Use of LDA combined with PLS for classification of lung cancer gene expression data
Journal Title: International Journal of Medical Research & Health Sciences (IJMRHS) - Year 2016, Vol 5, Issue 9
Abstract
Reliable and precise classification is essential for successful diagnosis and treatment of cancer. Thus, improvements in cancer classification are increasingly sought. Linear discriminant analysis (LDA) is the most effective method of cancer classification in high-dimensional prediction, but there are drawbacks to tumor classification by a formal method such as LDA. We propose a method for lung cancer gene microarray classification that combines a feature reduction approach, partial least squares (PLS), and discriminate method, LDA, for improving classification performance. The real dataset used related to lung cancer gene expression. After bioinformatics data preprocessing, data reduction and feature selection were carried out using PLS and then LDA was used for classification. The results were validated using the accuracy index and gene ontology analysis. Of the total of more than 50,000 genes, 214 genes were shown to have relevance. The classification accuracy of this method was 94.5% and gene ontology analysis results were good. It can be said that the LDA classifier combined with PLS is powerful method. This method can identify gene relationships warranting further biological investigation.
Authors and Affiliations
Keyghobad Ghadiri| Nosocomial Infection Research Center, Kermanshah University of Medical Sciences, Kermanshah, Iran, Mansour Rezaei| Biostatistics and Epidemiology Department, Faculty of Public Health, Kermanshah University of Medical Sciences, Kermanshah, Iran, Seyyed Mohammad Tabatabaei| Medical Informatics Department, Faculty of Paramedical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran, Meisam Shahsavari| Nursing Department, Shahid Beheshti University of Medical Sciences, Tehran, Iran, Soodeh Shahsavari| Health Information Technology Department, Faculty of Paramedical Sciences, Kermanshah University of Medical Sciences, Kermanshah, Iran, Corresponding Author: soodeh_shahsavari@yahoo.com
Keywords
Related Articles
- EP ID EP12026
- DOI -
- Views 337
- Downloads 11
DELTO-PECTORAL FLAPS FOR SECONDARY DEFECTS FOLLOWING EXCISION OF RECURRENT PAROTID TUMORS: CASE SERIES
Background: Extensive infiltration of the skin by parotid gland tumors often lead to the surgeon seeking various options that will lead to good cosmetic appearance and reduced donor site morbidity. Materials and Methods...
EFFECT OF KINSIOTAPING ON LUMBAR CURVATURE AND MUSCULAR FATIGUE IN CHRONIC NONSPECIFIC LOW BACK PAIN PATIENTS
Purpose: Kinesio Taping (KT) is a technique that has been used in the clinical management of people with chronic back pain. This study investigated the efficacy of KT on patient with chronic non-specific low back pain...
DETECTION OF BIOFILM PRODUCTION IN BLOOD CULTURE ISOLATES OF STAPHYLOCOCCI
Background: Biofilm producing bacteria which are inherently resistant to antibiotics and disinfectants are widely associated with implant associated infections. Staphylococcus is the most commonly associated pathogens w...
Relationship between Self-Efficacy and Academic Achievement of Zahedan Medical Sciences Students in 2016
Students with higher self-efficacy utilize higher tendency, endeavor, and strength in performing academic tasks and feel ensure of their ability, thus self-efficacy can influence their academic achievement. Current stud...
INFARCTION IN NORMAL AND INTRAUTERINE GROWTH RETARDATION [IUGR] PLACENTA
Background and Purpose: The purpose of the study is to compare the presence of Infarction in normal placentas and IUGR placentas. Study design and setting: Research study, Department of Anatomy, R.N.T. Medical College,...