regLM: Designing Realistic Regulatory DNA with Autoregressive Language Models

Avantika Lal, David Garfield, Tommaso Biancalani, Gökcen Eraslan

Abstract: We present regLM, a framework to design synthetic CREs with desired properties, such as high, low or cell type-specific activity, using autoregressive language models in conjunction with supervised sequence-to-function models. Using regLM, we designed synthetic yeast promoters of defined strength, as well as cell type-specific human enhancers. We show that the synthetic CREs generated by regLM contain biological features similar to experimentally validated CREs.