{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000334961,0.0001978662,0.0002843281,0.00004992016,0.00007504136,0.00001394232,0.0002512586,0.0001279339,0.00000531412],"category_scores_gemma":[0.00001660167,0.0001794408,0.0001294734,0.00007119444,0.0001553104,0.000002188484,0.000297277,0.00005897704,0.000003047408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001228543,"about_ca_system_score_gemma":0.00003774853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006466948,"about_ca_topic_score_gemma":0.00001798591,"domain_scores_codex":[0.9987686,0.0000200366,0.0006200594,0.0001676812,0.0001521348,0.0002714717],"domain_scores_gemma":[0.9990255,0.00002424575,0.0003464055,0.000438779,0.0001017295,0.00006332887],"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":[0.0001200345,0.0001001236,0.007502122,0.0005699209,0.0001503066,2.654542e-7,0.001025216,0.002140228,0.9736172,0.0007459925,0.002709345,0.01131926],"study_design_scores_gemma":[0.006022215,0.003389729,0.01187917,0.0002470105,0.0001070749,0.00003613623,0.007298447,0.008529129,0.7732441,0.0009970989,0.1865493,0.00170062],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6803179,0.0006104825,0.3166062,0.00001616561,0.000164183,0.0002160929,0.00008415747,0.000004011397,0.00198079],"genre_scores_gemma":[0.5943989,0.0005108272,0.4047373,0.00009305574,0.00007646064,0.0000150106,0.00007671811,0.00002348683,0.00006821409],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2003731,"threshold_uncertainty_score":0.7317385,"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."}}