A neural network model approach to the study of human TAP transporter.

V. Brusic, P. van Endert, J. Zeleznikow, S. Daniel, J. Hammer, N. Petrovsky

Research output: Contribution to journalArticle

43 Citations (Scopus)

Abstract

We used an artificial neural network (ANN) computer model to study peptide binding to the human transporter associated with antigen processing (TAP). After validation, an ANN model of TAP-peptide binding was used to mine a database of HLA-binding peptides to elucidate patterns of TAP binding. The affinity of HLA-binding peptides for TAP was found to differ according to the HLA supertype concerned: HLA-B27, -A3 or -A24 binding peptides had high, whereas HLA-A2, -B7 or -B8 binding peptides had low affinity for TAP. These results support the idea that TAP and particular HLA molecules may have co-evolved for efficient peptide processing and presentation. The strong similarity between the sets of peptides bound by TAP or HLA-B27 suggests functional co-evolution whereas the lack of a relationship between the sets of peptides bound by TAP or HLA-A2 is against these particular molecules having co-evolved. In support of these conclusions, the affinities of HLA-A2 and HLA-B7 binding peptides for TAP show similar distributions to that of randomly generated peptides. On the basis of these results we propose that HLA alleles constitute two separate classes: those that are TAP-efficient for peptide loading (HLA-B27, -A3 and -A24) and those that are TAP-inefficient (HLA-A2, -B7 and -B8). Computer modelling can be used to complement laboratory experiments and thereby speed up knowledge discovery in biology. In particular, we provide evidence that large-scale experiments can be avoided by combining initial experimental data with limited laboratory experiments sufficient to develop and validate appropriate computer models. These models can then be used to perform large-scale simulated experiments the results of which can then be validated by further small-scale laboratory experiments.

Original languageEnglish
Pages (from-to)109-121
Number of pages13
JournalIn Silico Biology
Volume1
Issue number2
Publication statusPublished - 1999
Externally publishedYes

Fingerprint

trypsinogen activation peptide
Neural Networks (Computer)
Neural Network Model
Peptides
HLA-A2 Antigen
HLA-B7 Antigen
Neural networks
HLA-B27 Antigen
HLA-A3 Antigen
Computer Simulation
Affine transformation
Experiment
Computer Model
Experiments
Artificial Neural Network
transporter associated with antigen processing (TAP)
Human
Alleles
Molecules
Databases

ASJC Scopus subject areas

  • Molecular Biology
  • Genetics

Cite this

Brusic, V., van Endert, P., Zeleznikow, J., Daniel, S., Hammer, J., & Petrovsky, N. (1999). A neural network model approach to the study of human TAP transporter. In Silico Biology, 1(2), 109-121.

A neural network model approach to the study of human TAP transporter. / Brusic, V.; van Endert, P.; Zeleznikow, J.; Daniel, S.; Hammer, J.; Petrovsky, N.

In: In Silico Biology, Vol. 1, No. 2, 1999, p. 109-121.

Research output: Contribution to journalArticle

Brusic, V, van Endert, P, Zeleznikow, J, Daniel, S, Hammer, J & Petrovsky, N 1999, 'A neural network model approach to the study of human TAP transporter.', In Silico Biology, vol. 1, no. 2, pp. 109-121.
Brusic V, van Endert P, Zeleznikow J, Daniel S, Hammer J, Petrovsky N. A neural network model approach to the study of human TAP transporter. In Silico Biology. 1999;1(2):109-121.
Brusic, V. ; van Endert, P. ; Zeleznikow, J. ; Daniel, S. ; Hammer, J. ; Petrovsky, N. / A neural network model approach to the study of human TAP transporter. In: In Silico Biology. 1999 ; Vol. 1, No. 2. pp. 109-121.
@article{730f89e0e4ce45af8a37c919657e0cb8,
title = "A neural network model approach to the study of human TAP transporter.",
abstract = "We used an artificial neural network (ANN) computer model to study peptide binding to the human transporter associated with antigen processing (TAP). After validation, an ANN model of TAP-peptide binding was used to mine a database of HLA-binding peptides to elucidate patterns of TAP binding. The affinity of HLA-binding peptides for TAP was found to differ according to the HLA supertype concerned: HLA-B27, -A3 or -A24 binding peptides had high, whereas HLA-A2, -B7 or -B8 binding peptides had low affinity for TAP. These results support the idea that TAP and particular HLA molecules may have co-evolved for efficient peptide processing and presentation. The strong similarity between the sets of peptides bound by TAP or HLA-B27 suggests functional co-evolution whereas the lack of a relationship between the sets of peptides bound by TAP or HLA-A2 is against these particular molecules having co-evolved. In support of these conclusions, the affinities of HLA-A2 and HLA-B7 binding peptides for TAP show similar distributions to that of randomly generated peptides. On the basis of these results we propose that HLA alleles constitute two separate classes: those that are TAP-efficient for peptide loading (HLA-B27, -A3 and -A24) and those that are TAP-inefficient (HLA-A2, -B7 and -B8). Computer modelling can be used to complement laboratory experiments and thereby speed up knowledge discovery in biology. In particular, we provide evidence that large-scale experiments can be avoided by combining initial experimental data with limited laboratory experiments sufficient to develop and validate appropriate computer models. These models can then be used to perform large-scale simulated experiments the results of which can then be validated by further small-scale laboratory experiments.",
author = "V. Brusic and {van Endert}, P. and J. Zeleznikow and S. Daniel and J. Hammer and N. Petrovsky",
year = "1999",
language = "English",
volume = "1",
pages = "109--121",
journal = "In Silico Biology",
issn = "1386-6338",
publisher = "IOS Press",
number = "2",

