Effects of replacing the unreliable cDNA microarray measurements on the disease classification based on gene expression profiles and functional modules.

Effects of replacing the unreliable cDNA microarray measurements on the disease classification based on gene expression profiles and functional modules. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Effects of replacing the unreliable cDNA microarray measurements on the disease classification based on gene expression profiles and functional modules. Abstract Text:

Dong Wang,Yingli Lv,Zheng Guo,Xia Li,Yanhui Li,Jing Zhu,Da Yang,Jianzhen Xu,Chenguang Wang,Shaoqi Rao,Baofeng Yang,

MOTIVATION: Microarrays datasets frequently contain a large number of missing values (MVs), which need to be estimated and replaced for subsequent data mining. The focus of the paper is to study the effects of different MV treatments for cDNA microarray data on disease classification analysis. RESULTS: By analyzing five datasets, we demonstrate that among three kinds of classifiers evaluated in this study, support vector machine (SVM) classifiers are robust to varied MV imputation methods [e.g. replacing MVs by zero, K nearest-neighbor (KNN) imputation algorithm, local least square imputation and Bayesian principal component analysis], while the classification and regression tree classifiers are sensitive in terms of classification accuracy. The KNNclassifiers built on differentially expressed genes (DEGs) are robust to the varied MV treatments, but the performances of the KNN classifiers based on all measured genes can be significantly deteriorated when imputing MVs for genes with larger missing rate (MR) (e.g. MR > 5%). Generally, while replacing MVs by zero performs relatively poor, the other imputation algorithms have little difference in affecting classification performances of the SVM or KNN classifiers. We further demonstrate the power and feasibility of our recently proposed functional expression profile (FEP) approach as means to handle microarray data with MVs. The FEPs, which are derived from the functional modules that are enriched with sets of DEGs and thus can be consistently identified under varied MV treatments, achieve precise disease classification with better biological interpretation. We conclude that the choice of MV treatments should be determined in context of the later approaches used for disease classification. The suggested exclusion criterion of ignoring the genes with larger MR (e.g. >5%), while justifiable for some classifiers such as KNN classifiers, might not be considered as a general rule for all classifiers.

Effects of replacing the unreliable cDNA microarray measurements on the disease classification based on gene expression profiles and functional modules. Publishing Authors By Initials

D Wang,Y Lv,Z Guo,X Li,Y Li,J Zhu,D Yang,J Xu,C Wang,S Rao,B Yang,

For similar biological factors: biological markers: tumor markers, biological research abstracts see: biological factors: biological markers: tumor markers, biological research

PUBMED ID PMID:

MEDLINE DATE:

Effects of replacing the unreliable cDNA microarray measurements on the disease classification based on gene expression profiles and functional modules. Journal Published:

PUBLICATION TYPE: Research Support, Non-U.S. Gov

Journal: Bioinformatics (Oxford, England)

VOLUME: 22

Page Numbers: 2883-9

Journal Abbreviation: Bioinformatics

ISSN: 1460-2059

DAY: 29

MONTH: 06

YEAR: 2006

Effects of replacing the unreliable cDNA microarray measurements on the disease classification based on gene expression profiles and functional modules. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 9808944

Effects of replacing the unreliable cDNA microarray measurements on the disease classification based on gene expression profiles and functional modules. Keywords Mesh Terms:

KEYWORDS: Tumor Markers, Biological

MESH TERMS: genetics

Chemical & Substance for Abstract: Effects of replacing the unreliable cDNA microarray measurements on the disease classification based on gene expression profiles and functional modules. Information

Substance Name: Tumor Markers, Biological

Registry Number: 0

Grant and Affiliation Information for Effects of replacing the unreliable cDNA microarray measurements on the disease classification based on gene expression profiles and functional modules.

AFFILIATION: Department of Bioinformatics and Bio-pharmaceutical Key Laboratory of Heilongjiang Province and State, Harbin Medical University Harbin 150086, China.

Country: England

AGENCY: United States NHLBI

GRANT: P50 HL077101-01

ACRONYM: HL

MEDLINETA: Bioinformatics

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Effects of replacing the unreliable cDNA microarray measurements on the disease classification based on gene expression profiles and functional modules Related Publications

• Application of mucin quantitative competitive reverse transcription polymerase chain reaction in assisting the diagnosis of malignant pleural effusion.
• Aquaporin gene delivery to kidney.
• Effects of vitamin E and selenium supplementation on esophageal adenocarcinogenesis in a surgical model with rats.
• Late postoperative complication of the foldable lens implantation: opacification of the intraocular lenses.
• Regulation of the Cool/Pix proteins: key binding partners of the Cdc42/Rac targets, the p21-activated kinases.
• Tissue array technique for p53 expression in human ovarian neoplasms.
• [A case of cerebral schistosomiasis misdiagnosed as brain tumor]
• [Chromosome t (8; 21) and t (15; 17) in a patient with acute myeloid leukemia]
• [Construction of a subtracted cDNA library of differentially expressed genes in human normal liver tissue and primary hepatocellular carcinoma tissue]
• [Control genes of chondrocyte apoptosis in osteoarthritic articular cartilage]
• [Effects of cactus, alove veral, momorcica charantia on reducing the blood glucose of diabetic mice]
• [Force-dependent effects of interleukin-8 gene expression in endothelial cells exposed on fluid shear stress]
• [Human cytomegalovirus inhibits the proliferation of CFU-MK in vitro]
• [Immunorelated pancytopenia]
• [Intro-extro cranial approach treat serious post fronto-orbital fracture deformities]
• [Oxaliplatin in combination with LV5FU2 for advanced/metastatic gastric cancer-a multicenter study]
• [Patients of severe acute respiratory syndrome with hypoxemia treated by anisodamine]
• [Polylactic acid combined with recombinant human bone morphogenetic protein and basic fibroblast growth factor to repair the mandibular defects in rabbits]
• [Protection on proliferation of intestinal epithelial cells against hypoxia-reoxygenation through recombinant heat shock protein 70 adenovirus transfection]
• [Relationship between the changes of beta2-microglobulin in blood and urine and kidney involvements in children with pneumonia]
• [Research progress on the signal transduction and the molecular regulation of oocyte meiotic maturation]
• [Schistosomiasis investigation at 4 villages of Yangjiayuan during a flood in 1999]
• [Second-line Hycamtin in the treatment of lung cancer]
• [Sequential intensified immunosuppressive therapy combining with hematopoietic growth factors in the treatment of severe aplastic anemia]
• [Seventy degrees lateral decubital intraperiteanal laparoscopic adrenal surgery]
• [Studies on photochemical disinfectant enamelled-ware of toxicity experiments]
• [Study on the transformation from myelodysplastic syndromes into acute leukemias]
• [Surgical management of sacrococcygeal chordomas]
• [The genetic characteristic of HLA-DRB1 locus in the Jiangsu-Zhejiang-Shanghai Han population and a comparison of its frequency distribution with that of other populations]
• [The postburn changes in gastric mucosal blood flow and Na+-K+-ATPase activity and their effects on gastric transmucosal potential difference in severely scalded rats]