AlphaGenome API
Get API key | Installation | Quick start | Documentation | Community | Terms of Use | Model code
The alphagenome package provides programmatic access to the AlphaGenome family
of models and the AlphaGenome Atlas, developed by Google DeepMind:
- AlphaGenome 2: Our latest multimodal DNA sequence model, with improved cell-type specificity, generalization to your own human scRNA-seq data (expression conditioning), and imputation of unobserved modalities across 1 Mb sequences.
- AlphaGenome Atlas: Genome-wide in silico mutagenesis across 9 billion human variants, providing pre-computed variant effect scores and the AlphaGenome Variant Impact (AVI) score on a zero-code website and through the API.
- AlphaGenome 1: The original model described in Avsec et al. (2026).
The API is offered free of charge for non-commercial use. Query rates vary with demand: pre-computed Atlas lookups support higher query rates than live model predictions, which suit small-scale analyses rather than large, genome-wide analyses.
For support and feedback:
- Bugs and code issues: GitHub Issues
- Questions and feature requests: Community forum
- Other inquiries: alphagenome@google.com
Terms
AlphaGenome API is subject to the AlphaGenome Terms of Service. Other than as expressly provided in the AlphaGenome Terms of Service (see references to Permissive Use Downloadable Artifacts for Commercial and Non-Commercial Use), outputs generated by AlphaGenome and other information provided in AlphaGenome Atlas are for non-commercial use only and should not be used for the training of other machine learning models. Predictions are for theoretical modelling and research purposes only. They must not be used for clinical decision-making or relied upon for medical or other professional advice.
AlphaGenome is also available for commercial use via Google Cloud.
Installation
Install alphagenome from PyPI:
pip install alphagenome
See the Installation guide
for setting up a virtual environment (venv, uv, or conda), installing from
source, and configuring your
AlphaGenome API key.
Quick start
See Getting started to choose the right tool for your task and walk through the AlphaGenome 2 and AlphaGenome Atlas API workflows.
Explore the documentation for interactive notebooks and guides:
- Tutorials: Step-by-step Colab notebooks covering reference conditions, making predictions, variant scoring, expression conditioning given your own scRNA-seq data, plotting, and the AlphaGenome Atlas.
- User guide: Conceptual guides on data objects, model metadata, imputation, variant scoring, visualization, and migrating from AlphaGenome 1.
- Vignettes: End-to-end biological analyses and case studies.
- API reference: Complete Python package reference.
For example, to score a variant with AlphaGenome 2:
from alphagenome.data import genome
from alphagenome.models.v2 import dna_client
dna_model = dna_client.create('YOUR_API_KEY')
# Choose a condition: CD14-positive monocytes in blood.
condition = 'UBERON:0000178_CL:0001054'
# Select a genomic region: center a 1 Mb interval on the variant.
variant = genome.Variant(
chromosome='chr2',
position=219243701,
reference_bases='C',
alternate_bases='T',
)
interval = variant.reference_interval.resize(dna_client.SEQUENCE_LENGTH_1MB)
# Score the variant across all recommended scorers and format as a DataFrame.
scores = dna_model.score_variant(
interval=interval,
variant=variant,
condition=condition,
)
Contributing
We welcome bug fixes and some new features to this project. Before sending your pull request, please read the CONTRIBUTING documentation, ensure all tests pass, and that your contributions are formatted correctly.
You can check your changes by running the following from the alphagenome root
directory:
$ python3 -m pip install hatch
$ python3 -m hatch run check:all # Runs linter and formatter.
