MProt-DPO: Breaking the ExaFLOPS Barrier for Multimodal Protein Design Workflows with Direct Preference Optimization

Gautham Dharuman, Kyle Hippe, Alexander Brace, Sam Foreman, Väinö Hatanpää, Varuni Katti Sastry, Huihuo Zheng, Logan T. Ward, Servesh Muralidharan, Archit Vasan, Bharat Kale, Carla M. Mann, Heng Ma, Yun-Hsuan Cheng, Yuliana Zamora, Shengchao Liu, Chaowei Xiao, Murali Emani, Tom Gibbs, Mahidhar Tatineni, Deepak Canchi, Jerome Mitchell, Koichi Yamada, Maria Garzaran, Michael E. Papka, Ian T. Foster, Rick Stevens, Anima Anandkumar, Venkatram Vishwanath, Arvind Ramanathan

Abstract

We present a scalable, end-to-end workflow for protein design. By augmenting protein sequences with natural language descriptions of their biochemical properties, we train generative models that can be preferentially aligned with protein fitness landscapes. Through complex experimental- and simulation-based observations, we integrate these measures as preferred parameters for generating new protein variants and demonstrate our workflow on five diverse supercomputers. We achieve >1 ExaFLOPS sustained performance in mixed precision on each supercomputer and a maximum sustained performance of 4.11 ExaFLOPS and peak performance of 5.57 ExaFLOPS. We establish the scientific performance of our model on two tasks: (1) across a predetermined benchmark dataset of deep mutational scanning experiments to optimize the fitness-determining mutations in the yeast protein HIS7, and (2) in optimizing the design of the enzyme malate dehydrogenase to achieve lower activation barriers (and therefore increased catalytic rates) using simulation data. Our implementation thus sets high watermarks for multimodal protein design workflows.
BibTeX
@inproceedings{dharuman2024mprot,
  author = {Gautham Dharuman and Kyle Hippe and Alexander Brace and Sam Foreman and Väinö Hatanpää and Varuni Katti Sastry and Huihuo Zheng and Logan T. Ward and Servesh Muralidharan and Archit Vasan and Bharat Kale and Carla M. Mann and Heng Ma and Yun-Hsuan Cheng and Yuliana Zamora and Shengchao Liu and Chaowei Xiao and Murali Emani and Tom Gibbs and Mahidhar Tatineni and Deepak Canchi and Jerome Mitchell and Koichi Yamada and Maria Garzaran and Michael E. Papka and Ian T. Foster and Rick Stevens and Anima Anandkumar and Venkatram Vishwanath and Arvind Ramanathan},
  title = {{MProt-DPO: Breaking the ExaFLOPS Barrier for Multimodal Protein Design Workflows with Direct Preference Optimization}},
  booktitle = {SC},
  year = {2024},
}

Loading related content...

Figure