Brown, A.J.L., Precious, H.M., Whitcomb, J.M., Wong, J.K., Quigg, M., Huang, W., Daar, E.S., Richard, T.D., Keiser, P.H., Connick, E. and Hellmann, N.S. (2000) Reduced Susceptibility of Human Immunodeficiency Virus Type 1 (HIV-1) from Patients with Primary HIV Infection to Nonnucleoside Reverse Transcriptase Inhibitors Is Associated with Variation at Novel Amino Acid Sites. Journal of Virology, 74, 10269-10273.
https://doi.org/10.1128/JVI.74.22.10269-10273.2000

has been cited by the following article:

• TITLE: Predicting the Underlying Structure for Phylogenetic Trees Using Neural Networks and Logistic Regression

  AUTHORS: Hassan W. Kayondo, Samuel Mwalili

  KEYWORDS: Artificial Neural Networks, Logistic Regression, Phylogenetic Tree, Tree Statistics, Classification, Clustering

  JOURNAL NAME: Open Journal of Statistics, Vol.10 No.2, April 3, 2020

  ABSTRACT: Understanding an underlying structure for phylogenetic trees is very important as it informs on the methods that should be employed during phylogenetic inference. The methods used under a structured population differ from those needed when a population is not structured. In this paper, we compared two supervised machine learning techniques, that is artificial neural network (ANN) and logistic regression models for prediction of an underlying structure for phylogenetic trees. We carried out parameter tuning for the models to identify optimal models. We then performed 10-fold cross-validation on the optimal models for both logistic regressionand ANN. We also performed a non-supervised technique called clustering to identify the number of clusters that could be identified from simulated phylogenetic trees. The trees were fromboth structuredand non-structured populations. Clustering and prediction using classification techniques weredone using tree statistics such as Colless, Sackin and cophenetic indices, among others. Results from 10-fold cross-validation revealed that both logistic regression and ANN models had comparable results, with both models having average accuracy rates of over 0.75. Most of the clustering indices used resulted in 2 or 3 as the optimal number of clusters.