{"id":"W4390115367","doi":"10.26434/chemrxiv-2023-z3t3b","title":"Machine Learning Guided AQFEP: A Fast & Efficient Absolute Free Energy Perturbation Solution for Virtual Screening","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Virtual screening; Drug discovery; Workflow; Free energy perturbation; Computer science; Chemical space; Perturbation (astronomy); Machine learning; Data mining; Chemistry; Computational chemistry; Physics; Molecular dynamics","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"],"consensus_categories":[],"category_scores_codex":[0.001307186,0.0004528835,0.0004466866,0.0004553583,0.000318415,0.0003751689,0.001662327,0.0002896654,0.0000225236],"category_scores_gemma":[0.001345057,0.0004984136,0.0003659297,0.000485582,0.00006648419,0.0001590011,0.003411065,0.0005051614,0.00005381206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002330329,"about_ca_system_score_gemma":0.0002238277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002443713,"about_ca_topic_score_gemma":0.00005851518,"domain_scores_codex":[0.9966701,0.000256573,0.0006098201,0.00127311,0.0006602635,0.0005301035],"domain_scores_gemma":[0.9971176,0.0008302715,0.0005020321,0.001119718,0.000278052,0.000152377],"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":[0.00002014573,0.00005901924,0.0000214977,0.00007649243,0.00009190155,0.000003526109,0.0005261103,0.9261191,0.0009484302,0.03526768,0.004081905,0.0327842],"study_design_scores_gemma":[0.0005487052,0.00003760907,0.0004771861,0.0001667509,0.00002854351,0.000007082244,0.00000872274,0.971042,0.0006622174,0.01593447,0.01058686,0.0004998182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003004315,0.0002455815,0.9913809,0.001356648,0.001480999,0.0003902788,0.00001762344,0.0009601269,0.001163542],"genre_scores_gemma":[0.1236269,0.00004795042,0.8404407,0.0002657598,0.00100505,0.0005209263,0.0009486657,0.0002643648,0.03287968],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1509402,"threshold_uncertainty_score":0.9997467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07650502705876047,"score_gpt":0.3178990604235101,"score_spread":0.2413940333647496,"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."}}