copick / discover-picks / 0.1.3

Classify and Match Embeddings to Known Particle Classes with Multithreading Across Multiple Directories

Uses multithreading to compare median embeddings from multiple Zarr datasets to known class medians and identifies matches based on a configurable distance threshold.
Tags
imagingcryoetPythonnaparicellcanvas
Solution written by
Kyle Harrington
License of solution
MIT
Source Code

Arguments

--embedding_directories
Paths to the embedding Zarr directories separated by commas. (default value: PARAMETER_VALUE)
--median_embeddings_path
Path to the CSV file with median embeddings and distances. (default value: PARAMETER_VALUE)
--matches_output_path
Path for the output file containing matches. (default value: PARAMETER_VALUE)
--distance_threshold
Distance threshold factor to consider a match. (default value: PARAMETER_VALUE)

Usage instructions

Please follow this link for details on how to install and run this solution.