regLM: Designing realistic regulatory DNA with autoregressive language models
Lal, A.; Garfield, D.; Biancalani, T.; Eraslan, G.
Show abstract
Cis-regulatory elements (CREs), such as promoters and en-hancers, are DNA sequences that regulate the expression of genes. The activity of a CRE is influenced by the order, composition and spacing of sequence motifs that bind to proteins called transcription factors (TFs). Synthetic CREs with specific properties are needed for biomanufacturing as well as for many therapeutic applications including cell and gene therapy. Here, 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. We used our framework to design synthetic yeast promoters and cell type-specific human enhancers. We demonstrate that the synthetic CREs generated by our approach are not only predicted to have the desired functionality but also contain biological features similar to experimentally validated CREs. regLM thus facilitates the design of realistic regulatory DNA elements while providing insights into the cis-regulatory code.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Enhancers display constrained sequence flexibility and context-specific modulation of motif function 95%
- Delineating yeast cleavage and polyadenylation signals using deep learning 94%
- Identifying transcription factor-bound gene activators and silencers in the chromatin accessible human genome using ATAC-STARR-seq 94%
Similar papers in this journal
- Polygraph: A Software Framework for the Systematic Assessment of Synthetic Regulatory DNA Elements 98%
- Integrative epigenomic and functional characterization assay based annotation of regulatory activity across diverse human cell types 96%
- Biologically-relevant transfer learning improves transcription factor binding prediction 95%
Similar papers in this journal
- Model-driven generation of artificial yeast promoters 95%
- Systematic analysis of low-affinity transcription factor binding site clusters in vitro and in vivo establishes their functional relevance 95%
- Massively parallel reporter perturbation assay uncovers temporal regulatory architecture during neural differentiation 95%
Similar papers in this journal
Similar papers in this journal
- Developing a general AI model for integrating diverse genomic modalities and comprehensive genomic knowledge 95%
- Deciphering the 3D genome organization across species from Hi-C data 95%
- RoboCOP: Jointly computing chromatin occupancy profiles for numerous factors from chromatin accessibility data 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.