{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004893943,0.0003389636,0.0002490042,0.0001315475,0.00009685838,0.0001036893,0.0002250123,0.0005025284,0.00002161233],"category_scores_gemma":[0.0003613627,0.0002841299,0.00004306802,0.0001074359,0.0001216506,0.000005345427,0.0006463088,0.001191384,0.000001257647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007596279,"about_ca_system_score_gemma":0.0002766531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006374312,"about_ca_topic_score_gemma":0.002048126,"domain_scores_codex":[0.9982265,0.0001625665,0.0003565154,0.0006153288,0.0003041759,0.0003349231],"domain_scores_gemma":[0.99905,0.0000186474,0.0002388301,0.0004818611,0.0001172902,0.00009339058],"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":[0.001151839,0.0002013862,0.1321763,0.007955726,0.0003691014,0.0001046029,0.001045552,0.4691261,0.3531902,0.0001375036,0.0003021419,0.03423953],"study_design_scores_gemma":[0.002202155,0.001765686,0.04980976,0.000645759,0.00007345866,0.00003627885,0.0004512885,0.879227,0.06252454,0.0003374912,0.001737634,0.001188962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.975234,0.0001071312,0.02225776,0.0004468615,0.00007924611,0.001318222,0.000103576,0.0001449188,0.0003082667],"genre_scores_gemma":[0.9723578,0.00003271474,0.02541015,0.00008504908,0.00007895174,0.0001200237,0.001198403,0.00005126687,0.0006656246],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4101008,"threshold_uncertainty_score":0.9999611,"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."}}