Nature Language Model: Deciphering the Language of Nature for Scientific Discovery
NatureLM addresses the problem of isolated scientific domain models for researchers and scientists across various fields, providing a generalist approach for tasks like drug discovery, material design, and therapeutic protein development.
The Nature Language Model (NatureLM) tackles the problem of integrating multiple scientific domains by representing entities as sequences, achieving state-of-the-art performance across different domains, and offering a unified model for various applications, with performance improving as model size increases from 1 billion to 46.7 billion parameters. NatureLM enables applications such as generating and optimizing small molecules, proteins, and materials, and achieves top performance in tasks like drug discovery and material design.
Foundation models have revolutionized natural language processing and artificial intelligence, significantly enhancing how machines comprehend and generate human languages. Inspired by the success of these foundation models, researchers have developed foundation models for individual scientific domains, including small molecules, materials, proteins, DNA, RNA and even cells. However, these models are typically trained in isolation, lacking the ability to integrate across different scientific domains. Recognizing that entities within these domains can all be represented as sequences, which together form the "language of nature", we introduce Nature Language Model (NatureLM), a sequence-based science foundation model designed for scientific discovery. Pre-trained with data from multiple scientific domains, NatureLM offers a unified, versatile model that enables various applications including: (i) generating and optimizing small molecules, proteins, RNA, and materials using text instructions; (ii) cross-domain generation/design, such as protein-to-molecule and protein-to-RNA generation; and (iii) top performance across different domains, matching or surpassing state-of-the-art specialist models. NatureLM offers a promising generalist approach for various scientific tasks, including drug discovery (hit generation/optimization, ADMET optimization, synthesis), novel material design, and the development of therapeutic proteins or nucleotides. We have developed NatureLM models in different sizes (1 billion, 8 billion, and 46.7 billion parameters) and observed a clear improvement in performance as the model size increases.