From Sentences to Sequences: Rethinking Languages in Biological System
This work provides insights for researchers in computational biology and bioinformatics on effectively translating NLP successes to biological domains, though it appears incremental in adapting existing paradigms.
The paper revisits the concept of language in biological systems to address the fundamental differences in structural correlations between natural and biological languages, demonstrating the applicability of auto-regressive generation in biological language modeling by treating 3D biomolecular structures as semantic content.
The paradigm of large language models in natural language processing (NLP) has also shown promise in modeling biological languages, including proteins, RNA, and DNA. Both the auto-regressive generation paradigm and evaluation metrics have been transferred from NLP to biological sequence modeling. However, the intrinsic structural correlations in natural and biological languages differ fundamentally. Therefore, we revisit the notion of language in biological systems to better understand how NLP successes can be effectively translated to biological domains. By treating the 3D structure of biomolecules as the semantic content of a sentence and accounting for the strong correlations between residues or bases, we highlight the importance of structural evaluation and demonstrate the applicability of the auto-regressive paradigm in biological language modeling. Code can be found at \href{https://github.com/zjuKeLiu/RiFold}{github.com/zjuKeLiu/RiFold}