SummaryDTA drug-target binding affinity prediction
Introduction
The target sequences obtain prior representation on the pre-trained protein sequence model, and the sequence feature vectors are obtained through the variable-length RNN network and averaging operation. The targets also use the concat maps as the structure information, which describe the interaction information between the residues. The residual blocks obtain the structure feature vector, and finally represent the target information through the concat operation. The drug SMILESs are constructed graphs through the node feature and adjacency matrix, which are obtained by the RDKit tool. Hence, the three GCN layers and the max-pooling operation are designed to obtain the graph representation vector of the drugs. Finally, the Kronecker Product is used to perform feature fusion on the candidate drug-target pair, and the final prediction binding affinity values are output through the linear layers.
Publications
No Publication Information
Credits
- Fei Guo fguo@tju.edu.cn Investigator
School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, China
Community Ratings
Usability | Efficiency | Reliability | Rated By |
---|---|---|---|
0 user | |||
Sign in to rate |
Accession | BT007258 |
---|---|
Tool Type | Application |
Category | Other tools |
Platforms | Linux/Unix |
Technologies | Python3 |
User Interface | Terminal Command Line |
Latest Release | 0.1 (September 14, 2021) |
Download Count | 254 |
Country/Region | China |
Submitted By | Fei Guo |
2018YFC0910400