{"id":"W3093627059","doi":"10.1186/s12864-020-07132-6","title":"Progress in quickly finding orthologs as reciprocal best hits: comparing blast, last, diamond and MMseqs2","year":2020,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":92,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University","funders":"Natural Sciences and Engineering Research Council of Canada; Consejo Nacional de Ciencia y Tecnología","keywords":"Software; Genome; Bottleneck; Proteome; Pairwise comparison; Biology; Computer science; Reciprocal; Computational biology; Data mining; Bioinformatics; Gene; Genetics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001199544,0.0002110999,0.0002623409,0.00003818989,0.00009895528,0.00004404443,0.0001867015,0.0001328226,0.000002815073],"category_scores_gemma":[0.00005843927,0.0002220973,0.00005520146,0.00009081452,0.0001564413,0.000001540763,0.0004033538,0.0001240509,0.00001587595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001812188,"about_ca_system_score_gemma":0.0001111011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001661115,"about_ca_topic_score_gemma":0.0003717483,"domain_scores_codex":[0.9987818,0.00004094017,0.0002805843,0.0004952871,0.00007226065,0.0003291375],"domain_scores_gemma":[0.9995367,0.00001899643,0.00008721176,0.0001842736,0.00003689877,0.000135946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001954138,0.00006516307,0.8749669,0.00007036795,0.00005351298,0.00001180632,0.0009534908,0.0004195432,0.1194199,0.0001167466,0.0002037131,0.003523457],"study_design_scores_gemma":[0.008865655,0.003983451,0.6542751,0.0001474564,0.0002257075,0.0001818145,0.007288548,0.004382738,0.1616095,0.0007314744,0.155276,0.003032577],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9929838,0.005623132,0.0001580397,0.0002430047,0.00009298712,0.0002568637,0.00001557505,0.000005982228,0.0006206233],"genre_scores_gemma":[0.9959232,0.0005468656,0.00281854,0.000291902,0.0002680044,0.00003082035,0.00002430129,0.00003272731,0.00006366069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2206918,"threshold_uncertainty_score":0.9056863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03370238972089545,"score_gpt":0.2621904617598919,"score_spread":0.2284880720389965,"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."}}