Graph Convolutional Capsule Regression (GCCR) : A Model for Accelerated Filtering of Novel Potential Candidates for SARS-CoV-2 based on Binding Affinity
Copyright© Bentham Science Publishers; For any queries, please email at epubbenthamscience.net..
BACKGROUND: There has been a growing interest in discovering a viable drug for the new coronavirus (SARS-CoV-2) since the beginning of the pandemic. Protein-ligand interaction studies are a crucial step in the drug discovery process, as it helps us narrow the search space for potential ligands with high drug-likeness. Derivatives of popular drugs like Remdesivir generated through tools employing evolutionary algorithms are usually considered potential candidates. However, screening promising molecules from such a large search space is difficult. In a conventional screening process, for each ligand-target pair, there are time-consuming interaction studies that use docking simulations before downstream tasks like thermodynamic, kinetic, and electrostatic-potential evaluation.
OBJECTIVE: This work aims to build a model based on deep learning applied over the graph structure of the molecules to accelerate the screening process for novel potential candidates for SARS-CoV-2 by predicting the binding energy of the protein-ligand complex.
METHODS: In this work, 'Graph Convolutional Capsule Regression' (GCCR), a model which uses Capsule Neural Networks (CapsNet) and Graph Convolutional Networks (GCN) to predict the binding energy of a protein-ligand complex is being proposed. The model's predictions were further validated with kinetic and free energy studies like Molecular Dynamics (MD) for kinetic stability and MM/GBSA analysis for free energy calculations.
RESULTS: The GCCR showed an RMSE value of 0.0978 for 81.3% of the concordance index. The RMSE of GCCR converged around the iteration of just 50 epochs scoring a lower RMSE than GCN and GAT. When training with Davis Dataset, GCCR gave an RMSE score of 0.3806 with a CI score of 87.5%.
CONCLUSION: The proposed GCCR model shows great potential in improving the screening process based on binding affinity and outperforms baseline machine learning models like DeepDTA, KronRLS, Sim- Boost, and other Graph Neural Networks (GNN) based models like Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT).
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 2023 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:20 |
---|---|
Enthalten in: |
Current computer-aided drug design - 20(2023), 1 vom: 30., Seite 33-41 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Krishnan, Aravind [VerfasserIn] |
---|
Links: |
---|
Themen: |
Binding affinity prediction |
---|
Anmerkungen: |
Date Revised 13.10.2023 published: Print Citation Status Publisher |
---|
doi: |
10.2174/1573409919666230331083953 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM355103818 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM355103818 | ||
003 | DE-627 | ||
005 | 20231226063636.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.2174/1573409919666230331083953 |2 doi | |
028 | 5 | 2 | |a pubmed24n1183.xml |
035 | |a (DE-627)NLM355103818 | ||
035 | |a (NLM)37005531 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Krishnan, Aravind |e verfasserin |4 aut | |
245 | 1 | 0 | |a Graph Convolutional Capsule Regression (GCCR) |b A Model for Accelerated Filtering of Novel Potential Candidates for SARS-CoV-2 based on Binding Affinity |
264 | 1 | |c 2024 | |
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 Revised 13.10.2023 | ||
500 | |a published: Print | ||
500 | |a Citation Status Publisher | ||
520 | |a Copyright© Bentham Science Publishers; For any queries, please email at epubbenthamscience.net. | ||
520 | |a BACKGROUND: There has been a growing interest in discovering a viable drug for the new coronavirus (SARS-CoV-2) since the beginning of the pandemic. Protein-ligand interaction studies are a crucial step in the drug discovery process, as it helps us narrow the search space for potential ligands with high drug-likeness. Derivatives of popular drugs like Remdesivir generated through tools employing evolutionary algorithms are usually considered potential candidates. However, screening promising molecules from such a large search space is difficult. In a conventional screening process, for each ligand-target pair, there are time-consuming interaction studies that use docking simulations before downstream tasks like thermodynamic, kinetic, and electrostatic-potential evaluation | ||
520 | |a OBJECTIVE: This work aims to build a model based on deep learning applied over the graph structure of the molecules to accelerate the screening process for novel potential candidates for SARS-CoV-2 by predicting the binding energy of the protein-ligand complex | ||
520 | |a METHODS: In this work, 'Graph Convolutional Capsule Regression' (GCCR), a model which uses Capsule Neural Networks (CapsNet) and Graph Convolutional Networks (GCN) to predict the binding energy of a protein-ligand complex is being proposed. The model's predictions were further validated with kinetic and free energy studies like Molecular Dynamics (MD) for kinetic stability and MM/GBSA analysis for free energy calculations | ||
520 | |a RESULTS: The GCCR showed an RMSE value of 0.0978 for 81.3% of the concordance index. The RMSE of GCCR converged around the iteration of just 50 epochs scoring a lower RMSE than GCN and GAT. When training with Davis Dataset, GCCR gave an RMSE score of 0.3806 with a CI score of 87.5% | ||
520 | |a CONCLUSION: The proposed GCCR model shows great potential in improving the screening process based on binding affinity and outperforms baseline machine learning models like DeepDTA, KronRLS, Sim- Boost, and other Graph Neural Networks (GNN) based models like Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a COVID-19 | |
650 | 4 | |a MD simulation | |
650 | 4 | |a MM/GBSA | |
650 | 4 | |a SARS-CoV-2 | |
650 | 4 | |a binding affinity prediction | |
650 | 4 | |a drug discovery | |
650 | 4 | |a graph neural network | |
650 | 4 | |a molecular docking | |
700 | 1 | |a Vinod, Dayanand |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Current computer-aided drug design |d 2008 |g 20(2023), 1 vom: 30., Seite 33-41 |w (DE-627)NLM191691046 |x 1875-6697 |7 nnns |
773 | 1 | 8 | |g volume:20 |g year:2023 |g number:1 |g day:30 |g pages:33-41 |
856 | 4 | 0 | |u http://dx.doi.org/10.2174/1573409919666230331083953 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 20 |j 2023 |e 1 |b 30 |h 33-41 |