SynLlama:用大型语言模型生成可合成的分子及其类似物
Kunyang Sun1, Dorian Bagni1, Joseph M Cavanagh1
1Kenneth S. Pitzer Theory Center and Department of Chemistry.
ArXiv
|May 5, 2025
概括
SynLlama是一个精心调整的大型语言模型 (LLM),为新药候选者生成实用的合成途径. 这种人工智能工具通过克服合成挑战并有效地探索更广泛的化学空间来增强小分子药物发现.
科学领域:
- 计算化学是一种计算化学.
- 人工智能在药物发现中的作用
- 有机合成 有机合成
背景情况:
- 生成型人工智能模型对小分子药物发现有希望.
- 一个关键的限制是产生具有复杂或不切实际合成路径的分子.
- 这阻碍了人工智能发现的化合物的进一步发展.
研究的目的:
- 开发一种新的AI方法来生成可合成的分子及其完整的合成途径.
- 微调Meta的Llama3大型语言模型 (LLM) 以实现强大的有机合成规划.
- 创建SynLlama,一个解决生成药物发现中的合成性挑战的AI工具.
主要方法:
- 微调Meta的Llama3大型语言模型 (LLM),以创建SynLlama.
- 关于有机反应模板和可访问的构建块的培训SynLlama.
- 评估SynLlama在自下而上的合成,模拟生成和打击扩展方面的表现.
主要成果:
- SynLlama使用可访问的构建块和反应模板生成完整的合成路径.
- 该模型探索了一个巨大的可合成化学空间,使用的数据比最先进的方法少.
- SynLlama展示了对未见的构建块的有效概括,扩大了其重建能力.
- 在模拟分子的合成规划中成功应用,并在制药环境中成功扩展.
结论:
- SynLlama为药物化学家提供了一种有价值的工具,在产生性药物发现中克服合成障碍.
- 该模型显著提高了人工智能驱动的小分子设计的实用性和效率.
- SynLlama 的概括能力扩大了可用于药物开发的可合成化学空间.
相关概念视频
Synthetic Biology
4.7K
Synthetic biology is an interdisciplinary science that involves using principles from disciplines such as engineering, molecular biology, cell biology, and systems biology. It involves remodeling existing organisms from nature or constructing completely new synthetic organisms for applications such as protein or enzyme production, bioremediation, value-added macromolecule production, and the addition of desirable traits to crops, to name a few.
Golden rice
Golden rice is a genetically modified...
Golden rice
Golden rice is a genetically modified...
4.7K
Molecular Models
37.5K
Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
37.5K
ATP and Macromolecule Synthesis
5.1K
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...
5.1K
Synthesis and Decomposition Reactions
31.8K
Synthesis and decomposition are two types of redox reactions. Synthesis means to make something, whereas decomposition means to break something. The reactions are accompanied by chemical and energy changes.
31.8K
Preparation of 1° Amines: Gabriel Synthesis
3.4K
Direct alkylation is not a suitable method for synthesizing amines because it produces polyalkylated products. Gabriel synthesis is the most preferred method to exclusively make primary amines. The method uses phthalimide, which contains a protected form of nitrogen that participates in alkylation only once to predominantly give primary amines.
Strong bases like NaOH or KOH deprotonate the phthalimide to form the corresponding anion, which acts as a nucleophile. Further, the anion attacks an...
Strong bases like NaOH or KOH deprotonate the phthalimide to form the corresponding anion, which acts as a nucleophile. Further, the anion attacks an...
3.4K
Polymers
33.8K
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...
33.8K


