https://github.com/sysbiochalmers/cancerproteinsecretionml
A collection of scripts to analyze cancer transcriptomics data using various statistical and machine-learning approaches.
https://github.com/sysbiochalmers/cancerproteinsecretionml
Last synced: over 1 year ago
JSON representation
A collection of scripts to analyze cancer transcriptomics data using various statistical and machine-learning approaches.
- Host: GitHub
- URL: https://github.com/sysbiochalmers/cancerproteinsecretionml
- Owner: SysBioChalmers
- License: mit
- Created: 2018-01-29T11:26:10.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2021-03-05T16:19:56.000Z (over 5 years ago)
- Last Synced: 2025-01-30T22:51:19.562Z (over 1 year ago)
- Language: R
- Homepage:
- Size: 12.1 MB
- Stars: 0
- Watchers: 1
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# CancerProteinSecretionML
Analysis of gene expression changes in the protein secretory pathway of different cancer types using machine learning.
## Reproducing the analyses in the manuscript
### Code
The python and R code necessary to reproduce the analyses in the manuscript can be found in the [scripts](scripts) directory of this repository. View the README therein for further details on the associated scripts.
### Environments
There are two conda environment files that define the packages necessary for running the python and R scripts: `environment_python.yml` and `environment_R.yml`, respectively. Create the environments from the files using the following command:
```
conda env create -f environment_python.yml
conda env create -f environment_R.yml
```
Activate either environment using `conda activate`:
```
conda activate psp-cancer-py
```
_Note:_ The environments were built on MacOS. If you are using a different OS and experience problems when creating either of the environments, try removing the version specified after each package in the `.yml` file (e.g., change `numpy=1.18.1` to `numpy`).
### Data
Note that you will first need to retrieve the larger data files from the associated Zenodo repository prior to re-running the analyses. This is described in further detail by the README in the [data](data) directory.
## Analysis result files
The raw analysis output files can be found in the [results](results) directory.