Myc Transcription Factor Inhibitor Design: Integrating Atomic and Mesoscale with Semi-Supervised Generative Deep Learning Models

Myc 转录因子抑制剂设计：将原子和中尺度与半监督生成深度学习模型相结合

• 批准号: 10745272
• 负责人: Gregory John Schwing
• 金额: $ 4.67万
• 依托单位: WAYNE STATE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-01 至 2027-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10745272
• 关键词: Affinity; Automobile Driving; Behavior; Binding; Binding Sites; Biological; Biological Assay; Cancer Biology; Cell Proliferation; Chemicals; Complex; DNA; Data; Databases; Disease; Docking; Excision; Free Energy; Glioma; Goals; Grain; Human; Hydrophobicity; In Vitro; Lead; Learning; Libraries; Ligand Binding; Ligands; Liquid substance; MYC Family Protein; Malignant Neoplasms; Maps; Methods; Modeling; Molecular Conformation; Molecular Weight; Mutate; Oncogenic; Pancreatic Adenocarcinoma; Pathologic; Pathway interactions; Performance; Pharmaceutical Preparations; Phase; Population; Process; Property; Proteins; Proto-Oncogene Proteins c-myc; Protocols documentation; Psychological reinforcement; Reaction; Reporting; Resolution; Role; Signal Transduction; Site; Solvents; Somatic Mutation; Structure; Techniques; Testing; Time; Training; Transactivation; Transducers; Trees; data integration; data mining; deep learning; deep learning model; design; drug discovery; drug efficacy; effectiveness testing; falls; high throughput screening; improved; in vivo; inhibitor; interest; lead optimization; learning strategy; machine learning method; molecular dynamics; nanomolar; peptidomimetics; phase change; protein protein interaction; public database; response; simulation; small molecule; small molecule inhibitor; small molecule libraries; statistics; success; transcription factor; triple-negative invasive breast carcinoma; virtual screening

C ABSTRACT Myc Transcription Factor Inhibitor Design: Integrating Atomic and Mesoscale with Semi-Supervised Gen- erative Deep Learning Models Inhibition of master regulators such as Myc have considerable interest due to the reversal of the oncogenic state evoked by their removal. Adding to the mystique is the technical challenge in targeting a protein which possesses large regions of disorder. Though widely considered “undruggable”, the library of hits that disrupt Myc function continuously grows. The chemical features of a hit are difficult to deduce besides high molecular weight, aro- maticity, rigidity, and hydrophobicity. Understanding the more specific features of a protein-protein interaction (PPI) inhibitor is considerably difficult. In order to circumvent answering this question, machine learning methods have been applied to expand the library of experimentally determined hits in hopes of finding an improved inhibitor nearby in chemical space. Recently, the natural application of generative deep learning techniques to this prob- lem have been reported. This proposal explains a protocol for a semi-supervised expansion of small molecules which inhibit various reactions in the Myc transactivation pathway. The PPI inhibitors from three publicly available databases make up the training set (n=9516) while the known Myc inhibitors are the test set (n=100). In order to surpass the effectiveness of the test set, all known Myc inhibitors are removed from the training set. A number of latent variables which suffice to recreate the training set are solved. These variables represent the general struc- tural properties of PPI inhibitors, which may be associated with activities at various binding sites. The efficient calculation of activities is crucial to obtaining good performance. Therefore, a well-tempered ensemble of target configurations is pre-calculated at the all-atom resolution. Additionally, in order to incorporate the population level behavior of multiple Myc molecules into inhibitor design, mesoscale coarse-grain simulations in various sol- vents which drive liquid-liquid phase separation are performed. To identify interactions which correlate with phase response, various points in coarse-grain phase space are converted to all-atom resolution, further refined, and converted into contact maps. When evaluating a new lead, ensemble-based docking calculations are used, which calculate an average of averages of a ligand in different poses binding to different conformations randomly drawn from the ensembles. Reinforcement learning is applied to significantly reduce the time spent docking batches of leads while maintaining confidence in the result. Once new molecules are generated, these new leads are also optimized using absolute and relative free energy of binding methods. Ultimately, this study will test the limits of generative models to integrate data across multiple scales and develop inhibitors which evoke potent inhibition of intrinsically disordered proteins.

C摘要 MYC转录因子抑制剂设计：将原子和中尺度与半监视的Gen- 精心学习模型 由于致癌状态的逆转，对MYC等主监管机构的抑制具有很大的兴趣 被他们的拆除引起了人们的看法。在靶向具有的蛋白质的技术挑战中加上神秘感 大型混乱区域。虽然被广泛认为“不可能”，但打乱了MYC功能的热门图书馆 不断增长。命中的化学特征很难推断出高分子重量以外 微分，刚性和疏水性。了解蛋白质 - 蛋白质相互作用的更具体特征 （PPI）抑制剂很难。为了规避回答这个问题，机器学习方法 已应用于扩展实验确定的命中库，以期找到改进的抑制剂 在化学空间附近。最近，通用深度学习技术的自然应用在这一问题上 LEM已有报道。该建议解释了小分子半监督扩张的方案 抑制MYC反式激活途径中的各种反应。来自三个公开可用的PPI抑制剂 数据库组成训练集（n = 9516），而已知的MYC抑制剂是测试集（n = 100）。为了 超过测试集的有效性，所有已知的MYC抑制剂均从训练组中删除。许多 解决训练组的潜在变量已解决。这些变量代表一般结构 - PPI抑制剂的Tural特性，可能与各种结合位点的活性有关。有效 活动的计算对于获得良好的性能至关重要。因此，脾气广泛的目标合奏 在全原子分辨率上预先计算了配置。此外，为了合并人口 多个MYC分子在抑制剂设计中的水平行为，各种溶液中的中尺度粗粒模拟 进行驱动液态相分离的通风口。确定与阶段相关的相互作用 响应，粗粒相空间中的各个点转化为全原子分辨率，进一步固定，并将其转换为 转换为接触地图。在评估新铅时，使用基于合奏的对接计算， 计算不同姿势的配体平均值与随机抽取不同考虑的结合 从合奏。加强学习可用于大大减少停靠的时间 导线在结果中保持信心的同时。一旦产生了新分子，这些新线索也是 使用结合方法的绝对和相对自由能进行了优化。最终，这项研究将测试 通用模型以多种尺度和开发人员抑制剂的范围集成数据，这些数据引起了潜在的抑制 本质上受干扰的蛋白质。