Informatics and Machine Learning Modules for Research Planning, Scheduling, Simulation, and Optimization in the ASPIRE Autonomous Laboratory

用于 ASPIRE 自主实验室研究规划、调度、模拟和优化的信息学和机器学习模块

• 批准号: 10642813
• 负责人: Connor Wilson Coley
• 金额: $ 57.5万
• 依托单位: MASSACHUSETTS INSTITUTE OF TECHNOLOGY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-06-10 至 2024-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10642813
• 关键词: Acceleration; Adoption; Algorithms; Artificial Intelligence; Automation; Benchmarking; Biological Assay; Biological Testing; Chemicals; Chemistry; Collection; Communication; Communities; Complex; Computer Assisted; Computer software; Consumption; Data; Data Science; Decision Making; Development; Disease; Documentation; Evaluation; Family; Feedback; Friends; Goals; Graph; Health; Human; Humanities; Informatics; Infrastructure; Laboratories; Learning; Learning Module; Literature; Machine Learning; Manuals; Medicine; Modeling; Molecular; National Center for Advancing Translational Sciences; Performance; Pharmaceutical Chemistry; Pharmacologic Substance; Procedures; Process; Property; Publishing; Reaction; Readability; Recommendation; Research; Route; Running; Schedule; Structure; Synthesis Chemistry; Therapeutic; Time; Training; Translations; Visualization; Visualization software; Work; Writing; application programming interface; chemical reaction; chemical synthesis; cheminformatics; cost; data-driven model; deep learning; design; digital twin; drug candidate; drug discovery; experimental study; graphical user interface; improved; innovation; interest; knowledge graph; lead optimization; negative affect; novel; novel therapeutics; open source; open source tool; operation; preclinical development; predictive modeling; process optimization; programs; response; screening; simulation; small molecule; software development; theories; therapeutic candidate; tool; virtual

PROJECT SUMMARY Access to complex chemical matter (e.g., small molecule drug candidates) is a core requirement for testing biological hypotheses and probing human health. Current approaches to chemical synthesis rely on time-consuming planning and labor-intensive manual synthesis, which is a rate-limiting step in the discovery of new functional molecules. This collaborative project comprises the development of several virtual modules to support the multi-step chemical synthesis of new molecules in autonomous laboratories. These modules are designed to benefit traditional synthetic chemists in addition to automation chemists using the integrated hardware platform being developed by the ASPIRE team at NCATS. Computer-aided synthesis planning can be viewed as a hierarchical process of elaboration starting from the list of molecules of interest: (1) retrosynthetic planning to identify suitable starting materials and intermediates, (2) reaction condition recommendation to identify the conditions with which each reaction step should be run, (3) translation of hypothetical reaction steps into action sequences executable on automated hardware. Optional but valuable components include (4) recording procedures through an experimental planning module, (5) optimization of the timing and order of action sequences to most efficiently synthesize multiple synthetic targets via a digital twin of the platform, and (6) the iterative optimization of process parameters based on experimental responses in a feedback loop. This program will address each of these needs through the development of new software solutions employing state of the art algorithms in graph network theory, cheminformatics, deep learning for chemistry, and optimization. Software modules will be written using established software development best practices for ease of cross-platform deployment (via containerization) and long-term maintainability (via extensive documentation). Further, each module will be deployed as an independent microservice with a common application programming interface (API) format for inter-module communication and integration with existing NCATS modules, including graphical user interfaces. These efforts will be accomplished through close partnership between MIT and NCATS to enhance the overall capabilities of the NCATS ASPIRE platform.

项目摘要 接触复杂的化学物质（例如，小分子候选药物）是核心要求 用于检验生物学假设和探索人类健康。目前化学品处理办法 合成依赖于耗时规划和劳动密集型人工合成， 发现新功能分子的限速步骤。这个合作项目 包括开发多个虚拟模块以支持多步骤化学反应 在自主实验室中合成新分子。这些模块旨在 除了自动化化学家之外，传统的合成化学家也可以使用集成的 NCATS的ASPIRE团队正在开发的硬件平台。计算机辅助合成 规划可以被看作是一个分层的过程，从清单开始， 目标分子：（1）逆合成计划以鉴定合适的起始材料， 中间体，（2）反应条件建议，以确定每一个 反应步骤应该运行，（3）假设的反应步骤转化为动作序列 可在自动化硬件上执行。可选但有价值的组件包括（4）记录 程序通过一个实验规划模块，（5）优化时序和顺序 最有效地合成多个合成目标， 基于实验的工艺参数迭代优化 反馈回路中的响应。该计划将通过以下方式满足每一项需求： 开发新的软件解决方案，采用图形网络中最先进的算法 理论、化学信息学、化学深度学习和优化。软件模块将 使用已建立的软件开发最佳实践编写，以便于跨平台 部署（通过容器化）和长期可维护性（通过广泛的 文档）。此外，每个模块都将部署为独立的微服务， 用于模块间通信的公共应用编程接口（API）格式，以及 与现有NCATS模块的集成，包括图形用户界面。这些努力将 通过麻省理工学院和NCATS之间的密切合作，以提高整体 NCATS ASPIRE平台的功能。