Skip to main content

membrane protein localization for cryo-ET

Project description

Membrain-Pick

Overview

Membrain-Pick is part of the MemBrain suite of tools for processing membranes in cryo-electron tomography. MemBrain-pick's main purpose is to localize membrane-associated particles in the tomograms. To this end, MemBrain-picks takes as input already existing membrane segmentations and processes these to limit the search space for membrane-associated particles. The output of MemBrain-pick is a set of coordinates that can be used for further analysis.

Workflow

The workflow of MemBrain-pick is as follows:

  1. Input: Membrane segmentations in the form of a binary mask (.mrc). Ideally, these segmentations should depict single membrane instances.
  2. Mesh Generation: The membrane segmentations are converted into a mesh representation. At this stage, also tomogram densities are projected onto the membrane mesh.
  3. Ground Truth Generation: The membrane mesh can be loaded into surforama to manually annotate membrane-associated particles. These annotations can then be used to train a MemBrain-pick model.
  4. Training: The generated meshes, along with the annotations, are used to train a model that can predict the location of membrane-associated particles.
  5. Prediction: The trained model is used to predict the location of membrane-associated particles in the membrane segmentations.

Example notebook

For a quick start, you can walk through our example notebook. You can easily run it on Google Colab by clicking on the badge below:

Open In Colab

Key Functionalities

  • Mesh Conversion: Transform membrane segmentations into a mesh representation that can easily be processed by MemBrain-pick and surforama.
  • Model training: Train a model to predict the location of membrane-associated particles.
  • Prediction: Use the trained model to predict the location of membrane-associated particles in membrane segmentations.
  • Initial orientaton assignment: Given a set of positions, MemBrain-pick can assign initial orientations to the particles by aligning them with the membrane normal. -- integration with surforama: MemBrain-pick can be used in conjunction with surforama to manually annotate membrane-associated particles.

Jump to

MemBrain-pick is part of the MemBrain v2 [1] package and still under early development. If you have any questions or suggestions, please contact us at lorenz.lamm@helmholtz-munich.de

[1] Lamm, L., Zufferey, S., Righetto, R.D., Wietrzynski, W., Yamauchi, K.A., Burt, A., Liu, Y., Zhang, H., Martinez-Sanchez, A., Ziegler, S., Isensee, F., Schnabel, J.A., Engel, B.D., and Peng, T, 2024. MemBrain v2: an end-to-end tool for the analysis of membranes in cryo-electron tomography. bioRxiv, https://doi.org/10.1101/2024.01.05.574336

Project details


Download files

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

Source Distribution

membrain_pick-0.0.6.tar.gz (86.7 kB view details)

Uploaded Source

Built Distribution

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

membrain_pick-0.0.6-py3-none-any.whl (99.0 kB view details)

Uploaded Python 3

File details

Details for the file membrain_pick-0.0.6.tar.gz.

File metadata

  • Download URL: membrain_pick-0.0.6.tar.gz
  • Upload date:
  • Size: 86.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.10.16

File hashes

Hashes for membrain_pick-0.0.6.tar.gz
Algorithm Hash digest
SHA256 416a8f9bea10d15fe046382a272c62734f299b7c10689ff6e77aa620236519d4
MD5 6dada3fcb37f031574791a79d729840d
BLAKE2b-256 16520cb90bf78ec1f7171bc062ea9941cf5cd0b4dbaa0a605717c5a7e4817739

See more details on using hashes here.

File details

Details for the file membrain_pick-0.0.6-py3-none-any.whl.

File metadata

  • Download URL: membrain_pick-0.0.6-py3-none-any.whl
  • Upload date:
  • Size: 99.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.10.16

File hashes

Hashes for membrain_pick-0.0.6-py3-none-any.whl
Algorithm Hash digest
SHA256 0f1f6b09febb56656d786bdd3d1f5e4bc1e82c60ef43451903389f6a172881cf
MD5 9b737ac80159c060167e8c2cbaf5e438
BLAKE2b-256 8f4ba3230d067417203a345bdd36854f425549170eeca7530ca7263e9a6b331f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page