← BioTransfer GEO Dataset Finder
GEO series

Iterative deep learning-design of human enhancers exploits condensed sequence grammar to achieve cell type-specificity [RNA-Seq]

GSE269036 Homo sapiens (human) Single-cell RNA-seq 16 samples Submitted 2024/06/14 Platform GPL27609Platform GPL21697
At a glance

Single-cell RNA-seq · human · 16 samples

What it is
Single-cell RNA-seqGene activity measured in thousands of individual cells, so cell types can be told apart. Read from the summary: GEO's own type field only says 'expression profiling by sequencing', so confirm it in the paper.
Organism
Homo sapiens (human)
Samples
16 samples: 7 conditions, mostly in duplicateGroups are read from the sample names, not from the paper. Check the list below.
Data you can get
A processed table (series matrix) and supplementary files from NCBI; the raw sequencing reads from ENA. Which of these hold counts depends on the study, so check the file list.
Paper
Iterative deep learning design of human enhancers exploits condensed sequence grammar to achieve cell-type specificityCell systems · 2025
Summary (written by the submitters)
An important and largely unsolved problem in synthetic biology is how to target gene expression to specific cell types. Here, we apply iterative deep learning to design synthetic enhancers with strong differential activity between two human cell lines. We initially train models on published datasets of enhancer activity and chromatin accessibility and use them to guide the design of synthetic enhancers that maximize predicted specificity.
Read the full summary ↓
We experimentally validate these sequences, use the measurements to re-optimize the predictor, and design a second generation of enhancers with improved specificity. Our design methods embed relevant transcription factor binding site (TFBS) motifs with higher frequencies than comparable endogenous enhancers while using a more selective motif vocabulary, and we show that enhancer activity is correlated with transcription factor expression at the single cell level. Finally, we characterize causal features of top enhancers via perturbation experiments and show enhancers as short as 50bp can maintain specificity.
Published in
Iterative deep learning design of human enhancers exploits condensed sequence grammar to achieve cell-type specificity
Yin C, Castillo-Hair S, Byeon GW et al. · Cell systems 2025 · PMID 40472848 · doi:10.1016/j.cels.2025.101302
This dataset
Open GSE269036 in finder → Find more RNA-seq datasets →
Download · which file do I need?

Direct links to NCBI and ENA, no account and no request form. Pick by what you want to do: take the small processed table to look, the supplementary files to re-analyse, or the original raw data to start over.

1 · Just have a look

Processed table

The series matrix: one table of values per sample as the submitters processed it. The smallest download, and it opens in Excel or R. Start here to see what the data look like.

Series matrix ↓
2 · Re-analyse it

Supplementary files

The count tables and other files the authors uploaded. Take only the samples you need, or the whole study as GSE269036_RAW.tar (it can run to tens of gigabytes).

All supplementary files ↗ Whole study · RAW.tar ↓
3 · Start from the raw reads

Raw sequencing reads

The original FASTQ files, straight from the sequencer, held at ENA. Large, and you align them yourself, so only choose this if you need to re-process the study from scratch.

Raw reads on ENA ↗

What the files usually look like: Single-cell studies usually ship their counts as 10x files (matrix.mtx, barcodes.tsv, features.tsv), an .h5 file, or an .rds / .h5ad object that Seurat or Scanpy can open. Look for those among the supplementary files.

Also filed as BioProject PRJNA1120004 and SRA study SRP511645. Searching any of these in the dataset finder brings you back here.

NCBI GEO page ↗ Paper (PMID 40472848) ↗
Study design
7 conditions, mostly in duplicate
R1-DHS_HepG2 ×2 R1-DHS_K562 ×2 R1-MPRA_HepG2 ×2 R1-MPRA_K562 ×2 R2_DNA ×2 R2_HepG2 ×2 R2_K562 ×2 R1-DHS_DNA ×1 +1 more

Supports a between-group comparison across 14 samples.

How we read this: 7 replicated groups read from 16 sample titles; they account for 14 of them. These groups are guessed from the sample names, not taken from the paper, so check them against the sample list below before relying on them.

Samples in this study
Popular RNA-seq datasets

No close match found for this topic, so these are simply the most-viewed datasets of the same kind.

Search all RNA-seq datasets in GEO →

Share this dataset

Metadata from NCBI GEO, cached and refreshed periodically — the NCBI page above is authoritative. Downloads link straight to NCBI/ENA; nothing is proxied through BioTransfer.