This release is a pre-release and may not be stable for production use.
dnax — DNA models in JAX
[!WARNING] This is an experimental implementation.
dnax provides JAX-based implementation of models like BPNet, ChromBPNet, DragoNNFruit.
The code is heavily based on original implementations (chrombpnet, bpnet-lite)
however attempts to be more readable, accessible, and maintainable.
Installation
pip install dnax
# or
pip install git+https://github.com/gtca/dnax.git
Usage
Vanilla ChromBPNet:
from dnax.models.chrombpnet import ChromBPNet
bias = BPNet(n_filters=512, n_layers=8)
accessibility = BPNet(n_filters=512, n_layers=8)
model = ChromBPNet(bias, accessibility)
x = ... # (batch, 2114, 4) tensor (1-hot)
profile, counts = model(x)
For inference, you can load existing ChromBPNet models:
from dnax.io import load_chrombpnet_model
model = load_chrombpnet_model(bias_file, accessibility_file)
profile, counts = model(x)
Implementation
dnax currently uses flax and its NNX API.
Metadata
Release files for dnax 2024.0.0a1
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 |
|---|---|---|---|---|
| dnax-2024.0.0a1.tar.gz | 14.5 kB | Without provenance | Details for dnax-2024.0.0a1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| dnax-2024.0.0a1-py3-none-any.whl | Python 3 | none | any | Details for dnax-2024.0.0a1-py3-none-any.whl |
Total release size: 24.7 kB
Release files / dnax-2024.0.0a1.tar.gz
| Download URL | dnax-2024.0.0a1.tar.gz |
|---|---|
| Size | 14.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ded2ce9e955c08eea88d3db19a61cac012a34e60e5aaf9b737fdb89315c01f81
|
|
BLAKE2b-256 checksum How to use checksums |
d4914bf39d3f7a8ea4883f5ec0e7ec887b6d58b4a6afd080934e7a5859a97235
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.11.9
|
Release files / dnax-2024.0.0a1-py3-none-any.whl
| Download URL | dnax-2024.0.0a1-py3-none-any.whl |
|---|---|
| Size | 10.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b534b79d3bbc555604ec658d61383be12581a012c341b45a4a084ed6d64583ae
|
|
BLAKE2b-256 checksum How to use checksums |
07d654b4396d74b9fd1a568d06e4429e9ea60497c2dd9703887fc438f6448038
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.11.9
|
Security for dnax 2024.0.0a1
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A 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.