Posts

You will find some comprehensive training materials on this site, and here I will add some shorter musings on other aspects of data analysis and Bioinformatics that I have found useful

Tidymodels for omics data: Part 4

15 min

Optimising Machine Learning Performance by cross-validation and tuning

Nov 27, 2025

Tidymodels for omics data: Part 3b

18 min

Two further methods for Machine Learning in R using tidymodels: K Nearest Neighbours (KNN) and Support Vector Machines (SVM)

Nov 21, 2025

Tidymodels for omics data: Part 3a

14 min

Identifying predictive markers for ER status from high-dimensional gene expression data. We compare the performance of penalized regression (GLMNet) and ensemble learning…

Nov 19, 2025

Tidymodels for omics data: Part 2

23 min

A proof of concept machine learning tasks to classify Estrogen Receptor status of TCGA breast cancers using logistic regression and decision trees

Nov 17, 2025

Tidymodels for omics data: Part 1

19 min

Downloading and exploring TCGA (breast cancer) expression data from GEO so we can proceed to use machine learning later. We’ll also make some exploratory plots such as…

Nov 11, 2025

Teaching an old dog new tricks; tidy analysis of RNA-seq

13 min

Can I retrain myself to use tidy methods for bulk rna-seq analysis?

Nov 4, 2025

Reading 10X Spatial Data from GEO into R

7 min

Lots of spatial transcriptomics data is becoming available in R, but how do you load it into R for analysis? I will discuss an example of a dataset uploaded to Gene…

Oct 23, 2025

Always check your input data

6 min

Why you always check your input data before starting

Oct 16, 2025