{"id":"W4391613724","doi":"10.26434/chemrxiv-2023-d0dqp-v2","title":"Graph Neural Networks for Identifying Protein-Reactive Compounds","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Nvidia","keywords":"Interpretability; chEMBL; Computer science; Covalent bond; Machine learning; DrugBank; Non-covalent interactions; Cheminformatics; Artificial intelligence; Convolutional neural network; Chemistry; Drug discovery; Computational biology; Molecule; Computational chemistry; Biochemistry; Biology; Drug","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":[0.0006884207,0.001202083,0.0004705444,0.001955216,0.0002413922,0.000599655,0.0007158844,0.0008862274,0.001476306],"category_scores_gemma":[0.002755871,0.0002990981,0.0006942085,0.001169764,0.0003883672,0.0008681774,0.0004019586,0.000918404,0.0004669052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001295683,"about_ca_system_score_gemma":0.0006741545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01104024,"about_ca_topic_score_gemma":0.01080074,"domain_scores_codex":[0.9996905,0.00007750674,0.00001799241,0.0001000646,0.00008123644,0.00003267557],"domain_scores_gemma":[0.9991404,0.0005061858,0.0001307155,0.00005776913,0.0001450543,0.00001986905],"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":[0.0002205597,0.0001458222,0.005961262,0.0002279596,0.000127218,0.0001023009,0.00004653127,0.8275755,0.009163924,0.005343692,0.002944051,0.1481411],"study_design_scores_gemma":[0.00000563865,0.00002721458,0.0005371302,0.000007671146,0.00001188052,0.00001356916,0.00000638542,0.9940736,0.001830872,0.002890492,0.0005903954,0.000005145823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2688245,0.004640342,0.7082212,0.001113003,0.0001689442,0.000299287,0.003159743,0.006210334,0.007362769],"genre_scores_gemma":[0.7991722,0.001460042,0.1908727,0.0003504165,0.00007758031,0.0002139424,0.003696333,0.0001305941,0.004026204],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01104024,"threshold_uncertainty_score":0.02195197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06324903041155919,"score_gpt":0.3464212828698672,"score_spread":0.283172252458308,"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."}}