I-Corps: Virtual Lab for Coatings Design and Development

这个I-Corps项目的更广泛的影响/商业潜力是提供一个软件产品，可以催化化学品，材料和能源领域的高通量设计。最初的重点是大幅缩短功能性有机涂料的上市时间和开发成本，这些涂料面临监管和消费者的压力，需要在不损失性能的情况下开发定制解决方案。一个相邻的市场是复合材料的开发，严重依赖于填料的轻质材料的需求。到2025年，计算机辅助工程市场将达到约130亿美元，而工业涂料市场本身目前在全球价值1150亿美元。这些用于开发先进聚合物材料的高通量解决方案的好处包括减少毒素和能源消耗。 这个I-Corps项目利用分子标记开发了一种用于功能涂层的新型工程设计软件。使用机器学习将分子标志物与渗透阈值相关联，从而通过屏障进入失败，该软件将提供一种独特的方法来向下选择制剂到最有希望的子集。“虚拟实验室”方法类似于高通量药物发现。目前的涂料开发方法不能为现场性能和最终失效提供物理化学或分子基础。用于涂层评估和配方开发的实验设计通常利用统计软件。这种与机械理解的分离通常导致主要基于化学直觉的试错方法;此外，这导致多次加速老化运行，这为作为次优解决方案的给定制剂的现场部署增加了显著的交付周期。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this I-Corps project is to provide a software products that can catalyze high throughput design in the chemicals, materials, and energy space. The initial focus is to drastically cut the time to market, and development costs of functional organic coatings, which are under both regulatory and consumer pressure to develop custom solutions without loss of performance. An adjacent market is composites development, heavily dependent on fillers for its needs for lightweight materials. The computer-aided engineering market will be approximately $13 billion by 2025, while the industrial coatings market by itself is currently worth $115 billion globally. The benefits of these high-throughput solutions for development of advanced polymeric materials include reduced toxins and energy consumption. This I-Corps project leverages the use of molecular markers to develop a novel engineering design software for functional coatings. Using machine learning to correlate molecular markers to percolation threshold, and thereby failure through barrier ingress, the software would provide a unique method to down-select formulations to the most promising subset. The “virtual lab” approach is akin to high-throughput drug discovery. Current methods in coatings development fail to provide a physico-chemical or molecular underpinning to field performance and eventual failure. The design of experiments for coating assessment and formulation development commonly utilizes statistical software. This separation from mechanistic understanding often results in trial and error approaches, based largely on chemical intuition; furthermore, this leads to multiple accelerated aging runs that add significant lead time for field deployment of a given formulation as sub-optimal solutions. Developed software would provide a significant leap in design that translates to tailored polymeric advanced materials beyond functional coatings.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.