scholarly journals Supervised principal component analysis for gene set enrichment of microarray data with continuous or survival outcomes

2008 ◽  
Vol 24 (21) ◽  
pp. 2474-2481 ◽  
Author(s):  
X. Chen ◽  
L. Wang ◽  
J. D. Smith ◽  
B. Zhang
Keyword(s):  
Principal Component Analysis ◽  
Microarray Data ◽  
Principal Component ◽  
Component Analysis ◽  
Survival Outcomes ◽  
Gene Set Enrichment ◽  
Gene Set

scholarly journals IM-03 IMMUNOLOGICAL SUBTYPES OF GLIOBLASTOMA BASED ON TUMOR INFILTRATING CELLS

2019 ◽  
Vol 1 (Supplement_2) ◽  
pp. ii12-ii12
Author(s):  
Kushihara Yoshihiro ◽  
Syota Tanaka ◽  
Erika Yamasawa ◽  
Tsukasa Koike ◽  
Taijun Hana ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
T Cell ◽  
Tumor Microenvironment ◽  
Nk Cells ◽  
Principal Component ◽  
Component Analysis ◽  
Gene Set ◽  
Significant Difference

Abstract To discover novel biological targets in glioblastoma, genomic and immunological analysis were performed using The Cancer Genome Atlas (TCGA) data set. The RNA-seq data of 156 primary glioblastoma cases were subjected to CIBERSORT to detect tumor infiltrating cell fractions. Principal component analysis was performed on this data to detect factors that strongly contribute to the first principal component, and hierarchical clustering was performed. Survival curves were compared for each of the derived clusters. Finally, Gene Set Enrichment Analysis (GSEA) using HALLMARK Gene Set was performed. In the principal component analysis, we detected seven factors (NK cells resting, T cell regulatory, NK cells activated, Macrophage type 0, T cell gamma delta, Macrophage type 2, Macrophage type 1) which strongly contribute to the first principal component. Based on these seven factors, hierarchical cluster analysis resulted in T cell regulatory (Treg), Macrophage type 0 (M0), Macrophage type 2 (M2) and Macrophage type 1 (M1) clusters. There was no significant difference between these groups in CD8 T cell. M2 and M1 clusters displayed better OS with a significant difference. TNFA signaling via NFκB in Treg group, IFNα response, IFNγ response and ALLOGRAFT response in M2 group, G2M CHECKPOINT, GLYCOLYSIS, WNTβ catenin signaling, MITOTIC SPINDLE and TGFβ signaling in M1 group were upregulated. In conclusion, tumor microenvironment of glioblastoma can be divided into 4 immunological subtypes, Treg, M0, M1, and M2. Because of the contribution of innate immunity for shaping the tumor microenvironment of glioblastoma, immunotherapies targeting these innate immune cells are anticipated.

scholarly journals Accounting for probe-level noise in principal component analysis of microarray data

2005 ◽  
Vol 21 (19) ◽  
pp. 3748-3754 ◽  
Author(s):  
G. Sanguinetti ◽  
M. Milo ◽  
M. Rattray ◽  
N. D. Lawrence
Keyword(s):  
Principal Component Analysis ◽  
Microarray Data ◽  
Principal Component ◽  
Component Analysis

scholarly journals Principal Component Analysis Sebagai Ekstraksi Fitur Data Microarray Untuk Deteksi Kanker Berbasis Linear Discriminant Analysis

2019 ◽  
Vol 3 (2) ◽  
pp. 72
Author(s):  
Widi Astuti ◽  
Adiwijaya Adiwijaya
Keyword(s):  
Principal Component Analysis ◽  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Microarray Data ◽  
Principal Component ◽  
Component Analysis ◽  
High Dimensions ◽  
Linear Discriminant ◽  
Cancer Data ◽  
Colon Cancer Data

