Jung Hsien Chiang

Dysregulated gene expression networks in human acute myelogenous leukemia stem cells

We performed the first genome-wide expression analysis directly comparing the expression profile of highly enriched normal human hematopoietic stem cells (HSC) and leukemic stem cells (LSC) from patients with acute myeloid leukemia (AML). Comparing the expression signature of normal HSC to that of LSC, we identified 3,005 differentially expressed genes. Using 2 independent analyses, we identified multiple pathways that are aberrantly regulated in leukemic stem cells compared with normal HSC. Several pathways, including Wnt signaling, MAP Kinase signaling, and Adherens Junction, are well known for their role in cancer development and stem cell biology. Other pathways have not been previously implicated in the regulation of cancer stem cell functions, including Ribosome and T Cell Receptor Signaling pathway. This study demonstrates that combining global gene expression analysis with detailed annotated pathway resources applied to highly enriched normal and malignant stem cell populations, can yield an understanding of the critical pathways regulating cancer stem cells.

Support vector learning mechanism for fuzzy rule-based modeling: a new approach

This paper describes a fuzzy modeling framework based on support vector machine, a rule-based framework that explicitly characterizes the representation in fuzzy inference procedure. The support vector learning mechanism provides an architecture to extract support vectors for generating fuzzy IF-THEN rules from the training data set, and a method to describe the fuzzy system in terms of kernel functions. Thus, it has the inherent advantage that the model does not have to determine the number of rules in advance, and the overall fuzzy inference system can be represented as series expansion of fuzzy basis functions. The performance of the proposed approach is compared to other fuzzy rule-based modeling methods using four data sets.

A new kernel-based fuzzy clustering approach: support vector clustering with cell growing

In this paper, the support vector clustering is extended to an adaptive cell growing model which maps data points to a high dimensional feature space through a desired kernel function. This generalized model is called multiple spheres support vector clustering, which essentially identifies dense regions in the original space by finding their corresponding spheres with minimal radius in the feature space. A multisphere clustering algorithm based on adaptive cluster cell growing method is developed, whereby it is possible to obtain the grade of memberships, as well as cluster prototypes in partition. The effectiveness of the proposed algorithm is demonstrated for the problem of arbitrary cluster shapes and for prototype identification in an actual application to a handwritten digit data set.

MeKE: discovering the functions of gene products from biomedical literature via sentence alignment

MOTIVATION Research on roles of gene products in cells is accumulating and changing rapidly, but most of the results are still reported in text form and are not directly accessible by computers. To expedite the progress of functional bioinformatics, it is, therefore, important to efficiently process large amounts of biomedical literature and transform the knowledge extracted into a structured format usable by biologists and medical researchers. Our aim was to develop an intelligent text-mining system that will extract from biomedical documents knowledge about the functions of gene products and thus facilitate computing with function. RESULTS We have developed an ontology-based text-mining system to efficiently extract from biomedical literature knowledge about the functions of gene products. We also propose methods of sentence alignment and sentence classification to discover the functions of gene products discussed in digital texts. AVAILABILITY http://ismp.csie.ncku.edu.tw/~yuhc/meke/

Choquet fuzzy integral-based hierarchical networks for decision analysis

A Choquet fuzzy integral-based approach to hierarchical network implementation is investigated. In this approach, we generalized the fuzzy integral as an excellent component for decision analysis. The generalization involves replacing the max (or min) operator in information aggregation with a fuzzy integral-based neuron, resulting in increased flexibility. The characteristics of the Choquet fuzzy integral are studied and a network-based decision-analysis framework is proposed. The trainable hierarchical network can be implemented utilizing the fuzzy integral-based neurons and connectives. The training algorithms are derived and several examples given to illustrate the behaviors of the networks. Also, we present a decision making experiment using the proposed network to learn appropriate functional relationships in the defective numeric fields detection domain.

