{"id":"W3003647270","doi":"10.1186/s12859-019-3190-x","title":"DeepECA: an end-to-end learning framework for protein contact prediction from a multiple sequence alignment","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; University of Tokyo; Japan Agency for Medical Research and Development","keywords":"End-to-end principle; Computational biology; Sequence (biology); Computer science; Sequence alignment; Multiple sequence alignment; DNA microarray; Artificial intelligence; Biology; Bioinformatics; Peptide sequence; Genetics; Gene","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":[],"consensus_categories":[],"category_scores_codex":[0.000110574,0.0001921257,0.0001704936,0.00002273312,0.0001261032,0.00006406996,0.0002199149,0.0002443977,0.00001451904],"category_scores_gemma":[0.0005029165,0.000181062,0.00008304913,0.00007714004,0.00002833423,0.00002108817,0.0001055818,0.0001555754,0.0000126587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002841247,"about_ca_system_score_gemma":0.00009622744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002350267,"about_ca_topic_score_gemma":0.0000362433,"domain_scores_codex":[0.998937,0.00003268576,0.0003445275,0.000246991,0.0001758662,0.0002629077],"domain_scores_gemma":[0.9992528,0.00002768632,0.0001555471,0.00027346,0.00006914811,0.0002213489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001569748,0.0001036728,0.01403006,0.0005332998,0.0002446899,0.000003471056,0.005397214,0.01802188,0.9201289,0.003977317,0.0005093218,0.0354804],"study_design_scores_gemma":[0.001816253,0.003077398,0.001609274,0.0001183181,0.00007126474,0.000007107616,0.001652633,0.7597227,0.1981254,0.001987174,0.03110752,0.0007049225],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2096756,0.00004245005,0.7887017,0.0000983298,0.00007637683,0.0008991326,0.0003835119,0.00004757705,0.00007536454],"genre_scores_gemma":[0.5575662,0.000007006741,0.4404659,0.0006489587,0.000272847,0.0001121165,0.0008928403,0.00001816936,0.00001591153],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7417008,"threshold_uncertainty_score":0.7383494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02276428842485458,"score_gpt":0.258106808117291,"score_spread":0.2353425196924364,"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."}}