©1996-2019. All Rights
Reserved. Online Journal of Bioinformatics . You may not store
these pages in any form except for your own personal use. All other usage or
distribution is illegal under international copyright treaties. Permission to
use any of these pages in any other way besides the
before mentioned must be gained in writing from the publisher. This
article is exclusively copyrighted in its entirety to OJB publications. This
article may be copied once but may not be, reproduced or
re-transmitted without the express permission of the editors. This
journal satisfies the refereeing requirements (DEST) for the Higher Education
Research Data Collection (Australia). Linking: To link to this
page or any pages linking to this page you must link directly to this page only
here rather than put up your own page.
OJBTM
Online Journal of Bioinformatics ©
Volume 16 (1): 29-50, 2015.
Support
vector machine to predict human death domain protein-protein interactions
1,*Prakash
A. Nemade, 2Kamal R. Pardasani
1Department of Bioinformatics, Maulana Azad
National Institute of Technology, 2Department of Mathematics,
Maulana Azad National Institute of Technology,
Bhopal, India
ABSTRACT
Nemade PA, Pardasani
KA., Support vector machine to predict human death domain protein-protein
interactions, Onl J Bioinform.,
16 (1): 29-50, 2015. Protein-Protein
Interactions (PPIs) regulate DNA transcription, replication, metabolic cycles and
signaling cascades and cell death via apoptosis and necrosis in eukaryotic
cells. Apoptosis an orderly cellular suicide program,
is critical for development and homeostasis of multi-cellular organisms.
Failure to control apoptosis can have catastrophic consequences. The cascade of reactions by
Caspase, CARD, NLRP, NOD, FADD, DEDD, POP, Myd88 proteins are involved in the
process of cell death. High throughput experimental methods for determining
PPIs are time consuming, expensive generating huge amounts of PPI data. There
is need to develop computational methods to efficiently and accurately predict
PPIs. We describe a model for predicting human death domain (DD) PPI based on
seven physicochemical, biochemical & structural features of amino acids monomers
of proteins. Protein primary sequences are encoded into sequential features
represented by descriptors. Then, the Support Vector Machine and Sequential
Minimal Optimization of WEKA tool is employed to classify interacting and
non-interacting protein pairs. The various kernel functions were evaluated to
build the model and it was observed that libSVM with
linear kernel was found to be best on the basis of performance measures. The
validation has been performed by 10 fold cross validation technique. The optimum
model gives accuracy of 75% in predicting human DD-PPI. Such models can be
useful in providing PPI information of DD proteins which can be useful in
understanding the molecular mechanisms involved in cell death taking place due
to ageing, programmed cell death and various diseases. It may through some
light on the study of cancerous cell and gerontology.
Keywords: Protein-Protein Interactions, Cell Death,
Support Vector Machine, Apoptosis, Death domain, Death effector domain, Caspase
recruitment domain, Pyrin domain, Caspases, Myd88.
FULL-TEXT(SUBSCRIBERS) OR PURCHASE ARTICLE $25USD