A New Hybrid Neural Network Deep Learning Method for Protein–Ligand Binding Affinity Prediction and De Novo Drug Design
Accurately predicting ligand binding affinity in a virtual screening campaign is still challenging. Here, we developed hybrid neural network (HNN) machine deep learning methods, HNN-denovo and HNN-affinity, by combining the 3D-CNN (convolutional neural network) and the FFNN (fast forward neural netw...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/23/22/13912 |
| _version_ | 1797465144965464064 |
|---|---|
| author | Sarita Limbu Sivanesan Dakshanamurthy |
| author_facet | Sarita Limbu Sivanesan Dakshanamurthy |
| author_sort | Sarita Limbu |
| collection | DOAJ |
| description | Accurately predicting ligand binding affinity in a virtual screening campaign is still challenging. Here, we developed hybrid neural network (HNN) machine deep learning methods, HNN-denovo and HNN-affinity, by combining the 3D-CNN (convolutional neural network) and the FFNN (fast forward neural network) hybrid neural network framework. The HNN-denovo uses protein pocket structure and protein–ligand interactions as input features. The HNN-affinity uses protein sequences and ligand features as input features. The HNN method combines the CNN and FCNN machine architecture for the protein structure or protein sequence and ligand descriptors. To train the model, the HNN methods used thousands of known protein–ligand binding affinity data retrieved from the PDBBind database. We also developed the Random Forest (RF), Gradient Boosting (GB), Decision Tree with AdaBoost (DT), and a consensus model. We compared the HNN results with models developed based on the RF, GB, and DT methods. We also independently compared the HNN method results with the literature reported deep learning protein–ligand binding affinity predictions made by the DLSCORE, KDEEP, and DeepAtom. The predictive performance of the HNN methods (max Pearson’s R achieved was 0.86) was consistently better than or comparable to the DLSCORE, KDEEP, and DeepAtom deep learning learning methods for both balanced and unbalanced data sets. The HNN-affinity can be applied for the protein–ligand affinity prediction even in the absence of protein structure information, as it considers the protein sequence as standalone feature in addition to the ligand descriptors. The HNN-denovo method can be efficiently implemented to the structure-based de novo drug design campaign. The HNN-affinity method can be used in conjunction with the deep learning molecular docking protocols as a standalone. Further, it can be combined with the conventional molecular docking methods as a multistep approach to rapidly screen billions of diverse compounds. The HNN method are highly scalable in the cloud ML platform. |
| first_indexed | 2024-03-09T18:17:22Z |
| format | Article |
| id | doaj.art-146eb7c143de4dd69ad03212a19bf2ec |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-09T18:17:22Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-146eb7c143de4dd69ad03212a19bf2ec2023-11-24T08:35:23ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672022-11-0123221391210.3390/ijms232213912A New Hybrid Neural Network Deep Learning Method for Protein–Ligand Binding Affinity Prediction and De Novo Drug DesignSarita Limbu0Sivanesan Dakshanamurthy1Lombardi Comprehensive Cancer Center, Georgetown University Medical Center, Washington, DC 20057, USALombardi Comprehensive Cancer Center, Georgetown University Medical Center, Washington, DC 20057, USAAccurately predicting ligand binding affinity in a virtual screening campaign is still challenging. Here, we developed hybrid neural network (HNN) machine deep learning methods, HNN-denovo and HNN-affinity, by combining the 3D-CNN (convolutional neural network) and the FFNN (fast forward neural network) hybrid neural network framework. The HNN-denovo uses protein pocket structure and protein–ligand interactions as input features. The HNN-affinity uses protein sequences and ligand features as input features. The HNN method combines the CNN and FCNN machine architecture for the protein structure or protein sequence and ligand descriptors. To train the model, the HNN methods used thousands of known protein–ligand binding affinity data retrieved from the PDBBind database. We also developed the Random Forest (RF), Gradient Boosting (GB), Decision Tree with AdaBoost (DT), and a consensus model. We compared the HNN results with models developed based on the RF, GB, and DT methods. We also independently compared the HNN method results with the literature reported deep learning protein–ligand binding affinity predictions made by the DLSCORE, KDEEP, and DeepAtom. The predictive performance of the HNN methods (max Pearson’s R achieved was 0.86) was consistently better than or comparable to the DLSCORE, KDEEP, and DeepAtom deep learning learning methods for both balanced and unbalanced data sets. The HNN-affinity can be applied for the protein–ligand affinity prediction even in the absence of protein structure information, as it considers the protein sequence as standalone feature in addition to the ligand descriptors. The HNN-denovo method can be efficiently implemented to the structure-based de novo drug design campaign. The HNN-affinity method can be used in conjunction with the deep learning molecular docking protocols as a standalone. Further, it can be combined with the conventional molecular docking methods as a multistep approach to rapidly screen billions of diverse compounds. The HNN method are highly scalable in the cloud ML platform.https://www.mdpi.com/1422-0067/23/22/13912protein–ligand binding affinity predictionvirtual screeningde novo drug designmachine learninghybrid neural networkconvolution neural network |
| spellingShingle | Sarita Limbu Sivanesan Dakshanamurthy A New Hybrid Neural Network Deep Learning Method for Protein–Ligand Binding Affinity Prediction and De Novo Drug Design International Journal of Molecular Sciences protein–ligand binding affinity prediction virtual screening de novo drug design machine learning hybrid neural network convolution neural network |
| title | A New Hybrid Neural Network Deep Learning Method for Protein–Ligand Binding Affinity Prediction and De Novo Drug Design |
| title_full | A New Hybrid Neural Network Deep Learning Method for Protein–Ligand Binding Affinity Prediction and De Novo Drug Design |
| title_fullStr | A New Hybrid Neural Network Deep Learning Method for Protein–Ligand Binding Affinity Prediction and De Novo Drug Design |
| title_full_unstemmed | A New Hybrid Neural Network Deep Learning Method for Protein–Ligand Binding Affinity Prediction and De Novo Drug Design |
| title_short | A New Hybrid Neural Network Deep Learning Method for Protein–Ligand Binding Affinity Prediction and De Novo Drug Design |
| title_sort | new hybrid neural network deep learning method for protein ligand binding affinity prediction and de novo drug design |
| topic | protein–ligand binding affinity prediction virtual screening de novo drug design machine learning hybrid neural network convolution neural network |
| url | https://www.mdpi.com/1422-0067/23/22/13912 |
| work_keys_str_mv | AT saritalimbu anewhybridneuralnetworkdeeplearningmethodforproteinligandbindingaffinitypredictionanddenovodrugdesign AT sivanesandakshanamurthy anewhybridneuralnetworkdeeplearningmethodforproteinligandbindingaffinitypredictionanddenovodrugdesign AT saritalimbu newhybridneuralnetworkdeeplearningmethodforproteinligandbindingaffinitypredictionanddenovodrugdesign AT sivanesandakshanamurthy newhybridneuralnetworkdeeplearningmethodforproteinligandbindingaffinitypredictionanddenovodrugdesign |