Hierarchically SVM classification based on support vector clustering method and its application to document categorization

Automatic categorization of documents into pre-defined topic hierarchies or taxonomies is a crucial step in knowledge and content management. Standard machine learning techniques like support vector machines and related large margin methods have been successfully applied for this task, albeit the fact is that they ignore the inter-class relationships. Unfortunately, in the context of document categorization, we face a large number of classes and a huge number of relevant features needed to distinguish between them. The computational cost of training a classifier for a problem of this size is prohibitive. It has also been observed that obtaining a classifier that discriminates between two groups of classes is much easier than distinguishing simultaneously among all classes. This has prompted substantial research in using hierarchical classifiers to address single multi-class problems. In this paper, we propose a novel hierarchical classification method that generalizes support vector machine learning that is based on the results of support vector clustering method, and are structured in a way that mirrors the class hierarchy. Compared to previous non-hierarchical SVM classifier and famous documents categorization systems, the proposed hierarchical SVM classification has a better improvement in classification accuracy in the standard Reuters corpus.

A role for the nucleoporin Nup170p in chromatin structure and gene silencing

Embedded in the nuclear envelope, nuclear pore complexes (NPCs) not only regulate nuclear transport but also interface with transcriptionally active euchromatin, largely silenced heterochromatin, as well as the boundaries between these regions. It is unclear what functional role NPCs play in establishing or maintaining these distinct chromatin domains. We report that the yeast NPC protein Nup170p interacts with regions of the genome that contain ribosomal protein and subtelomeric genes, where it functions in nucleosome positioning and as a repressor of transcription. We show that the role of Nup170p in subtelomeric gene silencing is linked to its association with the RSC chromatin-remodeling complex and the silencing factor Sir4p, and that the binding of Nup170p and Sir4p to subtelomeric chromatin is cooperative and necessary for the association of telomeres with the nuclear envelope. Our results establish the NPC as an active participant in silencing and the formation of peripheral heterochromatin.

Role of the Histone Variant H2A.Z/Htz1p in TBP Recruitment, Chromatin Dynamics, and Regulated Expression of Oleate-Responsive Genes

ABSTRACT The histone variant H2A.Z (Htz1p) has been implicated in transcriptional regulation in numerous organisms, including Saccharomyces cerevisiae. Genome-wide transcriptome profiling and chromatin immunoprecipitation studies identified a role for Htz1p in the rapid and robust activation of many oleate-responsive genes encoding peroxisomal proteins, in particular POT1, POX1, FOX2, and CTA1. The Swr1p-, Gcn5p-, and Chz1p-dependent association of Htz1p with these promoters in their repressed states appears to establish an epigenetic marker for the rapid and strong expression of these highly inducible promoters. Isw2p also plays a role in establishing the nucleosome state of these promoters and associates stably in the absence of Htz1p. An analysis of the nucleosome dynamics and Htz1p association with these promoters suggests a complex mechanism in which Htz1p-containing nucleosomes at fatty acid-responsive promoters are disassembled upon initial exposure to oleic acid leading to the loss of Htz1p from the promoter. These nucleosomes reassemble at later stages of gene expression. While these new nucleosomes do not incorporate Htz1p, the initial presence of Htz1p appears to mark the promoter for sustained gene expression and the recruitment of TATA-binding protein.

Fuzzy Regression Analysis by Support Vector Learning Approach

Support vector machines (SVMs) have been very successful in pattern classification and function approximation problems for crisp data. In this paper, we incorporate the concept of fuzzy set theory into the support vector regression machine. The parameters to be estimated in the SVM regression, such as the components within the weight vector and the bias term, are set to be the fuzzy numbers. This integration preserves the benefits of SVM regression model and fuzzy regression model and has been attempted to treat fuzzy nonlinear regression analysis. In contrast to previous fuzzy nonlinear regression models, the proposed algorithm is a model-free method in the sense that we do not have to assume the underlying model function. By using different kernel functions, we can construct different learning machines with arbitrary types of nonlinear regression functions. Moreover, the proposed method can achieve automatic accuracy control in the fuzzy regression analysis task. The upper bound on number of errors is controlled by the user-predefined parameters. Experimental results are then presented that indicate the performance of the proposed approach.

GIS: a biomedical text-mining system for gene information discovery

UNLABELLED We present a biomedical text-mining system focused on four types of gene-related information: biological functions, associated diseases, related genes and gene-gene relations. The aim of this system is to provide researchers an easy-to-use bio-information service that will rapidly survey the rapidly burgeoning biomedical literature. AVAILABILITY http://iir.csie.ncku.edu.tw/~yuhc/gis/