Prediction of HIV-1 protease resistance using genotypic, phenotypic, and molecular information with artificial neural networks
Drug resistance is a primary barrier to effective treatments of HIV/AIDS. Calculating quantitative relations between genotype and phenotype observations for each inhibitor with cell-based assays requires time and money-consuming experiments. Machine learning models are good options for tackling thes...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2023-03-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/14987.pdf |
| _version_ | 1797423978150625280 |
|---|---|
| author | Huseyin Tunc Berna Dogan Büşra Nur Darendeli Kiraz Murat Sari Serdar Durdagi Seyfullah Kotil |
| author_facet | Huseyin Tunc Berna Dogan Büşra Nur Darendeli Kiraz Murat Sari Serdar Durdagi Seyfullah Kotil |
| author_sort | Huseyin Tunc |
| collection | DOAJ |
| description | Drug resistance is a primary barrier to effective treatments of HIV/AIDS. Calculating quantitative relations between genotype and phenotype observations for each inhibitor with cell-based assays requires time and money-consuming experiments. Machine learning models are good options for tackling these problems by generalizing the available data with suitable linear or nonlinear mappings. The main aim of this study is to construct drug isolate fold (DIF) change-based artificial neural network (ANN) models for estimating the resistance potential of molecules inhibiting the HIV-1 protease (PR) enzyme. Throughout the study, seven of eight protease inhibitors (PIs) have been included in the training set and the remaining ones in the test set. We have obtained 11,803 genotype-phenotype data points for eight PIs from Stanford HIV drug resistance database. Using the leave-one-out (LVO) procedure, eight ANN models have been produced to measure the learning capacity of models from the descriptors of the inhibitors. Mean R2 value of eight ANN models for unseen inhibitors is 0.716, and the 95% confidence interval (CI) is [0.592–0.840]. Predicting the fold change resistance for hundreds of isolates allowed a robust comparison of drug pairs. These eight models have predicted the drug resistance tendencies of each inhibitor pair with the mean 2D correlation coefficient of 0.933 and 95% CI [0.930–0.938]. A classification problem has been created to predict the ordered relationship of the PIs, and the mean accuracy, sensitivity, specificity, and Matthews correlation coefficient (MCC) values are calculated as 0.954, 0.791, 0.791, and 0.688, respectively. Furthermore, we have created an external test dataset consisting of 51 unique known HIV-1 PR inhibitors and 87 genotype-phenotype relations. Our developed ANN model has accuracy and area under the curve (AUC) values of 0.749 and 0.818 to predict the ordered relationships of molecules on the same strain for the external dataset. The currently derived ANN models can accurately predict the drug resistance tendencies of PI pairs. This observation could help test new inhibitors with various isolates. |
| first_indexed | 2024-03-09T07:55:40Z |
| format | Article |
| id | doaj.art-72484c17117c4bc182dffdd6ae581f48 |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T07:55:40Z |
| publishDate | 2023-03-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-72484c17117c4bc182dffdd6ae581f482023-12-03T01:06:28ZengPeerJ Inc.PeerJ2167-83592023-03-0111e1498710.7717/peerj.14987Prediction of HIV-1 protease resistance using genotypic, phenotypic, and molecular information with artificial neural networksHuseyin Tunc0Berna Dogan1Büşra Nur Darendeli Kiraz2Murat Sari3Serdar Durdagi4Seyfullah Kotil5Department of Biostatistics and Medical Informatics, School of Medicine, Bahcesehir University, Istanbul, TurkeyDepartment of Medicinal Biochemistry, School of Medicine, Bahcesehir University, Istanbul, TurkeyDepartment of Biophysics, School of Medicine, Bahcesehir University, Istanbul, TurkeyDepartment of Mathematics Engineering, Faculty of Science and Letters, Istanbul Technical University, Istanbul, TurkeyComputational Biology and Molecular Simulations Laboratory, Department of Biophysics, School of Medicine, Bahcesehir University, Istanbul, TurkeyDepartment of Biophysics, School of Medicine, Bahcesehir University, Istanbul, TurkeyDrug resistance is a primary barrier to effective treatments of