knoweng/gene_prioritization_pipeline repository overview

⁠KnowEnG's Gene Prioritization Pipeline

This is the Knowledge Engine for Genomics (KnowEnG), an NIH, BD2K Center of Excellence, Gene Prioritization Pipeline.

This pipeline ranks the rows of a given spreadsheet, where spreadsheet's rows correspond to gene-labels and columns correspond to sample-labels. The ranking is based on correlating gene expression data (network smoothed) against pheno-type data.

There are four prioritization methods, using either pearson or t-test as the measure of correlation:

Note: all of the correlation methods mentioned above use the Pearson or t-test correlation measure method.

⁠How to run this pipeline with Our data

⁠1. Clone the Gene_Prioritization_Pipeline Repo

 git clone https://github.com/KnowEnG/Gene_Prioritization_Pipeline.git

⁠2. Install the following (Ubuntu or Linux)

apt-get install -y python3-pip
apt-get install -y libblas-dev liblapack-dev libatlas-base-dev gfortran
pip3 install numpy==1.11.1
pip3 install pandas==0.18.1
pip3 install scipy==0.19.1
pip3 install scikit-learn==0.17.1
apt-get install -y libfreetype6-dev libxft-dev
pip3 install matplotlib==1.4.2
pip3 install pyyaml
pip3 install knpackage

⁠3. Change directory to Gene_Prioritization_Pipeline

cd Gene_Prioritization_Pipeline

⁠4. Change directory to test

cd test

⁠5. Create a local directory "run_dir" and place all the run files in it

make env_setup

⁠6. Use one of the following "make" commands to select and run a clustering option:

⁠How to run this pipeline with Your data

Follow steps 1-3 above then do the following:

⁠* Create your run directory

mkdir run_directory

⁠* Change directory to the run_directory

cd run_directory

⁠* Create your results directory

mkdir results_directory

⁠* Create run_paramters file (YAML Format)

Look for examples of run_parameters in ./Gene_Prioritization_Pipeline/data/run_files/zTEMPLATE_GP_BENCHMARKS.yml

⁠* Modify run_paramters file (YAML Format)

set the spreadsheet, network and phenotype data file names to point to your data

⁠* Run the Gene Prioritization Pipeline:

• Update PYTHONPATH enviroment variable

export PYTHONPATH='../src':$PYTHONPATH    

• Run (in test directory with env_setup as described above)

python3 ../src/gene_prioritization.py -run_directory ./run_dir -run_file zTEMPLATE_GP_BENCHMARKS.yml

⁠Description of "run_parameters" file

gg_network_name = STRING_experimental_gene_gene.edge
spreadsheet_name = CCLE_Expression_ensembl.df
phenotype_name = CCLE_drug_ec50_cleaned_NAremoved_pearson.txt

⁠Description of Output files saved in results directory

• Any method saves separate files per phenotype with name {phenotype}_{method}_{correlation_measure}_{timestamp}_viz.tsv. Genes are sorted in descending order based on visualization_score.
  

• Any method saves sorted genes for each phenotype with name ranked_genes_per_phenotype_{method}_{correlation_measure}_{timestamp}_download.tsv.

• Any method saves spreadsheet with top ranked genes per phenotype with name top_genes_per_phenotype_{method}_{correlation_measure}_{timestamp}_download.tsv.