Generative protein design can now rapidly produce de novo binders with high affinity and functional activity against a wide range of targets, including lethal snake venom toxins. However, so far most ...

This Article demonstrates that direct preference optimization (DPO) can be used to effectively align an unsupervised structure-conditioned language model with biophysical information. The aligned mode...

This Article demonstrates that direct preference optimization (DPO) can be used to effectively align an unsupervised structure-conditioned language model with biophysical information. The aligned mode...

Many important biological functions arise not from single genes but from complex interactions encoded by entire genomes. We report the first generative design of complete bacteriophage genomes using g...

Many important biological functions arise not from single genes but from complex interactions encoded by entire genomes. We report the first generative design of complete bacteriophage genomes using g...

Germinal achieves epitope-targeted, de novo complementarity-determining region design with high experimental success rates.

YouTube video by Arc Institute

By learning a semantics of gene function based on genomic context, the genomic language model Evo autocompletes DNA prompts to generate novel genes encoding protein and RNA molecules with defined activities, whose sequences generalize beyond those found in nature.

MHC class II immunopeptidomics in human phagocytes infected with Mycobacterium tuberculosis enables vaccine immunogen design and optimization.

Mycobacterium tuberculosis (Mtb) persists within macrophages, yet how different host species shape bacterial state remains poorly understood. Here, we directly compared the intracellular transcriptome...

Many important biological functions arise not from single genes, but from complex interactions encoded by entire genomes. Genome language models have emerged as a promising strategy for designing biol...

Many important biological functions arise not from single genes, but from complex interactions encoded by entire genomes. Genome language models have emerged as a promising strategy for designing biol...

YouTube video by Valence Labs

By treating DNA as a language, Brian Hie’s “ChatGPT for genomes” could pick up patterns that humans can’t see, accelerating biological design.

The genome is a sequence that encodes the DNA, RNA, and proteins that orchestrate an organism’s function. We present Evo, a long-context genomic foundation model with a frontier architecture trained o...