MegaTox for analyzing and visualizing data across different screening systems

MegaTox 用于分析和可视化不同筛查系统的数据

• 批准号: 10674729
• 负责人: SEAN EKINS
• 金额: $ 85.5万
• 依托单位: COLLABORATIONS PHARMACEUTICALS, INC.
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-01 至 2024-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10674729
• 关键词: Adenosine A1 Receptor; Agonist; Agrochemicals; Algorithms; Androgen Receptor; Animal Model; Aromatase; Award; Bayesian Method; Bayesian Modeling; Behavior; Biotechnology; Chemicals; Chemistry; Client; Collaborations; Collection; Computer Models; Computer software; DNA; Data; Data Set; Databases; Decision Trees; Endocrine disruption; Estrogen Receptors; Fee-for-Service Plans; Fingerprint; Foundations; Future; Generations; Grant; Graph; In Vitro; Industry; Laboratories; Learning; Letters; Libraries; Licensing; Machine Learning; Marketing; Measures; Medical; Methods; Modeling; Molecular; Morphology; Paper; Pathway interactions; Pharmacologic Substance; Phase; Progress Reports; Property; Proteins; Public Domains; Publishing; Receiver Operating Characteristics; Source; Structure; System; Testing; Toxic effect; Toxicology; Training; Validation; Visualization; Work; Zebrafish; adverse outcome; cheminformatics; classification algorithm; commercialization; computational toxicology; consumer product; cost; dashboard; data modeling; data visualization; developmental toxicity; diverse data; drug discovery; drug induced liver injury; in vitro Assay; in vitro testing; in vivo; in vivo Model; in vivo evaluation; knowledge graph; large datasets; machine learning algorithm; machine learning model; model building; model development; mortality; multitask; neurotoxicity; novel; posters; prospective; prototype; public database; random forest; regression algorithm; screening; tool; web app; web site

Project Summary Computational toxicology aims to use rules, models and algorithms based on prior data for specific endpoints, to enable the prediction of whether a new molecule will possess similar liabilities or not. In some cases, the computational models are derived from discrete molecular endpoints (e.g. estrogen receptor agonism) while in others they are quite broad in scope (e.g. drug induced liver injury, DILI). Considerable progress has been made in computational toxicology in a decade both in model development and availability such that the latest generation of larger scale machine learning (ML) models will further focus in vitro and in vivo testing on verification of select predictions. Pharmaceutical, consumer products, agrochemical and other chemistry focused companies possess structure-activity data generated over many decades of screening that is not in the public domain, and this data is primarily only accessible to the cheminformatics experts in each company. Outside of these companies small pharmaceutical, biotech companies and academics must rely on data from public databases, commercial databases and their own data. Integrating such data from diverse sources and processing with algorithms to build machine learning (ML) models that can help to enable predictions for new compounds is a vast undertaking. Over Phase I of this project to develop the prototype for MegaToxÒ, we curated toxicity datasets then generated and tested well over 200 ML models initially focused on the Bayesian approach. We have also developed approaches to understand training and test set applicability and ultimately performed prospective predictions against several toxicity targets. Having completed these aims, we also collaborated with numerous academic laboratories and performed fee-for-service work with five commercial companies. We currently have several pharmaceutical, agrochemical and consumer product companies evaluating our computational toxicity models prior to licensing. These discussions with potential customers have influenced this Phase II proposal to include the following aims: 1. Compare and integrate novel graph-based models such as graphSAGE versus our suite of 15 different ML regression and classification algorithms for modeling toxicology datasets such as those generated in Phase I. 2. Integrate read across and adverse outcome pathway methods with our computational models for DILI and other toxicity models as needed. 3. Generate validated ML models from in vivo data for non-mammalian species (initially using Zebrafish) which will enable in vitro and in vivo correlations and can be validated relatively cost effectively. In this proposal over 2 years we expect to develop models with 15 different algorithms for at least 100 in vitro and in vivo datasets, leading to > 1500 toxicity ML models. We are not aware of any other company pursuing such an approach to both generate new high value datasets or models, performing testing of their own models and creating a wide array of toxicity ML models. MegaToxÒ will be a product available for licensing by pharmaceutical, consumer product, agrochemical and regulatory groups as well as used in fee-for-service consulting.

项目概要 计算毒理学旨在使用基于特定终点先前数据的规则、模型和算法， 在某些情况下，可以预测新分子是否具有类似的特性。 计算模型源自离散的分子终点（例如雌激素受体激动作用） 其他方面的范围相当广泛（例如药物引起的肝损伤，DILI）。 十年来在计算毒理学方面无论是在模型开发还是可用性方面都取得了进展，例如最新的 更大规模机器学习（ML）模型的生成将进一步侧重于体外和体内测试 验证选定的预测，重点关注制药、消费品、农用化学品和其他化学领域。 公司拥有经过数十年筛选产生的不公开的结构活性数据 域，并且这些数据主要只能由每个公司外部的化学信息学专家访问。 这些公司（小型制药公司、生物技术公司和学术机构）必须依赖公共数据 数据库、商业数据库和他们自己的数据。 使用算法进行处理以构建机器学习 (ML) 模型，帮助实现新的预测 我们策划了该项目第一阶段的 MegaToxÒ 原型开发工作，这是一项艰巨的任务。 然后，毒性数据集生成并测试了 200 多个最初专注于贝叶斯方法的 ML 模型。 我们还开发了理解训练和测试集适用性并最终执行的方法 在完成这些目标后，我们还与多个毒性目标进行了前瞻性预测。 众多学术实验室并与五家商业公司进行有偿服务工作。 目前有多家制药、农化和消费品公司正在评估我们的 许可之前的计算毒性模型影响了这一点。 第二阶段提案包括以下目标： 1. 比较和集成新颖的基于图的模型，例如 graphSAGE 与我们用于毒理学建模的 15 种不同 ML 回归和分类算法套件的比较 数据集，例如第一阶段生成的数据集。 2. 整合跨读和不良结果途径方法 根据需要使用我们的 DILI 计算模型和其他毒性模型 3. 生成经过验证的 ML 模型。 来自非哺乳动物物种（最初使用斑马鱼）的体内数据，这将使体外和体内 相关性，并且可以相对成本有效地进行验证，在该提案中，我们预计将在两年内进行开发。 具有 15 种不同算法的模型，适用于至少 100 个体外和体内数据集，导致 > 1500 个毒性 ML 我们不知道有任何其他公司采用这种方法来创造新的高价值。 数据集或模型，对自己的模型进行测试并创建各种毒性 ML 模型。 MegaToxÒ 将成为可供制药、消费品、农用化学品和 监管团体以及用于按服务收费的咨询。