{"id":"W3042330596","doi":"10.1093/bioinformatics/btaa447","title":"EvoLSTM: context-dependent models of sequence evolution using a sequence-to-sequence LSTM","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Compute Canada; Genome Canada","keywords":"Sequence (biology); Context (archaeology); Computer science; Alignment-free sequence analysis; Inference; Mutation; Code (set theory); Probabilistic logic; Sequence learning; Artificial intelligence; Computational biology; Sequence alignment; Biology; Genetics; Peptide sequence; Programming language","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":[0.000145944,0.0002027824,0.0002601522,0.00004172906,0.00008767594,0.00002205381,0.0003179217,0.0001189774,0.000007369701],"category_scores_gemma":[0.0001000797,0.000196427,0.000111802,0.0001570084,0.0001146647,0.000007363326,0.0002566466,0.00007523883,0.0000210774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005488055,"about_ca_system_score_gemma":0.0002185453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007163588,"about_ca_topic_score_gemma":0.00001349545,"domain_scores_codex":[0.9987276,0.00002356176,0.0004938076,0.0002289139,0.0002369832,0.0002891891],"domain_scores_gemma":[0.9990702,0.00001004504,0.000197573,0.0003401171,0.0002138511,0.0001682218],"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":[0.00006500845,0.00002244702,0.0006165089,0.0001372153,0.0001096773,0.00000185263,0.001470153,0.02554191,0.9680844,0.0007433211,0.0002599669,0.002947524],"study_design_scores_gemma":[0.001574056,0.001567683,0.0004429134,0.0001521666,0.0001744468,0.00007604223,0.003761264,0.708689,0.2737079,0.001711808,0.006920125,0.001222588],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9219589,0.0009840488,0.07510369,0.0002052017,0.0001385129,0.00046111,0.0003071689,0.00001143693,0.0008299662],"genre_scores_gemma":[0.9773547,0.0001583423,0.0215771,0.0007412731,0.00009099991,0.00001130488,0.00002342402,0.00001654288,0.00002632873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6943766,"threshold_uncertainty_score":0.801006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0826937897695777,"score_gpt":0.2807156309608377,"score_spread":0.19802184119126,"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."}}