RT Journal Article
SR Electronic
T1 Accurate Prediction of Antibody Resistance in Clinical HIV-1 Isolates
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 364828
DO 10.1101/364828
A1 Reda Rawi
A1 Raghvendra Mall
A1 Chen-Hsiang Shen
A1 Nicole A. Doria-Rose
A1 S. Katie Farney
A1 Andrea Shiakolas
A1 Jing Zhou
A1 Tae-Wook Chun
A1 Rebecca M. Lynch
A1 John R. Mascola
A1 Peter D. Kwong
A1 Gwo-Yu Chuang
YR 2018
UL http://biorxiv.org/content/early/2018/07/08/364828.abstract
AB Broadly neutralizing antibodies (bNAbs) targeting the HIV-1 envelope glycoprotein (Env) have promising utility in prevention and treatment of HIV-1 infection with several undergoing clinical trials. Due to high sequence diversity and mutation rate of HIV-1, viral isolates are often resistant to particular bNAbs. Resistant strains are commonly identified by time-consuming and expensive in vitro neutralization experiments. Here, we developed machine learning-based classifiers that accurately predict resistance of HIV-1 strains to 33 neutralizing antibodies. Notably, our classifiers achieved an overall prediction accuracy of 96% for 212 clinical isolates from patients enrolled in four different clinical trials. Moreover, use of the tree-based machine learning method gradient boosting machine enabled us to identify critical epitope features that distinguish between antibody resistance and sensitivity. The availability of an in silico antibody resistance predictor will facilitate informed decisions of antibody usage in clinical settings.