📚 Syllabus & Course Curriculum
AI & Machine Learning in Healthcare
Module-by-module breakdown of Analysis of Microarray Data using Machine Learning/AI in R, from foundations to a certified capstone project.
Platform
• Affymetrix, Illumina and two-colour platforms and the differences that matter
• CEL files, probe-to-gene mapping and multi-probe genes
• Retrieving and reading experiments from GEO with GEOquery
Preprocessing
• Background correction, RMA normalisation and quantile normalisation in affy and oligo
• Array quality assessment and the defensible grounds for excluding an array
• Batch effect detection by PCA before any modelling is attempted
Statistics
• limma, the linear model framework and empirical Bayes moderation
• Design and contrast matrices for anything beyond a two-group comparison
• FDR control and why an unadjusted p-value list is not a result
Learning
• Classification with caret or tidymodels when features vastly outnumber samples
• Feature selection inside the resampling loop, or the accuracy is inflated
• Clustering, heatmaps and the arbitrariness of the chosen distance metric
Meaning
• Over-representation against GSEA and the correct background gene set
• Validation in an independent GEO dataset as the honest check
• Where microarray conclusions do and do not agree with RNA-Seq
Earn government-registered certification in Analysis of Microarray Data using Machine Learning/AI in R
e-Certificate and e-Marksheet issued on successful completion.
