Charlotte Rochereau

GENTANGLE is a computational tool for designing overlapping gene pairs in microbial genomes, enabling safer genetic engineering through gene entanglements.

Protein-specific tuning of masking, depth and positional embeddings, rather than more parameters, yields an encoder-decoder model that tops structure and function benchmarks at a fraction of the compute.

This paper introduces RGN2, a deep learning model that predicts protein structure from single sequences without MSAs, outperforming AlphaFold2 and RoseTTAFold on orphan proteins and achieving faster computation.