{"id":"W4389070743","doi":"10.1101/2023.11.27.568841","title":"Discovering Secondary Protein Structures via Local Euler Curvature","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke","funders":"Ministerio de Ciencia e Innovación; Agencia Estatal de Investigación; Basque Center for Applied Mathematics; Eusko Jaurlaritza","keywords":"Cluster analysis; Computer science; Euler characteristic; Classifier (UML); Curvature; Topological data analysis; Protein secondary structure; Artificial intelligence; Topology (electrical circuits); Protein structure; Protein structure prediction; Theoretical computer science; Mathematics; Biology; Algorithm; Geometry","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":[0.0006001779,0.0007365195,0.0008181835,0.0007176636,0.0002632258,0.0008373461,0.003157853,0.0007653731,0.0001137925],"category_scores_gemma":[0.0003209735,0.0006400074,0.0003408318,0.002670176,0.0002121227,0.0005907096,0.004438694,0.001750347,0.0002626741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002052074,"about_ca_system_score_gemma":0.0004090866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002775009,"about_ca_topic_score_gemma":0.00001127999,"domain_scores_codex":[0.9955768,0.0001756211,0.0006540627,0.001943862,0.0007788163,0.0008708583],"domain_scores_gemma":[0.996097,0.00011837,0.0004456977,0.002668277,0.0002779088,0.000392773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001998035,0.001696539,0.01650931,0.005872153,0.007421769,0.005929273,0.0002474072,0.01719552,0.6919112,0.2268494,0.02383907,0.00232852],"study_design_scores_gemma":[0.001983742,0.0003988002,0.5807816,0.001186835,0.0005125476,2.602681e-7,0.00001795578,0.04164911,0.2864765,0.002882879,0.07569162,0.008418133],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1755842,0.001420259,0.8161869,0.00118941,0.002537078,0.0007154708,0.0005655204,0.001786273,0.00001491911],"genre_scores_gemma":[0.9768128,0.00006120557,0.02210089,0.0002539621,0.0004966395,0.0001568963,0.000001735558,0.00007911745,0.00003673391],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8012286,"threshold_uncertainty_score":0.9996051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01493476766963643,"score_gpt":0.2185472064016578,"score_spread":0.2036124387320214,"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."}}