MMoCHi - MultiModal Classifier Hierarchy

About

MMoCHi is a hierarchical classification system designed for CITE-Seq data, but applicable to diverse single-cell sequencing modalities. It includes tools for:

1. Integrating data of Antibody Derived Tag (ADT) expression

2. High-confidence thresholding of cell populations using ADT expression, gene expression, and cell metadata

3. Building a hierarchy of cell subset classifiers

4. Training and evaluating random forest classifiers at each hierarchy level

• To get started with MMoCHi, see Installation, Tutorials, and Example Hierarchies.

• For more details on formatting your data correctly, read the Input and Output Specifications.

• For complete documentation, check out our API.

• Check out our Github!

Details about the algorithm, example applications, and benchmarking is available in our paper: Daniel P. Caron, William L. Specht, David Chen, Steven B. Wells, Peter A. Szabo, Isaac J. Jensen, Donna L. Farber, Peter A. Sims. “Multimodal hierarchical classification of CITE-seq data delineates immune cell states across lineages and tissues.” Cell Reports Methods, 2025 [Open Access]