Overview

M2ASDA offers a variety of functionalities for single-cell omics data analysis, including but not limited to: 1) detecting anomalous cells 2) aligning multi-sample batch cells 3) subtyping anomalous cells across multi-batch. Additionally, all the functions can be implemented through both python package and terminal commands.

Preparations before tutorials

Before starting the tutorial, we need to make some preparations, including: installing M2ASDA and its required Python packages, downloading the datasets required for the tutorial, and so on. The preparations is available at M2ASDA Preparations. Additionally, when dealing with multimodal data structures involving large gene expression matrices, we strongly recommend using a GPU to train M2ASDA for faster execution.

Outline of tutorials

• Tutorial 1: Detecting anomalous cells with M2ASDA package
• Tutorial 2: Running M2ASDA to detect anomalous cells in terminal