}

TY - JOUR

T1 - A neural network model approach to the study of human TAP transporter.

AU - Brusic, V.

AU - van Endert, P.

AU - Zeleznikow, J.

AU - Daniel, S.

AU - Hammer, J.

AU - Petrovsky, N.

PY - 1999

Y1 - 1999

N2 - We used an artificial neural network (ANN) computer model to study peptide binding to the human transporter associated with antigen processing (TAP). After validation, an ANN model of TAP-peptide binding was used to mine a database of HLA-binding peptides to elucidate patterns of TAP binding. The affinity of HLA-binding peptides for TAP was found to differ according to the HLA supertype concerned: HLA-B27, -A3 or -A24 binding peptides had high, whereas HLA-A2, -B7 or -B8 binding peptides had low affinity for TAP. These results support the idea that TAP and particular HLA molecules may have co-evolved for efficient peptide processing and presentation. The strong similarity between the sets of peptides bound by TAP or HLA-B27 suggests functional co-evolution whereas the lack of a relationship between the sets of peptides bound by TAP or HLA-A2 is against these particular molecules having co-evolved. In support of these conclusions, the affinities of HLA-A2 and HLA-B7 binding peptides for TAP show similar distributions to that of randomly generated peptides. On the basis of these results we propose that HLA alleles constitute two separate classes: those that are TAP-efficient for peptide loading (HLA-B27, -A3 and -A24) and those that are TAP-inefficient (HLA-A2, -B7 and -B8). Computer modelling can be used to complement laboratory experiments and thereby speed up knowledge discovery in biology. In particular, we provide evidence that large-scale experiments can be avoided by combining initial experimental data with limited laboratory experiments sufficient to develop and validate appropriate computer models. These models can then be used to perform large-scale simulated experiments the results of which can then be validated by further small-scale laboratory experiments.

AB - We used an artificial neural network (ANN) computer model to study peptide binding to the human transporter associated with antigen processing (TAP). After validation, an ANN model of TAP-peptide binding was used to mine a database of HLA-binding peptides to elucidate patterns of TAP binding. The affinity of HLA-binding peptides for TAP was found to differ according to the HLA supertype concerned: HLA-B27, -A3 or -A24 binding peptides had high, whereas HLA-A2, -B7 or -B8 binding peptides had low affinity for TAP. These results support the idea that TAP and particular HLA molecules may have co-evolved for efficient peptide processing and presentation. The strong similarity between the sets of peptides bound by TAP or HLA-B27 suggests functional co-evolution whereas the lack of a relationship between the sets of peptides bound by TAP or HLA-A2 is against these particular molecules having co-evolved. In support of these conclusions, the affinities of HLA-A2 and HLA-B7 binding peptides for TAP show similar distributions to that of randomly generated peptides. On the basis of these results we propose that HLA alleles constitute two separate classes: those that are TAP-efficient for peptide loading (HLA-B27, -A3 and -A24) and those that are TAP-inefficient (HLA-A2, -B7 and -B8). Computer modelling can be used to complement laboratory experiments and thereby speed up knowledge discovery in biology. In particular, we provide evidence that large-scale experiments can be avoided by combining initial experimental data with limited laboratory experiments sufficient to develop and validate appropriate computer models. These models can then be used to perform large-scale simulated experiments the results of which can then be validated by further small-scale laboratory experiments.

UR - http://www.scopus.com/inward/record.url?scp=0033301580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033301580&partnerID=8YFLogxK

M3 - Article

VL - 1

SP - 109

EP - 121

JO - In Silico Biology

JF - In Silico Biology

SN - 1386-6338

IS - 2

ER -