labomics/midas
PyTorch implementation of the MIDAS algorithm for single-cell multimodal data integration (Nature Biotechnology 2024).
This project helps single-cell biologists and researchers integrate complex, fragmented single-cell datasets. It takes raw, incomplete data—where different experiments might measure different types of cellular information (like RNA, proteins, or chromatin accessibility)—and produces a complete, harmonized dataset with missing information filled in. This allows scientists to uncover deeper biological insights from their combined experiments.
Use this if you need to combine diverse single-cell measurements, even when some experiments are missing certain data types, to get a complete picture of cellular states.
Not ideal if your data is already perfectly complete and harmonized across all modalities and batches, or if you are not working with single-cell multimodal data.
Stars
62
Forks
8
Language
Python
License
MIT
Category
Last pushed
Mar 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/labomics/midas"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
scverse/scvi-tools
Deep probabilistic analysis of single-cell and spatial omics data
scverse/scanpy
Single-cell analysis in Python. Scales to >100M cells.
Teichlab/celltypist
A tool for semi-automatic cell type classification
theislab/scarches
Reference mapping for single-cell genomics
Lotfollahi-lab/nichecompass
End-to-end analysis of spatial multi-omics data