Prediction of Protein–Protein Interaction Sites Based on Stratified Attentional Mechanisms
Proteins are the basic substances that undertake human life activities, and they often perform their biological functions through interactions with other biological macromolecules, such as cell transmission and signal transduction. Predicting the interaction sites between proteins can deepen the und...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-11-01
|
| Series: | Frontiers in Genetics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fgene.2021.784863/full |
| _version_ | 1818741096486797312 |
|---|---|
| author | Minli Tang Minli Tang Longxin Wu Xinyu Yu Zhaoqi Chu Shuting Jin Shuting Jin Juan Liu |
| author_facet | Minli Tang Minli Tang Longxin Wu Xinyu Yu Zhaoqi Chu Shuting Jin Shuting Jin Juan Liu |
| author_sort | Minli Tang |
| collection | DOAJ |
| description | Proteins are the basic substances that undertake human life activities, and they often perform their biological functions through interactions with other biological macromolecules, such as cell transmission and signal transduction. Predicting the interaction sites between proteins can deepen the understanding of the principle of protein interactions, but traditional experimental methods are time-consuming and labor-intensive. In this study, a new hierarchical attention network structure, named HANPPIS, by adding six effective features of protein sequence, position-specific scoring matrix (PSSM), secondary structure, pre-training vector, hydrophilic, and amino acid position, is proposed to predict protein–protein interaction (PPI) sites. The experiment proved that our model has obtained very effective results, which was better than the existing advanced calculation methods. More importantly, we used the double-layer attention mechanism to improve the interpretability of the model and to a certain extent solved the problem of the “black box” of deep neural networks, which can be used as a reference for location positioning on the biological level. |
| first_indexed | 2024-12-18T01:51:11Z |
| format | Article |
| id | doaj.art-3f7a123c230141ca98a97e6b6ea59ee7 |
| institution | Directory Open Access Journal |
| issn | 1664-8021 |
| language | English |
| last_indexed | 2024-12-18T01:51:11Z |
| publishDate | 2021-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Genetics |
| spelling | doaj.art-3f7a123c230141ca98a97e6b6ea59ee72022-12-21T21:25:01ZengFrontiers Media S.A.Frontiers in Genetics1664-80212021-11-011210.3389/fgene.2021.784863784863Prediction of Protein–Protein Interaction Sites Based on Stratified Attentional MechanismsMinli Tang0Minli Tang1Longxin Wu2Xinyu Yu3Zhaoqi Chu4Shuting Jin5Shuting Jin6Juan Liu7Department of Computer Science and Technology, Xiamen University, Xiamen, ChinaSchool of Big Data Engineering, Kaili University, Kaili, ChinaDepartment of Computer Science and Technology, Xiamen University, Xiamen, ChinaDepartment of Computer Science and Technology, Xiamen University, Xiamen, ChinaDepartment of Instrumental and Electrical Engineering, School of Aerospace Engineering, Xiamen University, Xiamen, ChinaDepartment of Computer Science and Technology, Xiamen University, Xiamen, ChinaNational Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, ChinaDepartment of Instrumental and Electrical Engineering, School of Aerospace Engineering, Xiamen University, Xiamen, ChinaProteins are the basic substances that undertake human life activities, and they often perform their biological functions through interactions with other biological macromolecules, such as cell transmission and signal transduction. Predicting the interaction sites between proteins can deepen the understanding of the principle of protein interactions, but traditional experimental methods are time-consuming and labor-intensive. In this study, a new hierarchical attention network structure, named HANPPIS, by adding six effective features of protein sequence, position-specific scoring matrix (PSSM), secondary structure, pre-training vector, hydrophilic, and amino acid position, is proposed to predict protein–protein interaction (PPI) sites. The experiment proved that our model has obtained very effective results, which was better than the existing advanced calculation methods. More importantly, we used the double-layer attention mechanism to improve the interpretability of the model and to a certain extent solved the problem of the “black box” of deep neural networks, which can be used as a reference for location positioning on the biological level.https://www.frontiersin.org/articles/10.3389/fgene.2021.784863/fullprotein–protein interactionmultilevel attention mechanismfeature fusiondeep learningprotein features |
| spellingShingle | Minli Tang Minli Tang Longxin Wu Xinyu Yu Zhaoqi Chu Shuting Jin Shuting Jin Juan Liu Prediction of Protein–Protein Interaction Sites Based on Stratified Attentional Mechanisms Frontiers in Genetics protein–protein interaction multilevel attention mechanism feature fusion deep learning protein features |
| title | Prediction of Protein–Protein Interaction Sites Based on Stratified Attentional Mechanisms |
| title_full | Prediction of Protein–Protein Interaction Sites Based on Stratified Attentional Mechanisms |
| title_fullStr | Prediction of Protein–Protein Interaction Sites Based on Stratified Attentional Mechanisms |
| title_full_unstemmed | Prediction of Protein–Protein Interaction Sites Based on Stratified Attentional Mechanisms |
| title_short | Prediction of Protein–Protein Interaction Sites Based on Stratified Attentional Mechanisms |
| title_sort | prediction of protein protein interaction sites based on stratified attentional mechanisms |
| topic | protein–protein interaction multilevel attention mechanism feature fusion deep learning protein features |
| url | https://www.frontiersin.org/articles/10.3389/fgene.2021.784863/full |
| work_keys_str_mv | AT minlitang predictionofproteinproteininteractionsitesbasedonstratifiedattentionalmechanisms AT minlitang predictionofproteinproteininteractionsitesbasedonstratifiedattentionalmechanisms AT longxinwu predictionofproteinproteininteractionsitesbasedonstratifiedattentionalmechanisms AT xinyuyu predictionofproteinproteininteractionsitesbasedonstratifiedattentionalmechanisms AT zhaoqichu predictionofproteinproteininteractionsitesbasedonstratifiedattentionalmechanisms AT shutingjin predictionofproteinproteininteractionsitesbasedonstratifiedattentionalmechanisms AT shutingjin predictionofproteinproteininteractionsitesbasedonstratifiedattentionalmechanisms AT juanliu predictionofproteinproteininteractionsitesbasedonstratifiedattentionalmechanisms |