{"id":"W4415156865","doi":"10.1007/s00239-025-10272-6","title":"Quest for Orthologs in the era of Data Deluge and AI: Challenges and Innovations in Orthology Prediction and Data Integration","year":2025,"lang":"en","type":"review","venue":"Journal of Molecular Evolution","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Université du Québec à Montréal; Western University","funders":"Canadian Institutes of Health Research; Université de Lausanne; Université de Sherbrooke; Université du Québec à Montréal","keywords":"Data integration; Inference; Domain (mathematical analysis); DNA sequencing; Genomics; Annotation; Genome; Field (mathematics); Alternative splicing","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001130683,0.000136711,0.0004272853,0.000169232,0.00002940986,0.00001050383,0.0002783539,0.0002032768,7.552271e-8],"category_scores_gemma":[0.0003758975,0.0001010639,0.00003158937,0.0001103057,0.00008930255,0.000007840511,0.0003193496,0.0002169467,1.043627e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001274913,"about_ca_system_score_gemma":0.0001716489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001084479,"about_ca_topic_score_gemma":0.0003059597,"domain_scores_codex":[0.9988052,0.0001995553,0.0005497492,0.0002892302,0.00006732611,0.00008890524],"domain_scores_gemma":[0.9990286,0.00006778146,0.0003549296,0.0004104779,0.0001245122,0.00001369803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005651321,0.00009485918,0.0007129841,0.002636775,0.000192744,0.000007149062,0.0001602897,0.000006158371,0.002585751,0.002123285,0.0002135614,0.9912099],"study_design_scores_gemma":[0.005886228,0.004216243,0.10601,0.0181773,0.004071729,0.00254646,0.001991064,0.001001611,0.0002041549,0.009181499,0.8453983,0.001315348],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0140739,0.9811813,0.003697111,0.0003276221,0.00006879471,0.0003705227,0.0002674,3.878812e-7,0.0000130123],"genre_scores_gemma":[0.05019344,0.9480033,0.001256417,0.00003128624,0.00005428867,0.0000139264,0.0004384279,0.000007260654,0.00000167913],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9898946,"threshold_uncertainty_score":0.4121266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07098642829199277,"score_gpt":0.3641377826789152,"score_spread":0.2931513543869224,"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."}}