{"id":"W4225152409","doi":"10.1101/2022.04.27.489750","title":"Ligand Binding Prediction using Protein Structure Graphs and Residual Graph Attention Networks","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Canadian Institutes of Health Research; Dell Technologies","keywords":"Pooling; Computer science; Ligand (biochemistry); Drug discovery; Graph; Computational biology; Protein ligand; Machine learning; Artificial intelligence; Chemistry; Biology; Theoretical computer science; Biochemistry; Receptor","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005785068,0.001136939,0.0008243062,0.001644237,0.0002312942,0.0007147422,0.001011308,0.001053144,0.002183494],"category_scores_gemma":[0.001871588,0.0003567944,0.0006983645,0.0009995031,0.0004879455,0.0007679822,0.0007369315,0.0009083235,0.0006983066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001085186,"about_ca_system_score_gemma":0.0007649238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0124523,"about_ca_topic_score_gemma":0.01249303,"domain_scores_codex":[0.9996558,0.0001053069,0.000009960076,0.0001155456,0.00007121293,0.00004200718],"domain_scores_gemma":[0.9992825,0.0004375371,0.00007954113,0.00005784759,0.00009602034,0.00004655825],"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":[0.0001691323,0.0001028672,0.001627996,0.00012039,0.00007962857,0.00007743065,0.0000201312,0.9072059,0.004639797,0.003374031,0.003976776,0.07860595],"study_design_scores_gemma":[0.000003568878,0.000008551835,0.000125481,0.00000225507,0.00000422001,0.000004805144,0.000001350443,0.9973232,0.0004977623,0.001882369,0.0001448215,0.000001711366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1956553,0.003463455,0.7812824,0.001821863,0.0001071948,0.0001308536,0.001888721,0.008972912,0.006677355],"genre_scores_gemma":[0.9027523,0.000840912,0.08702081,0.0005117367,0.0001200355,0.0001044904,0.003589587,0.0002445732,0.004815674],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0124523,"threshold_uncertainty_score":0.02475965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01694935738318138,"score_gpt":0.24241836991167,"score_spread":0.2254690125284886,"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."}}