Regulatory grammar design of tissue-specific enhancers across species

Enhancers encode tissue-specific gene expression through the combinatorial identity, number, and arrangement of transcription factor motifs, collectively known as regulatory grammar. However, existing deep-learning methods directly optimize nucleotide sequences, leaving enhancer regulatory grammar implicit. Here we introduce REgulatory Grammar Architecture via reinforcement Learning (REGAL), a framework that explicitly programs enhancer grammar under sequence-to-function oracles. REGAL generated tissue-specific enhancers across species using the same placement architecture with interchangeable oracles and motif vocabularies. Experimental validation and perturbation revealed that tissue specificity requires coordinated target-tissue activation and off-target repression, depends on both motif composition and spatial organization, and employs distinct regulatory strategies across tissues. REGAL-designed enhancers drove predicted lineage-specific expression in transgenic mouse embryos, outperformed a nucleotide-level optimizer in human cells, and matched or exceeded leading designs in zebrafish and Drosophila at notably shorter length. Together, these findings establish regulatory grammar as a programmable and experimentally testable substrate underlying enhancer design and specificity.

Authors

Institutions

Publication Details

Journal
bioRxiv (Cold Spring Harbor Laboratory)
Published
2026-11-18
DOI
https://doi.org/10.64898/2026.11.17.767007
Primary Topic
Genomics and Chromatin Dynamics
Type
preprint

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Regulatory grammar design of tissue-specific enhancers across species

Ronald A. Conlon, Le Xiong, Takuya F. Sakaguchi, Aniket Jana et al.
4 links
bioRxiv (Cold Spring Harbor Laboratory)
Genomics and Chromatin Dynamics
preprint

Regulatory grammar design of tissue-specific enhancers across species

Ronald A. Conlon, Le Xiong, Takuya F. Sakaguchi, Aniket Jana, Liangqi XIE, Alexandra S. Ruffus, Sanaa Bhuleshkar, Liwen Yao, Mai Ngoc Tran
preprint en

Abstract

Enhancers encode tissue-specific gene expression through the combinatorial identity, number, and arrangement of transcription factor motifs, collectively known as regulatory grammar. However, existing deep-learning methods directly optimize nucleotide sequences, leaving enhancer regulatory grammar implicit. Here we introduce REgulatory Grammar Architecture via reinforcement Learning (REGAL), a framework that explicitly programs enhancer grammar under sequence-to-function oracles. REGAL generated tissue-specific enhancers across species using the same placement architecture with interchangeable oracles and motif vocabularies. Experimental validation and perturbation revealed that tissue specificity requires coordinated target-tissue activation and off-target repression, depends on both motif composition and spatial organization, and employs distinct regulatory strategies across tissues. REGAL-designed enhancers drove predicted lineage-specific expression in transgenic mouse embryos, outperformed a nucleotide-level optimizer in human cells, and matched or exceeded leading designs in zebrafish and Drosophila at notably shorter length. Together, these findings establish regulatory grammar as a programmable and experimentally testable substrate underlying enhancer design and specificity.

bioRxiv (Cold Spring Harbor Laboratory)
Cleveland Clinic (US), Cleveland Clinic Research (US), Case Western Reserve University (US)
Cleveland Clinic, Cleveland Clinic Foundation, National Institutes of Health, National Center for Advancing Translational Sciences, Lawrence Berkeley National Laboratory
Genomics and Chromatin Dynamics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon