DeeReCT-TSS: A novel meta-learning-based method annotates TSS in multiple cell types based on DNA sequences and RNA-seq data

This repository contains the implementation of DeeReCT-TSS from

Juexiao Zhou, Bin Zhang, et al. "DeeReCT-TSS: A novel meta-learning-based method annotates TSS in multiple cell types based on DNA sequences and RNA-seq data"

If you use our work in your research, please cite our paper:

Juexiao Zhou, Bin Zhang et al. DeeReCT-TSS: A novel meta-learning-based method annotates TSS in multiple cell types based on DNA sequences and RNA-seq data, 21 June 2021, PREPRINT (Version 1) available at Research Square [https://doi.org/10.21203/rs.3.rs-640669/v1]

Prerequisites

The code is tested with the following dependencies:

• python=3.6

• biopython=1.78

• bedtools=2.30.0

• cudatoolkit=10.1.243

• cudnn=7.6.5

• numpy=1.19.2

• scipy=1.5.2

• pandas=1.1.3

• scipy=1.5.2

• scikit-learn 0.22.1

• tensorflow-gpu=1.14.0

• Seaborn 0.11.1

• matplotlib=3.3.4

• seaborn=0.11.1

• samtools

The code is not guaranteed to work if different versions are used.

To analyze bam files with a size around 10G, each thread requires 4-5G memory when the job is splitted into 25 threads