knowengdev/feature_prioritization_pipeline repository overview

⁠KnowEnG's Feature Prioritization Pipeline

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

This pipeline ranks the rows of a given spreadsheet, where spreadsheet's rows correspond to feature-labels and columns correspond to sample-labels. The ranking is based on correlating feature expression data against response data.

There are two 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.

feature_prioritization_pipeline GitHub repo⁠

⁠How to run this pipeline's docker image with Our data

1. Install Docker - follow the instructions in this link. ============

Install Docker Engine⁠

1. Get the current Docker Image. On the command line with internet connection: ============

docker pull knowengdev/feature_prioritization_pipeline:10_12_2017

1. Create or change to a directory to hold the output data. ============

mkdir local_results and / or cd local_results

1. Start the docker image connected to the (local_results) directory. =========== docker run -v local_results:/home/test/run_dir -it knowengdev/feature_prioritization_pipeline:10_12_2017

2. At the docker image command prompt change to the test directory. =========== .../home# cd test

3. Set up the environment. ============= .../home/test# make env_setup

1. 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 ./Feature_Prioritization_Pipeline/data/run_files/zTEMPLATE_FP_BENCHMARKS.yml

⁠* Modify run_paramters file (YAML Format)

set the spreadsheet and response data file names to point to your data

⁠* Run the Feature Prioritization Pipeline:

• Update PYTHONPATH enviroment variable

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

• Run

python3 ../src/feature_prioritization.py -run_directory ./ -run_file zTEMPLATE_FP_BENCHMARKS.yml

⁠Description of "run_parameters" file

spreadsheet_name = CCLE_Expression_ensembl.df
response_name = CCLE_drug_ec50_cleaned_NAremoved_pearson.txt

⁠Description of Output files saved in results directory

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

• Any method saves sorted features for each response with name ranked_features_per_response_{method}_{correlation_measure}_{timestamp}_download.tsv.

• Any method saves spreadsheet with top ranked features per response with name top_features_per_response_{method}_{correlation_measure}_{timestamp}_download.tsv.