Prediction of HIV Drug Resistance by Combining Sequence and Structural Properties

Abstract

Drug resistance is a major obstacle faced by therapist in treating HIV infected patients. The reason behind these phenomena is either protein mutation or the changes in gene expression level that induces resistance to drug treatments. These mutations affect the drug binding activity, hence resulting in failure of treatment. Therefore, it is necessary to conduct resistance testing in order to carry out HIV effective therapy. This study combines both sequence and structural features for predicting HIV resistance by applying SVM and Random Forests classifiers. The model was tested on the mutants of HIV-1 protease and reverse transcriptase. Taken together the features we have used in our method, total contact energies among multiple mutations have a strong impact in predicting resistance as they are crucial in understanding the interactions of HIV mutants. The combination of sequence-structure features offers high accuracy with support vector machines as compared to Random Forests classifier. Both single and acquisition of multiple mutations are important in predicting HIV resistance to certain drug treatments. We have discovered the practicality of these features; hence, these can be used in the future to predict resistance for other complex diseases.

HIV-1 drug resistance profiling using amino acid sequence space cartography

“…Alternatively, ML algorithms can be used to overcome the aforementioned problems of rule-based approaches. Various ML algorithms were applied for HIV drug resistance profiling, including linear regression (Rhee et al, 2006;Yu et al, 2014), support vector machines (Khalid & Sezerman, 2018;Masso & Vaisman, 2013;Rhee et al, 2006), decision trees (Beerenwinkel et al, 2002;Rhee et al, 2006), random forest (Shen et al, 2016;Tarasova et al, 2018), artificial neural networks (Pasomsub et al, 2010;Rhee et al, 2006;Sheik Amamuddy et al, 2017;Steiner et al, 2020;Wang & Larder, 2003), and Bayesian approaches (Tarasova et al, 2017). They allowed achieving better accuracy of drug resistance predictions as compared to rule-based methods.…”

An Innovative Sequence-to-Structure-Based Approach to Drug Resistance Interpretation and Prediction: The Use of Molecular Interaction Fields to Detect HIV-1 Protease Binding-Site Dissimilarities

“…The most relevant computational predictors of antiviral drug resistance currently available share the shortcoming of being purely based on genotypic sequence data. By disregarding the three-dimensional structural context and enzymatic function of the mutated amino acid residues, these systems fail to capture the links between genetic viral mutations and the corresponding mutation-induced structural changes to the effector protein viral machinery (Cao et al, 2005;Weber and Harrison, 2016;Khalid and Sezerman, 2018). This means that such methods are limited in their predictive power and interpretability toward novel mutations and combinations of mutations that go beyond the information accessible for training, such as mutation patterns that are encountered in only a small number of patients.…”

“…As a result of such limitations, the primary challenge facing structure-based drug resistance prediction is to achieve an acceptable balance between prediction accuracy and computational efficiency to become both reliable and fast tools to be used in clinic context (Hao et al, 2012). In fact, some of the most recent reports describe the use of machine learning strategies merging both sequence and structural data in attempt to achieve such balance (Masso and Vaisman, 2013;Yu et al, 2014;Khalid and Sezerman, 2018).…”

HIV drug resistance prediction with weighted categorical kernel functions

“…This second approach is also very popular and there exists machine learning software to predict resistance online [8, 9]. Different methods have been proposed, the most common ones being Linear Regression [10, 11], Artificial Neural Networks (ANN) [10, 12–14], Support Vector Machines (SVMs) [10, 15, 16], Decision Trees (DT) [10, 17] and their ensemble counterpart, Random Forests (RF) [15, 16, 18, 19]. Some machine learning studies have complemented the sequence data with structural information, e.g., [11, 15, 16, 18], or have benefited from the knowledge about major drug associated mutations to perform feature selection.…”

“…A very different approach is found in [14], where each amino acid was codified as an integer ranging 1–22 (the 20 canonical amino acids plus two extra characters B and Z). Other encodings have been used with HIV sequence data, like amino acid composition frequencies, reduced amino acid alphabets or physicochemical properties [5, 16, 20].…”