Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL

TL;DR

Ctrl-DNA introduces a constrained reinforcement learning framework that enables the design of cell-type-specific regulatory DNA sequences, improving specificity and biological relevance over existing methods.

Contribution

The paper presents a novel RL-based approach that incorporates biological constraints for designing regulatory DNA with precise cell-type specificity.

Findings

Outperforms existing generative and RL methods in sequence quality and specificity.

Generates sequences with key cell-type-specific TFBS.

Achieves state-of-the-art cell-type-specific regulatory DNA design.

Abstract

Designing regulatory DNA sequences that achieve precise cell-type-specific gene expression is crucial for advancements in synthetic biology, gene therapy and precision medicine. Although transformer-based language models (LMs) can effectively capture patterns in regulatory DNA, their generative approaches often struggle to produce novel sequences with reliable cell-specific activity. Here, we introduce Ctrl-DNA, a novel constrained reinforcement learning (RL) framework tailored for designing regulatory DNA sequences with controllable cell-type specificity. By formulating regulatory sequence design as a biologically informed constrained optimization problem, we apply RL to autoregressive genomic LMs, enabling the models to iteratively refine sequences that maximize regulatory activity in targeted cell types while constraining off-target effects. Our evaluation on human promoters and enhancers demonstrates that Ctrl-DNA consistently outperforms existing generative and RL-based approaches, generating high-fitness regulatory sequences and achieving state-of-the-art cell-type specificity. Moreover, Ctrl-DNA-generated sequences capture key cell-type-specific transcription factor binding sites (TFBS), short DNA motifs recognized by regulatory proteins that control gene expression, demonstrating the biological plausibility of the generated sequences.