$ python3 -m hatch test
Citing alphagenome
If you use AlphaGenome in your research, please cite using:
@article{alphagenome,
title={Advancing regulatory variant effect prediction with {AlphaGenome}},
author={Avsec, {\v Z}iga and Latysheva, Natasha and Cheng, Jun and Novati, Guido and Taylor, Kyle R. and Ward, Tom and Bycroft, Clare and Nicolaisen, Lauren and Arvaniti, Eirini and Pan, Joshua and Thomas, Raina and Dutordoir, Vincent and Perino, Matteo and De, Soham and Karollus, Alexander and Gayoso, Adam and Sargeant, Toby and Mottram, Anne and Wong, Lai Hong and Drot{\'a}r, Pavol and Kosiorek, Adam and Senior, Andrew and Tanburn, Richard and Applebaum, Taylor and Basu, Souradeep and Hassabis, Demis and Kohli, Pushmeet},
journal={Nature},
volume={649},
number={8099},
pages={1206--1218},
year={2026},
doi={10.1038/s41586-025-10014-0},
publisher={Nature Publishing Group UK London}
}
If you use AlphaGenome Atlas website, API or scores, please cite:
@article{alphagenome_atlas,
title={{AlphaGenome} Atlas: in silico mutagenesis of the entire human genome improves prioritization and interpretation of non-coding variants},
author={Cheng, Jun and Taylor, Kyle R., Nicolaisen, Lauren and Pan, Joshua and Bycroft, Clare and Perino, Matteo and Ward, Tom and Hawkes, Gareth and Covil, Laura E. and Weilert, Melanie and Thomas, Raina W. and Latysheva, Natasha and Hirschmann, J. Maile and Chen, Xi Dawn and Beaumont, Robin N. and Chundru, V Kartik and Weedon, Michael N. and Bourdareau, Simon and Chu, Hoyin and Hariharan, Dhavanthi and Kagohara, Thais and Ten\'{o}rio, Lucas and Ushigome, Yosuke and Shearer, Courtney A. and Ikica, Barbara and Fang, Ada and Naciri, Mouad and Johnston, Victoria and Green, Richard and Wong, Lai Hong and Dutordoir, Vincent and Mottram, Anne and Gayoso, Adam and Arvaniti, Eirini and Rehm, Heidi L. and Chen, Fei and Lareau, Caleb A. and Wright, Caroline F. and O'Donnell-Luria, Anne and Zeitlinger, Julia and Kohli, Pushmeet, and Avsec, {\v Z}iga },
year = {2026},
doi = {10.64898/2026.09.16.26363192},
publisher = {Cold Spring Harbor Laboratory Press},
journal = {medRxiv}
}
Acknowledgements
AlphaGenome communicates with and/or references the following separate libraries and packages:
- Abseil
- anndata
- fsspec
- gRPC
- immutabledict
- intervaltree
- jaxtyping
- matplotlib
- ml_dtypes
- NumPy
- pandas
- protobuf
- pyarrow
- pyfaidx
- SciPy
- seaborn
- tqdm
- typeguard
- typing_extensions
- zstandard
We thank all their contributors and maintainers!
License and Disclaimer
Copyright 2024 Google LLC
All software in this repository is licensed under the Apache License, Version 2.0 (Apache 2.0); you may not use this except in compliance with the Apache 2.0 license. You may obtain a copy of the Apache 2.0 license at: https://www.apache.org/licenses/LICENSE-2.0. For the avoidance of doubt, as noted above, the API is offered free of charge for non-commercial use subject to the Terms of Use.
Examples and documentation to help you use the AlphaGenome API are licensed under the Creative Commons Attribution 4.0 International License (CC-BY). You may obtain a copy of the CC-BY license at: https://creativecommons.org/licenses/by/4.0/legalcode.
Unless required by applicable law or agreed to in writing, all software and materials distributed here under the Apache 2.0 or CC-BY licenses are distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the licenses for the specific language governing permissions and limitations under those licenses.
This is not an official Google product.
Third-party software
Your use of any third-party software, libraries or code referenced in the materials in this repository (including the libraries listed in the Acknowledgments section) may be governed by separate terms and conditions or license provisions. Your use of the third-party software, libraries or code is subject to any such terms and you should check that you can comply with any applicable restrictions or terms and conditions before use.
Reference Datasets
A modified version of the GENCODE dataset (which can be found here: https://www.gencodegenes.org/human/releases.html) is released with the client code package for illustrative purposes, and is available with reference to the following:
- Copyright © 2024 EMBL-EBI
- The GENCODE dataset is subject to the EMBL-EBI terms of use, available at https://www.ebi.ac.uk/about/terms-of-use.
- Citation: Frankish A, et al (2018) GENCODE reference annotation for the human and mouse genome.
- Further details about GENCODE can be found at https://www.gencodegenes.org/human/releases.html, with additional citation information at https://www.gencodegenes.org/pages/publications.html and further acknowledgements can be found at https://www.gencodegenes.org/pages/gencode.html.
Metadata
Release files for alphagenome 2.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| alphagenome-2.0.0.tar.gz | 12.2 MB | With provenance | Details for alphagenome-2.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| alphagenome-2.0.0-py3-none-any.whl | Python 3 | none | any | Details for alphagenome-2.0.0-py3-none-any.whl |
Total release size: 12.6 MB
Release files / alphagenome-2.0.0.tar.gz
| Download URL | alphagenome-2.0.0.tar.gz |
|---|---|
| Size | 12.2 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
cb1d49d39fc82627b7eb387d979e898b7397a499284f711481fef59d5533b844
|
|
BLAKE2b-256 checksum How to use checksums |
3eb455a44b7d344cb50b425914aeb33f9f417c19b64903a24b5d4a3b02db2017
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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 Nov 11, 2026.
Transparency logRelease files / alphagenome-2.0.0-py3-none-any.whl
| Download URL | alphagenome-2.0.0-py3-none-any.whl |
|---|---|
| Size | 358.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b76e97d69a806f19400e1d404345b180994e5c4d0ab9690c03380805fd65ee4d
|
|
BLAKE2b-256 checksum How to use checksums |
b3b85bd5ac7f79dfc71f3f99597ed8225d7e64a6ff44b3c8c1c0e06a712388e2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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 Nov 11, 2026.
Transparency logSecurity for alphagenome 2.0.0
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.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for alphagenome-2.0.0.tar.gz
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 Nov 11, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.