检索结果-内蒙古大学图书馆

IEEE International Conference on bioinformatics and Biomedicine (BIBM)

作者： Taewan Goo Chanhee Lee Sangyeon Shin Haeyoung Kim Taesung Park Interdisciplinary Program in Bioinformatics Seoul National University Seoul Republic of Korea Department of Statistics Seoul National University Seoul Republic of Korea

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

In precision medicine, deep learning models play an important role in identifying relevant biomarkers and making predictions for the early diagnosis and prognosis of diseases. While successful in developing accurate prediction models for prognosis and diagnosis, the ‘black box’ nature of deep learning poses significant challenges, which makes it difficult to have a meaningful biological interpretation. Recently, several biologically informed neural networks (BINNs), such as the Visible Neural Network and P-NET, have been proposed to incorporate biological knowledge for improved interpretation. These models assess node importance using quantitative measures such as SHAP and DeepLIFT. However, these approaches have limitations because they typically provide a single estimate of node importance without any information on the uncertainty of these estimates. This study aims to assess uncertainty of node importance through a novel statistical framework. Bootstrapping is used to calculate confidence interval of node importance. Our findings validate that the proposed statistical framework quantifies the uncertainty of nodes in BINNs. By providing robust confidence intervals of pathways and genes, this framework enhances the interpretability and reliability of BINNs.

关键词： Deep learning Uncertainty Biological system modeling Precision medicine Predictive models Metastasis Reliability Prognostics and health management Prostate cancer Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis for doubly repeated omics data from crossover design

Analysis for doubly repeated omics data from crossover desig...

引用

2016 IEEE International Conference on bioinformatics and Biomedicine, BIBM 2016

作者： Choi, Sunghoon Park, Soo-Yeon Kim, Hoejin Kwon, Oran Park, Taesung Department of Statistics Seoul National University Daehak-Dong Seoul Gwanak-gu Korea Republic of Department of Nutritional Science and Food Management Ewha Woman's University Daehyeon-dong Seodaemun-gu Seoul Korea Republic of Interdisciplinary Program in Bioinformatics Seoul National University Daehak-Dong Gwanak-gu Seoul Korea Republic of

ISBN: (纸本)9781509016105

Some crossover clinical trials produce doubly repeated omics data with two repeated factors. Linear mixed effect models (LMMs) are commonly applied to the data from the crossover design focusing on the analysis of repeatedly observed omics data themselves. Alternatively, the univariate analyses using the single summary measurements such as differences between time points and incremental area under curve (iAUC) are also widely used. In this study, we compare the performance of both methods for real doubly repeated omics data from a crossover study. © 2016 IEEE.

关键词： Crossover design Linear mixed effect model Repeated measurements

来源：评论

学校读者我要写书评

暂无评论

Identification of hyperparameters with high effects on performance of deep neural networks: application to clinicopathological data of ovarian cancer

Identification of hyperparameters with high effects on perfo...

引用

IEEE International Conference on bioinformatics and Biomedicine

作者： Suhyun Hwangbo Yong-Sang Song Se Ik Kim Taesung Park Untack Cho Interdisciplinary Program in Bioinformatics Seoul National University Department of Obstetrics and Gynecology Seoul National University College of Medicine Department of Statistics Seoul National University Interdisciplinary Program in Cancer Biology Seoul National University College of Medicine

ISBN: (纸本)9781728118680

Recent advances in deep learning have emerged as an effective approach for precision medicine. The applications of deep learning to medicine have been applied mainly to medical image data but not clinicopathological data. One of challenges of deep learning model to clinicopathological data is to optimize hyperparameters to get high predictive power. In this study, we identified hyperparameters of deep learning model that have large effects on power. Specifically, we focused on predicting platinum-based chemotherapy response for ovarian cancer patients. As a performance metric, we used the area under the curve. We optimized six hyperparameters: the number of hidden layers, number of hidden units, optimization algorithm, weight initialization, activation function, and dropout rate. We also identified significant interaction effects between hyperparameters. We successfully found the combination of hyperparameters having large effects on prediction. These optimal combinations are expected to increase the prediction accuracy for the response to chemotherapy for a variety of cancer patients.

关键词： deep neural network hyperparameter predictive power Hyperparameter Ovary Cancer Area Under Curve image data interaction effect Performance metrics Machine Learning network applications Drug Therapy weight initialization Neural network

来源：评论

学校读者我要写书评

暂无评论

FISH: Finding of identical spectra set for Homogenous peptide using two-stage clustering algorithm

FISH: Finding of identical spectra set for Homogenous peptid...

