Rationalization and design of the complementarity determining region sequences in an antibody-antigen recognition interface

Chung Ming Yu, Hung Pin Peng, Ing Chien Chen, Yu Ching Lee, Jun Bo Chen, Keng Chang Tsai, Ching Tai Chen, Jeng Yih Chang, Ei Wen Yang, Po Chiang Hsu, Jhih Wei Jian, Hung Ju Hsu, Hung Ju Chang, Wen Lian Hsu, Kai Fa Huang, Alex Che Ma, An Suei Yang

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Protein-protein interactions are critical determinants in biological systems. Engineered proteins binding to specific areas on protein surfaces could lead to therapeutics or diagnostics for treating diseases in humans. But designing epitope-specific protein-protein interactions with computational atomistic interaction free energy remains a difficult challenge. Here we show that, with the antibody-VEGF (vascular endothelial growth factor) interaction as a model system, the experimentally observed amino acid preferences in the antibody-antigen interface can be rationalized with 3-dimensional distributions of interacting atoms derived from the database of protein structures. Machine learning models established on the rationalization can be generalized to design amino acid preferences in antibody-antigen interfaces, for which the experimental validations are tractable with current high throughput synthetic antibody display technologies. Leave-one-out cross validation on the benchmark system yielded the accuracy, precision, recall (sensitivity) and specificity of the overall binary predictions to be 0.69, 0.45, 0.63, and 0.71 respectively, and the overall Matthews correlation coefficient of the 20 amino acid types in the 24 interface CDR positions was 0.312. The structure-based computational antibody design methodology was further tested with other antibodies binding to VEGF. The results indicate that the methodology could provide alternatives to the current antibody technologies based on animal immune systems in engineering therapeutic and diagnostic antibodies against predetermined antigen epitopes.

Original languageEnglish
Article numbere33340
JournalPLoS One
Volume7
Issue number3
DOIs
Publication statusPublished - Mar 22 2012
Externally publishedYes

Fingerprint

Complementarity Determining Regions
antigens
Antigens
antibodies
Antibodies
Vascular Endothelial Growth Factor A
protein-protein interactions
Proteins
Amino Acids
epitopes
amino acids
Epitopes
Technology
Benchmarking
therapeutics
Protein Databases
vascular endothelial growth factors
artificial intelligence
Immune system
protein binding

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Rationalization and design of the complementarity determining region sequences in an antibody-antigen recognition interface. / Yu, Chung Ming; Peng, Hung Pin; Chen, Ing Chien; Lee, Yu Ching; Chen, Jun Bo; Tsai, Keng Chang; Chen, Ching Tai; Chang, Jeng Yih; Yang, Ei Wen; Hsu, Po Chiang; Jian, Jhih Wei; Hsu, Hung Ju; Chang, Hung Ju; Hsu, Wen Lian; Huang, Kai Fa; Ma, Alex Che; Yang, An Suei.

In: PLoS One, Vol. 7, No. 3, e33340, 22.03.2012.

Research output: Contribution to journalArticle

Yu, CM, Peng, HP, Chen, IC, Lee, YC, Chen, JB, Tsai, KC, Chen, CT, Chang, JY, Yang, EW, Hsu, PC, Jian, JW, Hsu, HJ, Chang, HJ, Hsu, WL, Huang, KF, Ma, AC & Yang, AS 2012, 'Rationalization and design of the complementarity determining region sequences in an antibody-antigen recognition interface', PLoS One, vol. 7, no. 3, e33340. https://doi.org/10.1371/journal.pone.0033340
Yu, Chung Ming ; Peng, Hung Pin ; Chen, Ing Chien ; Lee, Yu Ching ; Chen, Jun Bo ; Tsai, Keng Chang ; Chen, Ching Tai ; Chang, Jeng Yih ; Yang, Ei Wen ; Hsu, Po Chiang ; Jian, Jhih Wei ; Hsu, Hung Ju ; Chang, Hung Ju ; Hsu, Wen Lian ; Huang, Kai Fa ; Ma, Alex Che ; Yang, An Suei. / Rationalization and design of the complementarity determining region sequences in an antibody-antigen recognition interface. In: PLoS One. 2012 ; Vol. 7, No. 3.
@article{a9753b7446bd486abfed1b7080dfca14,
title = "Rationalization and design of the complementarity determining region sequences in an antibody-antigen recognition interface",
abstract = "Protein-protein interactions are critical determinants in biological systems. Engineered proteins binding to specific areas on protein surfaces could lead to therapeutics or diagnostics for treating diseases in humans. But designing epitope-specific protein-protein interactions with computational atomistic interaction free energy remains a difficult challenge. Here we show that, with the antibody-VEGF (vascular endothelial growth factor) interaction as a model system, the experimentally observed amino acid preferences in the antibody-antigen interface can be rationalized with 3-dimensional distributions of interacting atoms derived from the database of protein structures. Machine learning models established on the rationalization can be generalized to design amino acid preferences in antibody-antigen interfaces, for which the experimental validations are tractable with current high throughput synthetic antibody display technologies. Leave-one-out cross validation on the benchmark system yielded the accuracy, precision, recall (sensitivity) and specificity of the overall binary predictions to be 0.69, 0.45, 0.63, and 0.71 respectively, and the overall Matthews correlation coefficient of the 20 amino acid types in the 24 interface CDR positions was 0.312. The structure-based computational antibody design methodology was further tested with other antibodies binding to VEGF. The results indicate that the methodology could provide alternatives to the current antibody technologies based on animal immune systems in engineering therapeutic and diagnostic antibodies against predetermined antigen epitopes.",
author = "Yu, {Chung Ming} and Peng, {Hung Pin} and Chen, {Ing Chien} and Lee, {Yu Ching} and Chen, {Jun Bo} and Tsai, {Keng Chang} and Chen, {Ching Tai} and Chang, {Jeng Yih} and Yang, {Ei Wen} and Hsu, {Po Chiang} and Jian, {Jhih Wei} and Hsu, {Hung Ju} and Chang, {Hung Ju} and Hsu, {Wen Lian} and Huang, {Kai Fa} and Ma, {Alex Che} and Yang, {An Suei}",
year = "2012",
month = "3",
day = "22",
doi = "10.1371/journal.pone.0033340",
language = "English",
volume = "7",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "3",

