Back

Deep learning design and in vivo validation of Müller glia-specific cis-regulatory elements

Fornes, O.; Koh, K. D.; Marton, R. M.; Chen, J.; Marroquin, K. A.; Kang, G. J.; Lal, A.; Müller, S.; Eraslan, G.; Shamir, E. R.; Thakore, P. I.; Jasper, H.; Garfield, D.

2026-07-21 genomics
10.64898/2026.07.15.738785 bioRxiv
Show abstract

Effective recombinant adeno-associated virus gene therapies require promoters that are compact and cell-type-specific. Ideally, promoters should also exhibit functional conservation when tested in model organisms to ensure that preclinical findings translate reliably to human patients. Here, we introduce a deep learning framework for designing cis-regulatory elements (CREs) meeting these criteria, applied to retinal Muller glia (MG). Using single-cell chromatin accessibility data from human and mouse retinas, we trained species-specific models to predict cell-type accessibility, and designed compact CREs using two complementary strategies. In silico validation predicted that the designed CREs exhibit high MG-specific accessibility (on-target) in both species with minimal off-target accessibility across hundreds of human cell types and tissues. Mechanistic analysis revealed that the predicted MG accessibility is driven by the creation of LHX2 motifs. In vivo validation confirmed that the designed CREs successfully restrict reporter expression to MG in the murine retina. Our deep learning framework is highly generalizable and enables the rapid design of compact, on-target, and species-conserved CREs for precision gene therapy.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
eLife
● 5828 papers in training set
Top 6%
14.4%
Similar papers in this journal
2
Nature Communications
○ 5641 papers in training set
Top 22%
7.6%
Similar papers in this journal
3
Cell Genomics
○ 172 papers in training set
Top 0.4%
7.0%
Similar papers in this journal
4
Nature Methods
○ 385 papers in training set
Top 1%
7.0%
Similar papers in this journal
5
Genome Research
● 468 papers in training set
Top 1%
5.4%
Similar papers in this journal
6
Cell
○ 431 papers in training set
Top 1%
5.3%
7
Molecular Systems Biology
○ 162 papers in training set
Top 0.3%
5.3%
50% of probability mass above
8
Nature Genetics
○ 286 papers in training set
Top 1%
5.3%
9
Science
● 477 papers in training set
Top 2%
3.4%
10
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 20%
2.6%
11
Nature Biotechnology
○ 172 papers in training set
Top 2%
2.4%
12
Nucleic Acids Research
◐ 1281 papers in training set
Top 7%
2.3%
13
Cell Reports Methods
○ 165 papers in training set
Top 1%
2.3%
14
Cell Reports
○ 1498 papers in training set
Top 16%
2.3%
15
Molecular Biology and Evolution
◐ 542 papers in training set
Top 3%
2.1%
16
Nature
○ 645 papers in training set
Top 6%
1.8%
17
Bioinformatics
◐ 1204 papers in training set
Top 7%
1.7%
18
The EMBO Journal
○ 309 papers in training set
Top 3%
1.7%
19
Genome Biology
○ 637 papers in training set
Top 6%
1.7%
20
Nature Ecology & Evolution
131 papers in training set
Top 1%
1.5%
21
Molecular Cell
○ 350 papers in training set
Top 4%
1.3%
22
Cell Systems
○ 201 papers in training set
Top 3%
1.3%
23
Neuron
○ 337 papers in training set
Top 5%
0.9%
24
Science Advances
● 1243 papers in training set
Top 32%
0.8%
25
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 4%
0.8%
26
G3: Genes, Genomes, Genetics
◐ 252 papers in training set
Top 5%
0.6%
27
Development
● 497 papers in training set
Top 5%
0.6%
28
Bioinformatics Advances
◐ 203 papers in training set
Top 5%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.