PREC Track 1: Cal State LA - MolSSI PREC Pathway to Diversity Program

该奖项全部或部分由《2021年美国救援计划法案》（公法117-2）资助。加州州立大学LA-MolSSI（化学研究与教育伙伴关系）多元化途径项目是加州州立大学洛杉矶分校（一所综合性公立大学）和西班牙裔服务机构之间的合作项目，与弗吉尼亚理工大学的分子软件科学研究所（MolSSI）合作，将机器学习（ML）技术纳入分子模拟研究，并开发创新的教学材料，以培养早期计算科学的本科生。加州州立大学洛杉矶分校的本科生和硕士生将全年参与指导研究，并参加MolSSI的年度研讨会。社区大学的学生将与这些学生一起参加加州州立大学洛杉矶分校的暑期研究经历。此外，来自当地社区学院和加州州立大学洛杉矶分校的早期本科生将参加由加州州立大学洛杉矶分校和MolSSI的讲师讲授的年度计算研讨会，该研讨会强调科学编程和各种分子模拟和ML技术，以及专业发展活动。总的来说，这个PREC旨在为招募和培训下一代分子模拟科学家做出重大贡献，这些科学家将需要对物理和化学原理以及计算技术有深刻的理解。近年来，机器学习方法已经改变了化学和分子科学领域，并将在未来继续这样做。加州州立大学LA-MolSSI PREC（化学研究和教育伙伴关系）将围绕三个主题研究重点组织，每个主题研究重点都使用ML和基于物理的模拟方法来创建适用于一系列化学和生化现象的新计算模型。推力1将专注于开发用于计算分子晶体多晶的相对熵和热力学稳定性的ML方法。Thrust 2将致力于开发一种基于混合物理和ML的方法来预测小蛋白质配体复合物的相对结合自由能。Thrust 3将使用ML来参数化小分子力场，包括直接极化静电模型和其他先进的非键电位。这项研究的结果将有助于回答化学、生物物理学、材料科学和药理学方面的紧迫问题。该奖项反映了美国国家科学基金会的法定使命，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。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2). The Cal State LA-MolSSI PREC (Partnership for Research and Education in Chemistry) Pathway to Diversity Program is a collaboration between California State University, Los Angeles, a comprehensive public university and Hispanic Serving Institution, and the Molecular Software Sciences Institute (MolSSI) at Virginia Tech to incorporate machine learning (ML) techniques in molecular simulation research and develop innovative pedagogical materials to train early-stage undergraduate students in computational science. Cal State LA undergraduate and master’s students will participate year-round in mentored research and attend an annual workshop at MolSSI. Community college students will take part in mentored summer research experiences at Cal State LA alongside these students. Additionally, early-stage undergraduate students from local community colleges and Cal State LA will participate in an annual computational workshop taught by instructors from Cal State LA and MolSSI that emphasizes scientific programming and a variety of molecular simulation and ML techniques, as well as professional development activities. Overall, this PREC aims to make a significant contribution to the recruitment and training of the next generation of molecular simulation scientists who will require a deep understanding of both physical and chemical principles and computational techniques.Machine learning (ML) methods have transformed the fields of chemistry and molecular sciences in recent years, and will continue to do so in the future. The Cal State LA-MolSSI PREC (Partnership for Research and Education in Chemistry) will be organized around three thematic research thrusts that each use ML and physics-based simulation methods to create new computational models applicable to a range of chemical and biochemical phenomena. Thrust 1 will focus on developing ML approaches for computing the relative entropies and thermodynamic stabilities of molecular crystal polymorphs. Thrust 2 will aim to develop a hybrid physics-based and ML approach for predicting the relative binding free energies of small protein-ligand complexes. Thrust 3 will use ML to parametrize small molecule force fields that include a direct polarization electrostatic model and other advanced nonbonded potentials. The results of this research will help answer pressing questions in chemistry, biophysics, materials science, and pharmacology.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.