Prediction of protein group function by iterative classification on functional relevance network

Ishita K. Khan, Aashish Jain, Reda Rawi, Halima Bensmail, Daisuke Kihara

Research output: Contribution to journalArticle

Abstract

Motivation: Biological experiments including proteomics and transcriptomics approaches often reveal sets of proteins that are most likely to be involved in a disease/disorder. To understand the functional nature of a set of proteins, it is important to capture the function of the proteins as a group, even in cases where function of individual proteins is not known. In this work, we propose a model that takes groups of proteins found to work together in a certain biological context, integrates them into functional relevance networks, and subsequently employs an iterative inference on graphical models to identify group functions of the proteins, which are then extended to predict function of individual proteins. Results: The proposed algorithm, iterative group function prediction (iGFP), depicts proteins as a graph that represents functional relevance of proteins considering their known functional, proteomics and transcriptional features. Proteins in the graph will be clustered into groups by their mutual functional relevance, which is iteratively updated using a probabilistic graphical model, the conditional random field. iGFP showed robust accuracy even when substantial amount of GO annotations were missing. The perspective of 'group' function annotation opens up novel approaches for understanding functional nature of proteins in biological systems. Availability and implementation: http://kiharalab.org/iGFP/.

Original languageEnglish
Pages (from-to)1388-1394
Number of pages7
JournalBioinformatics
Volume35
Issue number8
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

Proteins
Protein
Prediction
Proteomics
Graphical Models
Annotation
Relevance
Conditional Random Fields
Statistical Models
Biological systems
Graph in graph theory
Biological Systems
Probabilistic Model
Iterative Algorithm
Disorder
Availability
Likely
Integrate
Predict
Experiment

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

Prediction of protein group function by iterative classification on functional relevance network. / Khan, Ishita K.; Jain, Aashish; Rawi, Reda; Bensmail, Halima; Kihara, Daisuke.

In: Bioinformatics, Vol. 35, No. 8, 01.01.2019, p. 1388-1394.

Research output: Contribution to journalArticle

Khan, Ishita K. ; Jain, Aashish ; Rawi, Reda ; Bensmail, Halima ; Kihara, Daisuke. / Prediction of protein group function by iterative classification on functional relevance network. In: Bioinformatics. 2019 ; Vol. 35, No. 8. pp. 1388-1394.
@article{2dede47e9c8840f08864fae3201db3a4,
title = "Prediction of protein group function by iterative classification on functional relevance network",
abstract = "Motivation: Biological experiments including proteomics and transcriptomics approaches often reveal sets of proteins that are most likely to be involved in a disease/disorder. To understand the functional nature of a set of proteins, it is important to capture the function of the proteins as a group, even in cases where function of individual proteins is not known. In this work, we propose a model that takes groups of proteins found to work together in a certain biological context, integrates them into functional relevance networks, and subsequently employs an iterative inference on graphical models to identify group functions of the proteins, which are then extended to predict function of individual proteins. Results: The proposed algorithm, iterative group function prediction (iGFP), depicts proteins as a graph that represents functional relevance of proteins considering their known functional, proteomics and transcriptional features. Proteins in the graph will be clustered into groups by their mutual functional relevance, which is iteratively updated using a probabilistic graphical model, the conditional random field. iGFP showed robust accuracy even when substantial amount of GO annotations were missing. The perspective of 'group' function annotation opens up novel approaches for understanding functional nature of proteins in biological systems. Availability and implementation: http://kiharalab.org/iGFP/.",
author = "Khan, {Ishita K.} and Aashish Jain and Reda Rawi and Halima Bensmail and Daisuke Kihara",
year = "2019",
month = "1",
day = "1",
doi = "10.1093/bioinformatics/bty787",
language = "English",
volume = "35",
pages = "1388--1394",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "8",

}

TY - JOUR

T1 - Prediction of protein group function by iterative classification on functional relevance network

AU - Khan, Ishita K.

AU - Jain, Aashish

AU - Rawi, Reda

AU - Bensmail, Halima

AU - Kihara, Daisuke

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Motivation: Biological experiments including proteomics and transcriptomics approaches often reveal sets of proteins that are most likely to be involved in a disease/disorder. To understand the functional nature of a set of proteins, it is important to capture the function of the proteins as a group, even in cases where function of individual proteins is not known. In this work, we propose a model that takes groups of proteins found to work together in a certain biological context, integrates them into functional relevance networks, and subsequently employs an iterative inference on graphical models to identify group functions of the proteins, which are then extended to predict function of individual proteins. Results: The proposed algorithm, iterative group function prediction (iGFP), depicts proteins as a graph that represents functional relevance of proteins considering their known functional, proteomics and transcriptional features. Proteins in the graph will be clustered into groups by their mutual functional relevance, which is iteratively updated using a probabilistic graphical model, the conditional random field. iGFP showed robust accuracy even when substantial amount of GO annotations were missing. The perspective of 'group' function annotation opens up novel approaches for understanding functional nature of proteins in biological systems. Availability and implementation: http://kiharalab.org/iGFP/.

AB - Motivation: Biological experiments including proteomics and transcriptomics approaches often reveal sets of proteins that are most likely to be involved in a disease/disorder. To understand the functional nature of a set of proteins, it is important to capture the function of the proteins as a group, even in cases where function of individual proteins is not known. In this work, we propose a model that takes groups of proteins found to work together in a certain biological context, integrates them into functional relevance networks, and subsequently employs an iterative inference on graphical models to identify group functions of the proteins, which are then extended to predict function of individual proteins. Results: The proposed algorithm, iterative group function prediction (iGFP), depicts proteins as a graph that represents functional relevance of proteins considering their known functional, proteomics and transcriptional features. Proteins in the graph will be clustered into groups by their mutual functional relevance, which is iteratively updated using a probabilistic graphical model, the conditional random field. iGFP showed robust accuracy even when substantial amount of GO annotations were missing. The perspective of 'group' function annotation opens up novel approaches for understanding functional nature of proteins in biological systems. Availability and implementation: http://kiharalab.org/iGFP/.

UR - http://www.scopus.com/inward/record.url?scp=85068537562&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068537562&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/bty787

DO - 10.1093/bioinformatics/bty787

M3 - Article

VL - 35

SP - 1388

EP - 1394

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 8

ER -