The Relative Distance Prediction of Transmembrane Protein Surface Residue Based on Improved Residual Networks
(1) Background: Transmembrane proteins (TMPs) act as gateways connecting the intra- and extra-biomembrane environments, exchanging material and signals crossing the biofilm. Relevant evidence shows that corresponding interactions mostly happen on the TMPs’ surface. Therefore, knowledge of the relati...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/3/642 |
| _version_ | 1797623870212014080 |
|---|---|
| author | Qiufen Chen Yuanzhao Guo Jiuhong Jiang Jing Qu Li Zhang Han Wang |
| author_facet | Qiufen Chen Yuanzhao Guo Jiuhong Jiang Jing Qu Li Zhang Han Wang |
| author_sort | Qiufen Chen |
| collection | DOAJ |
| description | (1) Background: Transmembrane proteins (TMPs) act as gateways connecting the intra- and extra-biomembrane environments, exchanging material and signals crossing the biofilm. Relevant evidence shows that corresponding interactions mostly happen on the TMPs’ surface. Therefore, knowledge of the relative distance among surface residues is critically helpful in discovering the potential local structural characters and setting the foundation for the protein’s interaction with other molecules. However, the prediction of fine-grained distances among residues with sequences remains challenging; (2) Methods: In this study, we proposed a deep-learning method called TMP-SurResD, which capitalized on the combination of the Residual Block (RB) and Squeeze-and-Excitation (SE) for simultaneously predicting the relative distance of functional surface residues based on sequences’ information; (3) Results: The comprehensive evaluation demonstrated that TMP-SurResD could successfully capture the relative distance between residues, with a Pearson Correlation Coefficient (<i>PCC</i>) of 0.7105 and 0.6999 on the validation and independent sets, respectively. In addition, TMP-SurResD outperformed other methods when applied to TMPs surface residue contact prediction, and the maximum Matthews Correlation Coefficient (MCC) reached 0.602 by setting a threshold to the predicted distance of 10; (4) Conclusions: TMP-SurResD can serve as a useful tool in supporting a sequence-based local structural feature construction and exploring the function and biological mechanisms of structure determination in TMPs, which can thus significantly facilitate the research direction of molecular drug action, target design, and disease treatment. |
| first_indexed | 2024-03-11T09:34:57Z |
| format | Article |
| id | doaj.art-fe79ddf8e2604f8abfbf942c8b2a3527 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-11T09:34:57Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-fe79ddf8e2604f8abfbf942c8b2a35272023-11-16T17:22:31ZengMDPI AGMathematics2227-73902023-01-0111364210.3390/math11030642The Relative Distance Prediction of Transmembrane Protein Surface Residue Based on Improved Residual NetworksQiufen Chen0Yuanzhao Guo1Jiuhong Jiang2Jing Qu3Li Zhang4Han Wang5School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, ChinaSchool of Information Science and Technology, Institute of Computational Biology, Northeast Normal University, Changchun 130024, ChinaSchool of Information Science and Technology, Institute of Computational Biology, Northeast Normal University, Changchun 130024, ChinaSchool of Information Science and Technology, Institute of Computational Biology, Northeast Normal University, Changchun 130024, ChinaSchool of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, ChinaSchool of Information Science and Technology, Institute of Computational Biology, Northeast Normal University, Changchun 130024, China(1) Background: Transmembrane proteins (TMPs) act as gateways connecting the intra- and extra-biomembrane environments, exchanging material and signals crossing the biofilm. Relevant evidence shows that corresponding interactions mostly happen on the TMPs’ surface. Therefore, knowledge of the relative distance among surface residues is critically helpful in discovering the potential local structural characters and setting the foundation for the protein’s interaction with other molecules. However, the prediction of fine-grained distances among residues with sequences remains challenging; (2) Methods: In this study, we proposed a deep-learning method called TMP-SurResD, which capitalized on the combination of the Residual Block (RB) and Squeeze-and-Excitation (SE) for simultaneously predicting the relative distance of functional surface residues based on sequences’ information; (3) Results: The comprehensive evaluation demonstrated that TMP-SurResD could successfully capture the relative distance between residues, with a Pearson Correlation Coefficient (<i>PCC</i>) of 0.7105 and 0.6999 on the validation and independent sets, respectively. In addition, TMP-SurResD outperformed other methods when applied to TMPs surface residue contact prediction, and the maximum Matthews Correlation Coefficient (MCC) reached 0.602 by setting a threshold to the predicted distance of 10; (4) Conclusions: TMP-SurResD can serve as a useful tool in supporting a sequence-based local structural feature construction and exploring the function and biological mechanisms of structure determination in TMPs, which can thus significantly facilitate the research direction of molecular drug action, target design, and disease treatment.https://www.mdpi.com/2227-7390/11/3/642transmembrane proteindistances among residuesco-evolutionresidual network |
| spellingShingle | Qiufen Chen Yuanzhao Guo Jiuhong Jiang Jing Qu Li Zhang Han Wang The Relative Distance Prediction of Transmembrane Protein Surface Residue Based on Improved Residual Networks Mathematics transmembrane protein distances among residues co-evolution residual network |
| title | The Relative Distance Prediction of Transmembrane Protein Surface Residue Based on Improved Residual Networks |
| title_full | The Relative Distance Prediction of Transmembrane Protein Surface Residue Based on Improved Residual Networks |
| title_fullStr | The Relative Distance Prediction of Transmembrane Protein Surface Residue Based on Improved Residual Networks |
| title_full_unstemmed | The Relative Distance Prediction of Transmembrane Protein Surface Residue Based on Improved Residual Networks |
| title_short | The Relative Distance Prediction of Transmembrane Protein Surface Residue Based on Improved Residual Networks |
| title_sort | relative distance prediction of transmembrane protein surface residue based on improved residual networks |
| topic | transmembrane protein distances among residues co-evolution residual network |
| url | https://www.mdpi.com/2227-7390/11/3/642 |
| work_keys_str_mv | AT qiufenchen therelativedistancepredictionoftransmembraneproteinsurfaceresiduebasedonimprovedresidualnetworks AT yuanzhaoguo therelativedistancepredictionoftransmembraneproteinsurfaceresiduebasedonimprovedresidualnetworks AT jiuhongjiang therelativedistancepredictionoftransmembraneproteinsurfaceresiduebasedonimprovedresidualnetworks AT jingqu therelativedistancepredictionoftransmembraneproteinsurfaceresiduebasedonimprovedresidualnetworks AT lizhang therelativedistancepredictionoftransmembraneproteinsurfaceresiduebasedonimprovedresidualnetworks AT hanwang therelativedistancepredictionoftransmembraneproteinsurfaceresiduebasedonimprovedresidualnetworks AT qiufenchen relativedistancepredictionoftransmembraneproteinsurfaceresiduebasedonimprovedresidualnetworks AT yuanzhaoguo relativedistancepredictionoftransmembraneproteinsurfaceresiduebasedonimprovedresidualnetworks AT jiuhongjiang relativedistancepredictionoftransmembraneproteinsurfaceresiduebasedonimprovedresidualnetworks AT jingqu relativedistancepredictionoftransmembraneproteinsurfaceresiduebasedonimprovedresidualnetworks AT lizhang relativedistancepredictionoftransmembraneproteinsurfaceresiduebasedonimprovedresidualnetworks AT hanwang relativedistancepredictionoftransmembraneproteinsurfaceresiduebasedonimprovedresidualnetworks |