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:

.. code-block:: bash

   conda create -n epcot python=3.9
   conda activate epcot

Then, install dependencies via pip:

.. code-block:: bash

   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:

- Google Drive: https://drive.google.com/drive/folders/1gsveyTgYwlXK5Ntnx5nLKSzIW3JvxLse
- Zenodo: https://doi.org/10.5281/zenodo.7485616

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:

- `EPCOT_usage.ipynb`: https://github.com/liu-bioinfo-lab/EPCOT/blob/main/EPCOT_usage.ipynb

TF Motif Analysis
-----------------

For transcription factor sequence pattern visualization and comparison, see:

- `sequence_pattern.ipynb`: https://github.com/liu-bioinfo-lab/EPCOT/blob/main/Data/sequence_pattern.ipynb
- GitHub page: https://zzh24zzh.github.io/epcot.github.io/
- Motif summary Excel: https://github.com/liu-bioinfo-lab/EPCOT/blob/main/Data/motif_comparison_summary.xls