Fork me on GitHub

1. Download GCEN and add to the PATH

mkdir -p ~/software/
cd ~/software/
wget https://www.biochen.org/gcen/static/0.6.3/gcen-0.6.3-linux-x86_64.tar.gz
tar zxf gcen-0.6.3-linux-x86_64.tar.gz
echo "export PATH=$HOME/software/gcen-0.6.3-linux-x86_64/bin:\$PATH" >> ~/.bashrc
echo "export PATH=$HOME/software/gcen-0.6.3-linux-x86_64/util:\$PATH" >> ~/.bashrc
source ~/.bashrc
rm ~/software/gcen-0.6.3-linux-x86_64.tar.gz

2. Recommended pipeline

The executable program is located in the bin directory and the sample data is located in the sample_data directory. All of the following commands can be run with the sample data. We first switch the current directory to the bin directory.

cd ~/software/gcen-0.6.3-linux-x86_64/bin/

Step 1: data pretreatment

./data_norm -i ../sample_data/gene_expr.tsv -o ../sample_data/gene_expr_norm.tsv -m upqt
./data_filter -i ../sample_data/gene_expr_norm.tsv -o ../sample_data/gene_expr_norm_filter.tsv -p 0.75

Step 2: co-expression network construction

./network_build -i ../sample_data/gene_expr_norm_filter.tsv -o ../sample_data/gene_co_expr.network -m spearman -p 0.001 -c 0.8 -f -t 6

Step 3: module identification (optional)

./module_identify -i ../sample_data/gene_co_expr.network -o ../sample_data/module.txt -s 0.5 -t 6

Step 4: function annotation

network based annotation

./annotate -g ../sample_data/go-basic.obo -a ../sample_data/gene_go.assoc -n ../sample_data/gene_co_expr.network -o ../sample_data/network_go_annotation
./annotate -k ../sample_data/K2ko.tsv -a ../sample_data/gene_kegg.assoc -n ../sample_data/gene_co_expr.network -o ../sample_data/network_kegg_annotation

module based annotation (optional)

./annotate -g ../sample_data/go-basic.obo -a ../sample_data/gene_go.assoc -m ../sample_data/module.txt -o ../sample_data/module_go_annotation
./annotate -k ../sample_data/K2ko.tsv -a ../sample_data/gene_kegg.assoc -m ../sample_data/module.txt -o ../sample_data/module_kegg_annotation

identify genes with specific functions based on RWR (optional)

rwr -n ../sample_data/gene_co_expr.network -g ../sample_data/rwr_interested_gene.list -o ../sample_data/rwr_result.tsv

Install software

1. Install GCEN

mkdir -p ~/software/
cd ~/software/
wget https://www.biochen.org/gcen/static/0.6.3/gcen-0.6.3-linux-x86_64.tar.gz
tar zxf gcen-0.6.3-linux-x86_64.tar.gz
echo "export PATH=$HOME/software/gcen-0.6.3-linux-x86_64/bin:\$PATH" >> ~/.bashrc
echo "export PATH=$HOME/software/gcen-0.6.3-linux-x86_64/util:\$PATH" >> ~/.bashrc
source ~/.bashrc
rm ~/software/gcen-0.6.3-linux-x86_64.tar.gz

2. Install SRA Toolkit / STAR / RSEM

cd ~/software/

# SRA Toolkit
wget https://ftp-trace.ncbi.nlm.nih.gov/sra/sdk/2.11.3/sratoolkit.2.11.3-ubuntu64.tar.gz
tar zxf sratoolkit.2.11.3-ubuntu64.tar.gz
echo "export PATH=$HOME/software/sratoolkit.2.11.3-ubuntu64/bin:\$PATH" >> ~/.bashrc
source ~/.bashrc
rm ~/software/sratoolkit.2.11.3-ubuntu64.tar.gz

# STAR
wget https://github.com/alexdobin/STAR/archive/refs/tags/2.7.9a.tar.gz
tar zxf 2.7.9a.tar.gz
echo "export PATH=$HOME/software/STAR-2.7.9a/bin/Linux_x86_64_static:\$PATH" >> ~/.bashrc
source ~/.bashrc
rm ~/software/2.7.9a.tar.gz

# RSEM
cd ~/
wget https://github.com/deweylab/RSEM/archive/v1.3.3.tar.gz
tar zxf v1.3.3.tar.gz
cd RSEM-1.3.3/
make install DESTDIR=$HOME prefix=/software/RSEM-1.3.3
echo "export PATH=$HOME/software/RSEM-1.3.3/bin:\$PATH" >> ~/.bashrc
source ~/.bashrc
rm -rf ~/RSEM-1.3.3 
rm ~/v1.3.3.tar.gz

Download data and convert to FASTQ files

3. Download RNA-Seq data from NCBI SRA database

Download data to/home/chenwen/SRP009426/sra/directory. Run ls display files.

