Fusing Neural and Physical: Augment Protein Conformation Sampling with Tractable Simulations
Track: Machine learning: computational method and/or computational results
Keywords: proteins, conformational sampling, diffusion models, score-based models, generative modeling, equivariant network, molecular simulation
TL;DR: We proposed a novel way to couple and fine-tune the score-based protein conformation sampler with short molecular dynamics simulations
Abstract: The protein dynamics are common and important for their biological functions and properties, the study of which usually involves time-consuming molecular dynamics (MD) simulations *in silico*. Recently, generative models has been leveraged as a surrogate sampler to obtain conformation ensembles with orders of magnitude faster and without requiring any simulation data (a "zero-shot" inference). However, being agnostic of the underlying energy landscape, the accuracy of such generative model may still be limited. In this work, we explore the few-shot setting of such pre-trained generative sampler which incorporates MD simulations in a tractable manner. Specifically, given a target protein of interest, we first acquire some seeding conformations from the pre-trained sampler followed by a number of physical simulations in parallel starting from these seeding samples. Then we fine-tuned the generative model using the simulation trajectories above to become a target-specific sampler. Experimental results demonstrated the superior performance of such few-shot conformation sampler at a tractable computational cost.
Submission Number: 6
Loading