GPU workstation for deep learning-based protein design and cryo-EM data processing

GPU 工作站，用于基于深度学习的蛋白质设计和冷冻电镜数据处理

• 批准号: 10797767
• 负责人: BRIAN A KUHLMAN
• 金额: $ 4.8万
• 依托单位: UNIV OF NORTH CAROLINA CHAPEL HILL
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-06-01 至 2024-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10797767
• 关键词: Biosensor; Cryoelectron Microscopy; Data; Experimental Designs; Funding; Modeling; Modernization; Performance; Process; Protein Engineering; Proteins; Resolution; Structure; System; Testing; Time; Training; Validation; artificial intelligence method; computerized data processing; computing resources; deep learning; design; design verification; graph neural network; improved; inhibitor; learning strategy; model design; network architecture; neural network; novel strategies; protein structure; protein structure prediction; structural biology; success

Abstract We are requesting funds to purchase a GPU workstation that will be used for (1) deep learning in the context of protein design and (2) for solving protein structures using cryo-EM data. Currently there is a revolution going on protein modeling as deep learning methods have shown impressive success in both protein structure prediction and protein design. We are leveraging these new approaches in several ways that require access to GPU processers. First, we have developed a new protein design pipeline that iterates between protein structure prediction with AlphaFold and sequence optimization with a graph neural network to evolve sequences for a specific function. Initial experimental validation of the pipeline is very encouraging, and we are now eager to test it on a variety of protein design problems including the design of competitive inhibitors, protein switches and biosensors. The pipeline requires large blocks of GPU time (several days with multiple processors) to identify promising designs for experimental validation. Second, we are training new neural networks for improved performance in protein design. Access to GPUs is required for rapidly testing alternative network architectures and hyperparameters. The last step of many protein design projects is validation of the design model with a high-resolution structure. Some of our projects involve systems large enough to be studied with cryo-EM and we are now in need of computational resources to structures from cryo-EM data. Almost all modern cryo EM packages rely on GPUs for processing data.

摘要

项目成果

Advances in modular control of CAR-T therapy with adapter-mediated CARs.

• DOI: 10.1016/j.addr.2022.114358
• 发表时间: 2022-08
• 期刊: Advanced drug delivery reviews
• 影响因子: 16.1

An optogenetic switch for the Set2 methyltransferase provides evidence for transcription-dependent and -independent dynamics of H3K36 methylation.

• DOI: 10.1101/gr.264283.120
• 发表时间: 2020-11
• 期刊: Genome research
• 影响因子: 7
• 作者: Lerner AM;Hepperla AJ;Keele GR;Meriesh HA;Yumerefendi H;Restrepo D;Zimmerman S;Bear JE;Kuhlman B;Davis IJ;Strahl BD
• 通讯作者: Strahl BD

Transfer learning to leverage larger datasets for improved prediction of protein stability changes.

迁移学习利用更大的数据集来改进对蛋白质稳定性变化的预测。

• DOI: 10.1101/2023.07.27.550881
• 发表时间: 2023
• 期刊: bioRxiv : the preprint server for biology
• 作者: Dieckhaus,Henry;Brocidiacono,Michael;Randolph,Nicholas;Kuhlman,Brian
• 通讯作者: Kuhlman,Brian

Computer-based Engineering of Thermostabilized Antibody Fragments.

• DOI: 10.1002/aic.16864
• 发表时间: 2019-11
• 期刊: AIChE journal. American Institute of Chemical Engineers
• 作者: Jiwon Lee;Bryan S. Der;C. Karamitros;Wenzong Li;Nicholas M. Marshall;Oana I. Lungu;Aleksandr E. Miklos;Jianqing Xu;T. Kang;Chang-Han Lee;Bing Tan;R. Hughes;S. Jung;G. Ippolito;Jeffrey J. Gray;Yan Zhang;B. Kuhlman;G. Georgiou;A. Ellington

Design and engineering of light-sensitive protein switches.

• DOI: 10.1016/j.sbi.2022.102377
• 发表时间: 2022-06
• 期刊: CURRENT OPINION IN STRUCTURAL BIOLOGY
• 影响因子: 6.8
• 作者: McCue, Amelia C.;Kuhlman, Brian
• 通讯作者: Kuhlman, Brian