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

Harmony AI: State of the Art Natural Language Processing for Genetic Engineering

Harmony AI：用于基因工程的最先进的自然语言处理

基本信息

批准号：
10698805
负责人：
David Gaddes
金额：
$ 34.35万
依托单位：
CFD RESEARCH CORPORATION
依托单位国家：
美国
项目类别：
财政年份：
2023
资助国家：
美国
起止时间：
2023-09-22 至 2024-08-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10698805
关键词：
Affect Amino Acid Sequence Artificial Intelligence Artificial Intelligence platform Benchmarking Cells Code Codon Nucleotides Complex Computational Technique Computer software DNA Sequence Dependence Development Engineered Gene Ensure Escherichia coli Escherichia coli Proteins Frequencies Genes Genetic Engineering Human In Vitro Industry Learning Literature Methods Modeling Molecular Chaperones Multiprotein Complexes Natural Language Processing Organism Output Pharmaceutical Preparations Positioning Attribute Production Protein Conformation Proteins RNA vaccine Recombinant Proteins Reporting Research Research Personnel Running System Techniques Technology Testing Therapeutic Tissues Traction Training Translating Treatment Efficacy Work design gene therapy hands-on learning human model improved manufacture multimodality nucleic acid-based therapeutics prevent process optimization protein expression protein folding protein function therapeutically effective tool

项目摘要

Project Summary/Abstract: Computational techniques for gene engineering, such as codon optimization, use synonymous codon changes to increase protein production. Applications for these computational gene optimizations include recombinant protein drugs, nucleic acid therapies, and mRNA vaccines. Although codon optimization increases protein production in certain systems, synonymous changes to a gene sequence can cause unexpected detrimental results to the protein. Further, researchers have been critical of codon optimization for human therapeutics as the optimization process can affect protein conformation and function, and reduce efficacy. Therefore, codon optimization may not provide an optimal strategy for increasing protein production or designing safe and effective therapeutics. CFDRC has utilized state-of-the-art natural language processing techniques to learn how synonymous codons are used by a target organism and apply this learning to gene engineering. We demonstrated our model could predict the E. Coli synonymous codon usage with 73% accuracy, significantly above prior reports. We believe that using this AI-based approach to gene engineering will provide an optimal strategy for increasing protein production and may increase the efficacy of therapeutics.

项目概要/摘要：基因工程的计算技术，如密码子优化，使用同义词，改变密码子以增加蛋白质产量。这些计算基因的应用优化包括重组蛋白药物、核酸疗法和mRNA疫苗。虽然密码子优化在某些系统中增加蛋白质产量，但同义词基因序列的改变会对蛋白质造成意想不到的有害结果。此外，本发明还研究人员一直批评用于人类治疗的密码子优化，过程会影响蛋白质的构象和功能，并降低功效。因此，密码子优化可能不能提供用于增加蛋白质产量或设计安全有效的治疗方法。CFDRC利用了最先进的自然语言处理技术了解目标生物体如何使用同义密码子并应用这种学习的技术到基因工程我们证明了我们的模型可以预测E。大肠杆菌同义密码子准确率为73%，明显高于之前的报告。我们相信，使用这种基于人工智能的基因工程的方法将为增加蛋白质产量提供最佳策略并且可以增加治疗剂的功效。