Analysis of drug resistance in HIV protease

Shrikant D Pawar,Christopher Freas,Robert W Harrison,Irene T Weber

doi:10.1186/s12859-018-2331-y

Shrikant D Pawar, Christopher Freas + Show 2 more

Open Access

https://doi.org/10.1186/s12859-018-2331-y

Copy DOI

Journal: BMC bioinformatics	Publication Date: Oct 1, 2018
Citations: 16	License type: open-access

Affiliation: University of Atlanta

Abstract

BackgroundDrug resistance in HIV is the major problem limiting effective antiviral therapy. Computational techniques for predicting drug resistance profiles from genomic data can accelerate the appropriate choice of therapy. These techniques can also be used to select protease mutants for experimental studies of resistance and thereby assist in the development of next-generation therapies.ResultsThe machine learning produced highly accurate and robust classification of HIV protease resistance. Genotype data were mapped to the enzyme structure and encoded using Delaunay triangulation. Generative machine learning models trained on one inhibitor could classify resistance from other inhibitors with varying levels of accuracy. Generally, the accuracy was best when the inhibitors were chemically similar.ConclusionsRestricted Boltzmann Machines are an effective machine learning tool for classification of genomic and structural data. They can also be used to compare resistance profiles of different protease inhibitors.

Highlights

Drug resistance in Human Immunodeficiency Virus (HIV) is the major problem limiting effective antiviral therapy
The development of drug resistance in HIV is an ongoing threat to effective long-term therapy
This paper shows that Restricted boltzmann machine (RBM) are as accurate as other machine learning approaches for these data

Summary

Introduction

Drug resistance in HIV is the major problem limiting effective antiviral therapy. Computational techniques for predicting drug resistance profiles from genomic data can accelerate the appropriate choice of therapy. These techniques can be used to select protease mutants for experimental studies of resistance and thereby assist in the development of next-generation therapies. Retroviruses like HIV mutate rapidly since the conversion from the RNA genome to DNA is error-prone [3]. They readily form quasi-species and distinct viral strains. The development of drug resistance in HIV is an ongoing threat to effective long-term therapy

Methods

Results

Conclusion