Commit e4566060 authored by Heather Underwood's avatar Heather Underwood

Merge branch 'master' of biof-git.colorado.edu:hackathon/mining_eqtls

parents ee78d259 b04d9f45
# RNASeek
![Alt text](https://biof-git.colorado.edu/hackathon/mining_eqtls/tree/master/images/CuteIntroFigure.png)
![Logo](https://biof-git.colorado.edu/hackathon/mining_eqtls/blob/b7035c7d694ecd3e346c21aef6d1b6c62332e7c7/images/CuteIntroFigure.png)
The goal of this software is to discover biomarkers of cell line sensitivity to a specific drug. In this way, the input to the software is a file where each line corresponds to a specific cell line with the CCLE database and an associated EC50, proportional to cell line sensitivity. This software will output a ranked list of genes and associated confidence scores that some gene's expression state is diagnostic or discriminitive of cell line response.
Patient selection in Phase I clinical trials is a crucial step in seeing a drug to market. As such, databases like the Cancer Cell Line Encyclopedia (CCLE) are routinely used by pharmaceutical companies to identify biomarkers that confer sensitivity or resistance to a given drug. Needed are computational methods to not only automate the process of biomarker discovery but also provide biologically interpretable models of drug, gene expression and mutational interactions.
Maintained by the Broad Institute and Novartis, CCLE provides publically available RNA-seq, Microarray, Copy Number Variation and SNP array data for 1,083 cell lines. Coupled to this resource, the Cancer Therapeutics Response Portal (CTRP) has profiled for 860 cell lines for sensitivity to 481 different compounds. Indeed, each cell lines displays a wide degree of variability in their response to certain compounds. Here, we present a new automated platform for discovering gene expression biomarkers given CCLE drug response data.
......@@ -43,6 +43,20 @@ You then need to spin up the virtual environment. To do this:
./run.py
```
To spin up and run in background on the AMI
```
python -m venv venv
cd flask_app
pip install -r requirements.txt
sudo su (become root)
screen RNASeek
. venv/bin/activate
./run.py
ctrl-a d
```
......
click==6.7
cycler==0.10.0
Flask==0.12.2
Flask-WTF==0.14.2
itsdangerous==0.24
Jinja2==2.9.6
MarkupSafe==1.0
matplotlib==2.0.2
numpy==1.12.1
pandas==0.20.1
pyparsing==2.2.0
python-dateutil==2.6.0
pytz==2017.2
scikit-learn==0.18.1
scipy==0.19.0
seaborn==0.7.1
six==1.10.0
sklearn==0.0
Werkzeug==0.12.2
WTForms==2.1
pandas
seaborn
sklearn
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment