TY - JOUR
T1 - Computational analysis of muscular dystrophy sub-types using a novel integrative scheme
AU - Wang, Chen
AU - Ha, Sook
AU - Xuan, Jianhua
AU - Wang, Yue
AU - Hoffman, Eric
N1 - Funding Information:
This research was supported in part by NIH Grants (R01NS29525-13A1, R01NS29525-18A1, CA139246 and CA149147) .
PY - 2012/9/1
Y1 - 2012/9/1
N2 - To construct biologically interpretable gene sets for muscular dystrophy (MD) sub-type classification, we propose a novel computational scheme to integrate protein-protein interaction (PPI) network, functional gene set information, and mRNA profiling data. The workflow of the proposed scheme includes the following three major steps: firstly, we apply an affinity propagation clustering (APC) approach to identify gene sub-networks associated with each MD sub-type, in which a new distance metric is proposed for APC to combine PPI network information and gene-gene co-expression relationship; secondly, we further incorporate functional gene set knowledge, which complements the physical PPI information, into our scheme for biomarker identification; finally, based on the constructed sub-networks and gene set features, we apply multiclass support vector machines (MSVMs) for MD sub-type classification, with which to highlight the biomarkers contributing to sub-type prediction. The experimental results show that our scheme can help identify sub-networks and gene sets that are more relevant to MD than those constructed by other conventional approaches. Moreover, our integrative strategy improves the prediction accuracy substantially, especially for those 'hard-to-classify' sub-types.
AB - To construct biologically interpretable gene sets for muscular dystrophy (MD) sub-type classification, we propose a novel computational scheme to integrate protein-protein interaction (PPI) network, functional gene set information, and mRNA profiling data. The workflow of the proposed scheme includes the following three major steps: firstly, we apply an affinity propagation clustering (APC) approach to identify gene sub-networks associated with each MD sub-type, in which a new distance metric is proposed for APC to combine PPI network information and gene-gene co-expression relationship; secondly, we further incorporate functional gene set knowledge, which complements the physical PPI information, into our scheme for biomarker identification; finally, based on the constructed sub-networks and gene set features, we apply multiclass support vector machines (MSVMs) for MD sub-type classification, with which to highlight the biomarkers contributing to sub-type prediction. The experimental results show that our scheme can help identify sub-networks and gene sets that are more relevant to MD than those constructed by other conventional approaches. Moreover, our integrative strategy improves the prediction accuracy substantially, especially for those 'hard-to-classify' sub-types.
KW - Affinity propagation clustering
KW - Biomarker discovery
KW - Classification
KW - Gene expression
KW - Muscular dystrophy
UR - http://www.scopus.com/inward/record.url?scp=84862784886&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84862784886&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2011.08.037
DO - 10.1016/j.neucom.2011.08.037
M3 - Article
AN - SCOPUS:84862784886
SN - 0925-2312
VL - 92
SP - 9
EP - 17
JO - Neurocomputing
JF - Neurocomputing
ER -