Modelling protein covalent modifications with molecular simulation and machine learning

通过分子模拟和机器学习对蛋白质共价修饰进行建模

• 批准号: 2734456
• 金额: --
• 依托单位: University of Edinburgh
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2022
• 资助国家: 英国
• 起止时间: 2022 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2734456
• 关键词: Modelling; protein; covalent; modifications; molecular

This project will focus on developing and validating FEP methodologies to model the effect of protein structure modifications on molecular recognition mechanisms. Efforts will focus on biologics, peptidomimetic ligands, and covalent ligands for which robust simulation protocols are currently lacking. These classes of ligands present challenges for conventional FEP approaches tailored for small molecules because the ligands are often larger, more flexible, and can covalently bind to their target proteins. To address these issues this research will couple state of the art FEP simulation methodologies available in open-source software with advances in machine learning of potential energy functions to enable accurate modelling of binding energetics. The overall aim is to deliver a suite of protein FEP protocols sufficiently rapid and accurate to enable routine use in industrial R&D. This is an exciting opportunity to develop next-generation computer-aided drug design software and methodologies. Upon completion of the studentship, the successful applicant will have gained strong technical expertise in molecular modelling and worked closely with the life sciences softtware industry sector.

该项目将重点开发和验证FEP方法，以模拟蛋白质结构修饰对分子识别机制的影响。努力将集中在生物制剂，拟肽配体和共价配体，目前缺乏强大的模拟协议。这些类别的配体对针对小分子定制的常规FEP方法提出了挑战，因为配体通常更大，更灵活，并且可以共价结合到它们的靶蛋白。为了解决这些问题，本研究将结合开源软件中最先进的FEP模拟方法与势能函数机器学习的进步，以实现结合能量学的准确建模。总体目标是提供一套足够快速和准确的蛋白质FEP方案，以实现工业研发中的常规使用。这是一个开发下一代计算机辅助药物设计软件和方法的令人兴奋的机会。完成学业后，成功的申请人将在分子建模方面获得强大的技术专长，并与生命科学软件行业密切合作。