Conditional Monte Carlo Tree Diffusion for Designing Cell-Type-Specific and Biologically Faithful Regulatory DNA
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911614690656256 |
|---|---|
| author | Awasthi, Animesh Bednarsky, Raphael Schaefer, Moritz Bock, Christoph |
| author_facet | Awasthi, Animesh Bednarsky, Raphael Schaefer, Moritz Bock, Christoph |
| contents | Designing regulatory DNA elements with precise cell-type-specific activity is broadly relevant for cell engineering and gene therapy. Deep generative models can generate functional gene-regulatory elements, but existing methods struggle to achieve high specificity against undesired cell types while adhering to the genome's natural regulatory grammar. Here, we introduce DNA-CRAFT, a generative framework that integrates class-conditioned discrete diffusion with Monte Carlo tree search to design cell-type-specific and biologically faithful regulatory elements. We first train a discrete diffusion model on the ENCODE registry of 3.2 million candidate regulatory elements. Second, we condition the model to learn class-specific regulatory grammars of naturally occurring DNA sequences, including enhancers and promoters. Third, we employ conditional Monte Carlo tree guidance, an inference-time alignment algorithm designed to maximize the differential regulatory activity between desired and undesired cell types. By benchmarking DNA-CRAFT on regulatory sequence design tasks for human cell lines and immune cell types, we demonstrate that our model generates sequences with high predicted cell-type-specific activity and biological fidelity, achieving the best trade-offs compared to methods that use diffusion, autoregressive models, and gradient-based optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_20488 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Conditional Monte Carlo Tree Diffusion for Designing Cell-Type-Specific and Biologically Faithful Regulatory DNA Awasthi, Animesh Bednarsky, Raphael Schaefer, Moritz Bock, Christoph Genomics Designing regulatory DNA elements with precise cell-type-specific activity is broadly relevant for cell engineering and gene therapy. Deep generative models can generate functional gene-regulatory elements, but existing methods struggle to achieve high specificity against undesired cell types while adhering to the genome's natural regulatory grammar. Here, we introduce DNA-CRAFT, a generative framework that integrates class-conditioned discrete diffusion with Monte Carlo tree search to design cell-type-specific and biologically faithful regulatory elements. We first train a discrete diffusion model on the ENCODE registry of 3.2 million candidate regulatory elements. Second, we condition the model to learn class-specific regulatory grammars of naturally occurring DNA sequences, including enhancers and promoters. Third, we employ conditional Monte Carlo tree guidance, an inference-time alignment algorithm designed to maximize the differential regulatory activity between desired and undesired cell types. By benchmarking DNA-CRAFT on regulatory sequence design tasks for human cell lines and immune cell types, we demonstrate that our model generates sequences with high predicted cell-type-specific activity and biological fidelity, achieving the best trade-offs compared to methods that use diffusion, autoregressive models, and gradient-based optimization. |
| title | Conditional Monte Carlo Tree Diffusion for Designing Cell-Type-Specific and Biologically Faithful Regulatory DNA |
| topic | Genomics |
| url | https://arxiv.org/abs/2604.20488 |