# Coupling streaming AI and HPC ensembles to achieve 100-1000x faster biomolecular simulations

arXiv: https://arxiv.org/abs/2104.04797 · HTML: https://mlsanity.com/paper/2104.04797/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 66 references that are in the map.
- First posted on arXiv 10 Apr 2021.

## Builds on (most cited first, 14 of 14)

- [VAMPnets: Deep learning of molecular kinetics](https://mlsanity.com/paper/1710.06012/) (2017)
- [NVIDIA SimNet^{TM}: an AI-accelerated multi-physics simulation framework](https://mlsanity.com/paper/2012.07938/) (2020)
- [TorchMD: A deep learning framework for molecular simulations](https://mlsanity.com/paper/2012.12106/) (2020)
- [Variational Encoding of Complex Dynamics](https://mlsanity.com/paper/1711.08576/) (2017)
- [DeepDriveMD: Deep-Learning Driven Adaptive Molecular Simulations for Protein Folding](https://mlsanity.com/paper/1909.07817/) (2019)
- [Design and Performance Characterization of RADICAL-Pilot on Leadership-class Platforms](https://mlsanity.com/paper/2103.00091/) (2021)
- [Pandemic Drugs at Pandemic Speed: Infrastructure for Accelerating COVID-19 Drug Discovery with Hybrid Machine Learning- and Physics-based Simulations on High Performance Computers](https://mlsanity.com/paper/2103.02843/) (2021)
- [RADICAL-Cybertools: Middleware Building Blocks for Scalable Science](https://mlsanity.com/paper/1904.03085/) (2019)
- [IMPECCABLE: Integrated Modeling PipelinE for COVID Cure by Assessing Better LEads](https://mlsanity.com/paper/2010.06574/) (2020)
- [Machine Learning for Molecular Dynamics on Long Timescales](https://mlsanity.com/paper/1812.07669/) (2018)
- [A Comprehensive Perspective on Pilot-Job Systems](https://mlsanity.com/paper/1508.04180/) (2015)
- [Harnessing the Power of Many: Extensible Toolkit for Scalable Ensemble Applications](https://mlsanity.com/paper/1710.08491/) (2017)
- [Adaptive Ensemble Biomolecular Simulations at Scale](https://mlsanity.com/paper/1804.04736/) (2018)
- [Artificial intelligence techniques for integrative structural biology of intrinsically disordered proteins](https://mlsanity.com/paper/2012.00885/) (2020)

## Built on by (most cited first, 8 of 8)

- [Training Deep Surrogate Models with Large Scale Online Learning](https://mlsanity.com/paper/2306.16133/) (2023)
- [High Throughput Training of Deep Surrogates from Large Ensemble Runs](https://mlsanity.com/paper/2309.16743/) (2023)
- [Employing Artificial Intelligence to Steer Exascale Workflows with Colmena](https://mlsanity.com/paper/2408.14434/) (2024)
- [Connecting Large Language Model Agent to High Performance Computing Resource](https://mlsanity.com/paper/2502.12280/) (2025)
- [Asynchronous Execution of Heterogeneous Tasks in ML-driven HPC Workflows](https://mlsanity.com/paper/2208.11069/) (2022)
- [Simulation-Based Parallel Training](https://mlsanity.com/paper/2211.04119/) (2022)
- [From Edge to HPC: Investigating Cross-Facility Data Streaming Architectures](https://mlsanity.com/paper/2509.24030/) (2025)
- [LUMOS: Democratizing SciML Workflows with L0-Regularized Learning for Unified Feature and Parameter Adaptation](https://mlsanity.com/paper/2602.22537/) (2026)

## Abstract (arXiv)

Machine learning (ML)-based steering can improve the performance of ensemble-based simulations by allowing for online selection of more scientifically meaningful computations. We present DeepDriveMD, a framework for ML-driven steering of scientific simulations that we have used to achieve orders-of-magnitude improvements in molecular dynamics (MD) performance via effective coupling of ML and HPC on large parallel computers. We discuss the design of DeepDriveMD and characterize its performance. We demonstrate that DeepDriveMD can achieve between 100-1000x acceleration for protein folding simulations relative to other methods, as measured by the amount of simulated time performed, while covering the same conformational landscape as quantified by the states sampled during a simulation. Experiments are performed on leadership-class platforms on up to 1020 nodes. The results establish DeepDriveMD as a high-performance framework for ML-driven HPC simulation scenarios, that supports diverse MD simulation and ML back-ends, and which enables new scientific insights by improving the length and time scales accessible with current computing capacity.