https://github.com/bblodfon/survmob
An R package for benchmarking survival ML models on multi-omics data
https://github.com/bblodfon/survmob
Last synced: 9 months ago
JSON representation
An R package for benchmarking survival ML models on multi-omics data
- Host: GitHub
- URL: https://github.com/bblodfon/survmob
- Owner: bblodfon
- License: other
- Created: 2023-01-07T02:25:51.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-07-06T08:10:41.000Z (about 3 years ago)
- Last Synced: 2024-12-20T01:44:16.671Z (over 1 year ago)
- Language: R
- Homepage:
- Size: 163 KB
- Stars: 4
- Watchers: 2
- Forks: 0
- Open Issues: 7
-
Metadata Files:
- Readme: README.md
- Changelog: NEWS.md
- License: LICENSE
Awesome Lists containing this project
README
# survmob
`survmob` is an R library that makes it easier to benchmark survival models across multiomics datasets.
It builds upon [mlr3proba](https://github.com/mlr-org/mlr3proba/) and other packages from the [mlr3](https://github.com/mlr-org/) ML ecosystem using [R6](https://github.com/r-lib/R6/) classes.
Key classes and functions implemented:
- Preprocessing - [link](https://github.com/bblodfon/survmob/blob/main/R/preprocess.R)
- Survival learners and hyperparameter spaces class - [link](https://github.com/bblodfon/survmob/blob/main/R/SurvLPS.R)
- Survival measures - [link](https://github.com/bblodfon/survmob/blob/main/R/measures.R)
- Ensemble Feature Selection (eFS) class (uses Random Survival Forest learners and RFE algorithm for finding best feature subsets) - [link](https://github.com/bblodfon/survmob/blob/main/R/eFS.R)
- Multi-omics benchmarking - [link](https://github.com/bblodfon/survmob/blob/main/R/MOBenchmark.R)
## Installation
Install the latest development version of `survmob` using:
```r
remotes::install_github('bblodfon/survmob')
```