Identifying affinity classes of inorganic materials binding sequences via a graph-based model

Nan Du, Marc Knecht, Mark T. Swihart, Zhenghua Tang, Tiffany R. Walsh, Aidong Zhang

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Rapid advances in bionanotechnology have recently generated growing interest in identifying peptides that bind to inorganic materials and classifying them based on their inorganic material affinities. However, there are some distinct characteristics of inorganic materials binding sequence data that limit the performance of many widely-used classification methods when applied to this problem. In this paper, we propose a novel framework to predict the affinity classes of peptide sequences with respect to an associated inorganic material. We first generate a large set of simulated peptide sequences based on an amino acid transition matrix tailored for the specific inorganic material. Then the probability of test sequences belonging to a specific affinity class is calculated by minimizing an objective function. In addition, the objective function is minimized through iterative propagation of probability estimates among sequences and sequence clusters. Results of computational experiments on two real inorganic material binding sequence data sets show that the proposed framework is highly effective for identifying the affinity classes of inorganic material binding sequences. Moreover, the experiments on the structural classification of proteins (SCOP) data set shows that the proposed framework is general and can be applied to traditional protein sequences.

Original languageEnglish
Article number6808499
Pages (from-to)193-204
Number of pages12
JournalIEEE/ACM Transactions on Computational Biology and Bioinformatics
Volume12
Issue number1
DOIs
StatePublished - Jan 1 2015

Fingerprint

Affine transformation
Peptides
Graph in graph theory
Proteins
Model
Amino Acids
Objective function
Class
Transition Matrix
Protein Sequence
Amino acids
Computational Experiments
Large Set
Experiments
Datasets
Propagation
Protein
Distinct
Predict
Estimate

Keywords

  • classification
  • Inorganic material
  • peptide sequences

ASJC Scopus subject areas

  • Biotechnology
  • Genetics
  • Applied Mathematics

Cite this

Identifying affinity classes of inorganic materials binding sequences via a graph-based model. / Du, Nan; Knecht, Marc; Swihart, Mark T.; Tang, Zhenghua; Walsh, Tiffany R.; Zhang, Aidong.

In: IEEE/ACM Transactions on Computational Biology and Bioinformatics, Vol. 12, No. 1, 6808499, 01.01.2015, p. 193-204.

Research output: Contribution to journalArticle

Du, Nan ; Knecht, Marc ; Swihart, Mark T. ; Tang, Zhenghua ; Walsh, Tiffany R. ; Zhang, Aidong. / Identifying affinity classes of inorganic materials binding sequences via a graph-based model. In: IEEE/ACM Transactions on Computational Biology and Bioinformatics. 2015 ; Vol. 12, No. 1. pp. 193-204.
@article{bc767f174ac64018ba058b957ac56116,
title = "Identifying affinity classes of inorganic materials binding sequences via a graph-based model",
abstract = "Rapid advances in bionanotechnology have recently generated growing interest in identifying peptides that bind to inorganic materials and classifying them based on their inorganic material affinities. However, there are some distinct characteristics of inorganic materials binding sequence data that limit the performance of many widely-used classification methods when applied to this problem. In this paper, we propose a novel framework to predict the affinity classes of peptide sequences with respect to an associated inorganic material. We first generate a large set of simulated peptide sequences based on an amino acid transition matrix tailored for the specific inorganic material. Then the probability of test sequences belonging to a specific affinity class is calculated by minimizing an objective function. In addition, the objective function is minimized through iterative propagation of probability estimates among sequences and sequence clusters. Results of computational experiments on two real inorganic material binding sequence data sets show that the proposed framework is highly effective for identifying the affinity classes of inorganic material binding sequences. Moreover, the experiments on the structural classification of proteins (SCOP) data set shows that the proposed framework is general and can be applied to traditional protein sequences.",
keywords = "classification, Inorganic material, peptide sequences",
author = "Nan Du and Marc Knecht and Swihart, {Mark T.} and Zhenghua Tang and Walsh, {Tiffany R.} and Aidong Zhang",
year = "2015",
month = "1",
day = "1",
doi = "10.1109/TCBB.2014.2321158",
language = "English",
volume = "12",
pages = "193--204",
journal = "IEEE/ACM Transactions on Computational Biology and Bioinformatics",
issn = "1545-5963",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Identifying affinity classes of inorganic materials binding sequences via a graph-based model

AU - Du, Nan

AU - Knecht, Marc

AU - Swihart, Mark T.

AU - Tang, Zhenghua

AU - Walsh, Tiffany R.

AU - Zhang, Aidong

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Rapid advances in bionanotechnology have recently generated growing interest in identifying peptides that bind to inorganic materials and classifying them based on their inorganic material affinities. However, there are some distinct characteristics of inorganic materials binding sequence data that limit the performance of many widely-used classification methods when applied to this problem. In this paper, we propose a novel framework to predict the affinity classes of peptide sequences with respect to an associated inorganic material. We first generate a large set of simulated peptide sequences based on an amino acid transition matrix tailored for the specific inorganic material. Then the probability of test sequences belonging to a specific affinity class is calculated by minimizing an objective function. In addition, the objective function is minimized through iterative propagation of probability estimates among sequences and sequence clusters. Results of computational experiments on two real inorganic material binding sequence data sets show that the proposed framework is highly effective for identifying the affinity classes of inorganic material binding sequences. Moreover, the experiments on the structural classification of proteins (SCOP) data set shows that the proposed framework is general and can be applied to traditional protein sequences.

AB - Rapid advances in bionanotechnology have recently generated growing interest in identifying peptides that bind to inorganic materials and classifying them based on their inorganic material affinities. However, there are some distinct characteristics of inorganic materials binding sequence data that limit the performance of many widely-used classification methods when applied to this problem. In this paper, we propose a novel framework to predict the affinity classes of peptide sequences with respect to an associated inorganic material. We first generate a large set of simulated peptide sequences based on an amino acid transition matrix tailored for the specific inorganic material. Then the probability of test sequences belonging to a specific affinity class is calculated by minimizing an objective function. In addition, the objective function is minimized through iterative propagation of probability estimates among sequences and sequence clusters. Results of computational experiments on two real inorganic material binding sequence data sets show that the proposed framework is highly effective for identifying the affinity classes of inorganic material binding sequences. Moreover, the experiments on the structural classification of proteins (SCOP) data set shows that the proposed framework is general and can be applied to traditional protein sequences.

KW - classification

KW - Inorganic material

KW - peptide sequences

UR - http://www.scopus.com/inward/record.url?scp=84908012060&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908012060&partnerID=8YFLogxK

U2 - 10.1109/TCBB.2014.2321158

DO - 10.1109/TCBB.2014.2321158

M3 - Article

C2 - 26357089

AN - SCOPUS:84908012060

VL - 12

SP - 193

EP - 204

JO - IEEE/ACM Transactions on Computational Biology and Bioinformatics

JF - IEEE/ACM Transactions on Computational Biology and Bioinformatics

SN - 1545-5963

IS - 1

M1 - 6808499

ER -