polyBERT:一种化学语言模型,可以实现完全机器驱动的超快速聚合物信息学.
Christopher Kuenneth1,2, Rampi Ramprasad3
1School of Materials Science and Engineering, Georgia Institute of Technology, Atlanta, GA, 30332, USA.
Nature communications
|July 11, 2023
概括
我们使用polyBERT (聚合物BERT) 和多任务学习开发了一种机器驱动的聚合物信息管道,以快速识别特定应用的聚合物. 这种方法显著加速了聚合物特性预测,增强了材料发现.
科学领域:
- 材料科学 材料科学 材料科学
- 计算化学的计算化学
- 聚合物科学 聚合物科学
背景情况:
- 聚合物在日常生活中无处不在,为材料发现提供了广的化学空间.
- 鉴定特定应用的聚合物是具有挑战性的,因为可能性的巨大数量.
- 目前用于聚合物性质预测的方法往往缓慢且范围有限.
研究的目的:
- 为了展示一个新的,端到端的机器驱动的聚合物信息学管道.
- 为了快速准确地在聚合物化学空间中搜索合适的候选物.
- 克服现有的聚合物性能预测技术的局限性.
主要方法:
- 开发了polyBERT,一种受自然语言处理启发的聚合物化学指纹制造方法.
- 实施了一种多任务学习方法,将polyBERT指纹映射到聚合物属性.
- 创建了一个完整的机器驱动的信息管道用于聚合物候选物识别.
主要成果:
- 聚伯特指纹和多任务学习方法显著加速了聚合物性质的预测.
- 与手工制作的指纹方法相比,管道实现了前所未有的速度 (比手工制作的指纹方法快两倍).
- 保持精度,证明了机器驱动方法的有效性.
结论:
- 开发的聚合物信息学管道为加速材料发现提供了一个强大的工具.
- polyBERT和多任务学习提供了一个可扩展和准确的方法来预测聚合物特性.
- 这种方法适用于大型计算架构的部署,包括云基础设施.
相关概念视频
Polymers: Defining Molecular Weight
2.9K
Unlike small molecules with definite molecular weights, polymers are a mixture of individual polymer chains of varying lengths, each with a unique molecular weight. So, the molecular weight of a polymer is expressed as an average value based on the average size of the polymer chains. The two most common forms of averages used for polymers are the number average molecular weight and weight average molecular weight.
The number average molecular weight (Mn) is the summation of the number...
The number average molecular weight (Mn) is the summation of the number...
2.9K
Polymers: Molecular Weight Distribution
3.5K
For any given polymer, the weight average molecular weight (Mw) is higher than, if not equal to, the number average molecular weight (Mn). The only situation in which the weight average molecular weight and the number average molecular weight are equal is when a polymer consists only of chains with equal molecular weight. However, this never happens in a synthetic polymer, since it is difficult to control the polymerization process up to a molecular level with accuracy to a hundred percent.
3.5K
Polymers
35.9K
The word polymer is derived from the Greek words “poly” which means “many” and “mer” which means “parts”. Polymers are long chains of molecules composed of repeating units of smaller molecules, known as monomers. They either occur naturally, such as DNA and proteins, or can be constructed synthetically, like plastics. They have varied structural characteristics, such as linear chains, branched chains, or complex networks, that contribute to the...
35.9K
ATP and Macromolecule Synthesis
5.6K
Biological macromolecules are organic compounds, predominantly composed of carbon atoms. The carbon atoms are covalently bonded with hydrogen, oxygen, nitrogen, and other minor elements. There are four major biological macromolecule classes: carbohydrates, lipids, proteins, and nucleic acids.
Most macromolecules are composed of single subunits, or building blocks, called monomers. The monomers combine with each other using covalent bonds to form larger molecules known as polymers.
Conversion of...
Most macromolecules are composed of single subunits, or building blocks, called monomers. The monomers combine with each other using covalent bonds to form larger molecules known as polymers.
Conversion of...
5.6K
Characteristics and Nomenclature of Homopolymers
3.1K
Polymers that are made up of identical monomer units are called homopolymers. Only one repeating unit is involved in the construction of the homopolymer structure. For example, as depicted in Figure 1, polypropylene is a homopolymer constituted of propylene monomers. Here, the only repeating unit in the polymer chain is propylene.
3.1K
Cationic Chain-Growth Polymerization: Mechanism
2.4K
The cationic polymerization mechanism consists of three steps: initiation, propagation, and termination. In the initiation step of the polymerization process, the π bond of a monomer gets protonated by the Lewis acid catalyst, which is formed from boron trifluoride and water. The protonation of the π bond generates a carbocation stabilized by the electron‐donating group. In the propagation step, the π bond of the second monomer acts as a nucleophile and attacks the...
2.4K


