multi-OMics INtegration EXercise developed for new learners to learn
Please fill out the Questionnaire after completing the exercises. Thank you!💙
If you you have not download Python and JupyterNotebook, please see Jupyter_Notebook_Preparation
You can also use Binder for practice:
-
Chapeter 1 Data Loading and Preprocessing.ipynb
-
-
If you are not sure how to use the tutorial, check out How to use the tutorial notebooks
Any other problems, opinions or recommendations:Others
OMINEX is a project designed for new learners to learn how to integrate and analyse multi-omics datasets. The project will provide a step-by-step tutorial for learners to navigate. Python is the main programming language used in this project. With the JupyterNotebook, users can practice to improve their programming skills and understand how to integrate and analyse multi-omics datasets for cancer subtyping and biomarker identification.
Chapter 1 Data Loading and Preprocessing introduces the Pandas🐼 library. It demonstrates how to read datasets, handle missing values, and merge multiple datasets
Chapter 2 Integration with NMF demonstrates how to use NMF🦅 for dimensionality reduction, including a detailed explanation of NMF, the detailed usage of the NMF function from the sklearn package, and the implementation of NMF assumptions.
Chapter 3 MOFA+ provides an example of MOFA+😾 implementation on colorectal cancer and 2 exercises for practice.
- Multi-omics Data Integration: integrate data from genomics, transcriptomics
- Dimension Reduction: Reduce the dimentions using NMF and MOFA+
- Interactive Features: Generate and interact with principle components, volcano plots, heatmaps, and dendrograms.
- Statistical Analysis: NMF implementaion, z-score statistical tests
- User-friendly Interface: Easy-to-use interface with step-by-step instructions and comprehensive tutorials.
To install OMINEX, clone the repository and install the necessary dependencies:
git clone https://github.com/yourusername/OMINEX.git
cd OMINEX
pip install -r requirements.txt