biocloud:ccpe:13 (Article)
|
Author(s) | Concetto Spampinato, Isaak Kavasidis, Marco Aldinucci, Carmelo Pino, Daniela Giordano and Alberto Faro |
Title | « Discovering Biological Knowledge by Integrating High Throughput Data and Scientific Literature on the Cloud » |
Journal | Concurrency and Computation: Practice and Experience |
Volume | 26 |
Number | 10 |
Page(s) | 1771-1786 |
Year | 2014 |
URL | http://dx.doi.org/10.1002/cpe.3130 |
Abstract & Keywords |
In this paper, we present a bioinformatics knowledge discovery tool for extracting and validating associations between biological entities. By mining specialised scientific literature, the tool not only generates biological hypotheses in the form of associations between genes, proteins, miRNA and diseases, but also validates the plausibility of such associations against high-throughput biological data (e.g. microarray) and annotated databases (e.g. Gene Ontology). Both the knowledge discovery system and its validation are carried out by exploiting the advantages and the potentialities of the Cloud, which allowed us to derive and check the validity of thousands of biological associations in a reasonable amount of time. The system was tested on a dataset containing more than 1000 gene-disease associations achieving an average recall of about 71%, outperforming existing approaches. The results also showed that porting a data-intensive application in an IaaS cloud environment boosts significantly the application's efficiency.
Keywords: cloud
|
@article{biocloud:ccpe:13,
volume = {26},
number = {10},
author = {Concetto Spampinato and Isaak Kavasidis and Marco Aldinucci and
Carmelo Pino and Daniela Giordano and Alberto Faro},
keywords = {cloud},
url = {http://dx.doi.org/10.1002/cpe.3130},
abstract = {In this paper, we present a bioinformatics knowledge discovery
tool for extracting and validating associations between biological
entities. By mining specialised scientific literature, the tool
not only generates biological hypotheses in the form of
associations between genes, proteins, miRNA and diseases, but also
validates the plausibility of such associations against
high-throughput biological data (e.g. microarray) and annotated
databases (e.g. Gene Ontology). Both the knowledge discovery
system and its validation are carried out by exploiting the
advantages and the potentialities of the Cloud, which allowed us
to derive and check the validity of thousands of biological
associations in a reasonable amount of time. The system was tested
on a dataset containing more than 1000 gene-disease associations
achieving an average recall of about 71\%, outperforming existing
approaches. The results also showed that porting a data-intensive
application in an IaaS cloud environment boosts significantly the
application's efficiency.},
title = {Discovering Biological Knowledge by Integrating High Throughput Data
and Scientific Literature on the Cloud},
journal = {Concurrency and Computation: Practice and Experience},
pages = {1771-1786},
year = {2014},
}
This document was generated by bib2html 3.3.
(Modified by Luca Paolini, under the GNU General Public License)