Barrios-Nunez, I. | bioRxiv Science

bioRxiv2024

Illuminating the functional landscape of the dark proteome across the Animal Tree of Life through natural language processing models

Functional annotation is crucial in biology, but many protein-coding genes remain uncharacterized, especially in non-model organisms. FANTASIA (Functional ANnoTAtion based on embedding space SImilArity) integrates protein language models for large-scale functional annotation. Applied to [~]1,000 animal proteomes, it predicts functions to virtually all proteins, revealing previously uncharacterized functions that enhance our understanding of molecular evolution. FANTASIA is available on GitHub at https://github.com/CBBIO/FANTASIA.

evolutionary biology↗

bioRxiv2024

Decoding proteome functional information in model organisms using protein language models.

Protein language models have been tested and proved to be reliable when used on curated datasets but have not yet been applied to full proteomes. Accordingly, we tested how two different machine learning based methods performed when decoding functional information from the proteomes of selected model organisms. We found that protein Language Models are more precise and informative than Deep Learning methods for all the species tested and across the three gene ontologies studied, and that they better recover functional information from transcriptomics experiments. The results obtained indicate that these Language Models are likely to be suitable for large scale annotation and downstream analyses, and we recommend a guide for their use.

bioinformatics↗