Topics

TranscriptFormer was trained on 112 million cells and can compare types across species, including cells the model has never seen.

Researchers at the University of California, Berkeley built an efficient genomic language model that uses evolutionary comparisons to find DNA changes most likely to affect health and inherited traits.

The new SuSiE² statistical framework integrates gene expression data directly into genetic fine mapping, allowing researchers to pinpoint true causal disease variants with unprecedented precision.

A new interpretation method traces each prediction back to individual DNA bases, strips out laboratory artifacts, and points to unexpected rules of how the genome is folded.

Machine learning trained on hundreds of thousands of experiments reveals the sequence pattern that starts gene activity in human cells and opens new ways to study disease mutations.

MIT research shows how strategic gene arrangement on DNA can boost performance of engineered synthetic gene circuits.

Researchers have developed a new way to make virus-like particles more effective at delivering gene-editing tools into human cells by changing the cells that produce them.