); Pairwise comparison; Domain (mathematical analysis); Computer science; DNA microarray; Data mining; Genome; Computational biology; Architecture domain; Biology; Pattern recognition (psychology); Artificial intelligence; Gene; Genetics; Software; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007326044,0.001846496,0.001944577,0.002914913,0.001281549,0.001272541,0.002222162,0.001176005,0.002144653],"category_scores_gemma":[0.01482293,0.0005933823,0.001883101,0.002034718,0.0006295039,0.001866996,0.00188972,0.001896054,0.00148536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008409654,"about_ca_system_score_gemma":0.001679672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002916039,"about_ca_topic_score_gemma":0.003679072,"domain_scores_codex":[0.9963577,0.00108663,0.0003246166,0.0008788184,0.001118579,0.0002335019],"domain_scores_gemma":[0.9942648,0.001772274,0.0006267612,0.0009694386,0.002126326,0.0002404277],"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":[0.001420719,0.0007381206,0.064691,0.001451979,0.0008504366,0.0004883772,0.001138684,0.2048767,0.2005961,0.005734874,0.01618229,0.5018307],"study_design_scores_gemma":[0.0001490112,0.0002767423,0.01285166,0.00006395258,0.0001403469,0.0002891532,0.0002407938,0.8753054,0.09906547,0.004478313,0.006988066,0.0001511021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2107108,0.0006215346,0.7720263,0.0002050292,0.00009005316,0.0002726259,0.00104968,0.01345727,0.001566566],"genre_scores_gemma":[0.2456092,0.0001444025,0.7488491,0.00007904279,0.00001724979,0.0001821027,0.002975814,0.001661612,0.0004815095],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007326044,"threshold_uncertainty_score":0.03874433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02150140156673435,"score_gpt":0.2238152753373628,"score_spread":0.2023138737706284,"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."}}