A Database and Evaluation for Classification of RNA Molecules Using Graph Methods

Enes Algul; Richard Charles Wilson

A Database and Evaluation for Classification of RNA Molecules Using Graph Methods

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

In this paper, we introduce a new graph dataset based on
the representation of RNA. The RNA dataset includes 3178 RNA chains
which are labelled in 8 classes according to their reported biological functions.
The goal of this database is to provide a platform for investigating
the classication of RNA using graph-based methods. The molecules are
represented by graphs representing the sequence and base-pairs of the
RNA, with a number of labelling schemes using base labels and local
shape. We report the results of a number of state-of-the-art graph based
methods on this dataset as a baseline comparison and investigate how
these methods can be used to categorise RNA molecules on their type and
functions. The methods applied are Weisfeiler Lehman and optimal assignment
kernels, shortest paths kernel and the all paths and cycle methods.
We also compare to the standard Needleman-Wunsch algorithm used
in bioinformatics for DNA and RNA comparison, and demonstrate the
superiority of graph kernels even on a string representation. The highest
classication rate is obtained by the WL-OA algorithm using base labels
and base-pair connections.

Original language	English
Title of host publication	Graph-Based Representations in Pattern Recognition - 12th IAPR-TC-15 International Workshop, GbRPR 2019, Tours, France, June 19-21, 2019, Proceedings
Publisher	Springer
Pages	78-87
Number of pages	10
Publication status	Published - 13 Jun 2019

Access to Document

paper_12Accepted author manuscript, 2.03 MB

Cite this

@inbook{62df5d40ae20498dbc3e1a26000a68a2,

title = "A Database and Evaluation for Classification of RNA Molecules Using Graph Methods",

abstract = "In this paper, we introduce a new graph dataset based onthe representation of RNA. The RNA dataset includes 3178 RNA chainswhich are labelled in 8 classes according to their reported biological functions.The goal of this database is to provide a platform for investigatingthe classication of RNA using graph-based methods. The molecules arerepresented by graphs representing the sequence and base-pairs of theRNA, with a number of labelling schemes using base labels and localshape. We report the results of a number of state-of-the-art graph basedmethods on this dataset as a baseline comparison and investigate howthese methods can be used to categorise RNA molecules on their type andfunctions. The methods applied are Weisfeiler Lehman and optimal assignmentkernels, shortest paths kernel and the all paths and cycle methods.We also compare to the standard Needleman-Wunsch algorithm usedin bioinformatics for DNA and RNA comparison, and demonstrate thesuperiority of graph kernels even on a string representation. The highestclassication rate is obtained by the WL-OA algorithm using base labelsand base-pair connections.",

author = "Enes Algul and Wilson, {Richard Charles}",

year = "2019",

month = jun,

day = "13",

language = "English",

pages = "78--87",

booktitle = "Graph-Based Representations in Pattern Recognition - 12th IAPR-TC-15 International Workshop, GbRPR 2019, Tours, France, June 19-21, 2019, Proceedings",

publisher = "Springer",

address = "Germany",

}

A Database and Evaluation for Classification of RNA Molecules Using Graph Methods. / Algul, Enes; Wilson, Richard Charles.
Graph-Based Representations in Pattern Recognition - 12th IAPR-TC-15 International Workshop, GbRPR 2019, Tours, France, June 19-21, 2019, Proceedings. Springer, 2019. p. 78-87.

Research output: Chapter in Book/Report/Conference proceeding › Chapter

TY - CHAP

T1 - A Database and Evaluation for Classification of RNA Molecules Using Graph Methods

AU - Algul, Enes

AU - Wilson, Richard Charles

PY - 2019/6/13

Y1 - 2019/6/13

N2 - In this paper, we introduce a new graph dataset based onthe representation of RNA. The RNA dataset includes 3178 RNA chainswhich are labelled in 8 classes according to their reported biological functions.The goal of this database is to provide a platform for investigatingthe classication of RNA using graph-based methods. The molecules arerepresented by graphs representing the sequence and base-pairs of theRNA, with a number of labelling schemes using base labels and localshape. We report the results of a number of state-of-the-art graph basedmethods on this dataset as a baseline comparison and investigate howthese methods can be used to categorise RNA molecules on their type andfunctions. The methods applied are Weisfeiler Lehman and optimal assignmentkernels, shortest paths kernel and the all paths and cycle methods.We also compare to the standard Needleman-Wunsch algorithm usedin bioinformatics for DNA and RNA comparison, and demonstrate thesuperiority of graph kernels even on a string representation. The highestclassication rate is obtained by the WL-OA algorithm using base labelsand base-pair connections.

AB - In this paper, we introduce a new graph dataset based onthe representation of RNA. The RNA dataset includes 3178 RNA chainswhich are labelled in 8 classes according to their reported biological functions.The goal of this database is to provide a platform for investigatingthe classication of RNA using graph-based methods. The molecules arerepresented by graphs representing the sequence and base-pairs of theRNA, with a number of labelling schemes using base labels and localshape. We report the results of a number of state-of-the-art graph basedmethods on this dataset as a baseline comparison and investigate howthese methods can be used to categorise RNA molecules on their type andfunctions. The methods applied are Weisfeiler Lehman and optimal assignmentkernels, shortest paths kernel and the all paths and cycle methods.We also compare to the standard Needleman-Wunsch algorithm usedin bioinformatics for DNA and RNA comparison, and demonstrate thesuperiority of graph kernels even on a string representation. The highestclassication rate is obtained by the WL-OA algorithm using base labelsand base-pair connections.

M3 - Chapter

SP - 78

EP - 87

BT - Graph-Based Representations in Pattern Recognition - 12th IAPR-TC-15 International Workshop, GbRPR 2019, Tours, France, June 19-21, 2019, Proceedings

PB - Springer

ER -