Protein Language Model Embeddings Improve Generalization of Implicit Transfer Operators

2026-02-11

AI Summary

This work addresses the high computational cost of conventional molecular dynamics sampling and the limited generalization capability of existing generative models by proposing the PLaTITO framework. PLaTITO uniquely integrates protein language models (pLMs) into a Transferable Implicit Transition Operator (TITO), effectively fusing multimodal conditioning signals—including structural features, temperature, and pLM-derived representations. The approach substantially enhances both the efficiency and accuracy of equilibrium sampling for out-of-distribution protein systems. It achieves state-of-the-art performance on benchmark tasks such as fast-folding proteins and demonstrates that coarse-grained TITO exhibits superior data efficiency compared to Boltzmann generators.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Molecular dynamics (MD) is a central computational tool in physics, chemistry, and biology, enabling quantitative prediction of experimental observables as expectations over high-dimensional molecular distributions such as Boltzmann distributions and transition densities. However, conventional MD is fundamentally limited by the high computational cost required to generate independent samples. Generative molecular dynamics (GenMD) has recently emerged as an alternative, learning surrogates of molecular distributions either from data or through interaction with energy models. While these methods enable efficient sampling, their transferability across molecular systems is often limited. In this work, we show that incorporating auxiliary sources of information can improve the data efficiency and generalization of transferable implicit transfer operators (TITO) for molecular dynamics. We find that coarse-grained TITO models are substantially more data-efficient than Boltzmann Emulators, and that incorporating protein language model (pLM) embeddings further improves out-of-distribution generalization. Our approach, PLaTITO, achieves state-of-the-art performance on equilibrium sampling benchmarks for out-of-distribution protein systems, including fast-folding proteins. We further study the impact of additional conditioning signals -- such as structural embeddings, temperature, and large-language-model-derived embeddings -- on model performance.

Problem

• molecular dynamics
• transferability
• out-of-distribution generalization
• protein language models
• implicit transfer operators

Innovation

• Protein Language Model
• Transferable Implicit Transfer Operators
• Generative Molecular Dynamics
• Out-of-Distribution Generalization
• Equilibrium Sampling