[WIP] Gene Attribute (regulatory) Prediction Pipeline

*part of my MSc project

Current workflow:

Overview

Integrating multiple prediction tools in a single pipeline to produce a data matrix.

1. Current integrated tools:

   • DeepTFactor [Paper] [Repository]
   • BPROM [Paper] [Webtool]
   • PathoFact [Paper] [Repository]

2. Workflow system: Snakemake

Pre-requisites

Follow all the installation steps of PathoFact

Usage

Activate Conda Environment

conda activate snakemake

CLI

snakemake --cores 4 --use-conda -p

Configuration

1. Edit the config.yaml file
2. Create a blank files with your sample accension IDs, eg: NC_006350.1

Note:

• The U amino acid is replaced to X during DeepTFactor, as U is not included in the DeepTFactor model.