Last updated: 2022-11-10

Checks: 0 1

Knit directory: irAE_LungCancer/analysis/

This reproducible R Markdown analysis was created with workflowr (version 1.7.0). The Checks tab describes the reproducibility checks that were applied when the results were created. The Past versions tab lists the development history.

Repository version: no version control

Tracking code development and connecting the code version to the results is critical for reproducibility. To start using Git, open the Terminal and type git init in your project directory.

This project is not being versioned with Git. To obtain the full reproducibility benefits of using workflowr, please see ?wflow_start.

Section 1: Exploratory data analysis

In this analysis, I firstly explored the overall data structure to see if any normalization and/or transformation is needed. I also performed PCA and clustering analysis to see if there’s any potential technical confounders.

Section 2: Association tests between molecular features and disease phenotypes

Hypothesis testing (ANOVA or t-tests) were used to detect differential feature (cytokines or metabolites) abundance in different disease groups in samples from different time points.

Section 3: Supervised machine learning for feature selection and prediction

In this part, different machine learning models (random forest, SVM and multi-variate linear regression) were used to select features that can predict disease outcomes. However, due to the small sample size, please view current results with great caution.

Section 4: Multi-omics factor analysis (MOFA)

In this part, MOFA was used to integrate CBA and NMR data to see if we can identify MOFA factors that separate disease groups. Also please view current results with great caution, due to the current small sample size.