{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001647927,0.001528213,0.0009932934,0.00120679,0.0007412448,0.001463287,0.00365262,0.001636036,0.004833415],"category_scores_gemma":[0.004479428,0.0007969995,0.0009965152,0.001636448,0.001203322,0.00310165,0.002520942,0.004736864,0.002571637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00123008,"about_ca_system_score_gemma":0.001693594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003012136,"about_ca_topic_score_gemma":0.004740356,"domain_scores_codex":[0.9989221,0.0002673159,0.00006254439,0.0003387267,0.0003276748,0.00008165227],"domain_scores_gemma":[0.9988114,0.0004628417,0.0001247107,0.000246635,0.0002631813,0.00009132938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004044347,0.0002973284,0.002557852,0.0005033058,0.0002210491,0.0002311576,0.0002299939,0.242138,0.02070656,0.0513835,0.03106604,0.6502608],"study_design_scores_gemma":[0.00002159784,0.00005824597,0.0001600942,0.00002401576,0.00001450465,0.00006685587,0.00002134526,0.9558259,0.007036903,0.0303025,0.00645511,0.00001289633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005891289,0.000507101,0.9816737,0.0003469687,0.00009050692,0.00007429576,0.0004086971,0.009477875,0.001529545],"genre_scores_gemma":[0.1064104,0.0006308818,0.8834686,0.0006491877,0.0001255492,0.0003123249,0.002975129,0.001246861,0.004181093],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004833415,"threshold_uncertainty_score":0.01616943,"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."}}