https://github.com/merck/bart-qsar
https://github.com/merck/bart-qsar
Last synced: 9 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/merck/bart-qsar
- Owner: Merck
- License: gpl-3.0
- Created: 2019-04-01T18:20:04.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2019-04-13T13:13:16.000Z (about 7 years ago)
- Last Synced: 2025-07-07T08:09:18.150Z (10 months ago)
- Language: R
- Size: 20.9 MB
- Stars: 1
- Watchers: 4
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: COPYING
Awesome Lists containing this project
README
# BART-QSAR Documentation
Authors: Dai Feng, Andy Liaw.
Contact: dai_feng@merck.com, andy_liaw@merck.com.
Affiliation: Merck Biometrics Research, Merck Sharp & Dohme Corp. a subsidiary of Merck & Co., Inc., Kenilworth, NJ, USA.
Date: 03/25/2019
Acknowledgement:
If you use the BART-QSAR for scientific work that gets published, you should include in that publication a citation
of the following paper:
Dai Feng, Vladimir Svetnik, Andy Liaw, Matthew Pratola, and Robert P. Sheridan. "Building Quantitative Structure-Activity
Relationship Models Using Bayesian Additive Regression Trees". Journal of Chemical Information and Modeling, 2019.
## Basic info
### System requirements:
R (>= 3.5.1)
### Installation of R Packages:
[randomForest:] https://cran.r-project.org/web/packages/randomForest/
[quantregForest:] https://cran.r-project.org/web/packages/quantregForest/
[randomForestCI:] https://github.com/swager/randomForestCI
[dbarts:] https://cran.r-project.org/web/packages/dbarts/
[OpenBT:] https://bitbucket.org/mpratola/openbt
[coda:] https://cran.r-project.org/web/packages/coda/
## Brief explaination of all R files
[getPIrf.R:] Get prediction intervals using three methods based on Random Forest: IJRF, IJQRF, and QRF.
[rf.R:] An example showing how to obtain different prediction intervals using different methods based on Random Forest.
[getPIbart.R] Get prediction intervals using three methods based on BART: BART, OpenBT-bart, and OpenBT-hbart.
[bart.R] An example showing how to obtain differetn prediction intervals using different methods based on BART.
## Brief explaination of all data files
[x.train.rda] Features of training data
[y.train.rda] Response of training data
[x.test.rda] Features of test data
[y.test.rda] Response of test data