Artificial Intelligence Toolkit for Predicting Mixture Toxicity

用于预测混合物毒性的人工智能工具包

• 批准号: 10379210
• 负责人: Alexander Tropsha
• 金额: $ 25.55万
• 依托单位: PREDICTIVE, LLC
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-12-20 至 2023-11-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10379210
• 关键词: Acute; Address; Advanced Development; Adverse effects; Artificial Intelligence; Chemicals; Complex; Computer Models; Corrosion; Custom; Data; Data Collection; Data Set; Databases; Dermal; Descriptor; Development; Drug Carriers; Drug Delivery Systems; Drug Interactions; Drug Synergism; Environmental Health; Evaluation; Eye; FAIR principles; Graph; Healthcare; Individual; Industrial Health; Industrial Waste; Industrialization; Inhalation; Knowledge; Laboratories; Life Cycle Stages; Maintenance; Methodology; Modeling; Modernization; Molecular Structure; Natural Products; Online Systems; Oral; Pesticides; Pharmaceutical Preparations; Phase; Procedures; Product Approvals; Production; Pythons; Quantitative Structure-Activity Relationship; Research Personnel; Resources; Risk; Risk Assessment; Safety; Skin; Small Business Technology Transfer Research; Structure; Technology; Toxic effect; Validation; Waste Products; artificial intelligence algorithm; base; cheminformatics; environmental chemical; graph neural network; innovation; irritation; model development; novel; phase 1 study; predictive modeling; prospective; random forest; safety assessment; searchable database; skin irritation; software as a service; software development; success; synergism; tool; user-friendly; web app; web portal; web server

Chemical safety assessment is typically conducted for individual chemicals. However, industrial chemicals rarely act in isolation to produce adverse effects, so mixture toxicity assessment represents a complex but more realistic approach to alleviating environmental chemical safety concerns. There is an exciting and highly impactful challenge to develop innovative approaches employing modern AI algorithms to provide accurate toxicity prediction of mixtures from their chemical composition, including the assessment of synergistic effects. We recently formed Predictive, LLC, to enable the development and distribution of commercial and regulatory strength models to predict important toxicity endpoints. In this Phase I STTR application, we propose to establish a novel web based PreMixT (Predictor of Mixture Toxicity) toolkit built on best practices for (i) data collection, cleaning, harmonization, and integration, (ii) model development using current and emerging AI approaches and thoughtful strategies of prospective validation of mixture models, and (iii) prediction of specific endpoint toxicities for both pure chemicals and mixtures. We will achieve this objective by focusing on the following Specific Aims. Specific Aim 1: Collect, curate, and integrate the largest publicly available mixture toxicity datasets. We will explore all the publicly accessible data on mixture toxicity. Initial datasets will include acute oral toxicity, acute inhalation toxicity, acute dermal toxicity, skin sensitization, skin irritation and corrosion, and eye irritation and corrosion endpoints (collectively known as "6-pack") as well as pesticides. We will also collect and curate datasets of untested chemicals and mixtures of the environmental concern with known composition such as High Production Volume (HPV) chemicals and registered substances in the REACH database. The data will be (re)structured, harmonized, and prepared for cheminformatics analysis following custom procedures. Specific Aim 2: Develop AI Models of mixture toxicity. Using data prepared in Aim 1, we will develop rigorously validated models of several selected endpoint mixture toxicities of relevance to environmental health risk assessment. We will employ two types of mixture-specific descriptors: Simplex Representation of Molecular Structure (SiRMS) and mixture graph convolution descriptors. Modeling approaches will include both common (e.g., Random Forest) as well as innovative Graph Convolutional Networks (GCN) approaches. Specific Aim 3. Develop the PreMixT toolkit and portal supporting the toxicity prediction of chemicals and their mixtures. We will integrate curated data and validated models into the PreMixT web application. This PreMixT server will be able to predict mixture toxicity, including possible synergy of mixture components, based on the knowledge of chemicals found and characterized in the mixture. Successful completion of our Phase I studies will result in the development of the PreMixT web application as a centralized resource to evaluate mixture toxicity, including the synergy between mixture components.

通常针对单个化学物质进行化学安全评估。但是，工业化学品很少 孤立起作用产生不良影响，因此混合毒性评估代表了一个复杂但更多 减轻环境化学安全问题的现实方法。有一个令人兴奋的 有影响力的挑战，以开发使用现代AI算法来提供准确的创新方法 从其化学组成中对混合物的毒性预测，包括评估协同作用。 我们最近成立了预测性有限责任公司，以实现商业和监管的开发和分布 强度模型预测重要的毒性终点。在此阶段I STTR应用程序中，我们建议建立 基于Web的新型Premixt（混合毒性的预测指标）工具包建立在（i）数据收集的最佳实践上， 清洁，协调和集成，（ii）使用当前和新兴的AI方法进行建模开发，并且 预期验证混合模型的周到策略，以及（iii）特定终点毒性的预测 用于纯化学物质和混合物。我们将通过关注以下特定目标来实现这一目标。 特定目标1：收集，策划和整合最大的公开混合物毒性数据集。我们 将探索所有有关混合毒性的公开访问数据。初始数据集将包括急性口服毒性，急性 吸入毒性，急性皮肤毒性，皮肤敏感性，皮肤刺激和腐蚀以及眼睛刺激性 腐蚀终点（统称为“ 6包”）和农药。我们还将收集和策划 未经测试的化学品和环境问题的混合物的数据集与已知成分（例如高） 到达数据库中的生产量（HPV）化学物质和注册物质。数据将是 （重新）按照自定义程序进行结构，协调和准备进行化学信息分析。具体的 目标2：开发混合毒性的AI模型。使用在AIM 1中准备的数据，我们将严格发展 经过验证的几种与环境健康风险相关的终点混合物毒性的模型 评估。我们将采用两种类型的混合特异性描述符：分子的单纯形表示 结构（SIRMS）和混合图卷积描述符。建模方法将包括两个常见 （例如随机森林）以及创新的图形卷积网络（GCN）方法。具体目标3。 开发Premixt工具包和门户，以支持化学物质及其混合物的毒性预测。 我们将将策划的数据和验证的模型集成到Premixt Web应用程序中。此Premixt服务器将 能够根据知识来预测混合毒性，包括混合物成分的可能协同作用 在混合物中发现和表征的化学物质。成功完成我们的第一阶段研究将导致 Premixt Web应用程序作为评估混合毒性的集中资源的开发， 包括混合组件之间的协同作用。