Sangjo Han
Research Subjects
Research Interests
Sangjo Han has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Jin-Young Jang
Department of Surgery and Cancer Research Institute, Seoul National University College of Medicine, Seoul, Republic of Korea
3 shared publications - Seungyeoun Lee
Department of Mathematics and Statistics, Sejong University, Seoul 05006, Korea
3 shared publications - Taesung Park
Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, Republic of Korea
3 shared publications - Mee Joo Kang
Division of Cancer Registration and Surveillance, National Cancer Control Institute, National Cancer Center, Goyang, Republic of Korea
2 shared publications - Sun-Whe Kim
Seoul National University College of Medicine
2 shared publications - Yongkang Kim
Department of Statistics, Seoul National University, Seoul, Republic of Korea
2 shared publications
Latest Publications
- 1 January 2016
- Published by Inderscience Publishers in International Journal of Data Mining and Bioinformatics
- Vol. 16 (1) , 64
Comparative studies for developing protein based cancer prediction model to maximise the ROC-AUC with various variable selection methods
The era of protein data analysis is coming with more accurate quantification experiments such as the multiple reaction monitoring (MRM). Protein is easier to obtain than the other genetic variants or gene expression data, which makes it more suitable for early diagnosis of cancer. Each patient has unique patterns of protein data, which makes it imperative for the researcher to select the effective markers to construct a consistent model to predict the patients. This research focuses on finding the most effective variable selection method to be applied in the early diagnosis of the pancreatic cancer. In the process, we compare classical selection methods (stepwise selection based on AIC, BIC), machine learning based selection method (support vector machine recursive feature selection; SVM-REF), and stepwise selection method using the area under the receiver operating characteristic curve (Step-AUC). Based on the simulation and real data analysis, we suggest a Step-AUC method to maximise the prediction performance of the early diagnosis by protein data.
- 1 January 2016
- Published by Inderscience Publishers in International Journal of Data Mining and Bioinformatics
- Vol. 16 (1) , 64
Comparative studies for developing protein based cancer prediction model to maximise the ROC-AUC with various variable selection methods
The era of protein data analysis is coming with more accurate quantification experiments such as the multiple reaction monitoring (MRM). Protein is easier to obtain than the other genetic variants or gene expression data, which makes it more suitable for early diagnosis of cancer. Each patient has unique patterns of protein data, which makes it imperative for the researcher to select the effective markers to construct a consistent model to predict the patients. This research focuses on finding the most effective variable selection method to be applied in the early diagnosis of the pancreatic cancer. In the process, we compare classical selection methods (stepwise selection based on AIC, BIC), machine learning based selection method (support vector machine recursive feature selection; SVM-REF), and stepwise selection method using the area under the receiver operating characteristic curve (Step-AUC). Based on the simulation and real data analysis, we suggest a Step-AUC method to maximise the prediction performance of the early diagnosis by protein data.
- Open Access
- 17 August 2015
- Published by Springer Nature in BMC Genomics
- Vol. 16 (S9) , S4
Integrative analysis of multi-omics data for identifying multi-markers for diagnosing pancreatic cancer
MicroRNA (miRNA) expression plays an influential role in cancer classification and malignancy, and miRNAs are feasible as alternative diagnostic markers for pancreatic cancer, a highly aggressive neoplasm with silent early symptoms, high metastatic potential, and resistance to conventional therapies. In this study, we evaluated the benefits of multi-omics data analysis by integrating miRNA and mRNA expression data in pancreatic cancer. Using support vector machine (SVM) modelling and leave-one-out cross validation (LOOCV), we evaluated the diagnostic performance of single- or multi-markers based on miRNA and mRNA expression profiles from 104 PDAC tissues and 17 benign pancreatic tissues. For selecting even more reliable and robust markers, we performed validation by independent datasets from the Gene Expression Omnibus (GEO) and the Cancer Genome Atlas (TCGA) data depositories. For validation, miRNA activity was estimated by miRNA-target gene interaction and mRNA expression datasets in pancreatic cancer. Using a comprehensive identification approach, we successfully identified 705 multi-markers having powerful diagnostic performance for PDAC. In addition, these marker candidates annotated with cancer pathways using gene ontology analysis. Our prediction models have strong potential for the diagnosis of pancreatic cancer.
- 17 August 2015
- Published by Springer Nature in BMC Genomics
- Vol. 16 (S9) , S4
Open AccessIntegrative analysis of multi-omics data for identifying multi-markers for diagnosing pancreatic cancer
MicroRNA (miRNA) expression plays an influential role in cancer classification and malignancy, and miRNAs are feasible as alternative diagnostic markers for pancreatic cancer, a highly aggressive neoplasm with silent early symptoms, high metastatic potential, and resistance to conventional therapies. In this study, we evaluated the benefits of multi-omics data analysis by integrating miRNA and mRNA expression data in pancreatic cancer. Using support vector machine (SVM) modelling and leave-one-out cross validation (LOOCV), we evaluated the diagnostic performance of single- or multi-markers based on miRNA and mRNA expression profiles from 104 PDAC tissues and 17 benign pancreatic tissues. For selecting even more reliable and robust markers, we performed validation by independent datasets from the Gene Expression Omnibus (GEO) and the Cancer Genome Atlas (TCGA) data depositories. For validation, miRNA activity was estimated by miRNA-target gene interaction and mRNA expression datasets in pancreatic cancer. Using a comprehensive identification approach, we successfully identified 705 multi-markers having powerful diagnostic performance for PDAC. In addition, these marker candidates annotated with cancer pathways using gene ontology analysis. Our prediction models have strong potential for the diagnosis of pancreatic cancer.
- Open Access
- 11 December 2014
- Published by Springer Nature in BioMedical Engineering OnLine
- Vol. 13 (S2) , S5
Identifying molecular subtypes related to clinicopathologic factors in pancreatic cancer
Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal tumors and usually presented with locally advanced and distant metastasis disease, which prevent curative resection or treatments. In this regard, we considered identifying molecular subtypes associated with clinicopathological factor as prognosis factors to stratify PDAC for appropriate treatment of patients. In this study, we identified three molecular subtypes which were significant on survival time and metastasis. We also identified significant genes and enriched pathways represented for each molecular subtype. Considering R0 resection patients included in each subtype, metastasis and survival times are significantly associated with subtype 1 and subtype 2. We observed three PDAC molecular subtypes and demonstrated that those subtypes were significantly related with metastasis and survival time. The study may have utility in stratifying patients for cancer treatment.
- 11 December 2014
- Published by Springer Nature in BioMedical Engineering OnLine
- Vol. 13 (S2) , S5
Open AccessIdentifying molecular subtypes related to clinicopathologic factors in pancreatic cancer
Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal tumors and usually presented with locally advanced and distant metastasis disease, which prevent curative resection or treatments. In this regard, we considered identifying molecular subtypes associated with clinicopathological factor as prognosis factors to stratify PDAC for appropriate treatment of patients. In this study, we identified three molecular subtypes which were significant on survival time and metastasis. We also identified significant genes and enriched pathways represented for each molecular subtype. Considering R0 resection patients included in each subtype, metastasis and survival times are significantly associated with subtype 1 and subtype 2. We observed three PDAC molecular subtypes and demonstrated that those subtypes were significantly related with metastasis and survival time. The study may have utility in stratifying patients for cancer treatment.