A comparison of machine learning techniques for classification of HIV patients with antiretroviral therapy-induced mitochondrial toxicity from those without mitochondrial toxicity

Abstract

BackgroundAntiretroviral therapy (ART) has significantly reduced HIV-related morbidity and mortality. However, therapeutic benefit of ART is often limited by delayed drug-associated toxicity. Nucleoside reverse transcriptase inhibitors (NRTIs) are the backbone of ART regimens. NRTIs compete with endogenous deoxyribonucleotide triphosphates (dNTPs) in incorporation into elongating DNA chain resulting in their cytotoxic or antiviral effect. Thus, the efficacy of NRTIs could be affected by direct competition with endogenous dNTPs and/or feedback inhibition of their metabolic enzymes. In this paper, we assessed whether the levels of ribonucleotides (RN) and dNTP pool sizes can be used as biomarkers in distinguishing between HIV-infected patients with ART-induced mitochondrial toxicity and HIV-infected patients without toxicity.MethodsWe used data collected through a case-control study from 50 subjects. Cases were defined as HIV-infected individuals with clinical and/or laboratory evidence of mitochondrial toxicity. Each case was age, gender, and race matched with an HIV-positive without evidence of toxicity. We used a range of machine learning procedures to distinguish between patients with and without toxicity. Using resampling methods like Monte Carlo k-fold cross validation, we compared the accuracy of several machine learning algorithms applied to our data. We used the algorithm with highest classification accuracy rate in evaluating the diagnostic performance of 12 RN and 14 dNTP pool sizes as biomarkers of mitochondrial toxicity.ResultsWe used eight classification algorithms to assess the diagnostic performance of RN and dNTP pool sizes distinguishing HIV patients with and without NRTI-associated mitochondrial toxicity. The algorithms resulted in cross-validated classification rates of 0.65–0.76 for dNTP and 0.72–0.83 for RN, following reduction of the dimensionality of the input data. The reduction of input variables improved the classification performance of the algorithms, with the most pronounced improvement for RN. Complex tree-based methods worked the best for both the deoxyribose dataset (Random Forest) and the ribose dataset (Classification Tree and AdaBoost), but it is worth noting that simple methods such as Linear Discriminant Analysis and Logistic Regression were very competitive in terms of classification performance.ConclusionsOur finding of changes in RN and dNTP pools in participants with mitochondrial toxicity validates the importance of dNTP pools in mitochondrial function. Hence, levels of RN and dNTP pools can be used as biomarkers of ART-induced mitochondrial toxicity.

Machine-Learning Points at Endoscopic, Quality of Life, and Olfactory Parameters as Outcome Criteria for Endoscopic Paranasal Sinus Surgery in Chronic Rhinosinusitis

“…The above workflow was run in a 1000-fold cross-validation scenario as advised for example in [ 74 ], using Monte-Carlo [ 75 ] resampling to split the data set class-proportionally into two disjoint subsets, of which 2/3 of the original data served as the training data subset and the remaining 1/3 served as the test data subset. The size of the final set of variables (features) selected corresponded to the most frequent size of subsets “A” in the 1000 runs, and its members were the variables most frequently placed in the ABC subset “A” in the 1000 runs, in descending order of their occurrence in the retained sets.…”

Minimum Redundancy Maximal Relevance Gene Selection of Apoptosis Pathway Genes in Peripheral Blood Mononuclear Cells of HIV-infected Patients with Antiretroviral Therapy-associated Mitochondrial Toxicity

“…KNN makes predictions for new instances by searching through the entire training set for the K most similar instances (the neighbors) and summarizing the output variable for those K instances, for our study, classifying the mode (or the most common) class value. To determine which of the K instances in the training dataset are most like new input, we used a Euclidean distance measure (24,25).…”

“…Ridge regression creates a regression model penalized with the L2-norm, which shrinks the coe cient values allowing coe cients with a minor contribution to the target variable to get close to zero. On the other hand, LASSO creates a regression model penalized with the L1-norm, which affects shrinking coe cient values allowing some with a minor impact on the target variable to become zero (23,24). Elastic net penalization creates a regression model with both the L1-norm and L2-norm.…”

Machine Learning Refutes Loss of Smell as a Risk Indicator of Diabetes Mellitus

“…Training of the machine-learned of the classifiers was performed in 1000-fold repeated random subsampling cross-validation experiments as advised, for example, in [80], using Monte-Carlo [81] resampling to split the data set class-proportionally into two disjoint subsets, of which two-thirds of the original data served as the training data subset, and the remaining third served as the test data subset. This was done using the R library "sampling" (https://cran.r-project.org/package=sampling [82]).…”