Decoding the Molecular Language of Proteins with Evola

Proteins, nature’s intricate molecular machines, are the products of billions of years of evolution and play fundamental roles in sustaining life. Yet, deciphering their molecular language - that is, understanding how protein sequences and structures encode and determine biological functions - remains a cornerstone challenge in modern biology. Here, we introduce Evola, an 80 billion frontier protein-language generative model designed to decode the molecular language of proteins. By integrating information from protein sequences, structures, and user queries, Evola generates precise and contextually nuanced insights into protein function. A key innovation of Evola lies in its training on an unprecedented AI-generated dataset: 546 million protein question-answer pairs and 150 billion word tokens, designed to reflect the immense complexity and functional diversity of proteins. Post-pretraining, Evola integrates Direct Preference Optimization (DPO) to refine the model based on preference signals and Retrieval-Augmented Generation (RAG) for external knowledge incorporation, improving response quality and relevance. To evaluate its performance, we propose a novel framework, Instructional Response Space (IRS), demonstrating that Evola delivers expert-level insights, advancing research in proteomics and functional genomics while shedding light on the molecular logic encoded in proteins. The online demo is available at http://www.chat-protein.com/ .