引用

IEEE International Conference on bioinformatics and Biomedicine Workshops (BIBMW)

作者： Seungmook Lee Min-Seok Kwon Hyoung-Joo Lee Young-Ki Paik Jae K. Lee Taesung Park Department of Statistics and Interdisciplinary program in Bioinformatics Seoul National University South Korea Interdisciplinary program in Bioinformatics Seoul National University South Korea Department of Biochemistry Yonsei Proteome Research Center and Biomedical Proteome Research Center Yonsei University South Korea Department of Public Health Sciences Division of Biostatistics University of Virginia School of Medicine USA

MS/MS experiments generate hundreds to tens of thousands of fragment ion spectra during the experiment. In the peptide identification, MS/MS spectra are often identified by database searching algorithms such as SEQUEST and Mascot. Most database searching algorithms calculate score functions to compare the experimental MS/MS spectra with theoretical MS/MS spectra of certain peptides derived from protein sequence databases. However, these indirect methods are vulnerable to potential errors. Thus, some spectra may not be assigned to peptides. To overcome these limitations, we propose a novel algorithm called Finding Identical Spectra for Homogenous peptide (FISH) by using two-stage clustering algorithm. Our proposed FISH algorithm can cluster spectra from the same peptide as a group based on the direct comparison. That is, through all possible pair-wise comparisons, our FISH method provides a set of spectra from the same peptide. To investigate the efficiency of our proposed method, we performed Nano-LC-MS/MS experiment for human tissue samples. Also, we conducted the simulation study to compare the performance of our proposed method with other database searching methods. Our simulation study showed that FISH yielded higher sensitivity than the other methods.

关键词： Peptides Databases Marine animals Proteomics Ions Proteins Correlation

来源：评论

学校读者我要写书评

暂无评论

Comparing family-based rare variant association tests for dichotomous phenotypes

引用

BMC proceedings 2016年第SUPPL 7期10卷 181-186页

作者： Longfei Wang Sungkyoung Choi Sungyoung Lee Taesung Park Sungho Won Interdisciplinary Program in bioinformatics Seoul National University Seoul 151-742 Korea. Interdisciplinary Program in bioinformatics Seoul National University Seoul 151-742 Korea Department of Statistics Seoul National University Seoul 151-742 Korea. Department of Public Health Science Seoul National University Seoul 151-742 Korea Institute of Health Environment Seoul National University Seoul 151-742 Korea.

BACKGROUND:It has been repeatedly stressed that family-based samples suffer less from genetic heterogeneity and that association analyses with family-based samples are expected to be powerful for detecting susceptibility loci for rare disease. Various approaches for rare-variant analysis with family-based samples have been proposed. METHODS:In this report, performances of the existing methods were compared with the simulated data set provided as part of Genetic Analysis Workshop 19 (GAW19). We considered the rare variant transmission disequilibrium test (RV-TDT), generalized estimating equations-based kernel association (GEE-KM) test, an extended combined multivariate and collapsing test for pedigree data (known as Pedigree Combined Multivariate and Collapsing [PedCMC]), gene-level kernel and burden association tests with disease status for pedigree data (PedGene), and the family-based rare variant association test (FARVAT). RESULTS:The results show that PedGene and FARVAT are usually the most efficient, and the optimal test statistic provided by FARVAT is robust under different disease models. Furthermore, FARVAT was implemented with C++, which is more computationally faster than other methods. CONCLUSIONS:Considering both statistical and computational efficiency, we conclude that FARVAT is a good choice for rare-variant analysis with extended families.

关键词： Rare Variant Pedigree Data Genetic Analysis Workshop Empirical Size Rare Variant Association

来源：评论

学校读者我要写书评

暂无评论

Two-way interaction analysis of obesity trait from Korean population using generalized MDR

Two-way interaction analysis of obesity trait from Korean po...

引用

IEEE International Conference on bioinformatics and Biomedicine Workshops (BIBMW)

作者： Sungyoung Lee Sohee Oh Min-Seok Kwon Seungyeoun Lee Taesung Park Interdisciplinary Program in Bioinformatics Seoul National University Seoul South Korea Department of Statistics Seoul National University Seoul South Korea Department of Applied Mathematics Sejong University Seoul South Korea

Most common complex traits such as obesity, hypertension, diabetes, and cancers are known to be associated with multiple genes, environmental factors, and epistasis. Recently, the development of advanced genotyping technologies allows us to perform the genome-wide association studies (GWAS). For detecting the effects of multiple genes on complex traits, many approaches have been proposed for GWAS. Multifactor dimensionality reduction (MDR) proposed by Ritchie et al. (2001) is one of the powerful methods for detecting epistasis, which detects high order interactions among genes. However, MDR is computationally intensive due to its requirement of testing all possible n-way combinations. Thus, it is not practically feasible to apply MDR directly to analyzing large-scale GWAS data. We propose an efficient strategy to perform MDR analysis for GWAS data. First, select a subset of genetic factors such as SNPs with some marginal significance. Second, perform MDR analysis only for the selected genetic factors. Third, provide MDR summary results through network graph. Even for the MDR analysis for the selected SNPs, a fast computing system is required. We developed our own GPU based system for the large-scale GWAS data. We applied our strategy to Korean Association REsource (KARE) (8,838 individuals with 101,837 SNPs) for detecting two-way interactions of genetic factors associated with body mass index (BMI). We identified several genes and pathways which have been known to be associated with obesity.

