Chemical instruments-aware distributed blockchain based open AI platform to accelerate drug discovery

基于化学仪器感知的分布式区块链开放人工智能平台，加速药物发现

• 批准号: 10665719
• 负责人: GAURAV CHOPRA
• 金额: $ 56.01万
• 依托单位: PURDUE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-07-15 至 2025-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10665719
• 关键词: Academia; Acceleration; Adopted; Affect; Affinity; Artificial Intelligence; Artificial Intelligence platform; Automation; Awareness; Binding; Biological; Chemical Structure; Chemicals; Chemistry; Code; Collaborations; Collection; Communities; Complex; Computer software; Coupled; Data; Data Analyses; Data Set; Databases; Decentralization; Development; Diagnostic; Disclosure; Encapsulated; Face; Failure; Feedback; Generations; Government; High Pressure Liquid Chromatography; Human; Information Technology; Infrastructure; Institution; Interruption; Ions; Joints; Laboratories; Learning; Location; Manuals; Measurement; Medicine; Modeling; Molecular; Molecular Structure; National Center for Advancing Translational Sciences; Outcome; Patients; Performance; Process; Property; Protocols documentation; Publishing; Reaction; Reproducibility; Research; Research Proposals; Resource Allocation; Resources; Schedule; Scientist; Secure; Site; Standardization; System; Systems Integration; Techniques; Technology; Testing; Training; Vision; Work; application programming interface; automated analysis; blockchain; computing resources; cost; cyber infrastructure; data integration; data sharing; design; distributed data; distributed ledger; drug candidate; drug discovery; experience; experimental analysis; experimental study; graphical user interface; innovation; instrument; learning algorithm; learning progression; novel; open data; open source; programs; screening; timeline; tool; virtual

PROJECT SUMMARY Artificial Intelligence (AI) and Automation has the potential to accelerate several stages of the drug discovery process, including the design-make-test-analyze optimization cycle, typically faced by medicinal chemists. However, several roadblocks exist resulting in too long timelines to deliver much needed innovation to patients with unmet needs. Both human and AI face similar limitations mainly due to disjointed steps needed to obtain and integrate the data that is generated by different organizations or laboratories and cannot be readily shared without disclosing IP-sensitive information (e.g., non-patented novel chemical structures). In addition, there is lack of negative (failures) data available publicly, which are critical for generating accurate AI models, but are typically not made available outside of the originating institution or laboratory due to a variety of reasons related to IP. And, even among positive results, greater reproducibility of protocols is desirable. A solution to develop a fully integrated system in-house can be effective but it is hard to scale and not easily adopted mainly due to the costs and infrastructure involved. Our solution encapsulates the vision of NCATS ASPIRE program of integrating and automating laboratories to accelerate the drug discovery process while taking into account the above problems that exist. Blockchain, a distributed ledger technology, coupled with AI and Automation has the potential to solve all of the above problems as it has done in several other technology sectors, such as finance and medicine to securely share and learn from data without revealing its identity. We will develop a blockchain based open science AI framework as a decentralized laboratory cloud for the drug discovery community to enhance collaboration and reproducibility. This includes decentralized performance of experiments and enabling efficient multi-party analysis and learning on remote datasets using application programming interface (API) and graphical user interface (GUI) to engage both computational and experimental scientists. Continuous learning from measurements and accessible data (with GUI for humans and API for machines) will enable unprecedented reproducibility. Our decentralized blockchain network will be interfaced across four sites (Purdue, IBRI, IU and NCATS) in a modular manner that is extendable to large scale to accommodate several thousand laboratories without affecting efficiency at scale. Our network solution is modular, in that, it works with multiple resources (instruments, databases) either within one laboratory or across multiple laboratories and organizations. This distributed blockchain network will enable secure multi-party joint training of AI model on databases at different locations (cloud instances, IU and NCATS) and schedule experiments with a physical instrument (Purdue) with data interpretation and secure sharing of results to enhance the efficiency of cross-organizational and collaborative research. The integrated API and GUI will be developed by utilizing core technology components from the NCATS Information Technology Resource Branch to facilitate transfer and integration with the ASPIRE platform. Collectively, this open-source solution will enhance cycle times to accelerate drug discovery research.

项目摘要 人工智能（AI）和自动化有可能加速药物发现的几个阶段 过程，包括设计-制造-测试-分析优化周期，通常由药物化学家面对。 然而，存在几个障碍，导致为患者提供急需的创新的时间表过长 未满足的需求。人类和人工智能都面临着类似的限制，主要是由于获得 整合不同组织或实验室生成的、无法轻易共享的数据 而不公开IP敏感信息（例如，非专利的新颖化学结构）。此外还有 缺乏公开的负面（失败）数据，这对于生成准确的人工智能模型至关重要，但 通常由于各种相关原因而不能在发起机构或实验室之外获得 到IP。而且，即使在阳性结果中，也希望方案具有更高的可重复性。一种解决方案， 内部完全集成的系统可能是有效的，但它很难扩展，不容易采用，主要是由于 成本和基础设施。我们的解决方案封装了NCATS ASPIRE计划的愿景， 自动化实验室以加速药物发现过程，同时考虑到上述因素 存在的问题。区块链是一种分布式账本技术，再加上人工智能和自动化， 解决上述所有问题的潜力，就像它在其他几个技术领域所做的那样，如金融 和医学来安全地共享和学习数据，而不会泄露其身份。我们将开发一个区块链 基于开放科学的人工智能框架，作为药物发现社区的分散实验室云， 加强协作和可重复性。这包括分散的实验性能， 使用应用程序编程接口（API）对远程数据集进行高效的多方分析和学习 图形用户界面（GUI），以吸引计算和实验科学家。不断学习 从测量结果和可访问的数据（使用人类的GUI和机器的API）将实现前所未有的 再现性我们的去中心化区块链网络将在四个站点（Purdue，IBRI，IU和 NCATS）以模块化的方式，可扩展到大规模，以容纳数千个实验室 而不影响规模效率。我们的网络解决方案是模块化的，因为它可以使用多种资源 （仪器，数据库）在一个实验室内或跨多个实验室和组织。这 分布式区块链网络将在不同的数据库上实现人工智能模型的安全多方联合训练。 位置（云实例，IU和NCATS），并使用物理仪器（Purdue）安排实验， 数据解释和安全共享结果，以提高跨组织和 合作研究。集成的API和GUI将利用核心技术组件开发 从NCATS信息技术资源分支，以促进转移和与ASPIRE的整合 平台总的来说，这个开源解决方案将缩短周期时间，加速药物发现研究。