{"id":"W3160244225","doi":"10.26434/chemrxiv.14045072.v1","title":"A Bag of Tricks for Automated De Novo Design of Molecules with the Desired Properties: Application to EGFR Inhibitor Discovery","year":2021,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Chemistry; Office of Naval Research; Ministero dello Sviluppo Economico; Genome Canada; Fundação de Amparo à Pesquisa do Estado de São Paulo; Ontario Ministry of Economic Development and Innovation; Directorate for Mathematical and Physical Sciences; Merck KGaA; Novartis Pharma; Nvidia; Pfizer; National Institutes of Health; National Science Foundation","keywords":"Reinforcement learning; Computer science; Generative grammar; Artificial intelligence; Deep neural networks; Artificial neural network; Machine learning; Generative model; Deep learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001281159,0.0005569878,0.0006681599,0.0002946586,0.0002835577,0.0005568542,0.0008922725,0.001004867,0.002100722],"category_scores_gemma":[0.003293175,0.0004342207,0.0006150728,0.0003003402,0.00103405,0.0008551226,0.001235119,0.001521297,0.0005335161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004375142,"about_ca_system_score_gemma":0.0007194679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006441931,"about_ca_topic_score_gemma":0.0008554356,"domain_scores_codex":[0.999652,0.0001188576,0.00001950181,0.00006624981,0.0001136551,0.00002967164],"domain_scores_gemma":[0.9990296,0.0005497252,0.0001268403,0.0001641105,0.0000726844,0.00005709489],"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":[0.0002572052,0.0002599,0.001021529,0.0002428334,0.00008998443,0.0002030838,0.00009492711,0.680883,0.02541432,0.06590837,0.003546473,0.2220783],"study_design_scores_gemma":[0.00004017114,0.00007339795,0.0000821764,0.000007976589,0.00001231607,0.00004498148,0.000003579408,0.9806271,0.003484091,0.01389145,0.001722124,0.00001064728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02413975,0.0003151383,0.9717286,0.00048251,0.00005021942,0.0000507045,0.00005302593,0.0009104079,0.002269641],"genre_scores_gemma":[0.4845472,0.0004654043,0.5096148,0.0003727622,0.00006368258,0.0002284985,0.0001414429,0.0001976957,0.004368597],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002100722,"threshold_uncertainty_score":0.007027686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04152736925203047,"score_gpt":0.2898238147006849,"score_spread":0.2482964454486544,"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."}}