New Methods and Tools for Computational Drug Discovery

计算药物发现的新方法和工具

• 批准号: 10633106
• 负责人: David Ryan Koes
• 金额: $ 37.19万
• 依托单位: UNIVERSITY OF PITTSBURGH AT PITTSBURGH
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-06-01 至 2026-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10633106
• 关键词: 3-Dimensional; Acceleration; Actins; Address; Autoimmune Diseases; Award; Binding; Biological Assay; Chemicals; Code; Computer software; Computing Methodologies; Development; Diabetic Retinopathy; Disease; Docking; Drug Design; Evaluation; Generations; Goals; Health; Human; Learning; Libraries; Ligands; Malignant Neoplasms; Methods; Modeling; Molecular; Molecular Structure; Molecular Target; Neural Network Simulation; Pharmaceutical Preparations; Physiology; Process; Productivity; Property; Proteins; Pythons; Research; Research Support; Resources; Sampling; Structure; Training; Update; Work; antiangiogenesis therapy; candidate identification; computerized tools; deep learning; deep neural network; drug discovery; improved; inhibitor; lead candidate; lead optimization; novel; novel therapeutics; open source; open source tool; profilin; prospective; research clinical testing; screening; small molecule; tool; user-friendly; web app; web site

Project Summary My goal is to develop effective and efficient computational methods for drug discovery, apply these methods to find new and efficacious drugs to treat diseases, and deploy these methods in easy-to-use open source tools. My research group pioneered the development and integration of deep neural networks in user-friendly molecular docking software for structure-based drug design to predict poses and potency of small molecules binding to their molecular targets. We will build on our foundational work by using deep learning to simultaneously solving the scoring and sampling problems, which will overcome scalability limitations inherent in current approaches. We propose to develop the first deep generative models for structure-based drug design. Unlike tra- ditional screening, generative modeling is not limited to a predefined chemical space. In generative mod- eling, a deep neural network learns an underlying distribution of molecular structures and properties represented as a latent space. New structures can be extracted from this learned latent space to have desirable properties. Ideally, a generative model will produce novel, near-optimal molecular structures almost instantaneously. We hypothesize that training generative models using existing 3D protein and ligand structures will allow us to create general models that can be productively applied to new, struc- turally enabled targets due to the richness and universality of protein-ligand interactions. We will further develop these methods to support the generation of optimized lead candidates, where the generative process is updated to include results from experimental assays as the drug discovery process progresses. We will continually apply our methods to identify small molecule modulators of molecular interac- tions relevant to normal physiology and disease. For example, using our current tools, we identified the first inhibitors of the profilin-actin interaction, an anti-angiogenesis target with relevance to cancer and diabetic retinopathy, and we plan to further improve these compounds with the goal of identifying candi- dates for clinical testing. We will apply our methods to address other under-explored molecular targets, such as NFATc2, which is implicated in cancer and autoimmune diseases. These prospective applications of our methods will provide unbiased and realistic evaluations that further inform their development. Finally, all of our code and trained deep neural network models will be deployed either as new tools for generative modeling or as enhancements to our widely used open source tools for computational drug discovery: (1) PHARMIT, an interactive web application for structure-based drug discovery; (2) GNINA, a C/C++ deep learning framework for molecular docking; and (3) the newly released LIBMOLGRID, a Python library for accelerated molecular gridding that integrates with popular deep learning toolkits. These tools and methods will make the drug discovery process more accessible and efficient.

项目摘要 我的目标是开发有效且有效的药物发现计算方法，应用这些 找到新的和有效的药物来治疗疾病并将这些方法部署在易于使用的方法中的方法 源工具。我的研究小组开创了深度神经网络的发展和整合 用户友好的分子对接软件，用于基于结构的药物设计，以预测姿势和效力 与它们的分子靶标结合的小分子。我们将通过深入的基础工作来建立我们的基础工作 学会同时解决评分和抽样问题，这将克服可伸缩性 当前方法固有的局限性。 我们建议开发基于结构的药物设计的第一个深刻通用模型。不像 附属筛选，通用建模不仅限于预先确定的化学空间。在通用mod- Eling，深层神经网络学习了分子结构和性质的潜在分布 表示为潜在空间。可以从这个学习的潜在空间中提取新结构 理想的属性。理想情况下，通用模型将产生新颖的，近乎最佳的分子结构 几乎瞬间。我们假设使用现有3D蛋白质和 配体结构将使我们能够创建可以有效地应用于新结构的通用模型 由于蛋白质 - 配体相互作用的丰富性和普遍性，Trally启用了目标。我们将进一步 开发这些方法来支持生成优化的主要候选者的生成 随着药物发现过程的进行，过程将更新以包括实验性断言的结果。 我们将不断应用我们的方法来鉴定分子间的小分子调节剂 与正常生理学和疾病有关的问题。例如，使用我们当前的工具，我们确定 促脂肌蛋白相互作用的第一个抑制剂，这是一种与癌症相关的抗血管生成靶标 糖尿病性视网膜病，我们计划进一步改善这些化合物，目的是确定候选 临床测试的日期。我们将应用我们的方法来解决其他探索较低的分子靶标， 例如在癌症和自身免疫性疾病中实施的NFATC2。这些潜在的应用 我们的方法将提供公正和现实的评估，以进一步为他们的发展提供信息。 最后，我们的所有代码和经过训练的深神经网络模型将被作为新工具部署 用于通用建模或作为我们广泛使用的计算药物的开源工具的增强功能 发现：（1）PharmIt，一种基于结构的药物发现的交互式Web应用程序； （2）Gnina， 分子对接的C/C ++深度学习框架； （3）新发布的libmolgrid，一个 Python库用于加速分子研磨，与流行的深度学习工具包相结合。 这些工具和方法将使药物发现过程更容易获得和有效。