Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MPRA Predictor Models

Project Overview

This repository contains the code for the training, inference, and interpretation of Massively Parallel Reporter Assay (MPRA) prediction models.

This project utilizes a transfer-learning approach. Our source models (originally trained to predict chromatin tracks or MPRA activity in other cell types from DNA sequences) are adapted from the following works:


Installation

To set up the environment and install the package locally:

git clone [https://github.com/osyafinkelberg/mpra-predictor.git](https://github.com/osyafinkelberg/mpra-predictor.git)
cd mpra-predictor

python3 -m venv .venv
source .venv/bin/activate

pip install -e .

Input Data

The example code in this repository was trained on MPRA data covering ~60,000 200bp tiles derived from viral genomes. The assays were performed in 6 cell lines (GM12878, Jurkat, MRC5, A549, HEK293, K562).

Data Source: Tommy H. Taslim, Joseph A. Finkelberg, et al. (2025). Global cis-regulatory landscape of double-stranded DNA viruses. bioRxiv: 10.1101/2025.07.20.665756v1

About

Transfer-learning models for cell type-specific MPRA prediction.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages