{"id":"W2104239076","doi":"10.1186/1471-2105-10-241","title":"Multi-level learning: improving the prediction of protein, domain and residue interactions by allowing information flow between levels","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institutes of Health; Yale University","keywords":"Computer science; Computational biology; Domain (mathematical analysis); DNA microarray; Bioinformatics; Chemistry; Biology; Biochemistry; Mathematics; Gene expression; Gene","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":[],"consensus_categories":[],"category_scores_codex":[0.0002409665,0.0001338313,0.0001212422,0.00004936404,0.000171872,0.00005519395,0.0001319089,0.0001361583,0.000001582187],"category_scores_gemma":[0.0001817023,0.0001020645,0.00005238255,0.00007944523,0.00005653496,0.00007330669,0.00007109875,0.000177553,0.000001661354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001541125,"about_ca_system_score_gemma":0.00005664587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001146127,"about_ca_topic_score_gemma":0.00001229482,"domain_scores_codex":[0.9991508,0.00003552597,0.0004329565,0.00008358969,0.000137412,0.0001596969],"domain_scores_gemma":[0.9993826,0.0000165672,0.0002595907,0.0002075774,0.00008691147,0.00004672824],"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":[0.0002049132,0.00007882732,0.01124616,0.0006688409,0.0002101,3.470432e-7,0.005442322,0.00356731,0.5308749,0.0003271886,0.001457894,0.4459212],"study_design_scores_gemma":[0.004746118,0.001567645,0.13814,0.0002905822,0.0001860941,0.00006874961,0.005079681,0.5635317,0.2473544,0.0007157998,0.03725591,0.001063328],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.259362,0.000074184,0.7395201,0.00007781512,0.00004688681,0.0004629807,0.0001986015,0.00002194334,0.0002354302],"genre_scores_gemma":[0.7696154,0.0000144955,0.2295667,0.0001102689,0.00007274617,0.00001458651,0.0004763258,0.000007454878,0.0001220704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5599644,"threshold_uncertainty_score":0.416207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01712045424852498,"score_gpt":0.240373284226945,"score_spread":0.2232528299784201,"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."}}