Graph Neural Network and BERT Model for Antimalarial Drug Predictions Using Plasmodium Potential Targets
Malaria continues to pose a significant global health burden despite concerted efforts to combat it. In 2020, nearly half of the world’s population faced the risk of malaria, underscoring the urgency of innovative strategies to tackle this pervasive threat. One of the major challenges lies in the em...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-02-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/14/4/1472 |
_version_ | 1797299035744239616 |
---|---|
author | Medard Edmund Mswahili Goodwill Erasmo Ndomba Kyuri Jo Young-Seob Jeong |
author_facet | Medard Edmund Mswahili Goodwill Erasmo Ndomba Kyuri Jo Young-Seob Jeong |
author_sort | Medard Edmund Mswahili |
collection | DOAJ |
description | Malaria continues to pose a significant global health burden despite concerted efforts to combat it. In 2020, nearly half of the world’s population faced the risk of malaria, underscoring the urgency of innovative strategies to tackle this pervasive threat. One of the major challenges lies in the emergence of the resistance of parasites to existing antimalarial drugs. This challenge necessitates the discovery of new, effective treatments capable of combating the Plasmodium parasite at various stages of its life cycle. Advanced computational approaches have been utilized to accelerate drug development, playing a crucial role in every stage of the drug discovery and development process. We have witnessed impressive and groundbreaking achievements, with GNNs applied to graph data and BERT from transformers across diverse NLP text analysis tasks. In this study, to facilitate a more efficient and effective approach, we proposed the integration of an NLP based model for SMILES (i.e., BERT) and a GNN model (i.e., RGCN) to predict the effect of antimalarial drugs against Plasmodium. The GNN model was trained using designed antimalarial drug and potential target (i.e., PfAcAS, F/GGPPS, and PfMAGL) graph-structured data with nodes representing antimalarial drugs and potential targets, and edges representing relationships between them. The performance of BERT-RGCN was further compared with that of Mordred-RGCN to evaluate its effectiveness. The BERT-RGCN and Mordred-RGCN models performed consistently well across different feature combinations, showcasing high accuracy, sensitivity, specificity, MCC, AUROC, and AUPRC values. These results suggest the effectiveness of the models in predicting antimalarial drugs against Plasmodium falciparum in various scenarios based on different sets of features of drugs and potential antimalarial targets. |
first_indexed | 2024-03-07T22:43:41Z |
format | Article |
id | doaj.art-958c28b49f544c9fa5ea91f79b9b488e |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-07T22:43:41Z |
publishDate | 2024-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-958c28b49f544c9fa5ea91f79b9b488e2024-02-23T15:06:05ZengMDPI AGApplied Sciences2076-34172024-02-01144147210.3390/app14041472Graph Neural Network and BERT Model for Antimalarial Drug Predictions Using Plasmodium Potential TargetsMedard Edmund Mswahili0Goodwill Erasmo Ndomba1Kyuri Jo2Young-Seob Jeong3Department of Computer Engineering, Chungbuk National University, Cheongju 28644, Republic of KoreaDepartment of Computer Engineering, Chungbuk National University, Cheongju 28644, Republic of KoreaDepartment of Computer Engineering, Chungbuk National University, Cheongju 28644, Republic of KoreaDepartment of Computer Engineering, Chungbuk National University, Cheongju 28644, Republic of KoreaMalaria continues to pose a significant global health burden despite concerted efforts to combat it. In 2020, nearly half of the world’s population faced the risk of malaria, underscoring the urgency of innovative strategies to tackle this pervasive threat. One of the major challenges lies in the emergence of the resistance of parasites to existing antimalarial drugs. This challenge necessitates the discovery of new, effective treatments capable of combating the Plasmodium parasite at various stages of its life cycle. Advanced computational approaches have been utilized to accelerate drug development, playing a crucial role in every stage of the drug discovery and development process. We have witnessed impressive and groundbreaking achievements, with GNNs applied to graph data and BERT from transformers across diverse NLP text analysis tasks. In this study, to facilitate a more efficient and effective approach, we proposed the integration of an NLP based model for SMILES (i.e., BERT) and a GNN model (i.e., RGCN) to predict the effect of antimalarial drugs against Plasmodium. The GNN model was trained using designed antimalarial drug and potential target (i.e., PfAcAS, F/GGPPS, and PfMAGL) graph-structured data with nodes representing antimalarial drugs and potential targets, and edges representing relationships between them. The performance of BERT-RGCN was further compared with that of Mordred-RGCN to evaluate its effectiveness. The BERT-RGCN and Mordred-RGCN models performed consistently well across different feature combinations, showcasing high accuracy, sensitivity, specificity, MCC, AUROC, and AUPRC values. These results suggest the effectiveness of the models in predicting antimalarial drugs against Plasmodium falciparum in various scenarios based on different sets of features of drugs and potential antimalarial targets.https://www.mdpi.com/2076-3417/14/4/1472malariagraph neural networkBERTtokenizerPlasmodium falciparummachine learning |
spellingShingle | Medard Edmund Mswahili Goodwill Erasmo Ndomba Kyuri Jo Young-Seob Jeong Graph Neural Network and BERT Model for Antimalarial Drug Predictions Using Plasmodium Potential Targets Applied Sciences malaria graph neural network BERT tokenizer Plasmodium falciparum machine learning |
title | Graph Neural Network and BERT Model for Antimalarial Drug Predictions Using Plasmodium Potential Targets |
title_full | Graph Neural Network and BERT Model for Antimalarial Drug Predictions Using Plasmodium Potential Targets |
title_fullStr | Graph Neural Network and BERT Model for Antimalarial Drug Predictions Using Plasmodium Potential Targets |
title_full_unstemmed | Graph Neural Network and BERT Model for Antimalarial Drug Predictions Using Plasmodium Potential Targets |
title_short | Graph Neural Network and BERT Model for Antimalarial Drug Predictions Using Plasmodium Potential Targets |
title_sort | graph neural network and bert model for antimalarial drug predictions using plasmodium potential targets |
topic | malaria graph neural network BERT tokenizer Plasmodium falciparum machine learning |
url | https://www.mdpi.com/2076-3417/14/4/1472 |
work_keys_str_mv | AT medardedmundmswahili graphneuralnetworkandbertmodelforantimalarialdrugpredictionsusingplasmodiumpotentialtargets AT goodwillerasmondomba graphneuralnetworkandbertmodelforantimalarialdrugpredictionsusingplasmodiumpotentialtargets AT kyurijo graphneuralnetworkandbertmodelforantimalarialdrugpredictionsusingplasmodiumpotentialtargets AT youngseobjeong graphneuralnetworkandbertmodelforantimalarialdrugpredictionsusingplasmodiumpotentialtargets |