Kompot¶

Kompot is a Python package for differential abundance and gene expression analysis using Gaussian Process models with JAX backend.

Overview¶

Kompot implements methodologies from the Mellon package for computing differential abundance and gene expression, with a focus on using Mahalanobis distance as a measure of differential expression significance. It leverages JAX for efficient computations and provides a scikit-learn like API with .fit() and .predict() methods.

Key features:

Computation of differential abundance between conditions
Gene expression smoothing and uncertainty estimation
Mahalanobis distance calculation for differential expression significance
Weighted log fold change analysis with density difference weighting
Support for covariance matrices and optional landmarks
JAX-accelerated computations
Empirical variance estimation
Resource estimation and dry run for planning large analyses
Disk-backed covariance storage for sample variance estimation
Visualization tools (volcano plots, heatmaps, expression plots)
Full scverse compatibility with direct AnnData integration
Command-line interface for pipeline integration and batch processing

Use Cases¶

Kompot is particularly useful for:

Comparing cell type abundances across different samples
Identifying differentially expressed genes between conditions
Integrating multi-sample or multi-batch variability
Handling large covariance tensors during sample variance estimation via disk-backed storage
Creating visualizations of differential analysis results

Installation¶

Install from PyPI:

pip install kompot

Or via conda/mamba:

conda install -c bioconda kompot

For optional dependencies and JAX GPU support, see the installation guide.

Quick Start¶

import kompot

# Minimal call — uses sensible defaults
kompot.de(adata, "condition", "Young", "Old")

# Differential abundance
kompot.da(adata, "condition", "Young", "Old")

# Customize GP and FDR settings
kompot.de(
    adata, "condition", "Young", "Old",
    sample_col="donor_id",
    gp=kompot.GPSettings(sigma=0.5, use_empirical_variance=True),
    fdr=kompot.FDRSettings(threshold=0.01),
)

See AnnData Interface for the full API and all available settings.

New to Kompot? Start with the Getting Started tutorial for a comprehensive introduction to differential abundance and expression analysis.

Ready for more? Explore advanced topics:

Advanced Differential Expression - Parameter customization, multiple comparisons, and visualization options
Sample Variance Analysis - Accounting for biological replicates in multi-sample studies
Gene Expression Smoothing - GP smoothing, uncertainty decomposition, and CITE-seq validation

Command-Line Interface¶

For pipeline integration and batch processing, use the Command-Line Interface:

# Compute diffusion maps (preprocessing)
kompot dm input.h5ad -o input_dm.h5ad --pca-key X_pca

# Run differential expression
kompot de input_dm.h5ad -o results.h5ad \
  --groupby condition --condition1 control --condition2 treatment \
  --obsm-key DM_EigenVectors

See the CLI documentation for complete usage and examples.

Citation¶

If you use Kompot in your research, please cite:

Otto, D. J., Arriaga-Gomez, E., Thieme, E., Yang, R., Lee, S. C., & Setty, M. (2025). Comparing phenotypic manifolds with Kompot: Detecting differential abundance and gene expression at single-cell resolution. bioRxiv. https://doi.org/10.1101/2025.06.03.657769

BibTeX:

@article{Otto2025.06.03.657769,
    author = {Otto, Dominik J. and Arriaga-Gomez, Erica and Thieme, Elana and Yang, Ruijin and Lee, Stanley C. and Setty, Manu},
    title = {Comparing phenotypic manifolds with Kompot: Detecting differential abundance and gene expression at single-cell resolution},
    year = {2025},
    doi = {10.1101/2025.06.03.657769},
    publisher = {Cold Spring Harbor Laboratory},
    journal = {bioRxiv},
    URL = {https://www.biorxiv.org/content/10.1101/2025.06.03.657769}
}

Index¶

Index