Decima
Introduction
Decima is a Python library to train sequence models on single-cell RNA-seq data.
Weights
Weights of the trained Decima models (4 replicates) are now available at https://zenodo.org/records/15092691. See the tutorial for how to load and use these.
Preprint
Please cite https://www.biorxiv.org/content/10.1101/2024.10.09.617507v3. Also see https://github.com/Genentech/decima-applications for all the code used to train and apply models in this preprint.
Requirements
Decima has been tested on Ubuntu 24.04.3 and MacOS 15.6.1 using Python 3.9-3.12.
Installation
Install the package from PyPI,
pip install decima
Or if you want to be on the cutting edge,
pip install git+https://github.com/genentech/decima.git@main
Typical installation time including all dependencies is under 10 minutes.
Tutorials
See the tutorials for instructions, including how to train your own Decima model with an example dataset.
Note
This project has been set up using BiocSetup and PyScaffold.
1 maintainer
Metadata
1 maintainer
Release files for decima 0.7.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| decima-0.7.2.tar.gz | 2.1 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| decima-0.7.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.2 MB
Release files / decima-0.7.2.tar.gz
| Download URL | decima-0.7.2.tar.gz |
|---|---|
| Size | 2.1 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b0e6e610a0292120be42bc647a1ee206e2815a0c01d5db9327bbfc5e6a838350
|
|
BLAKE2b-256 checksum How to use checksums |
9420c0bef40793349b63ca08842c22eb3a5faa9f7172997d4bd2a06cbfea2712
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 4, 2026.
Transparency logRelease files / decima-0.7.2-py3-none-any.whl
| Download URL | decima-0.7.2-py3-none-any.whl |
|---|---|
| Size | 102.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b146327179b0d71661305d3be7fa9c0c8d3cd5b1b7ba4cb75d602a5cff27ddc1
|
|
BLAKE2b-256 checksum How to use checksums |
f8ba26f51259346e0bb584161c7a312b83cc2fa61f28bc907346904f8f5b4ca5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 4, 2026.
Transparency log
