Studies from Zhengzhou University Have Provided New Information about Life Scien ce (Protein-protein Interaction Site Prediction Based On Attention Mechanism and Convolutional Neural Networks)
Networks;
Protein Interact ion;
Neural Networks;
Convolutional Network;
Machine Learning;
Emerging Technologies;
Asia;
Proteomics;
Henan;
Drugs and Therapies;
People's Republic of China;
Life Science;
Pharmaceuticals;
Zhengzhou University;
期刊名称：
Network Daily News
i s s n：
年卷期：
2024 年
Mar.11 期
页 码：
16-17
页 码：
摘 要：
By a News Reporter-Staff News Editor at Network Daily Ne ws-A new study on Life Science is now available. According to news originatin g from Henan, People's Republic of China, by NewsRx correspondents, research sta ted, "Proteins usually perform their cellular functions by interacting with othe r proteins. Accurate identification of protein-protein interaction sites (PPIs) from sequence is import for designing new drugs and developing novel therapeutic s." Financial support for this research came from Bingtuan Science and Technology. Our news journalists obtained a quote from the research from Zhengzhou Universit y, "A lot of computational models for PPIs prediction have been developed becaus e experimental methods are slow and expensive. Most models employ a sliding wind ow approach in which local neighbors are concatenated to present a target residu e. However, those neighbors are not distinguished by pairwise information betwee n a neighbor and the target. In this study, we propose a novel PPIs prediction m odel AttCNNPPISP, which combines attention mechanism and convolutional neural ne tworks (CNNs). The attention mechanism dynamically captures the pairwise correla tion of each neighbor-target pair within a sliding window, and therefore makes a better understanding of the local environment of target residue. And then, CNNs take the local representation as input to make prediction. Experiments are empl oyed on several public benchmark datasets. Compared with the state-of-the-art mo dels, AttCNNPPISP improves the prediction performance.
分享
载入中，请稍后...
