scholarly journals Three-way clustering of multi-tissue multi-individual gene expression data using semi-nonnegative tensor decomposition

2019 ◽  
Vol 13 (2) ◽  
pp. 1103-1127 ◽  
Author(s):  
Miaoyan Wang ◽  
Jonathan Fischer ◽  
Yun S. Song
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Tensor Decomposition ◽  
Expression Data ◽  
Nonnegative Tensor ◽  
Individual Gene ◽  
Nonnegative Tensor Decomposition

scholarly journals Collaborative Cross Founder Expression Analysis (CCFEA)

2021 ◽  
Author(s):  
Richard R Green ◽  
Renee C Ireton ◽  
Martin Ferris ◽  
Kathleen Muenzen ◽  
David R Crosslin ◽  
...  
Keyword(s):  
Gene Expression ◽  
Genetic Variation ◽  
Gene Expression Data ◽  
Viral Infections ◽  
Collaborative Cross ◽  
Visualization Tool ◽  
Expression Data ◽  
Individual Gene ◽  
Rnaseq Data

To understand the role of genetic variation in SARS and Influenza infections we developed CCFEA, a shiny visualization tool using public RNAseq data from the collaborative cross (CC) founder strains (A/J, C57BL/6J, 129s1/SvImJ, NOD/ShILtJ, NZO/HILtJ, CAST/EiJ, PWK/PhJ, and WSB/EiJ). Individual gene expression data is displayed across founders, viral infections and days post infection.

scholarly journals Potential biomarker detection for liver cancer stem cell by machine learning approach

2020 ◽  
Vol 6 (6) ◽  
Author(s):  
Ali Farzane ◽  
Maryam Akbarzadeh ◽  
Reza Ferdousi ◽  
Mohammadreza Rashidi ◽  
Reza Safdari
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Liver Cancer ◽  
Gene Expression Data ◽  
Supervised Machine Learning ◽  
Data Series ◽  
Expression Data ◽  
Gene Set ◽  
Individual Gene ◽  
Potential Biomarker

Objectives: In this study, we aimed to identify putative biomarkers for identification and characterization of these cells in liver cancer. Methods: We employed a supervised machine learning method, XGBoost, to data from 13 GEO data series to classify samples using gene expression data. Results.  Across the 376 samples (129 CSCs and 247 non-CSCs cases), XGBoost displayed high performance in the classification of data. XGBoost feature importance scores and SHAP (Shapley Additive explanation) values were used for the interpretation of results and analysis of individual gene importance. We confirmed that expression levels of a 10-gene set (PTGER3, AURKB, C15orf40, IDI2, OR8D1, NACA2, SERPINB6, L1CAM, SMC1A, and RASGRF1) were predictive. The results showed that these 10 genes can detect CSCs robustly with accuracy, sensitivity, and specificity of 97 %, 100 %, and 95 %, respectively. Conclusions. We suggest that the ten-gene set may be used as a biomarker set for detecting and characterizing CSCs using gene expression data.

Sign in / Sign up

Export Citation Format

Share Document