HIV/AIDS. Calculating quantitative relations between genotype and phenotype observations for each inhibitor with cell-based assays requires time and money-consuming experiments. Machine learning models are good options for tackling these problems by generalizing the available data with suitable linear or nonlinear mappings. The main aim of this study is to construct drug isolate fold (DIF) change-based artificial neural network (ANN) models for estimating the resistance potential of molecules inhibiting the HIV-1 protease (PR) enzyme. Throughout the study, seven of eight protease inhibitors (PIs) have been included in the training set and the remaining ones in the test set. We have obtained 11,803 genotype-phenotype data points for eight PIs from Stanford HIV drug resistance database. Using the leave-one-out (LVO) procedure, eight ANN models have been produced to measure the learning capacity of models from the descriptors of the inhibitors. Mean R2 value of eight ANN models for unseen inhibitors is 0.716, and the 95% confidence interval (CI) is [0.592–0.840]. Predicting the fold change resistance for hundreds of isolates allowed a robust comparison of drug pairs. These eight models have predicted the drug resistance tendencies of each inhibitor pair with the mean 2D correlation coefficient of 0.933 and 95% CI [0.930–0.938]. A classification problem has been created to predict the ordered relationship of the PIs, and the mean accuracy, sensitivity, specificity, and Matthews correlation coefficient (MCC) values are calculated as 0.954, 0.791, 0.791, and 0.688, respectively. Furthermore, we have created an external test dataset consisting of 51 unique known HIV-1 PR inhibitors and 87 genotype-phenotype relations. Our developed ANN model has accuracy and area under the curve (AUC) values of 0.749 and 0.818 to predict the ordered relationships of molecules on the same strain for the external dataset. The currently derived ANN models can accurately predict the drug resistance tendencies of PI pairs. This observation could help test new inhibitors with various isolates.https://peerj.com/articles/14987.pdfMachine learningArtificial neural networksHIV/AIDSDrug resistanceProtease inhibitors |
| spellingShingle | Huseyin Tunc Berna Dogan Büşra Nur Darendeli Kiraz Murat Sari Serdar Durdagi Seyfullah Kotil Prediction of HIV-1 protease resistance using genotypic, phenotypic, and molecular information with artificial neural networks PeerJ Machine learning Artificial neural networks HIV/AIDS Drug resistance Protease inhibitors |
| title | Prediction of HIV-1 protease resistance using genotypic, phenotypic, and molecular information with artificial neural networks |
| title_full | Prediction of HIV-1 protease resistance using genotypic, phenotypic, and molecular information with artificial neural networks |
| title_fullStr | Prediction of HIV-1 protease resistance using genotypic, phenotypic, and molecular information with artificial neural networks |
| title_full_unstemmed | Prediction of HIV-1 protease resistance using genotypic, phenotypic, and molecular information with artificial neural networks |
| title_short | Prediction of HIV-1 protease resistance using genotypic, phenotypic, and molecular information with artificial neural networks |
| title_sort | prediction of hiv 1 protease resistance using genotypic phenotypic and molecular information with artificial neural networks |
| topic | Machine learning Artificial neural networks HIV/AIDS Drug resistance Protease inhibitors |
| url | https://peerj.com/articles/14987.pdf |
| work_keys_str_mv | AT huseyintunc predictionofhiv1proteaseresistanceusinggenotypicphenotypicandmolecularinformationwithartificialneuralnetworks AT bernadogan predictionofhiv1proteaseresistanceusinggenotypicphenotypicandmolecularinformationwithartificialneuralnetworks AT busranurdarendelikiraz predictionofhiv1proteaseresistanceusinggenotypicphenotypicandmolecularinformationwithartificialneuralnetworks AT muratsari predictionofhiv1proteaseresistanceusinggenotypicphenotypicandmolecularinformationwithartificialneuralnetworks AT serdardurdagi predictionofhiv1proteaseresistanceusinggenotypicphenotypicandmolecularinformationwithartificialneuralnetworks AT seyfullahkotil predictionofhiv1proteaseresistanceusinggenotypicphenotypicandmolecularinformationwithartificialneuralnetworks |