kundajelab/dragonn
A toolkit to learn how to model and interpret regulatory sequence data using deep learning.
This tool helps computational biologists and geneticists understand how specific DNA sequences regulate gene activity. You provide DNA sequence data, and it builds predictive models to identify important regulatory elements within those sequences. The output includes model performance metrics, predictions for new sequences, and interpretations highlighting the most impactful parts of the DNA sequence for a particular regulatory outcome.
264 stars. No commits in the last 6 months.
Use this if you need to build and interpret deep learning models to understand the regulatory function of genomic sequences and pinpoint critical DNA motifs.
Not ideal if you are working with protein sequences or need a general-purpose machine learning library not specific to genomics.
Stars
264
Forks
67
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Aug 01, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kundajelab/dragonn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aertslab/CREsted
CREsted is a Python package for training sequence-based deep learning models on scATAC-seq data,...
AI-sandbox/gnomix
A fast, scalable, and accurate local ancestry method.
BIMSBbioinfo/janggu
Deep learning infrastructure for genomics
kr-colab/ReLERNN
Recombination Landscape Estimation using Recurrent Neural Networks
grimmlab/easyPheno
easyPheno: a model agnostic phenotype prediction framework