We propose an approach to predicting implicit gene-disease associations based on the inference
network, whereby genes and diseases are represented as nodes and are connected via two types
of intermediate nodes: gene functions and phenotypes. To estimate the probabilities involved in
the model, two learning schemes are compared; one baseline using co-annotations of keywords
and the other taking advantage of free text. Additionally, we explore the use of domain ontologies
to complement data sparseness and examine the impact of full text documents. The validity
of the proposed framework is demonstrated on the benchmark data set created from real-world
data.
%0 Journal Article
%1 gene-disease-Seki2007
%A SEKI, KAZUHIRO
%A MOSTAFA, JAVED
%D 2007
%J Pacific Symposium on Biocomputing
%K CAT CAT-REL-COOR CAT-REL-STAT-RANK CAT-REL-SWANSON disease gene inference network
%P 316-327
%T DISCOVERING IMPLICIT ASSOCIATIONS BETWEEN
GENES AND HEREDITARY DISEASES
%U http://psb.stanford.edu/psb-online/proceedings/psb07/seki.pdf
%V 12
%X We propose an approach to predicting implicit gene-disease associations based on the inference
network, whereby genes and diseases are represented as nodes and are connected via two types
of intermediate nodes: gene functions and phenotypes. To estimate the probabilities involved in
the model, two learning schemes are compared; one baseline using co-annotations of keywords
and the other taking advantage of free text. Additionally, we explore the use of domain ontologies
to complement data sparseness and examine the impact of full text documents. The validity
of the proposed framework is demonstrated on the benchmark data set created from real-world
data.
@article{gene-disease-Seki2007,
abstract = {We propose an approach to predicting implicit gene-disease associations based on the inference
network, whereby genes and diseases are represented as nodes and are connected via two types
of intermediate nodes: gene functions and phenotypes. To estimate the probabilities involved in
the model, two learning schemes are compared; one baseline using co-annotations of keywords
and the other taking advantage of free text. Additionally, we explore the use of domain ontologies
to complement data sparseness and examine the impact of full text documents. The validity
of the proposed framework is demonstrated on the benchmark data set created from real-world
data.},
added-at = {2009-03-05T05:36:07.000+0100},
author = {SEKI, KAZUHIRO and MOSTAFA, JAVED},
biburl = {https://www.bibsonomy.org/bibtex/264c4ce2e12d8bb29e413162658ee86b4/huiyangsfsu},
interhash = {558c5e871a2a82ce01c34cf3985108a7},
intrahash = {64c4ce2e12d8bb29e413162658ee86b4},
journal = {Pacific Symposium on Biocomputing},
keywords = {CAT CAT-REL-COOR CAT-REL-STAT-RANK CAT-REL-SWANSON disease gene inference network},
pages = {316-327},
timestamp = {2010-11-12T05:03:07.000+0100},
title = {DISCOVERING IMPLICIT ASSOCIATIONS BETWEEN
GENES AND HEREDITARY DISEASES},
url = {http://psb.stanford.edu/psb-online/proceedings/psb07/seki.pdf},
volume = 12,
year = 2007
}