Understanding the relationships between protein sequence, structure and function is a long-standing biological challenge with manifold implications from drug design to our understanding of evolution. Recently, protein language models have emerged as the preferred method for this challenge, thanks to their ability to harness large sequence databases. Yet, their reliance on expansive sequence data and parameter sets limits their flexibility and practicality in real-world scenarios. Concurrently, the recent surge in computationally predicted protein structures unlocks new opportunities in protein representation learning. While promising, the computational burden carried by such complex data still hinders widely-adopted practical applications. To address these limitations, we introduce a novel framework that enhances protein language models by integrating protein structural data. Drawing from recent advances in graph transformers, our approach refines the self-attention mechanisms of pretrained language transformers by integrating structural information with structure extractor modules. This refined model, termed Protein Structure Transformer (PST), is further pretrained on a small protein structure database, using the same masked language modeling objective as traditional protein language models. Empirical evaluations of PST demonstrate its superior parameter efficiency relative to protein language models, despite being pretrained on a dataset comprising only 542K structures. Notably, PST consistently outperforms the state-of-the-art foundation model for protein sequences, ESM-2, setting a new benchmark in protein function prediction. Our findings underscore the potential of integrating structural information into protein language models, paving the way for more effective and efficient protein modeling Code and pretrained models are available at https://github.com/BorgwardtLab/PST.

翻译：理解蛋白质序列、结构和功能之间的关系是一项长期的生物学挑战，对药物设计乃至我们对进化的理解具有多方面的影响。近年来，蛋白质语言模型凭借其利用大型序列数据库的能力，已成为应对这一挑战的首选方法。然而，它们对大量序列数据和参数集的依赖限制了其在现实场景中的灵活性和实用性。与此同时，最近计算预测的蛋白质结构的激增为蛋白质表示学习开启了新的机遇。尽管前景广阔，但这类复杂数据带来的计算负担仍然阻碍着广泛采用的实际应用。为应对这些限制，我们引入了一种新框架，通过整合蛋白质结构数据来增强蛋白质语言模型。借鉴图变换器的最新进展，我们的方法通过结构提取器模块将结构信息与预训练语言变换器的自注意力机制相结合。这种改进后的模型被称为蛋白质结构变换器（PST），并在小型蛋白质结构数据库上进行进一步预训练，使用与传统蛋白质语言模型相同的掩码语言建模目标。对PST的实证评估表明，其参数效率优于蛋白质语言模型，尽管其仅基于包含542K个结构的数据库进行预训练。值得注意的是，PST一致优于最先进的蛋白质序列基础模型ESM-2，为蛋白质功能预测树立了新标杆。我们的研究结果强调了将结构信息整合到蛋白质语言模型中的潜力，为更有效、高效的蛋白质建模铺平了道路。代码和预训练模型可在 https://github.com/BorgwardtLab/PST 获取。