权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Molecule Maker Lab Institute (MMLI): An AI Institute for Molecular Discovery, Synthetic Strategy, and Manufacturing

Molecule Maker Lab Institute (MMLI)：分子发现、合成策略和制造的人工智能研究所

基本信息

批准号：
2019897
负责人：
Huimin Zhao
金额：
$ 2000万
依托单位：
University of Illinois at Urbana-Champaign
依托单位国家：
美国
项目类别：
Cooperative Agreement
财政年份：
2020
资助国家：
美国
起止时间：
2020-09-01 至 2025-08-31
项目状态：
未结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2019897&HistoricalAwards=false
关键词：
Molecule Maker Lab Institute MMLI

项目摘要

The NSF Molecule Maker Lab Institute (MMLI): An AI Institute for Molecular Discovery, Synthetic Strategy, and Manufacturing is supported by National AI Research Institutes Program of the Directorate for Computer and Information Science and Engineering (CISE), in collaboration with the Division of Chemistry (CHE) and the Division of Chemical, Bioengineering, and Environmental Transport Systems (CBET). The institute brings together a team of chemists, engineers, and AI-experts from the University of Illinois Urbana-Champaign, Pennsylvania State University and the Rochester Institute of Technology. The goal of the MMLI is to accelerate the synthesis and manufacture of complex organic molecules. A new AI-enabled synthesis platform is being developed to integrate chemical and enzymatic catalysis with literature mining and machine learning to predict the best way to make new molecules with desirable biological and material properties. This institute is transforming chemical synthesis and generating use-inspired AI advances. Simultaneously, the MMLI is also acting as a training ground for the next generation of scientists with combined expertise in chemical synthesis, bioengineering, and AI-enabled tool development. Outreach efforts aimed towards high school students and the public are being used to show how AI-enable tools can help to make chemical synthesis accessible to non-experts.Chemical synthesis is currently an intuition-driven field that requires experienced experts to design iterative test cycles to make progress towards targeted molecules. The MMLI is developing new AI-enabled tools for chemical synthesis planning, catalyst design, property prediction, and manufacturing to address this bottleneck and accelerate the synthesis and discovery of new molecules. The institute combines expertise in AI, organic synthesis, and bioengineering to achieve the integration of chemical and enzymatic catalysis with a versatile set of building blocks in a new AI-driven synthesis planning tool called AlphaSynthesis. Optimization of this tool is being supported by new foundational AI approaches to text- and image mining, advances in machine learning for synthesis planning and catalyst optimization, as well as the established automated synthesis and bioengineering facilities at the University of Illinois Urbana-Champaign. Demonstration of the utility of the AlphaSynthesis tool is being achieved through the preparation of target molecules and new materials. An open-access reactivity database is being assembled and a hit-list of desirable transformations is being accumulated to encourage collaboration. These foundational studies bridging AI, chemical synthesis, and bioengineering to accelerate the iterative design and test process of chemical synthesis are further serving to bolstering the competitiveness of pharmaceutical, chemical, and technology industries in the US.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF分子制造实验室研究所（MMLI）：分子发现，合成策略和制造的人工智能研究所由计算机和信息科学与工程理事会（CISE）的国家人工智能研究所计划支持，与化学部门（CHE）和化学，生物工程和环境运输系统部门（CBET）合作。该研究所汇集了来自伊利诺伊大学厄巴纳-香槟分校、宾夕法尼亚州立大学和罗切斯特理工学院的化学家、工程师和人工智能专家。MMLI的目标是加速复杂有机分子的合成和制造。目前正在开发一个新的人工智能合成平台，将化学和酶催化与文献挖掘和机器学习相结合，以预测制造具有理想生物和材料特性的新分子的最佳方法。该研究所正在改变化学合成，并产生使用启发的人工智能进步。同时，MMLI也是下一代科学家的培训基地，他们在化学合成，生物工程和人工智能工具开发方面具有综合专业知识。针对高中生和公众的外联工作正在被用来展示人工智能工具如何帮助非专家访问化学合成。化学合成目前是一个直觉驱动的领域，需要经验丰富的专家设计迭代测试循环，以朝着目标分子取得进展。MMLI正在开发新的人工智能工具，用于化学合成规划、催化剂设计、性能预测和制造，以解决这一瓶颈，并加速新分子的合成和发现。该研究所结合了人工智能，有机合成和生物工程方面的专业知识，以实现化学和酶催化与一套通用的构建模块的集成，这套构建模块是一种新的人工智能驱动的合成规划工具，称为AlphaSynthesis。该工具的优化得到了文本和图像挖掘的新基础人工智能方法，合成规划和催化剂优化机器学习的进步，以及伊利诺伊大学厄巴纳-香槟分校建立的自动化合成和生物工程设施的支持。正在通过制备目标分子和新材料来证明AlphaSynthesis工具的实用性。目前正在建立一个开放的反应性数据库，并正在积累一份理想的转化清单，以鼓励合作。这些基础研究将人工智能、化学合成和生物工程连接起来，以加速化学合成的迭代设计和测试过程，进一步增强了美国制药、化学和技术行业的竞争力。该奖项反映了NSF的法定使命，通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

期刊论文数量（20）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-Guided Distant Supervision

ChemNER：具有本体引导远程监督的细粒度化学命名实体识别

DOI：
10.18653/v1/2021.emnlp-main.424
发表时间：
2021
期刊：
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
影响因子：
0
作者：
Wang, Xuan;Hu, Vivian;Song, Xiangchen;Garg, Shweta;Xiao, Jinfeng;Han, Jiawei
通讯作者：
Han, Jiawei

Fine-Grained Chemical Entity Typing with Multimodal Knowledge Representation