(base) chenwen@workstation:~/SRP009426/sra$ ls
SRR372787.sra
SRR372788.sra
SRR372789.sra
SRR372790.sra
SRR372791.sra
SRR372792.sra
SRR372793.sra
SRR372794.sra
SRR372795.sra
SRR372796.sra
SRR372797.sra
SRR372798.sra
SRR372799.sra
SRR372800.sra
SRR372801.sra
SRR372802.sra
SRR372803.sra

4. Convert SRA files to FASTQ files

cd /home/chenwen/SRP009426/
mkdir fastq
for i in sra/*.sra; do fastq-dump --split-files --origfmt --gzip --outdir fastq $i; done

RNA-Seq analysis

5. Download reference genome

cd /home/chenwen/SRP009426/
mkdir ref
wget -P ref ftp://ftp.ensembl.org/pub/release-101/fasta/danio_rerio/dna/Danio_rerio.GRCz11.dna.primary_assembly.fa.gz
wget -P ref ftp://ftp.ensembl.org/pub/release-101/gtf/danio_rerio/Danio_rerio.GRCz11.101.chr.gtf.gz
gunzip ref/*.gz

6. Build STAR and RSEM index

cd /home/chenwen/SRP009426/
mkdir index
rsem-prepare-reference --gtf ref/Danio_rerio.GRCz11.101.chr.gtf --star --star-sjdboverhang 76 ref/Danio_rerio.GRCz11.dna.primary_assembly.fa index/GRCz11 -p 8

7. Calculate gene expression

cd /home/chenwen/SRP009426/
mkdir rsem
for i in sra/*.sra; do prefix=$(basename $i .sra); rsem-calculate-expression --paired-end --star --star-gzipped-read-file --estimate-rspd -no-bam-output -p 8 fastq/${prefix}_1.fastq.gz fastq/${prefix}_2.fastq.gz index/GRCz11 rsem/${prefix}; done;

GCEN analysis

8. Get gene expression matrix for GCEN analysis

Write the sample information to the rsem_sample.txt file, and then run the following command:

SRR372787	/home/chenwen/SRP009426/rsem/SRR372787.genes.results
SRR372788	/home/chenwen/SRP009426/rsem/SRR372788.genes.results
SRR372789	/home/chenwen/SRP009426/rsem/SRR372789.genes.results
SRR372790	/home/chenwen/SRP009426/rsem/SRR372790.genes.results
SRR372791	/home/chenwen/SRP009426/rsem/SRR372791.genes.results
SRR372792	/home/chenwen/SRP009426/rsem/SRR372792.genes.results
SRR372793	/home/chenwen/SRP009426/rsem/SRR372793.genes.results
SRR372794	/home/chenwen/SRP009426/rsem/SRR372794.genes.results
SRR372795	/home/chenwen/SRP009426/rsem/SRR372795.genes.results
SRR372796	/home/chenwen/SRP009426/rsem/SRR372796.genes.results
SRR372797	/home/chenwen/SRP009426/rsem/SRR372797.genes.results
SRR372798	/home/chenwen/SRP009426/rsem/SRR372798.genes.results
SRR372799	/home/chenwen/SRP009426/rsem/SRR372799.genes.results
SRR372800	/home/chenwen/SRP009426/rsem/SRR372800.genes.results
SRR372801	/home/chenwen/SRP009426/rsem/SRR372801.genes.results
SRR372802	/home/chenwen/SRP009426/rsem/SRR372802.genes.results
SRR372803	/home/chenwen/SRP009426/rsem/SRR372803.genes.results
generate_expr_matrix_from_rsem -i rsem_sample.txt -o gene_expr.tsv --tpm

9. Data normalization and filter

data_norm -i gene_expr.tsv -o gene_expr_norm.tsv -m tmm
data_filter -i gene_expr_norm.tsv -o gene_expr_norm_filter.tsv -p 0.75

10. Build network

network_build -i gene_expr_norm_filter.tsv -o gene_co_expr.network -m spearman -p 0.001 -c 0.8 -f -t 8

11. GO annotation

go-basic.obo and zebrafish_gene_go.tsv can be downloaded from our website.

annotate -g go-basic.obo -a zebrafish_gene_go.tsv -n gene_co_expr.network -o network_go_annotation -t 8

12. KEGG annotation

K2ko.tsv and zebrafish_gene_kegg.tsv can be downloaded from our website.

annotate -k K2ko.tsv -a zebrafish_gene_kegg.tsv -n gene_co_expr.network -o network_kegg_annotation -t 8