{"id":"W4389616450","doi":"10.1080/07391102.2023.2291829","title":"DeepCompoundNet: enhancing compound–protein interaction prediction with multimodal convolutional neural networks","year":2023,"lang":"en","type":"article","venue":"Journal of Biomolecular Structure and Dynamics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Protein–protein interaction; Computer science; Interaction network; Convolutional neural network; Machine learning; Artificial neural network; Artificial intelligence; Drug discovery; Interaction information; Virtual screening; Computational biology; Similarity (geometry); Chemistry; Bioinformatics; Biology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002999947,0.0001594602,0.0002040816,0.0002847587,0.0001444081,0.0002167413,0.0002589157,0.00007742711,0.000002116375],"category_scores_gemma":[0.00003192455,0.0001303656,0.00007758581,0.0005502215,0.00006852634,0.0006602646,0.0001154046,0.0003157056,4.608561e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001240158,"about_ca_system_score_gemma":0.00008766056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001243338,"about_ca_topic_score_gemma":0.00003066369,"domain_scores_codex":[0.9986407,0.0001508602,0.0003756821,0.0002164388,0.0004168118,0.0001995099],"domain_scores_gemma":[0.9990654,0.0001246938,0.0003301824,0.0001461685,0.0002294011,0.0001041419],"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":[0.000201912,0.00003367357,0.00141687,0.00003051498,0.0001603163,0.0002839951,0.0002745651,0.9471108,0.01944566,0.009604678,0.00004073318,0.02139633],"study_design_scores_gemma":[0.0005468925,0.0002301418,0.01323474,0.00004908596,0.0000191526,0.001365475,0.00005185338,0.9801445,0.0005677231,0.003627919,0.00003540976,0.0001270963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4429494,0.00005543186,0.5563279,0.0001853468,0.0003802607,0.00006063059,0.000006973024,0.00002627332,0.000007844953],"genre_scores_gemma":[0.9496742,0.000006425696,0.05002581,0.000080809,0.0001625602,0.000001105037,0.00003161886,0.00001152656,0.000005876099],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5067249,"threshold_uncertainty_score":0.5316155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005986660746759368,"score_gpt":0.247958487273745,"score_spread":0.2419718265269857,"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."}}