{"id":"W4296293027","doi":"10.1016/j.csbj.2022.08.070","title":"Protein–protein interaction prediction with deep learning: A comprehensive review","year":2022,"lang":"en","type":"review","venue":"Computational and Structural Biotechnology Journal","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":181,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Computational biology; Protein–protein interaction; Protein ligand; Drug discovery; Function (biology); Computer science; Protein function; Protein function prediction; Deep learning; Machine learning; Artificial intelligence; Bioinformatics; Biology; Biochemistry; Genetics; 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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0004212502,0.0005787066,0.001242057,0.0006831783,0.0009208736,0.0003026075,0.0009709541,0.0003078285,0.00009957597],"category_scores_gemma":[0.0001527135,0.0004333589,0.0003004443,0.001032121,0.0002352549,0.0006727837,0.0006905619,0.003005581,0.000009935009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000349721,"about_ca_system_score_gemma":0.0004651511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002719464,"about_ca_topic_score_gemma":4.411696e-7,"domain_scores_codex":[0.996172,0.000995007,0.0009503487,0.000802775,0.0007102577,0.00036965],"domain_scores_gemma":[0.9976541,0.0004299944,0.001239909,0.0002911302,0.0002369185,0.0001479819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001117312,0.00001268278,6.861362e-7,0.003612556,0.0002066866,0.00008841775,0.00002693279,0.005121887,0.000001430122,0.007970766,0.00005103843,0.9828957],"study_design_scores_gemma":[0.0003661412,0.0005981367,0.00003136067,0.0100129,0.0002040113,0.02070601,0.00002597424,0.04148656,0.000001908965,0.01685452,0.9091475,0.0005650077],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001229479,0.8688341,0.1281834,0.001298389,0.0003319236,0.0009636508,0.00001587407,0.0002211439,0.00002858101],"genre_scores_gemma":[0.0001104458,0.9438502,0.05541801,0.0001336179,0.0001261481,0.0001318967,0.0001595848,0.00003419786,0.00003592333],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9823307,"threshold_uncertainty_score":0.9998118,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03781696936285747,"score_gpt":0.3257655430372404,"score_spread":0.287948573674383,"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."}}