Accurate Prediction for Antibody Resistance of Clinical HIV-1 Isolates

Reda Rawi, RaghvenPhDa Mall, Chen Hsiang Shen, S. Katie Farney, Andrea Shiakolas, Jing Zhou, Halima Bensmail, Tae Wook Chun, Nicole A. Doria-Rose, Rebecca M. Lynch, John R. Mascola, Peter D. Kwong, Gwo Yu Chuang

Research output: Contribution to journalArticle

Abstract

Broadly neutralizing antibodies (bNAbs) targeting the HIV-1 envelope glycoprotein (Env) have promising utility in prevention and treatment of HIV-1 infection, and several are currently undergoing clinical trials. Due to the high sequence diversity and mutation rate of HIV-1, viral isolates are often resistant to specific bNAbs. Currently, resistant isolates are commonly identified by time-consuming and expensive in vitro neutralization assays. Here, we report machine learning classifiers that accurately predict resistance of HIV-1 isolates to 33 bNAbs. 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 gradient boosting machine – a tree-based machine learning method – enabled us to identify critical features, which had high accordance with epitope residues that distinguished between antibody resistance and sensitivity. The availability of an in silico antibody resistance predictor should facilitate informed decisions of antibody usage and sequence-based monitoring of viral escape in clinical settings.

Original languageEnglish
Article number14696
JournalScientific reports
Volume9
Issue number1
DOIs
Publication statusPublished - 1 Dec 2019

Fingerprint

HIV-1
Neutralizing Antibodies
Antibodies
Clinical Trials
env Gene Products
Mutation Rate
Computer Simulation
HIV Infections
Epitopes
Machine Learning
Therapeutics

ASJC Scopus subject areas

  • General

Cite this

Rawi, R., Mall, R., Shen, C. H., Farney, S. K., Shiakolas, A., Zhou, J., ... Chuang, G. Y. (2019). Accurate Prediction for Antibody Resistance of Clinical HIV-1 Isolates. Scientific reports, 9(1), [14696]. https://doi.org/10.1038/s41598-019-50635-w

Accurate Prediction for Antibody Resistance of Clinical HIV-1 Isolates. / Rawi, Reda; Mall, RaghvenPhDa; Shen, Chen Hsiang; Farney, S. Katie; Shiakolas, Andrea; Zhou, Jing; Bensmail, Halima; Chun, Tae Wook; Doria-Rose, Nicole A.; Lynch, Rebecca M.; Mascola, John R.; Kwong, Peter D.; Chuang, Gwo Yu.

In: Scientific reports, Vol. 9, No. 1, 14696, 01.12.2019.

Research output: Contribution to journalArticle

Rawi, R, Mall, R, Shen, CH, Farney, SK, Shiakolas, A, Zhou, J, Bensmail, H, Chun, TW, Doria-Rose, NA, Lynch, RM, Mascola, JR, Kwong, PD & Chuang, GY 2019, 'Accurate Prediction for Antibody Resistance of Clinical HIV-1 Isolates', Scientific reports, vol. 9, no. 1, 14696. https://doi.org/10.1038/s41598-019-50635-w
Rawi, Reda ; Mall, RaghvenPhDa ; Shen, Chen Hsiang ; Farney, S. Katie ; Shiakolas, Andrea ; Zhou, Jing ; Bensmail, Halima ; Chun, Tae Wook ; Doria-Rose, Nicole A. ; Lynch, Rebecca M. ; Mascola, John R. ; Kwong, Peter D. ; Chuang, Gwo Yu. / Accurate Prediction for Antibody Resistance of Clinical HIV-1 Isolates. In: Scientific reports. 2019 ; Vol. 9, No. 1.
@article{0998810390af41b6afd460cb2e79f79b,
title = "Accurate Prediction for Antibody Resistance of Clinical HIV-1 Isolates",
abstract = "Broadly neutralizing antibodies (bNAbs) targeting the HIV-1 envelope glycoprotein (Env) have promising utility in prevention and treatment of HIV-1 infection, and several are currently undergoing clinical trials. Due to the high sequence diversity and mutation rate of HIV-1, viral isolates are often resistant to specific bNAbs. Currently, resistant isolates are commonly identified by time-consuming and expensive in vitro neutralization assays. Here, we report machine learning classifiers that accurately predict resistance of HIV-1 isolates to 33 bNAbs. 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 gradient boosting machine – a tree-based machine learning method – enabled us to identify critical features, which had high accordance with epitope residues that distinguished between antibody resistance and sensitivity. The availability of an in silico antibody resistance predictor should facilitate informed decisions of antibody usage and sequence-based monitoring of viral escape in clinical settings.",
author = "Reda Rawi and RaghvenPhDa Mall and Shen, {Chen Hsiang} and Farney, {S. Katie} and Andrea Shiakolas and Jing Zhou and Halima Bensmail and Chun, {Tae Wook} and Doria-Rose, {Nicole A.} and Lynch, {Rebecca M.} and Mascola, {John R.} and Kwong, {Peter D.} and Chuang, {Gwo Yu}",
year = "2019",
month = "12",
day = "1",
doi = "10.1038/s41598-019-50635-w",
language = "English",
volume = "9",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Accurate Prediction for Antibody Resistance of Clinical HIV-1 Isolates

AU - Rawi, Reda

AU - Mall, RaghvenPhDa

AU - Shen, Chen Hsiang

AU - Farney, S. Katie

AU - Shiakolas, Andrea

AU - Zhou, Jing

AU - Bensmail, Halima

AU - Chun, Tae Wook

AU - Doria-Rose, Nicole A.

AU - Lynch, Rebecca M.

AU - Mascola, John R.

AU - Kwong, Peter D.

AU - Chuang, Gwo Yu

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Broadly neutralizing antibodies (bNAbs) targeting the HIV-1 envelope glycoprotein (Env) have promising utility in prevention and treatment of HIV-1 infection, and several are currently undergoing clinical trials. Due to the high sequence diversity and mutation rate of HIV-1, viral isolates are often resistant to specific bNAbs. Currently, resistant isolates are commonly identified by time-consuming and expensive in vitro neutralization assays. Here, we report machine learning classifiers that accurately predict resistance of HIV-1 isolates to 33 bNAbs. 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 gradient boosting machine – a tree-based machine learning method – enabled us to identify critical features, which had high accordance with epitope residues that distinguished between antibody resistance and sensitivity. The availability of an in silico antibody resistance predictor should facilitate informed decisions of antibody usage and sequence-based monitoring of viral escape in clinical settings.

AB - Broadly neutralizing antibodies (bNAbs) targeting the HIV-1 envelope glycoprotein (Env) have promising utility in prevention and treatment of HIV-1 infection, and several are currently undergoing clinical trials. Due to the high sequence diversity and mutation rate of HIV-1, viral isolates are often resistant to specific bNAbs. Currently, resistant isolates are commonly identified by time-consuming and expensive in vitro neutralization assays. Here, we report machine learning classifiers that accurately predict resistance of HIV-1 isolates to 33 bNAbs. 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 gradient boosting machine – a tree-based machine learning method – enabled us to identify critical features, which had high accordance with epitope residues that distinguished between antibody resistance and sensitivity. The availability of an in silico antibody resistance predictor should facilitate informed decisions of antibody usage and sequence-based monitoring of viral escape in clinical settings.

UR - http://www.scopus.com/inward/record.url?scp=85073168308&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073168308&partnerID=8YFLogxK

U2 - 10.1038/s41598-019-50635-w

DO - 10.1038/s41598-019-50635-w

M3 - Article

C2 - 31604961

AN - SCOPUS:85073168308

VL - 9

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 14696

ER -