{"id":"W4386496033","doi":"10.1038/s41587-023-01917-2","title":"Protein remote homology detection and structural alignment using deep learning","year":2023,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":150,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Canadian Institute for Advanced Research","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Diabetes and Digestive and Kidney Diseases; Los Alamos National Laboratory; National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; University of California, San Diego; National Institute of Child Health and Human Development; Flatiron Health; Division of Chemical, Bioengineering, Environmental, and Transport Systems; Samsung Advanced Institute of Technology; Samsung; National Institutes of Health; National Science Foundation","keywords":"Sequence alignment; Computational biology; Sequence (biology); Protein superfamily; Similarity (geometry); Structural alignment; Homology modeling; Sequence homology; Computer science; Structural similarity; Alignment-free sequence analysis; Loop modeling; Homology (biology); Protein structure; Metric (unit); Structural motif; Artificial intelligence; Protein sequencing; Sequence motif; Peptide sequence; Biology; Protein structure prediction; Genetics; Amino acid; Gene; Image (mathematics); Biochemistry; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0006747748,0.0008902289,0.0008562445,0.00127205,0.0006930247,0.001063695,0.001441573,0.001351389,0.002210409],"category_scores_gemma":[0.001381407,0.0004571041,0.0006888815,0.001123539,0.0007775089,0.001709641,0.001436691,0.001786326,0.001267433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00127514,"about_ca_system_score_gemma":0.001085707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003738194,"about_ca_topic_score_gemma":0.005808735,"domain_scores_codex":[0.9995202,0.00008170753,0.00002408264,0.0001710105,0.0001248533,0.00007812634],"domain_scores_gemma":[0.9994991,0.0001695401,0.00009074342,0.00009668332,0.00008817989,0.00005568123],"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":[0.0006325669,0.0006805393,0.008399048,0.0003527571,0.0002096498,0.0002612807,0.000176622,0.289654,0.07203504,0.02343349,0.01578889,0.5883762],"study_design_scores_gemma":[0.00001481116,0.00004656223,0.0005590257,0.00001160411,0.000008539153,0.00005194902,0.00002051224,0.979419,0.009824934,0.008471678,0.001562578,0.000008881345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1842782,0.001639438,0.7967783,0.0007956093,0.0001046826,0.0001013346,0.001093846,0.009752792,0.005455836],"genre_scores_gemma":[0.6386313,0.0006560604,0.3514075,0.0005088071,0.00005441035,0.0001569087,0.004394826,0.0002385658,0.003951606],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003738194,"threshold_uncertainty_score":0.009251833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004179138652031465,"score_gpt":0.2407260761788087,"score_spread":0.2365469375267772,"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."}}