关键词： Obesity bioinformatics Genomics Graphics processing unit Diabetes

来源：评论

学校读者我要写书评

暂无评论

Biomarker development for pancreatic ductal adenocarcinoma using integrated analysis of mRNA and miRNA expression

Biomarker development for pancreatic ductal adenocarcinoma u...

引用

IEEE International Conference on bioinformatics and Biomedicine (BIBM)

作者： Min-Seok Kwon Yongkang Kim Seungyeoun Lee Junghyun Namkung Taegyun Yun Sung Gon Yi Sangjo Han Meejoo Kang Sun Whe Kim Jin-Young Jang Taesung Park Interdisciplinary program in Bioinformatics Seoul National University Seoul Korea Department of Statistics Seoul National University Seoul Korea Department of Mathematics and Statistics Sejong University Seoul Korea Healthcare group SK telecom Bioinformatics Tech. Lab. Seoul Korea Department of Surgery Seoul National University Hospital Seoul Korea

ISBN: (纸本)9781479956708

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.

关键词： Cancer Barium Blood Lungs Predictive models Ontologies Reliability

来源：评论

学校读者我要写书评

暂无评论

Efficient and Fast Analysis for Detecting High Order Gene-by-Gene Interactions in a Genome-Wide Association Study

Efficient and Fast Analysis for Detecting High Order Gene-by...

引用

IEEE International Conference on bioinformatics and Biomedicine (BIBM)

作者： Sohee Oh Jaehoon Lee Min-Seok Kwon Kyunga Kim Taesung Park Department of Statistics Seoul National University Seoul South Korea Interdisciplinary program in Bioinformatics Seoul National University Seoul South Korea Department of Statistics Sookmyung womens University Seoul South Korea Seoul National University Gwanak-gu Seoul KR

Most common complex traits are affected by multiple genes and/or environmental factors. To understand genetic architecture of complex traits, the investigation of gene-gene and gene-environment interactions can be essential. However, conducting gene-gene interaction using genome-wide data requires exploring a huge search space and suffers from a computation burden due to high dimensionality of genetic data. To identify gene-gene interaction more efficiently, we propose a gene-based reduction method which first summarizes the gene effect by combining multiple single nucleotide polymorphism (SNP) and then performs the gene-gene interaction via the summarized gene effect. By reducing the search space from SNPs to gene, our gene-based method becomes efficient and fast for identifying gene-gene interaction in genome wide association studies. The gene-based reduction method is illustrated by hypertension data from a Korean population.

关键词： bioinformatics Genomics Hypertension Barium Diseases Logistics

来源：评论

学校读者我要写书评

暂无评论

Quality Control Plot for High Dimensional Omics Data

Quality Control Plot for High Dimensional Omics Data

引用

IEEE International Conference on bioinformatics and Biomedicine

作者： Gyu-tae Kim Yongkang Kim Min-Seok Kwon Taesung Park Department of Statistics Seoul National University Daehak-Dong Gwanak-gu 08826 Republic of Korea Interdisciplinary Program in Bioinformatics Seoul National University Daehak-Dong Gwanak-gu 08826 Republic of Korea

ISBN: (纸本)9781509016129

Quality control (QC) becomes more important in pre-processing analysis of high dimensional omics data. Several routine QC processes became a standard process in omics data analysis. The standard QC analysis includes calculating quality-related measures, checking the consistency among samples, detecting outlying observations and so forth. QC analysis tends to be more important in the era of high dimensional omics data. Although several QC analysis tools providing simple graphical display have been developed by many researchers, they usually require a subjective decision on QC. Here, we propose high-dimensional data quality control (HidQC) plot which is a simple and efficient QC tool for handling high dimensional omics data. HidQC plot primarily focuses on identifying samples of poor quality by conducting a contrast analysis for the between/within group distances and the summary distances. HidQC plot checks the quality by investigating the consistency of samples for each group. Unlike other QC plots, HidQC plot provides the p-value of each sample based on the permutation test, which can be used as a more objective criterion to determine whether to use the sample or not. We applied HidQC plot to MicroArray Quality Control (MAQC) project 1 data to demonstrate its usefulness.

关键词： High-dimensional data quality control (HidQC) plot Quality Control (QC) Microarray Omics data MicroArray Quality Control(MAQC) project

来源：评论

学校读者我要写书评

暂无评论

Analysis for doubly repeated omics data from crossover design

Analysis for doubly repeated omics data from crossover desig...

引用

IEEE International Conference on bioinformatics and Biomedicine (BIBM)

作者： Sunghoon Choi Soo-yeon Park Hoejin Kim Oran Kwon Taesung Park Department of Statistics Seoul National University Seoul Republic of Korea Department of Nutritional Science and Food Management Ewha Woman's University Seoul Republic of Korea Interdisciplinary Program in Bioinformatics Seoul National University Seoul Republic of Korea

ISBN: (纸本)9781509016129

关键词： Hardware design languages Time measurement Genomics bioinformatics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：