AlFontal / DNN_conditional-WGAN

Conditional WGAN was used to improve protein solubility prediction performance of DNN by data augmentation.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

"cleandata_1.csv": The whole dataset including 3148 proteins after data preprocessing "cleandata_1train.csv": The training data of the balanced dataset "cleandata_1test.csv": The test data of balanced dataset "fake_sample_epoch_009.npy", "netG_epoch_9.pth": The generated data from conditional WGAN "gan.py": The code implementing conditional WGAN "main.py": The code implementing DNN "bio_dataset.py": The code reshaping the dataset for tensor "network.py": The code defining the architecture of DNN

About

Conditional WGAN was used to improve protein solubility prediction performance of DNN by data augmentation.


Languages

Language:Python 100.0%