mantispy - Image-based profiling in Python#
mantispy brings Cell Painting and other image-based profiling data into the scverse ecosystem, from reading what a pipeline wrote through quality control, normalization and batch correction to evaluating what survived.
Everything operates on an AnnData, so scanpy’s PCA, neighbors, UMAP and Leiden work on the same object, and read_plate() reads the images behind the profiles as SpatialData.
mantispy follows three canonical workflows, and each has its own tutorials:
Compound screens: call hits, group them by mechanism of action, test enrichment and fit dose responses.
Genetic screens: aggregate guides to genes and read a CRISPR screen as clusters and gene sets.
Learned embeddings: bring in features from a trained model and treat them like measured ones.
New to mantispy? Check out the installation guide.
The whole workflow on one page, from a public screen to called hits.
The tutorials walk you through real-world applications of mantispy.
The API reference contains a detailed description of the mantispy API.
Need help? Reach out on our forum to get your questions answered.
Found a bug? Interested in improving mantispy? Check out our GitHub for the latest developments.
Citation#
A preprint describing mantispy is in preparation. Until then, please cite the repository directly.
If you use a method mantispy implements or wraps, please also cite its original publication. All method references are listed in References.