{"id":"W4286632253","doi":"10.21203/rs.3.rs-1775089/v1","title":"EDLMPPI: Learning the Protein Language of Proteome-wide Protein-protein Binding Sites via Explainable Ensemble Deep Learning","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Hong Kong Institute for Data Science; Shenzhen Research Institute, City University of Hong Kong; Food and Health Bureau; People's Government of Jilin Province; National Natural Science Foundation of China; Natural Science Foundation of Jilin Province; Health and Medical Research Fund; City University of Hong Kong","keywords":"Computer science; Ensemble learning; Artificial intelligence; Machine learning; Generalization; Identification (biology); Protein–protein interaction; Deep learning; Computational biology; Biology; Mathematics; Biochemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000893647,0.0009252318,0.0007844674,0.0007282333,0.0002868259,0.000650226,0.001617046,0.00100244,0.001639744],"category_scores_gemma":[0.001916799,0.0004905181,0.0007864566,0.0007420601,0.0004170974,0.00137578,0.001318916,0.002136947,0.000490347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000749635,"about_ca_system_score_gemma":0.0007453031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005320224,"about_ca_topic_score_gemma":0.00588183,"domain_scores_codex":[0.9996904,0.00009047706,0.00001203762,0.0001018579,0.0000626236,0.00004272726],"domain_scores_gemma":[0.9993846,0.0003102914,0.00007142143,0.00008622556,0.0001012049,0.00004632343],"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":[0.000156115,0.0001801072,0.002304642,0.00008465641,0.0001670941,0.0001306959,0.00003738578,0.8774261,0.005679109,0.004142707,0.004974604,0.1047168],"study_design_scores_gemma":[0.000002311226,0.00000588597,0.00005388924,0.000001190274,0.000002600282,0.000003526562,0.000001110971,0.9983298,0.0003071109,0.001214979,0.00007614363,0.000001373319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1270129,0.00107841,0.8641377,0.0007245541,0.00009175557,0.00005201711,0.0008218464,0.004412859,0.001667881],"genre_scores_gemma":[0.859324,0.0004573243,0.1325523,0.0005090019,0.00008770224,0.0001328153,0.002704903,0.0002344535,0.003997548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005320224,"threshold_uncertainty_score":0.01057851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04870068993852016,"score_gpt":0.374562041787905,"score_spread":0.3258613518493849,"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."}}