{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001578117,0.0001192078,0.00008475856,0.00004072509,0.0001072987,0.0000540484,0.0001121023,0.0001410647,0.000007783301],"category_scores_gemma":[0.0001533825,0.0001100757,0.00007707319,0.0001055084,0.00004945567,0.000002320897,0.00004257015,0.0002715105,0.000003639796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000160814,"about_ca_system_score_gemma":0.00004306571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002374043,"about_ca_topic_score_gemma":0.00001436039,"domain_scores_codex":[0.9992023,0.00002727779,0.0001532393,0.0003830325,0.00007340775,0.0001607337],"domain_scores_gemma":[0.9997113,0.00001976007,0.00003932414,0.0001251541,0.00007561158,0.0000288265],"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":[0.00003954232,0.00000590087,0.001483911,0.00005735064,0.00004724263,0.000002423698,0.0001138241,0.001597121,0.8025932,0.000884457,0.00008938068,0.1930857],"study_design_scores_gemma":[0.00007294684,0.0002374502,0.0005400952,0.00009094689,0.00002050303,0.00008683788,0.0001798009,0.01340425,0.949761,0.005695348,0.02964293,0.0002678909],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.893343,0.01343659,0.09065618,0.0004263757,0.0008674738,0.0004504424,0.00002306927,0.00002726526,0.0007696227],"genre_scores_gemma":[0.9924271,0.0003298628,0.006025902,0.00005449641,0.0003810144,0.00006043492,0.00004824956,0.00001690487,0.0006560138],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1928178,"threshold_uncertainty_score":0.4488758,"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."}}