Paper Info
Title
Biomarker development for pancreatic ductal adenocarcinoma using integrated analysis of mRNA and miRNA expression
Abstract
Pancreatic ductal adenocarcinoma (PDAC) is the most common type of pancreatic cancer, which has dismal prognosis because of its silent early symptoms, high metastatic potential, and resistance to conventional therapies. Although a PDAC patient who is diagnosed at an early stage would have a substantial increase in chance of survival, the survival rate is poor because there is no efficient non-invasive diagnostic test in the early stage. In this study, we developed an efficient prediction models to detect PDAC in its early stages. Our prediction models use both mRNA and miRNA expression data from 104 PDAC tissues and 17 normal pancreatic tissues using microarray technology. After quality control, we built prediction models based on support vector machine (SVM) from mRNA and miRNA expressions for detecting early PDAC. To prevent over-fitting effect, we conducted leave-one-out cross validation (LOOCV) and 5-fold cross validation (CV). For independent validation of prediction models, we performed evaluation on independent datasets from Gene Expression Omnibus (GEO). After the validation, we identified 28 single markers and 231 combinations of markers with powerful prediction performance. In addition, the marker candidates are annotated with cancer pathways using gene ontology analysis. Our prediction models for PDAC may have potential for early diagnosis of PDAC.
Year
DOI
Venue
2014
10.1109/BIBM.2014.6999167
BIBM
Keywords
Field
DocType
mirna expression,5-fold cross validation,microarray technology,pancreatic tissues,gene ontology analysis,pdac metastatic potential,pdac detection,mirna expression data,pancreatic cancer,loocv,pdac tissues,leave-one-out cross validation,biomedical measurement,noninvasive diagnostic test,pdac prediction model validation,pdac diagnosis,pdac symptoms,svm,pancreatic ductal adenocarcinoma (pdac),mirna integrated analysis,geo,over-fitting effect,cancer,mrna expression,support vector machine,cancer pathways,biomarker development,lab-on-a-chip,pancreatic ductal adenocarcinoma,gene expression omnibus,biological tissues,mrna expression data,bioinformatics,rna,biological organs,prediction model,mrna integrated analysis,pdac theraphy,conventional therapy,patient diagnosis,support vector machines,dismal prognosis,barium,reliability,ontologies,predictive models
Survival rate,Pancreatic cancer,Computer science,microRNA,Biomarker (medicine),Adenocarcinoma,Bioinformatics,Gene chip analysis,Cross-validation,Cancer
Conference
ISSN
Citations 
PageRank 
2156-1125
0
0.34
References 
Authors
2
11
Name
Order
Citations
PageRank
Minseok Kwon133928.71
Yongkang Kim223.83
Seung Yeoun Lee316820.48
Junghyun Namkung4132.69
Taegyun Yun500.34
Sung-Gon Yi613912.28
Sangjo Han701.01
Meejoo Kang800.68
Sun Whe Kim900.34
Jinyoung Jang10295.66
Taesung Park1149064.41