genome

Reads a million letters of DNA at once and predicts how a mutation changes gene regulation, splicing and chromatin.

Scored all 71 million possible single-letter protein changes in humans as likely harmful or benign.

Models that predict how DNA sequence controls gene activity, used to interpret non-coding cancer mutations.

A DNA language model trained on 9.3 trillion bases that can flag cancer-causing BRCA1 variants without being told about them.

DNA language models trained on thousands of genomes for variant and regulatory prediction.