Cancer is one of the leading causes of death globally. Early detection of cancer allows better treatment for patients. One method to detect cancer is using microarray data classification. However, microarray data has high dimensions which complicates the classification process. Linear Discriminant Analysis is a classification technique which is easy to implement and has good accuracy. However, Linear Discriminant Analysis has difficulty in handling high dimensional data. Therefore, Principal Component Analysis, a feature extraction technique is used to optimize Linear Discriminant Analysis performance. Based on the results of the study, it was found that usage of Principal Component Analysis increases the accuracy of up to 29.04% and f-1 score by 64.28% for colon cancer data.

scholarly journals A NOVEL DIMENSIONALITY REDUCTION APPROACH TO IMPROVE MICROARRAY DATA CLASSIFICATION

2021 ◽  
Vol 22 (1) ◽  
pp. 1-22
Author(s):  
Mohammed Hamim ◽  
Ismail El Mouden ◽  
Mounir Ouzir ◽  
Hicham Moutachaouik ◽  
Mustapha Hain
Keyword(s):  
Principal Component Analysis ◽  
Microarray Data ◽  
Dimensional Reduction ◽  
Treatment Success ◽  
Principal Component ◽  
Component Analysis ◽  
Prediction Performance ◽  
Machine Learning Algorithms ◽  
Kernel Principal Component Analysis ◽  
Support Vector

Cancer tumor prediction and diagnosis at an early stage has become a necessity in cancer research, as it provides an increase in the treatment success chances. Recently, DNA microarray technology became a powerful tool for cancer identification, that can analyze the expression level of a different and huge number of genes simultaneously. In microarray data, the large genes number versus a few records may affect the prediction performance. In order to handle this "curse of dimensionality” constraint of microarray dataset while improving the cancer identification performance, a dimensional reduction phase is necessary. In this paper, we proposed a framework that combines dimensional reduction methods and machine learning algorithms in order to achieve the best cancer prediction performance using different microarray datasets. In the dimensional reduction phase, a combination of feature selection and feature extraction techniques was proposed. Pearson and Ant Colony Optimization was used to select the most important genes. Principal Component Analysis and Kernel Principal Component Analysis were used to linearly and non-linearly transform the selected genes to a new reduced space. In the cancer identification phase, we proposed four algorithms C5.0, Logistic Regression, Artificial Neural Network, and Support Vector Machine. Experimental results demonstrated that the framework performs effectively and competitively compared to state-of-the-art methods. ABSTRAK: Ramalan tumor kanser dan diagnosis pada peringkat awal telah menjadi keperluan dalam kajian kanser, kerana ia membuka peluang peningkatan kejayaan dalam rawatan. Kebelakangan ini, teknologi mikrotatasusunan DNA menjadi alat berkuasa bagi mengenal pasti kanser, di mana ia mampu menganalisa level ekspresi yang pelbagai dan gen-gen yang banyak secara serentak. Dalam data mikrotatasusunan, gen-gen yang banyak ini bakal menentukan ramalan prestasi berbanding analisa melalui rekod-rekod yang sebilangan. Fasa pengurangan dimensi adalah perlu bagi mengawal kakangan “penentuan kedimensian” dataset mikrotatasusunan, sementara itu ia memantapkan lagi keberkesanan kenal pasti kanser. Kajian ini mencadangkan rangka kombinasi kaedah pengurangan dimensi dan algoritma pembelajaran mesin bagi mencapai prestasi ramalan kanser terbaik dengan menggunakan pelbagai dataset mikrotatasusunan. Dalam fasa pengurangan dimensi, kombinasi pemilihan ciri dan teknik pengekstrakan ciri telah dicadangkan, Pengoptimuman Pearson dan Koloni Semut bagi memilih gen yang paling penting, Analisis Komponen Prinsipal dan Analisis Komponen Prinsipal Kernel, bagi menukar gen terpilih yang linear dan tak linear kepada ruang baru yang dikurangkan. Dalam menentukan fasa mengenal pasti kanser, kajian ini mencadangkan empat algoritma iaitu C5.0, Regresi Logistik, Rangkaian Neural Buatan dan Mesin Vektor Sokongan. Dapatan kajian menunjukkan rangka ini adalah berkesan dan kompetitif berbanding kaedah semasa.

Sign in / Sign up

Export Citation Format

Share Document