aertslab/CREsted
CREsted is a Python package for training sequence-based deep learning models on scATAC-seq data, for capturing enhancer code and for designing cell type-specific sequences.
This helps life scientists, geneticists, and bioinformaticians understand how enhancers control gene expression at a single-cell level. By inputting single-cell ATAC sequencing (scATAC-seq) data, it outputs models that reveal "enhancer codes" and allows for the design of new, cell-type-specific enhancer sequences. Researchers studying gene regulation and cell differentiation would use this.
Available on PyPI.
Use this if you need to train deep learning models on scATAC-seq data to uncover how specific DNA sequences (enhancers) drive gene activity in different cell types, or to design synthetic enhancer sequences.
Not ideal if your primary focus is not on single-cell ATAC-seq data or if you are not interested in the sequence-level details of enhancer function.
Stars
57
Forks
9
Language
Python
License
—
Category
Last pushed
Feb 20, 2026
Commits (30d)
0
Dependencies
15
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aertslab/CREsted"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
AI-sandbox/gnomix
A fast, scalable, and accurate local ancestry method.
kr-colab/ReLERNN
Recombination Landscape Estimation using Recurrent Neural Networks
BIMSBbioinfo/janggu
Deep learning infrastructure for genomics
arnor-sigurdsson/EIR
A toolkit for training deep learning models on genotype, tabular, sequence, image, array and binary data.
grimmlab/easyPheno
easyPheno: a model agnostic phenotype prediction framework