{"id":"W4405515214","doi":"10.1038/s42256-024-00935-2","title":"Leveraging ancestral sequence reconstruction for protein representation learning","year":2024,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"University of British Columbia; Australian National University","keywords":"Sequence (biology); Embedding; Computer science; Representation (politics); Protein sequencing; Artificial intelligence; Machine learning; Sequence learning; Sequence space; Peptide sequence; Biology; Mathematics; Genetics","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":[0.002081222,0.000846905,0.001355377,0.00222871,0.0008273622,0.00174193,0.002346148,0.001910248,0.003633747],"category_scores_gemma":[0.00942672,0.0007194833,0.001566095,0.002497641,0.001179544,0.004099468,0.002707721,0.003613549,0.001809323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007624933,"about_ca_system_score_gemma":0.001062131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001652662,"about_ca_topic_score_gemma":0.002396439,"domain_scores_codex":[0.9989697,0.0003395082,0.00006511537,0.000314401,0.0002085525,0.00010281],"domain_scores_gemma":[0.9960324,0.001943329,0.0002119782,0.001296363,0.0003788438,0.000137108],"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":[0.0009286545,0.0003784148,0.01089114,0.0004178309,0.0004286581,0.0006136001,0.0004042886,0.2972302,0.02649548,0.06402303,0.008053266,0.5901354],"study_design_scores_gemma":[0.00001581214,0.0000472681,0.0003872442,0.00001956435,0.00003838276,0.0001290314,0.00003694361,0.9339176,0.003142319,0.06092272,0.001327235,0.00001583014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0759289,0.000923982,0.9164014,0.0007325458,0.0001116135,0.00005091618,0.0007108821,0.003149569,0.001990312],"genre_scores_gemma":[0.6551138,0.000955496,0.3368546,0.0003515358,0.0001665799,0.0001038354,0.004075677,0.0005382586,0.001840155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003633747,"threshold_uncertainty_score":0.01215607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02392669229963933,"score_gpt":0.3233806238014653,"score_spread":0.2994539315018259,"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."}}