{"id":"W4406170484","doi":"10.1093/bioinformatics/btaf009","title":"BetaAlign: a deep learning approach for multiple sequence alignment","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Tel Aviv University; Azrieli Foundation; Israel Science Foundation","keywords":"Computer science; Artificial intelligence; Inference; Subspace topology; Multiple sequence alignment; Chunking (psychology); Sequence (biology); Sequence alignment; Smith–Waterman algorithm; Machine learning; Deep learning; Set (abstract data type); Phylogenomics; Phylogenetic tree; Biology","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":[0.0001644416,0.0001342984,0.0001081012,0.0000301152,0.0001074625,0.00006199322,0.0001224278,0.00008094261,0.000001962631],"category_scores_gemma":[0.00004809358,0.0001166422,0.00009991575,0.00004516691,0.00004218015,0.000001533437,0.00009057071,0.00004915073,0.000009871234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000155455,"about_ca_system_score_gemma":0.00003448657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002816155,"about_ca_topic_score_gemma":0.000001639912,"domain_scores_codex":[0.9993078,0.000009653517,0.0002162761,0.0001607067,0.00008353848,0.0002220782],"domain_scores_gemma":[0.9996881,0.00002098647,0.00004055247,0.0001594603,0.0000405688,0.00005027522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001523969,0.0001791587,0.003827035,0.002624943,0.001361817,0.000004852237,0.005952908,0.02840487,0.7735693,0.006507813,0.01000575,0.1674091],"study_design_scores_gemma":[0.000593079,0.0005373394,0.0002206489,0.00003018205,0.00008024334,0.00002967558,0.0009682571,0.5657169,0.04665251,0.0002778821,0.3843735,0.0005197847],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3387373,0.007902363,0.642973,0.0001419214,0.0006674665,0.001223708,0.0001655889,0.00006062881,0.008128027],"genre_scores_gemma":[0.9122586,0.0003225434,0.0862539,0.0001197459,0.000186536,0.00009816431,0.0002023948,0.00002029822,0.0005377987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7269168,"threshold_uncertainty_score":0.4756532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02501061628905633,"score_gpt":0.2544738749771737,"score_spread":0.2294632586881173,"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."}}