https://github.com/aspirincode/stackppi
Improving protein-protein interactions prediction accuracy using XGBoost feature selection and stacked ensemble classifier
https://github.com/aspirincode/stackppi
Last synced: 12 months ago
JSON representation
Improving protein-protein interactions prediction accuracy using XGBoost feature selection and stacked ensemble classifier
- Host: GitHub
- URL: https://github.com/aspirincode/stackppi
- Owner: AspirinCode
- Created: 2019-08-17T12:23:40.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-08-11T14:02:04.000Z (over 6 years ago)
- Last Synced: 2025-01-29T07:30:30.880Z (about 1 year ago)
- Language: Python
- Size: 13 MB
- Stars: 3
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: ReadMe.md
Awesome Lists containing this project
README
##StackPPI
Improving protein-protein interactions prediction accuracy using XGBoost feature selection and stacked ensemble classifier.
###GcForest-PPI uses the following dependencies:
* python 3.6
* numpy
* scipy
* scikit-learn
###Guiding principles:
**The dataset file contains the S. cerevisiae, H. pylori, the independent dataset and network dataset.
**Feature extraction
1) Evolutionary information:
Evolutionary_information.py is the implementation of AAC-PSSM and Bi-PSSM.
2) PseAAC.m is the implementation of PseAAC.
3) CTDC.py, CTDT.py, CTDD.py are the implementation of CTD.
4) Auto_yeast.m is the implementation of AD.
** Dimensional reduction:
XGBoost.py represents XGBoost feature selection
stacking_KPCA.py represents KPCA.
stacking_LLE.py represents LLE.
stacking_TSVD.py represents SVD.
stacking_MDS.py represents MDS.
** Classifier:
stacking_test.py is the implementation of the stacked ensemble classifier.
yeast_Ad.py is the implementation of AdaBoost.
yeast_KNN.py is the implementation of KNN.
yeast_LR.py is the implementation of LR.
yeast_RF.py is the implementation of RF.
yeast_SVM.py is the implementation of SVM.