{"id":"W2950355818","doi":"10.48550/arxiv.1307.7798","title":"Towards Reliable Automatic Protein Structure Alignment","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Similarity (geometry); Consistency (knowledge bases); Structural alignment; Computer science; Multiple sequence alignment; Sequence (biology); Structural similarity; Pattern recognition (psychology); Sequence alignment; Artificial intelligence; Algorithm; Local structure; Mathematics; Data mining; Biology; Peptide sequence; Image (mathematics); Crystallography","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001301795,0.0003788312,0.0002872917,0.00008806727,0.0001035226,0.00007073977,0.0007437931,0.000606958,0.0003599148],"category_scores_gemma":[0.00006665685,0.00039392,0.0001704388,0.0001159858,0.00009920495,0.000008433446,0.001341693,0.0005194125,0.0001027666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001013935,"about_ca_system_score_gemma":0.0002145195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001687246,"about_ca_topic_score_gemma":0.0000175172,"domain_scores_codex":[0.9985864,0.0000816353,0.0002540266,0.0006200898,0.0001052033,0.0003526275],"domain_scores_gemma":[0.9983057,0.000005162908,0.0003232273,0.001095843,0.0001212683,0.0001488167],"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":[0.0001715998,0.0003396536,0.007280609,0.003300432,0.001420986,0.0001360697,0.0005905018,0.852981,0.05608631,0.02869201,0.04523495,0.0037659],"study_design_scores_gemma":[0.002377199,0.0007756785,0.002691485,0.0006658835,0.0003844936,0.00003638267,0.0003442858,0.8382855,0.05405023,0.03187446,0.06545959,0.003054803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.97855,0.00005724128,0.01326338,0.00007341493,0.0002710106,0.0007851685,0.00005645225,0.00008919507,0.006854121],"genre_scores_gemma":[0.9867114,0.00005438331,0.004477238,0.0001327797,0.0001346158,0.000004315088,0.0003597333,0.00004029635,0.008085184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02022464,"threshold_uncertainty_score":0.9998513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01887520051879708,"score_gpt":0.1820648219013108,"score_spread":0.1631896213825137,"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."}}