Summary: Understanding the “switches” that turn genes on and off is one of biology’s greatest puzzles. While AI has begun to crack this code, the tools have been fragmented and difficult to reuse—until now.
Researchers have unveiled CREsted, a comprehensive software powerhouse. CREsted doesn’t just describe how DNA works; it allows scientists to design entirely new, synthetic enhancers—short DNA sequences that can program a gene to turn on only in a specific cell type, such as a neuron or an immune cell.
Key Facts
- The “All-in-One” Framework: CREsted merges four critical steps—preprocessing, AI model training, interpretation, and synthetic design—into a single, scalable workflow.
- Cell-Type Specificity: The AI can look at “chromatin accessibility” (which parts of the DNA are open and active) to learn exactly what makes an enhancer work in one tissue but stay silent in another.
- Proven Versatility: The team successfully tested CREsted on diverse systems, including the mouse brain, human immune cells, and zebrafish development.
- In Vivo Validation: Synthetic enhancers designed by the AI were physically built and tested in living zebrafish, confirming the AI’s predictions were accurate in a real biological environment.
- Programmable Biology: By moving from describing DNA to designing it, CREsted opens doors for precision medicine, where therapies could be programmed to activate only in diseased cells.
Source: VIB
Understanding how genes are switched on and off in specific cell types remains one of biology’s central challenges. While AI has made major progress in decoding the regulatory logic of DNA, applying these approaches across datasets, tissues, and species has remained difficult.
In a new Nature Methods paper, a research team led by Prof. Stein Aerts (VIB & KU Leuven) presents CREsted, a software package that enables both the analysis and design of gene regulatory elements in a systematic and scalable way.
Enhancers are gene regulatory elements—short DNA sequences that control when and where genes are active. Deep learning models can help decode this “regulatory code”, but existing approaches are often tailored to one dataset or one task, making them hard to reuse or extend.
To address this, Prof. Stein Aerts and his team developed CREsted, a new framework that turns enhancer modeling from a collection of one-off analyses into a more systematic and reusable workflow.
“We wanted to move beyond one-off models,” says Niklas Kempynck, PhD student in the Aerts lab.
“CREsted allows researchers to systematically study enhancer logic across biological systems, starting from cell-by-cell maps of accessible regulatory DNA and going all the way to sequence design.”
CREsted brings together several steps that are usually handled separately: preprocessing, model training, interpretation, and synthetic enhancer design. It is also built to fit into existing single-cell analysis workflows, making it easier for researchers to adopt and use.
“With CREsted, we give researchers a complete workflow,” says Dr. Seppe De Winter, who shares first authorship with Kempynck.
“You can train deep learning models on chromatin accessibility data, interpret which regulatory features they capture, and then use those models to design new DNA sequences with predicted cell-type-specific activity.”
To show its versatility, the team applied CREsted to multiple systems, including mouse brain tissue, human immune cells, cancer cell states, and zebrafish development. Across these settings, the framework identified regulatory patterns, predicted enhancer activity, and enabled the design of synthetic enhancers, which were validated in vivo in zebrafish.
For Prof. Stein Aerts, Scientific Director of VIB.AI, the strength of CREsted lies in making a powerful development more coherent and reusable.
“CREsted makes it much easier to train, interpret, and compare enhancer models across datasets,” he says.
“That is important if we want these approaches to become broadly useful, not just for understanding regulatory DNA, but also for designing and testing new sequences in a systematic way.”
Taken together, the work shows how AI can help move the field from describing regulatory DNA to actively exploring and designing it. With applications ranging from fundamental biology to biotechnology and medicine, CREsted lays the groundwork for more systematic and programmable control of gene regulation.
Key Questions Answered:
A: In a way, yes! Just as ChatGPT learns the rules of human language to write a poem, CREsted learns the “regulatory language” of DNA to write an enhancer. It identifies the specific patterns (motifs) that tell a cell to “start building this protein now,” allowing scientists to draft their own custom genetic instructions.
A: Natural enhancers are often complex and can be “leaky,” turning on in places they shouldn’t. Synthetic enhancers designed by CREsted can be “cleaner” and more specific. This is a game-changer for gene therapy: imagine a treatment that only activates inside a tumor cell while leaving the surrounding healthy tissue completely untouched.
A: That’s the core mission of CREsted. Previously, you needed to be an elite computational biologist to build these models. CREsted is built to plug directly into standard single-cell analysis workflows, making “programmable biology” accessible to much broader groups of researchers.
Editorial Notes:
- This article was edited by a Neuroscience News editor.
- Journal paper reviewed in full.
- Additional context added by our staff.
About this AI and genetics research news
Author: Gunnar De Winter
Source: VIB
Contact: Gunnar De Winter – VIB
Image: The image is credited to Neuroscience News
Original Research: Open access.
“CREsted: modeling genomic and synthetic cell type-specific enhancers across tissues and species” by Niklas Kempynck, Seppe De Winter, Casper H. Blaauw, Vasileios Konstantakos, Eren Can Ekşi, Sam Dieltiens, Darina Abaffyová, Valérie Bercier, Ibrahim I. Taskiran, Gert Hulselmans, Katina Spanier, Valerie Christiaens, Ludo Van Den Bosch, Lukas Mahieu & Stein Aerts. Nature Methods
DOI:10.1038/s41592-026-03057-2
Abstract
CREsted: modeling genomic and synthetic cell type-specific enhancers across tissues and species
Sequence-based deep learning models have become the state of the art for analyzing the genomic regulatory code. Particularly for enhancers, these models excel at deciphering sequence grammar that underlies their activity.
To enable end-to-end enhancer modeling and design, we developed a software package called CREsted (cis-regulatory element sequence training, explanation and design). It combines preprocessing and analysis of single-cell assay for transposase-accessible chromatin using sequencing data, modeling chromatin accessibility from sequence, sequence design and downstream analysis to decipher enhancer grammar.
We demonstrate CREsted’s functionality on a mouse cortex and a human peripheral blood mononuclear cell dataset. Additionally, we use CREsted to compare mesenchymal-like cancer cell states between tumor types, and we investigate different fine-tuning strategies of genomic foundation models within CREsted.
Finally, we train a model on a zebrafish development atlas and use this to design and in vivo validate cell-type-specific enhancers. For varying datasets, we demonstrate that CREsted facilitates efficient training and analyses, enabling scrutinization of the enhancer logic and design of synthetic enhancers across tissues and species.
