A Computational Approach for the Prediction of HIV Resistance Based on Amino Acid and Nucleotide Descriptors

Abstract

The high variability of the human immunodeficiency virus (HIV) is an important cause of HIV resistance to reverse transcriptase and protease inhibitors. There are many variants of HIV type 1 (HIV-1) that can be used to model sequence-resistance relationships. Machine learning methods are widely and successfully used in new drug discovery. An emerging body of data regarding the interactions of small drug-like molecules with their protein targets provides the possibility of building models on “structure-property” relationships and analyzing the performance of various machine-learning techniques. In our research, we analyze several different types of descriptors in order to predict the resistance of HIV reverse transcriptase and protease to the marketed antiretroviral drugs using the Random Forest approach. First, we represented amino acid sequences as a set of short peptide fragments, which included several amino acid residues. Second, we represented nucleotide sequences as a set of fragments, which included several nucleotides. We compared these two approaches using open data from the Stanford HIV Drug Resistance Database. We have determined the factors that modulate the performance of prediction: in particular, we observed that the prediction performance was more sensitive to certain drugs than a type of the descriptor used.

A Computational Approach for the Prediction of Treatment History and the Effectiveness or Failure of Antiretroviral Therapy

“…From the results of the prediction of drug exposure and effective/failed drug combinations, we could observe the association between nucleotide sequences encoding HIV-1 PR and a set of drugs taken by a patient with a prevalent isolate that was collected and subjected to sequencing. Although there was an association between drug exposure and drug resistance, average AUC/ROC values were about 0.81, while the standard AUC/ROC accuracy of classifying HIV variants into resistant and susceptible was above 0.90 [10]. The following reasons may explain this.…”

“…The random forest (RF) approach was applied in combination with the PASS approach, as described below. The binary descriptors for the random forest classifier were obtained based on nucleotide sequences, as described in [10]. We generated the set of short nucleotide fragments (descriptors).…”

“…Experimental tests allow for the evaluation of HIV-1 resistance against RT and PR inhibitors [7,8]. Several machine learning approaches predict the resistance and/or exposure of a particular HIV-1 variant to a drug on the basis of the nucleotide or amino acid sequences of the HIV-1 PR and RT [9][10][11][12][13][14][15][16][17]. Earlier, we reported computational approaches for predicting HIV-1 resistance to RT and PR inhibitors [10,18,19] based on sequences of HIV-1 variants collected from around the world, available from the Stanford HIV Resistance Database (STDB) [20].…”

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.…”

“…Mixtures introduce ambiguity in the genotype-phenotype correlation [6] and a problem of technical nature: the vast majority of machine learning methods are not able to deal directly with these “multiallelic” codes. To our knowledge, algorithms so far have handled allele mixtures with some sort of previous pre-processing of the data, e.g., keeping only the most frequent amino acid of the mixture [19], replacing the positions by a missing value [17], excluding the affected sequences [15] or expanding the data to obtain all the possible sequences that could be generated with the observed mixtures [11, 14, 18].…”