{"id":"W3177472573","doi":"10.1101/2021.06.20.449169","title":"High-accuracy alignment ensembles enable unbiased assessments of sequence homology and phylogeny","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":162,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of British Columbia","keywords":"Phylogenetic tree; Phylogenetics; Inference; Polyphyly; Computer science; Multiple sequence alignment; Tree (set theory); Hidden Markov model; Computational biology; Biology; Artificial intelligence; Evolutionary biology; Sequence alignment; Mathematics; Clade; Genetics; Combinatorics; Gene","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003153529,0.0004732753,0.0006210991,0.00008435648,0.0001128549,0.00007457393,0.0003752621,0.0004725049,0.00001271237],"category_scores_gemma":[0.0001496874,0.0005194116,0.0001320956,0.0001252167,0.000225254,0.000002448454,0.001090894,0.0002232626,0.000001628818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005549655,"about_ca_system_score_gemma":0.0005380063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001818806,"about_ca_topic_score_gemma":0.000009124235,"domain_scores_codex":[0.9976777,0.000159478,0.0004999672,0.001020066,0.0002019648,0.0004408014],"domain_scores_gemma":[0.9978779,0.00004274069,0.0004494801,0.001067137,0.0004083055,0.0001544614],"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":[0.00002921702,0.0001070347,0.00664947,0.0002427646,0.0004420558,0.00002749662,0.000007714077,0.000119823,0.9921516,0.0001343792,0.00008113619,0.000007311079],"study_design_scores_gemma":[0.0004902972,0.0001826989,0.04375839,0.0001019327,0.0001274222,9.696811e-8,0.00001381858,0.00002527665,0.9529222,0.00000712396,0.00186204,0.0005087046],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9910601,0.006982789,0.0005074799,0.00005565296,0.0006220085,0.000400463,0.0003513065,0.00001198844,0.000008203565],"genre_scores_gemma":[0.9849307,0.004525225,0.00994933,0.0001640304,0.0002279173,0.0001234696,0.000003751188,0.00006830881,0.000007292524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0392294,"threshold_uncertainty_score":0.9997258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01917017094318144,"score_gpt":0.2490745188194095,"score_spread":0.229904347876228,"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."}}