Skip to content

Finterly/Siamese-Neural-Network-PyTorch

Repository files navigation

SiameseNN

Siamese neural network for protein remote homology

The following architecture was built using Pytorch:

The final model consisted of twin four-layer convolutional neural networks:

Our model was validated using stratified 5-fold cross-validation:

SiameseNN Model performance on Saripella PFAM, GENE3D, and SUPFAM datasets compared to existing methods:

SiameseNN Model was found to have higher precision and lower FPR.

About

Siamese neural network for protein remote homology detection

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages