{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01380726,0.001508389,0.001271719,0.003661652,0.001010246,0.002536806,0.002937224,0.001326895,0.003161984],"category_scores_gemma":[0.02540974,0.0009146507,0.001737645,0.002833786,0.0006866434,0.00426972,0.002652566,0.002425856,0.002418639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001150017,"about_ca_system_score_gemma":0.001665928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003086838,"about_ca_topic_score_gemma":0.004261657,"domain_scores_codex":[0.9933425,0.002034225,0.0008444428,0.00137045,0.002003409,0.0004050817],"domain_scores_gemma":[0.9815043,0.01125823,0.0009046011,0.001650857,0.003929174,0.0007528909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.009527728,0.001145541,0.0774393,0.007922045,0.001863855,0.0006344871,0.003309709,0.02197862,0.1643254,0.01513414,0.07737858,0.6193406],"study_design_scores_gemma":[0.001428181,0.004427981,0.07834597,0.001506245,0.001575393,0.004854215,0.003504972,0.2513191,0.3199044,0.02209054,0.3098082,0.001234874],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6572752,0.01542169,0.2557399,0.003210648,0.001002664,0.00036198,0.01114684,0.04308859,0.01275249],"genre_scores_gemma":[0.3163734,0.003834511,0.6391801,0.0007946076,0.0001268797,0.0003007212,0.02889147,0.00820487,0.002293446],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01380726,"threshold_uncertainty_score":0.0730207,"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."}}