Biofy Technologies Advancing Science: AI Breakthroughs Reveal Diversity of Microbial Proteins with the Global smORFs Catalog

Our Head of Life Sciences & AI, Celio Dias Santos Junior, recently co-published an innovative study in the prestigious journal Nature Communications, in collaboration with the Big Data Research Group led by Prof. Luis Pedro Coelho, and spearheaded by PhD candidate Yiqian Duan. The study highlights the production of a global catalog of microbial peptide-coding genes (smORFs), an important advancement in the field of Artificial Intelligence applied to biotechnology.

The smORFs ("small genes" in free translation) encode proteins with fewer than 100 codons and play crucial roles in various cellular functions of microorganisms, such as signaling pathways, stress responses, and antibacterial activities. However, until now, the ecology, distribution, and function of these small proteins in the global microbiome remained unknown.

Celio Dias in front of the Group's office

The study, which involved researchers from around the world, resulted in the construction of a global catalog of microbial smORFs (GMSC), derived from 63,410 public metagenomes and 87,920 high-quality isolated genomes, covering 75 distinct habitats. The GMSC contains an impressive 965 million non-redundant smORFs, all with detailed annotations, revealing an immense and underexplored diversity of small proteins. An interesting finding was the discovery that archaea have a higher proportion of smORFs than bacteria.

Furthermore, the team developed the GMSC-mapper tool, designed to identify and annotate small proteins from microbial genomes and metagenomes, allowing new insights into this class of proteins.

"This work highlights how AI and Big Data analysis can transform the understanding of global microbial systems, revealing new ecological and biochemical patterns that could have a direct impact on areas such as biotechnology, health, and the development of new antibacterial treatments," Santos stated.

Once again, Biofy positions itself as a leader in advancing science and innovation, contributing to discoveries that shape the future of biotechnology.

Check out the full article: https://www.nature.com/articles/s41467-024-51894-6