}

TY - JOUR

T1 - Rationalization and design of the complementarity determining region sequences in an antibody-antigen recognition interface

AU - Yu, Chung Ming

AU - Peng, Hung Pin

AU - Chen, Ing Chien

AU - Lee, Yu Ching

AU - Chen, Jun Bo

AU - Tsai, Keng Chang

AU - Chen, Ching Tai

AU - Chang, Jeng Yih

AU - Yang, Ei Wen

AU - Hsu, Po Chiang

AU - Jian, Jhih Wei

AU - Hsu, Hung Ju

AU - Chang, Hung Ju

AU - Hsu, Wen Lian

AU - Huang, Kai Fa

AU - Ma, Alex Che

AU - Yang, An Suei

PY - 2012/3/22

Y1 - 2012/3/22

N2 - Protein-protein interactions are critical determinants in biological systems. Engineered proteins binding to specific areas on protein surfaces could lead to therapeutics or diagnostics for treating diseases in humans. But designing epitope-specific protein-protein interactions with computational atomistic interaction free energy remains a difficult challenge. Here we show that, with the antibody-VEGF (vascular endothelial growth factor) interaction as a model system, the experimentally observed amino acid preferences in the antibody-antigen interface can be rationalized with 3-dimensional distributions of interacting atoms derived from the database of protein structures. Machine learning models established on the rationalization can be generalized to design amino acid preferences in antibody-antigen interfaces, for which the experimental validations are tractable with current high throughput synthetic antibody display technologies. Leave-one-out cross validation on the benchmark system yielded the accuracy, precision, recall (sensitivity) and specificity of the overall binary predictions to be 0.69, 0.45, 0.63, and 0.71 respectively, and the overall Matthews correlation coefficient of the 20 amino acid types in the 24 interface CDR positions was 0.312. The structure-based computational antibody design methodology was further tested with other antibodies binding to VEGF. The results indicate that the methodology could provide alternatives to the current antibody technologies based on animal immune systems in engineering therapeutic and diagnostic antibodies against predetermined antigen epitopes.

AB - Protein-protein interactions are critical determinants in biological systems. Engineered proteins binding to specific areas on protein surfaces could lead to therapeutics or diagnostics for treating diseases in humans. But designing epitope-specific protein-protein interactions with computational atomistic interaction free energy remains a difficult challenge. Here we show that, with the antibody-VEGF (vascular endothelial growth factor) interaction as a model system, the experimentally observed amino acid preferences in the antibody-antigen interface can be rationalized with 3-dimensional distributions of interacting atoms derived from the database of protein structures. Machine learning models established on the rationalization can be generalized to design amino acid preferences in antibody-antigen interfaces, for which the experimental validations are tractable with current high throughput synthetic antibody display technologies. Leave-one-out cross validation on the benchmark system yielded the accuracy, precision, recall (sensitivity) and specificity of the overall binary predictions to be 0.69, 0.45, 0.63, and 0.71 respectively, and the overall Matthews correlation coefficient of the 20 amino acid types in the 24 interface CDR positions was 0.312. The structure-based computational antibody design methodology was further tested with other antibodies binding to VEGF. The results indicate that the methodology could provide alternatives to the current antibody technologies based on animal immune systems in engineering therapeutic and diagnostic antibodies against predetermined antigen epitopes.

UR - http://www.scopus.com/inward/record.url?scp=84863338291&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863338291&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0033340

DO - 10.1371/journal.pone.0033340

M3 - Article

C2 - 22457753

AN - SCOPUS:84863338291

VL - 7

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 3

M1 - e33340

ER -