https://github.com/agnjuh/matlab_pca_analysis
Manual principal component analysis (PCA) implementation in MATLAB/Octave for dimensionality reduction of gene expression data.
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (7.3%) to scientific vocabulary
Repository
Manual principal component analysis (PCA) implementation in MATLAB/Octave for dimensionality reduction of gene expression data.
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Principal Component Analysis (PCA) — (Computing project 2)
This repository contains two scripts developed for Computing Project 2 in the Mathematical and computational methods bioinformatics-focused course module (programme title: Stratified/Personalised Medicine at Ulster University). The project involves implementing PCA from first principles to explore patterns in simulated gene expression data measured across a group of patients. The goal is to visualise high-dimensional biological data in reduced dimensions while preserving variance trends.
Project Structure Part A – manual PCA in 2D
Script: pca_preprocessing.m Objective: implement PCA from scratch on a 2×25 matrix containing measurements of two genes across 25 patients. Tasks include: constructing the gene expression matrix. centering the data on the origin. evaluating variances along rotated axes (0 to π/2). identifying the axis with the maximum variance. plotting the first principal component and its orthogonal axis. Output: three scatter plots (original data, centered data, and principal axes overlay). Part B – Covariance matrix and eigen decomposition in 5D
Script: pcavisualization.m Objective: apply PCA to a 5×25 matrix containing five gene measurements across 25 patients. Tasks include: constructing the matrix and centering it by row-wise means. calculating a 5×5 covariance matrix. performing eigen decomposition using: [V, D] = eig(covmatrix); identifying the two components (eigenvectors) with the largest eigenvalues (variance). projecting the 5D data onto the top 2 principal components. visualising the projection in a 2D scatter plot.
Cite: Juhász, Á. J. (2018). Principal Component Analysis (PCA) – Computing Project 2 [Course project]. Ulster University. https://github.com/agnjuh/pcamicroarrayanalysis
@misc{juhasz2018pca, author = {Juhász, Ágnes Judit}, title = {Principal Component Analysis (PCA) – Computing Project 2}, year = {2018}, howpublished = {\url{https://github.com/agnjuh/pcamicroarrayanalysis}}, note = {Course project submitted as part of a bioinformatics computing module}, institution = {Ulster University} }
Owner
- Name: Ágnes J Juhász
- Login: agnjuh
- Kind: user
- Location: Sweden
- Repositories: 1
- Profile: https://github.com/agnjuh
Biomedical Scientist, Molecular Biotechnology grad student, passionate about regeneration, development, genomic & transcriptomic analysis | MTB-er, saxophonist
GitHub Events
Total
- Release event: 1
- Push event: 6
- Create event: 1
Last Year
- Release event: 1
- Push event: 6
- Create event: 1