G. Brixi

Few-shot regulatory sequence design with a genomic language model

Efficient biological design via genomic in-context learning

It is shown that ICL emerges in the genome language model Evo 2 and enables biological design and is established as a versatile and efficient paradigm for biological sequence design.

Coevolutionary mining of prokaryotic non-coding elements with a genome language model

Microbial genomes encode non-coding RNAs (ncRNAs) and nucleic-acid-interacting proteins essential to biology and biotechnology. However, discovery of these systems remains protein-centric and based on similarity to known sequences. Here, we introduce Minerva, a framework for coevolutionary mining that uses genome langu...

Forecasting viral evolution from phylogenetic trees

This work introduces antiGen, a machine learning model that forecasts the evolutionary future of viruses by learning from their evolutionary past, and achieves state-of-the-art performance for predicting mutations to the SARS-CoV-2 spike protein.