Explainable deep drug–target representations for binding affinity prediction
Abstract Background Several computational advances have been achieved in the drug discovery field, promoting the identification of novel drug–target interactions and new leads. However, most of these methodologies have been overlooking the importance of providing explanations to the decision-making...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-06-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-022-04767-y |
| _version_ | 1818205334689284096 |
|---|---|
| author | Nelson R. C. Monteiro Carlos J. V. Simões Henrique V. Ávila Maryam Abbasi José L. Oliveira Joel P. Arrais |
| author_facet | Nelson R. C. Monteiro Carlos J. V. Simões Henrique V. Ávila Maryam Abbasi José L. Oliveira Joel P. Arrais |
| author_sort | Nelson R. C. Monteiro |
| collection | DOAJ |
| description | Abstract Background Several computational advances have been achieved in the drug discovery field, promoting the identification of novel drug–target interactions and new leads. However, most of these methodologies have been overlooking the importance of providing explanations to the decision-making process of deep learning architectures. In this research study, we explore the reliability of convolutional neural networks (CNNs) at identifying relevant regions for binding, specifically binding sites and motifs, and the significance of the deep representations extracted by providing explanations to the model’s decisions based on the identification of the input regions that contributed the most to the prediction. We make use of an end-to-end deep learning architecture to predict binding affinity, where CNNs are exploited in their capacity to automatically identify and extract discriminating deep representations from 1D sequential and structural data. Results The results demonstrate the effectiveness of the deep representations extracted from CNNs in the prediction of drug–target interactions. CNNs were found to identify and extract features from regions relevant for the interaction, where the weight associated with these spots was in the range of those with the highest positive influence given by the CNNs in the prediction. The end-to-end deep learning model achieved the highest performance both in the prediction of the binding affinity and on the ability to correctly distinguish the interaction strength rank order when compared to baseline approaches. Conclusions This research study validates the potential applicability of an end-to-end deep learning architecture in the context of drug discovery beyond the confined space of proteins and ligands with determined 3D structure. Furthermore, it shows the reliability of the deep representations extracted from the CNNs by providing explainability to the decision-making process. |
| first_indexed | 2024-12-12T03:55:29Z |
| format | Article |
| id | doaj.art-ce862bbbb14f4e208b0489dee1f9f22c |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-12T03:55:29Z |
| publishDate | 2022-06-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-ce862bbbb14f4e208b0489dee1f9f22c2022-12-22T00:39:16ZengBMCBMC Bioinformatics1471-21052022-06-0123112410.1186/s12859-022-04767-yExplainable deep drug–target representations for binding affinity predictionNelson R. C. Monteiro0Carlos J. V. Simões1Henrique V. Ávila2Maryam Abbasi3José L. Oliveira4Joel P. Arrais5Univ Coimbra, Centre for Informatics and Systems of the University of Coimbra, Department of Informatics EngineeringBSIM Therapeutics, Instituto Pedro NunesUniv Coimbra, Centre for Informatics and Systems of the University of Coimbra, Department of Informatics EngineeringUniv Coimbra, Centre for Informatics and Systems of the University of Coimbra, Department of Informatics EngineeringIEETA, Department of Electronics, Telecommunications and Informatics, University of AveiroUniv Coimbra, Centre for Informatics and Systems of the University of Coimbra, Department of Informatics EngineeringAbstract Background Several computational advances have been achieved in the drug discovery field, promoting the identification of novel drug–target interactions and new leads. However, most of these methodologies have been overlooking the importance of providing explanations to the decision-making process of deep learning architectures. In this research study, we explore the reliability of convolutional neural networks (CNNs) at identifying relevant regions for binding, specifically binding sites and motifs, and the significance of the deep representations extracted by providing explanations to the model’s decisions based on the identification of the input regions that contributed the most to the prediction. We make use of an end-to-end deep learning architecture to predict binding affinity, where CNNs are exploited in their capacity to automatically identify and extract discriminating deep representations from 1D sequential and structural data. Results The results demonstrate the effectiveness of the deep representations extracted from CNNs in the prediction of drug–target interactions. CNNs were found to identify and extract features from regions relevant for the interaction, where the weight associated with these spots was in the range of those with the highest positive influence given by the CNNs in the prediction. The end-to-end deep learning model achieved the highest performance both in the prediction of the binding affinity and on the ability to correctly distinguish the interaction strength rank order when compared to baseline approaches. Conclusions This research study validates the potential applicability of an end-to-end deep learning architecture in the context of drug discovery beyond the confined space of proteins and ligands with determined 3D structure. Furthermore, it shows the reliability of the deep representations extracted from the CNNs by providing explainability to the decision-making process.https://doi.org/10.1186/s12859-022-04767-yDrug–target interactionBinding affinityExplainable deep learningConvolutional neural network |
| spellingShingle | Nelson R. C. Monteiro Carlos J. V. Simões Henrique V. Ávila Maryam Abbasi José L. Oliveira Joel P. Arrais Explainable deep drug–target representations for binding affinity prediction BMC Bioinformatics Drug–target interaction Binding affinity Explainable deep learning Convolutional neural network |
| title | Explainable deep drug–target representations for binding affinity prediction |
| title_full | Explainable deep drug–target representations for binding affinity prediction |
| title_fullStr | Explainable deep drug–target representations for binding affinity prediction |
| title_full_unstemmed | Explainable deep drug–target representations for binding affinity prediction |
| title_short | Explainable deep drug–target representations for binding affinity prediction |
| title_sort | explainable deep drug target representations for binding affinity prediction |
| topic | Drug–target interaction Binding affinity Explainable deep learning Convolutional neural network |
| url | https://doi.org/10.1186/s12859-022-04767-y |
| work_keys_str_mv | AT nelsonrcmonteiro explainabledeepdrugtargetrepresentationsforbindingaffinityprediction AT carlosjvsimoes explainabledeepdrugtargetrepresentationsforbindingaffinityprediction AT henriquevavila explainabledeepdrugtargetrepresentationsforbindingaffinityprediction AT maryamabbasi explainabledeepdrugtargetrepresentationsforbindingaffinityprediction AT joseloliveira explainabledeepdrugtargetrepresentationsforbindingaffinityprediction AT joelparrais explainabledeepdrugtargetrepresentationsforbindingaffinityprediction |