Synthesizability-constrained expansion and multi-objective evolution of antitubercular compounds

抗结核化合物的可合成性约束扩展和多目标进化

基本信息

批准号：
10430402
负责人：
Connor Wilson Coley
金额：
$ 19.73万
依托单位：
RBHS-NEW JERSEY MEDICAL SCHOOL
依托单位国家：
美国
项目类别：
财政年份：
2022
资助国家：
美国
起止时间：
2022-03-18 至 2023-02-28
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10430402
关键词：
Acyl Carrier Protein Address Age Algorithms Anabolism Antitubercular Agents Area Bacteria Bacterial Infections Biological Biological Assay COVID-19 pandemic Cell Wall Cessation of life Chemicals Communicable Diseases Complement Complex Data Data Set Development Docking Drug Kinetics Drug resistance Drug resistant Mycobacteria Tuberculosis Equilibrium Evaluation Evolution Genetic Programming Goals Growth In Vitro Infection Lead Libraries Ligands Machine Learning Microbiology Modeling Molecular Mus Mycobacterium tuberculosis Neural Network Simulation Organic Synthesis Oxidoreductase Performance Pharmaceutical Chemistry Pharmaceutical Preparations Pharmacologic Substance Pharmacology Plasma Population Privatization Probability Process Property Proteins Proto-Oncogene Protein c-kit Quantitative Structure-Activity Relationship Reaction Regimen Reporting Research Personnel Resistance Route Series Testing Therapeutic Time Training Treatment Failure Treatment Protocols Tuberculosis United States Validation Vendor World Health Organization analog base candidate selection clinically relevant computerized tools cost cost efficient design design and construction drug candidate drug discovery drug-sensitive exhaustion experience global health in silico in vivo inhibitor interest lead candidate lead optimization machine learning method meetings multi-task learning multitask mycobacterial novel novel strategies novel therapeutic intervention novel therapeutics pandemic disease pre-clinical predictive modeling process optimization resistant strain screening skills small molecule statistics therapy duration tool tuberculosis drugs

项目摘要

PROJECT SUMMARY New approaches are urgently needed to advance new chemical entities as antitubercular agents of clinical relevance. A key hurdle is the multiple criteria process that constitutes hit-to-lead optimization of small molecules with demonstrated in vitro potency versus drug-sensitive and drug-resistant strains of the causative bacterium Mycobacterium tuberculosis (Mtb). This project will address the design, construction, and validation of novel machine learning approaches to predict two of these critical molecular properties: in vitro Mtb growth inhibition and mouse pharmacokinetic exposure in the plasma. The resulting models, validated through external test statistics, will be complemented by computational approaches, relying on expert-encoded reaction templates and/or learned reaction prediction models, to predict optimal synthetic routes to two promising antitubercular small molecules: JSF-3005 and CD117. These data will inform the enumeration of synthesizable analogs for hit expansion to be followed by the selection of candidate analogs scored with a multi-objective Pareto optimization criterion combining multiple surrogate QSAR models with or without docking scores. Optimality scores will guide a genetic algorithm for synthesizability-constrained molecular optimization as a replacement for exhaustive forward enumeration. The top-scoring candidate lead compounds in each series will be then assayed for critical molecular properties to validate this novel approach and supply novel antitubercular agents for further study outside the scope of this proposal.

项目概要迫切需要新方法来推进新化学实体作为临床抗结核药物的发展关联。一个关键障碍是构成小分子的从命中到先导优化的多重标准过程与致病细菌的药物敏感和耐药菌株相比，具有体外效力结核分枝杆菌 (Mtb)。该项目将解决新颖的设计、构建和验证机器学习方法可以预测其中两个关键分子特性：体外 Mtb 生长抑制和小鼠血浆中的药代动力学暴露。通过外部测试验证生成的模型统计数据将得到计算方法的补充，依赖于专家编码的反应模板和/或学习的反应预测模型，以预测两种有前途的抗结核药物的最佳合成路线小分子：JSF-3005和CD117。这些数据将告知命中的可合成类似物的枚举扩展之后是选择通过多目标帕累托优化评分的候选类似物结合多个替代 QSAR 模型（有或没有对接分数）的标准。最优分数将指导用于可合成性约束的分子优化的遗传算法，作为详尽的替代前向枚举。然后将分析每个系列中得分最高的候选先导化合物的关键性分子特性来验证这种新方法并为进一步研究提供新型抗结核药物超出了本提案的范围。