EPCOT Installation

This guide walks you through the installation of the original EPCOT framework, which predicts epigenomic features, chromatin organization, and transcriptional activity from DNA sequence and cell-type-specific chromatin accessibility data.

Environment Setup

We recommend using conda to create an isolated environment:

conda create -n epcot python=3.9
conda activate epcot

Then, install dependencies via pip:

pip install -r requirements.txt

Dependencies

The main dependencies are:

  • einops==0.3.2

  • kipoiseq==0.5.2

  • numpy==1.19.5

  • torch==1.10.1

  • scipy==1.7.3

  • scikit-learn==1.0.2

Pretrained Models

You can download the pretrained models (trained on DNA sequence and DNase-seq or ATAC-seq) from:

Input Preparation

To prepare the required input formats (e.g., one-hot encoded DNA sequences and normalized DNase-seq), visit:

https://github.com/liu-bioinfo-lab/EPCOT/tree/main/Input

Note: All data used in EPCOT are based on the human hg38 reference genome.

Colab Tutorial

A ready-to-run notebook is available to demonstrate EPCOT usage:

TF Motif Analysis

For transcription factor sequence pattern visualization and comparison, see: