Drug design

ADMET

Prediction of ADMET features based on BiLSTM model.

admet

DLIGAND2

DLIGAND2 is a knowledge-based method to predict protein-ligand binding affinity based on a distance-scaled, finite, ideal-gas reference (DFIRE) state.

DLIGAND2

Virtual Screening

Virtual Screening can simulate the interaction between target and drug candidate, calculate the affinity between the two, reduce the actual number of compounds screened, and improve the efficiency of lead compound discovery.

Virtual Screening


  Protein

Protein Function Prediction

Sequence-based protein function prediction

Protein Function Prediction

CACFun

Sequence-based protein function prediction through multi-task learning

CACFun

GraphPPIS

Structure-aware protein-protein interacting site prediction using deep graph convolutional network.

GraphPPIS

GraphSol

Structure-aware protein solubility prediction from sequence through graph convolutional network and predicted contact map.

GraphSol

DeepANIS

Predicting antibody paratope via deep learning with concatenated CDR sequences.

DeepANIS

Spider2

Predicting secondary structure, local backbone angles, ASA, HSE, and Expected Errors of proteins.

Spider2

Spider3

Improved prediction on secondary structure and other structural properties of proteins by LSTM.

Spider3

DeepGOPlus

Predicting protein functions from sequence which combines deep convolutional neural network (CNN) model with sequence similarity based predictions.

DeepGOPlus

SeqVecFun

Predicting GO terms through annotation transfer annotation transfer not using sequence similarity, but similarity in embedding space.

SeqVecFun


  Medical

Covid19

It can accurately predict COVID19 infection from CT images.

covid19

Copyright © NSCC-GZ