{"id":"W4385611353","doi":"10.1101/2023.08.03.551827","title":"A Multimodal Deep Learning Framework for Predicting PPI-Modulator Interactions","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Deep learning; Machine learning","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":[0.0009029714,0.001253484,0.0008950437,0.0009814084,0.0003233837,0.0006468857,0.001392997,0.001257634,0.002220032],"category_scores_gemma":[0.001635949,0.0004445581,0.0006039258,0.0007677978,0.0004826091,0.0009151442,0.001146767,0.00162684,0.0004343805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001131852,"about_ca_system_score_gemma":0.001122604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006693466,"about_ca_topic_score_gemma":0.006682921,"domain_scores_codex":[0.9997151,0.00008142668,0.00001137399,0.0000837148,0.00005273531,0.0000555934],"domain_scores_gemma":[0.9996191,0.0001671775,0.00005496549,0.00002802927,0.00007445268,0.00005623216],"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":[0.0003112202,0.0002627368,0.003371216,0.00008465454,0.0001309373,0.000120422,0.00002741331,0.8835112,0.005449371,0.002461882,0.004014732,0.1002542],"study_design_scores_gemma":[0.000004199877,0.00001730464,0.00007434087,0.000001682992,0.000004068456,0.000003626443,0.000001312997,0.9988065,0.0003578878,0.0006374149,0.00009010082,0.000001630182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.262397,0.004192008,0.719906,0.001819258,0.0001241281,0.0001495513,0.001422871,0.004941192,0.005047902],"genre_scores_gemma":[0.9389995,0.0004267129,0.05550573,0.0004599296,0.00007659505,0.0001150605,0.001567504,0.0000703959,0.0027785],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006693466,"threshold_uncertainty_score":0.013309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03048095216962918,"score_gpt":0.2984528743347891,"score_spread":0.26797192216516,"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."}}