Summary of Hgtdp-dta: Hybrid Graph-transformer with Dynamic Prompt For Drug-target Binding Affinity Prediction, by Xi Xiao and Wentao Wang and Jiacheng Xie and Lijing Zhu and Gaofei Chen and Zhengji Li and Tianyang Wang and Min Xu
HGTDP-DTA: Hybrid Graph-Transformer with Dynamic Prompt for Drug-Target Binding Affinity Prediction
by Xi Xiao, Wentao Wang, Jiacheng Xie, Lijing Zhu, Gaofei Chen, Zhengji Li, Tianyang Wang, Min Xu
First submitted to arxiv on: 25 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed method, HGTDP-DTA, is a novel approach for predicting drug target binding affinity (DTA). It utilizes dynamic prompts within a hybrid Graph-Transformer framework to capture unique interactions between drugs and targets. The model integrates contextual data and comprehensive modeling of drug-target interactions, improving upon existing learning-based methods. This is achieved through the combination of structural information from Graph Convolutional Networks (GCNs) and sequence information captured by Transformers. Additionally, the method employs multi-view feature fusion to combine molecular graph views and affinity subgraph views into a common feature space. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The HGTDP-DTA method predicts DTA better than state-of-the-art methods on two public datasets: Davis and KIBA. It achieves this through its ability to capture unique interactions between drugs and targets, as well as its comprehensive modeling of drug-target interactions. |
Keywords
» Artificial intelligence » Transformer
