{"id":"W4366215728","doi":"10.22541/au.168170992.27078535/v1","title":"Improving Protein Structure Prediction with Extended Sequence Similarity Searches and Deep-Learning-Based Refinement in CASP15","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; RIKEN; DeepMind","keywords":"Similarity (geometry); Artificial intelligence; Sequence (biology); Computer science; Deep learning; Protein structure prediction; Machine learning; Pattern recognition (psychology); Protein structure; Biology; Genetics","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":[0.004716553,0.001517373,0.001696446,0.001037337,0.0005555527,0.001105035,0.002378594,0.001494963,0.001823295],"category_scores_gemma":[0.009082062,0.0006353144,0.001297812,0.0007408547,0.0005593714,0.002103323,0.002007359,0.002223457,0.001130893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001127013,"about_ca_system_score_gemma":0.001883207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006635032,"about_ca_topic_score_gemma":0.006949176,"domain_scores_codex":[0.9980819,0.0006609975,0.0001419731,0.000419001,0.0004359795,0.0002602556],"domain_scores_gemma":[0.9972534,0.001262672,0.0001514318,0.0004379406,0.0006028534,0.0002917347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003197936,0.001530317,0.0309955,0.0007974635,0.0006802604,0.0005990887,0.0005512898,0.5189603,0.03512611,0.004856477,0.03409102,0.3686142],"study_design_scores_gemma":[0.0001330152,0.0002735994,0.00172019,0.00002862168,0.00004655213,0.00005688737,0.0000692583,0.9853932,0.00943138,0.00160253,0.001219442,0.00002532287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8849558,0.002563261,0.09335536,0.001076933,0.0003128308,0.0001637869,0.001212165,0.01261798,0.003741924],"genre_scores_gemma":[0.8575509,0.0003521374,0.1331181,0.0005407798,0.00006192229,0.0001167992,0.006155962,0.0006192327,0.001484251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006635032,"threshold_uncertainty_score":0.02494383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01862041375343037,"score_gpt":0.2679550432471968,"score_spread":0.2493346294937664,"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."}}