About: The code in this repository was used to generate the results presented in the articles Sequential multi-omics analysis identifies clinical phenotypes and predictive biomarkers for long COVID in Cell Reports Medicine and Multi-omics and Machine Learning Analysis of Human Plasma to Identify Biomarkers in Patients with Post-COVID Condition in STAR protocol. (https://doi.org/10.1016/j.xcrm.2023.101254)
Background: These analyses aim to identify correlations between biomarkers and clinical variables, cluster patients based on their multi-omics profile, and find predictive biomarkers, which is applicable to biomarker studies performed in various diseases.
Repository Structure:
-
Data Preprocessing and Statistical Analysis (R) This section focuses on the initial steps of data preparation and statistical analysis using R. The goal is to clean and preprocess raw data and identify correlations between biomarkers and clinical variables.
-
Clustering Analysis (Python) The clustering analysis section contains code and resources for grouping patients based on their multi-omics profile.
-
Classification Analysis (Python) Here, we delve into the classification analysis to identify predictive biomarkers. This involves the development and evaluation of models to classify patients based on adverse clinical outcomes.