Deep Scoring Neural Network Replacing the Scoring Function Components to Improve the Performance of Structure-Based Molecular Docking
Accurate prediction of protein-ligand interactions can greatly promote drug development. Recently, a number of deep-learning-based methods have been proposed to predict protein-ligand binding affinities. However, these methods independently extract the feature representations of proteins and ligands but ignore the relative spatial positions and interaction pairs between them. Here, we propose a virtual screening method based on deep learning, called Deep Scoring, which directly extracts the relative position information and atomic attribute information on proteins and ligands from the docking poses. Furthermore, we use two Resnets to extract the features of ligand atoms and protein residues, respectively, and generate an atom-residue interaction matrix to learn the underlying principles of the interactions between proteins and ligands. This is then followed by a dual attention network (DAN) to generate the attention for two related entities (i.e., proteins and ligands) and to weigh the contributions of each atom and residue to binding affinity prediction. As a result, Deep Scoring outperforms other structure-based deep learning methods in terms of screening performance (area under the receiver operating characteristic curve (AUC) of 0.901 for an unbiased DUD-E version), pose prediction (AUC of 0.935 for PDBbind test set), and generalization ability (AUC of 0.803 for the CHEMBL data set). Finally, Deep Scoring was used to select novel ERK2 inhibitor, and two compounds (D264-0698 and D483-1785) were obtained with potential inhibitory activity on ERK2 through the biological experiments.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:12 |
|---|---|
| Enthalten in: |
ACS chemical neuroscience - 12(2021), 12 vom: 16. Juni, Seite 2133-2142 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Yang, Lijuan [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Dual attention network |
|---|
| Anmerkungen: |
Date Completed 21.06.2021 Date Revised 21.06.2021 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1021/acschemneuro.1c00110 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM326302077 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM326302077 | ||
| 003 | DE-627 | ||
| 005 | 20231225194311.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1021/acschemneuro.1c00110 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1087.xml |
| 035 | |a (DE-627)NLM326302077 | ||
| 035 | |a (NLM)34081851 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Yang, Lijuan |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Deep Scoring Neural Network Replacing the Scoring Function Components to Improve the Performance of Structure-Based Molecular Docking |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 21.06.2021 | ||
| 500 | |a Date Revised 21.06.2021 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Accurate prediction of protein-ligand interactions can greatly promote drug development. Recently, a number of deep-learning-based methods have been proposed to predict protein-ligand binding affinities. However, these methods independently extract the feature representations of proteins and ligands but ignore the relative spatial positions and interaction pairs between them. Here, we propose a virtual screening method based on deep learning, called Deep Scoring, which directly extracts the relative position information and atomic attribute information on proteins and ligands from the docking poses. Furthermore, we use two Resnets to extract the features of ligand atoms and protein residues, respectively, and generate an atom-residue interaction matrix to learn the underlying principles of the interactions between proteins and ligands. This is then followed by a dual attention network (DAN) to generate the attention for two related entities (i.e., proteins and ligands) and to weigh the contributions of each atom and residue to binding affinity prediction. As a result, Deep Scoring outperforms other structure-based deep learning methods in terms of screening performance (area under the receiver operating characteristic curve (AUC) of 0.901 for an unbiased DUD-E version), pose prediction (AUC of 0.935 for PDBbind test set), and generalization ability (AUC of 0.803 for the CHEMBL data set). Finally, Deep Scoring was used to select novel ERK2 inhibitor, and two compounds (D264-0698 and D483-1785) were obtained with potential inhibitory activity on ERK2 through the biological experiments | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 650 | 4 | |a ERK2 inhibitor | |
| 650 | 4 | |a Protein−ligand interaction | |
| 650 | 4 | |a dual attention network | |
| 650 | 4 | |a pose prediction | |
| 650 | 4 | |a residual network | |
| 650 | 4 | |a virtual screening | |
| 650 | 7 | |a Ligands |2 NLM | |
| 650 | 7 | |a Proteins |2 NLM | |
| 700 | 1 | |a Yang, Guanghui |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Xiaolong |e verfasserin |4 aut | |
| 700 | 1 | |a Yang, Qiong |e verfasserin |4 aut | |
| 700 | 1 | |a Yao, Xiaojun |e verfasserin |4 aut | |
| 700 | 1 | |a Bing, Zhitong |e verfasserin |4 aut | |
| 700 | 1 | |a Niu, Yuzhen |e verfasserin |4 aut | |
| 700 | 1 | |a Huang, Liang |e verfasserin |4 aut | |
| 700 | 1 | |a Yang, Lei |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t ACS chemical neuroscience |d 2010 |g 12(2021), 12 vom: 16. Juni, Seite 2133-2142 |w (DE-627)NLM19578832X |x 1948-7193 |7 nnns |
| 773 | 1 | 8 | |g volume:12 |g year:2021 |g number:12 |g day:16 |g month:06 |g pages:2133-2142 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1021/acschemneuro.1c00110 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 12 |j 2021 |e 12 |b 16 |c 06 |h 2133-2142 | ||