miss-alignment

260_etomo_vs_3x3

Better alignment = cleaner tomograms. GIF shows a denoised reconstruction after patch tracking alignment and miss-alignment.

Installation

Installation is limited at the moment to a specific python, CUDA, and torch version. This might be fixed at some point in the future. For now, its easiest to set everything up in a conda environment.

First create an environment called miss-alignment with cuda-toolkit 12.9 and activate it:

conda create -n miss-alignment -c conda-forge python=3.11 cuda-toolkit=12.9 -y
conda activate miss-alignment

We need to fix some GPU dependencies for accelerated reconstruction:

python -m pip install torch==2.8.0
python -m pip install torch-projectors --index-url https://warpem.github.io/torch-projectors/cu129/simple/

[!IMPORTANT] If your GPU's have the Blackwell-architecture make sure to install at least v0.11 of torch-projectors.

Finally install miss-alignment with this command:

python -m pip install miss-alignment

Check that the CLI shows up with:

miss-alignment --help

This lists the available commands (train and infer); run miss-alignment train --help or miss-alignment infer --help for details on each.

How to run?

See docs/usage.md for instructions.

Changelog

A full list of changes per release is available on the GitHub Releases page.

Citation

Chaillet, M.L., van Loenhout, J., Leung, M.R., Burt, A., and Tegunov, D. (2026) MissAlignment Teaches Itself Better Cryo-ET Tilt-Series Alignment by Making It Worse. bioRxiv. https://doi.org/10.64898/2026.04.29.721716

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

miss_alignment-0.2.0.tar.gz (27.6 MB view details)

Uploaded Jun 29, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

miss_alignment-0.2.0-py3-none-any.whl (68.8 kB view details)

Uploaded Jun 29, 2026 Python 3

File details

Details for the file miss_alignment-0.2.0.tar.gz.

File metadata

Download URL: miss_alignment-0.2.0.tar.gz
Upload date: Jun 29, 2026
Size: 27.6 MB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for miss_alignment-0.2.0.tar.gz
Algorithm	Hash digest
SHA256	`c9525a59d1df1248218aca6d3ddf89e8a56ee11c99aae0adbfb0ee94662dd966`
MD5	`e1dad12512eb6be15bb7e9e4f060997e`
BLAKE2b-256	`bed89ecd6e630941b93383b706b09de5d5373b3b04aaaeb8bb962514cd58812e`

See more details on using hashes here.

Provenance

The following attestation bundles were made for miss_alignment-0.2.0.tar.gz:

Publisher: ci.yml on warpem/miss-alignment

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: miss_alignment-0.2.0.tar.gz
- Subject digest: c9525a59d1df1248218aca6d3ddf89e8a56ee11c99aae0adbfb0ee94662dd966
- Sigstore transparency entry: 2007519416
- Sigstore integration time: Jun 29, 2026
Source repository:
- Permalink: warpem/miss-alignment@989714d260b856d7a63e6841c22f2c32e3448cf5
- Branch / Tag: refs/tags/v0.2.0
- Owner: https://github.com/warpem
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: ci.yml@989714d260b856d7a63e6841c22f2c32e3448cf5
- Trigger Event: push