Web Service for HIV Drug Resistance Prediction Based on Analysis of Amino Acid Substitutions in Main Drug Targets
Predicting viral drug resistance is a significant medical concern. The importance of this problem stimulates the continuous development of experimental and new computational approaches. The use of computational approaches allows researchers to increase therapy effectiveness and reduce the time and e...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Viruses |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4915/15/11/2245 |
| _version_ | 1797457486771388416 |
|---|---|
| author | Anastasiia Iu. Paremskaia Anastassia V. Rudik Dmitry A. Filimonov Alexey A. Lagunin Vladimir V. Poroikov Olga A. Tarasova |
| author_facet | Anastasiia Iu. Paremskaia Anastassia V. Rudik Dmitry A. Filimonov Alexey A. Lagunin Vladimir V. Poroikov Olga A. Tarasova |
| author_sort | Anastasiia Iu. Paremskaia |
| collection | DOAJ |
| description | Predicting viral drug resistance is a significant medical concern. The importance of this problem stimulates the continuous development of experimental and new computational approaches. The use of computational approaches allows researchers to increase therapy effectiveness and reduce the time and expenses involved when the prescribed antiretroviral therapy is ineffective in the treatment of infection caused by the human immunodeficiency virus type 1 (HIV-1). We propose two machine learning methods and the appropriate models for predicting HIV drug resistance related to amino acid substitutions in HIV targets: (i) k-mers utilizing the random forest and the support vector machine algorithms of the scikit-learn library, and (ii) multi-n-grams using the Bayesian approach implemented in MultiPASSR software. Both multi-n-grams and k-mers were computed based on the amino acid sequences of HIV enzymes: reverse transcriptase and protease. The performance of the models was estimated by five-fold cross-validation. The resulting classification models have a relatively high reliability (minimum accuracy for the drugs is 0.82, maximum: 0.94) and were used to create a web application, HVR (HIV drug Resistance), for the prediction of HIV drug resistance to protease inhibitors and nucleoside and non-nucleoside reverse transcriptase inhibitors based on the analysis of the amino acid sequences of the appropriate HIV proteins from clinical samples. |
| first_indexed | 2024-03-09T16:22:51Z |
| format | Article |
| id | doaj.art-9b1ff66c141b42b7bbbf74f3888e5d9a |
| institution | Directory Open Access Journal |
| issn | 1999-4915 |
| language | English |
| last_indexed | 2024-03-09T16:22:51Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Viruses |
| spelling | doaj.art-9b1ff66c141b42b7bbbf74f3888e5d9a2023-11-24T15:10:57ZengMDPI AGViruses1999-49152023-11-011511224510.3390/v15112245Web Service for HIV Drug Resistance Prediction Based on Analysis of Amino Acid Substitutions in Main Drug TargetsAnastasiia Iu. Paremskaia0Anastassia V. Rudik1Dmitry A. Filimonov2Alexey A. Lagunin3Vladimir V. Poroikov4Olga A. Tarasova5Department of Bioinformatics, Pirogov Russian National Research Medical University, Ostrovitianov Str. 1, Moscow 117997, RussiaLaboratory of Structure-Function Based Drug Design, Institute of Biomedical Chemistry, 10 bldg. 8, Pogodinskaya Str., Moscow 119121, RussiaLaboratory of Structure-Function Based Drug Design, Institute of Biomedical Chemistry, 10 bldg. 8, Pogodinskaya Str., Moscow 119121, RussiaDepartment of Bioinformatics, Pirogov Russian National Research Medical University, Ostrovitianov Str. 1, Moscow 117997, RussiaLaboratory of Structure-Function Based Drug Design, Institute of Biomedical Chemistry, 10 bldg. 8, Pogodinskaya Str., Moscow 119121, RussiaLaboratory of Structure-Function Based Drug Design, Institute of Biomedical Chemistry, 10 bldg. 8, Pogodinskaya Str., Moscow 119121, RussiaPredicting viral drug resistance is a significant medical concern. The importance of this problem stimulates the continuous development of experimental and new computational approaches. The use of computational approaches allows researchers to increase therapy effectiveness and reduce the time and expenses involved when the prescribed antiretroviral therapy is ineffective in the treatment of infection caused by the human immunodeficiency virus type 1 (HIV-1). We propose two machine learning methods and the appropriate models for predicting HIV drug resistance related to amino acid substitutions in HIV targets: (i) k-mers utilizing the random forest and the support vector machine algorithms of the scikit-learn library, and (ii) multi-n-grams using the Bayesian approach implemented in MultiPASSR software. Both multi-n-grams and k-mers were computed based on the amino acid sequences of HIV enzymes: reverse transcriptase and protease. The performance of the models was estimated by five-fold cross-validation. The resulting classification models have a relatively high reliability (minimum accuracy for the drugs is 0.82, maximum: 0.94) and were used to create a web application, HVR (HIV drug Resistance), for the prediction of HIV drug resistance to protease inhibitors and nucleoside and non-nucleoside reverse transcriptase inhibitors based on the analysis of the amino acid sequences of the appropriate HIV proteins from clinical samples.https://www.mdpi.com/1999-4915/15/11/2245HIV/AIDSantiretroviralsresistancemachine learningrandom forestsupporting vector machines |
| spellingShingle | Anastasiia Iu. Paremskaia Anastassia V. Rudik Dmitry A. Filimonov Alexey A. Lagunin Vladimir V. Poroikov Olga A. Tarasova Web Service for HIV Drug Resistance Prediction Based on Analysis of Amino Acid Substitutions in Main Drug Targets Viruses HIV/AIDS antiretrovirals resistance machine learning random forest supporting vector machines |
| title | Web Service for HIV Drug Resistance Prediction Based on Analysis of Amino Acid Substitutions in Main Drug Targets |
| title_full | Web Service for HIV Drug Resistance Prediction Based on Analysis of Amino Acid Substitutions in Main Drug Targets |
| title_fullStr | Web Service for HIV Drug Resistance Prediction Based on Analysis of Amino Acid Substitutions in Main Drug Targets |
| title_full_unstemmed | Web Service for HIV Drug Resistance Prediction Based on Analysis of Amino Acid Substitutions in Main Drug Targets |
| title_short | Web Service for HIV Drug Resistance Prediction Based on Analysis of Amino Acid Substitutions in Main Drug Targets |
| title_sort | web service for hiv drug resistance prediction based on analysis of amino acid substitutions in main drug targets |
| topic | HIV/AIDS antiretrovirals resistance machine learning random forest supporting vector machines |
| url | https://www.mdpi.com/1999-4915/15/11/2245 |
| work_keys_str_mv | AT anastasiiaiuparemskaia webserviceforhivdrugresistancepredictionbasedonanalysisofaminoacidsubstitutionsinmaindrugtargets AT anastassiavrudik webserviceforhivdrugresistancepredictionbasedonanalysisofaminoacidsubstitutionsinmaindrugtargets AT dmitryafilimonov webserviceforhivdrugresistancepredictionbasedonanalysisofaminoacidsubstitutionsinmaindrugtargets AT alexeyalagunin webserviceforhivdrugresistancepredictionbasedonanalysisofaminoacidsubstitutionsinmaindrugtargets AT vladimirvporoikov webserviceforhivdrugresistancepredictionbasedonanalysisofaminoacidsubstitutionsinmaindrugtargets AT olgaatarasova webserviceforhivdrugresistancepredictionbasedonanalysisofaminoacidsubstitutionsinmaindrugtargets |