RegDesign-Bench: Benchmarking computational methods for cell-type-specific regulatory DNA design
- 1Zhongguancun Academy
Abstract
The de novo design of regulatory DNA sequences that drive cell-type-specific gene expression could enable precise gene control in synthetic biology, cell engineering and gene therapy. Various computational methods have been developed for this task, yet systematic comparisons that guide method selection for different design objectives remain limited. Here, we introduce RegDesign-Bench, a standardized framework for evaluating cell-type-specific cis-regulatory element design through a comprehensive set of computational analyses. Among the methods tested, strong predicted activity was not consistently accompanied by cell-type-selective accessibility or prominent cell-type-associated motif signals. Similarity to reference sequence distributions also did not ensure high predicted target-cell activity or specificity. These findings demonstrate that favourable performance on individual measurements does not necessarily extend across regulatory properties and library characteristics, revealing application-dependent strengths and limitations of current design methods. Overall, RegDesign-Bench offers a general-purpose computational framework for comparing and selecting methods to design regulatory DNA that drives cell-type-specific gene expression.
Related
- OncoSpot enables benchmarking of cancer spatial transcriptomics methods across tumor evolutionary modes
- Benchmarking normalisation methods for differential binding analysis in CUT&RUN
- Benchmarking interface confidence as a selection criterion for computational nanobody design against survivin's BIR-domain groove
- Benchmarking Microbiome Methods for Improved Metagenomic Sequencing of Lower Respiratory Tract Samples
- BixBench3: Benchmarking AI agents on research-study-scale computational biology tasks
BibTeX
@misc{xu2026regdesignbench,
title = {{RegDesign-Bench: Benchmarking computational methods for cell-type-specific regulatory DNA design}},
author = {J. Xu and Z. Guo and C. Zhong and Q. Yin and Y. He and Z. Chen and H. Xin and P. Jin and P. Deng},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.18.759890},
url = {https://www.biorxiv.org/content/10.64898/2026.10.18.759890v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - RegDesign-Bench: Benchmarking computational methods for cell-type-specific regulatory DNA design
AU - J. Xu
AU - Z. Guo
AU - C. Zhong
AU - Q. Yin
AU - Y. He
AU - Z. Chen
AU - H. Xin
AU - P. Jin
AU - P. Deng
PY - 2026
DA - 2026/10/18
PB - bioRxiv
DO - 10.64898/2026.10.18.759890
UR - https://www.biorxiv.org/content/10.64898/2026.10.18.759890v1
AB - The de novo design of regulatory DNA sequences that drive cell-type-specific gene expression could enable precise gene control in synthetic biology, cell engineering and gene therapy. Various computational methods have been developed for this task, yet systematic comparisons that guide method selection for different design objectives remain limited. Here, we introduce RegDesign-Bench, a standardized framework for evaluating cell-type-specific cis-regulatory element design through a comprehensive set of computational analyses. Among the methods tested, strong predicted activity was not consistently accompanied by cell-type-selective accessibility or prominent cell-type-associated motif signals. Similarity to reference sequence distributions also did not ensure high predicted target-cell activity or specificity. These findings demonstrate that favourable performance on individual measurements does not necessarily extend across regulatory properties and library characteristics, revealing application-dependent strengths and limitations of current design methods. Overall, RegDesign-Bench offers a general-purpose computational framework for comparing and selecting methods to design regulatory DNA that drives cell-type-specific gene expression.
ER -