MicAssess: Automated micrograph assessment
MicAssess uses a pre-trained deep learning neural network in order to categorize micrographs into ‘good’ or ‘bad’ groups. The motivation and use of this tool are described in our publication and software repository on Github.
How do I use MicAssess?
If you want to run it locally on your own machine, you can follow the instructions here to download & install the software.
If you want to run it remotely, you can run MicAssess on COSMIC²!
Submitting a MicAssess job on COSMIC²:
NOTE: If you have your micrographs in a RELION job directory (e.g. MotionCorr/job001/) then you can just select the directory “job001” for upload into COSMIC².
- Create a new directory (e.g. micrographs_for_cosmic2)
- Create another directory within this directory (e.g. ‘micrographs_for_cosmic2/Micrographs‘)
- Place all micrographs to be classified into the new subdirectory (e.g. ‘micrographs_for_cosmic2/Micrographs‘)
- Create a .star file with micrograph names within micrographs_for_cosmic2 by using this command:
cd micrographs_for_cosmic2 printf 'data_\nloop_\n_rlnMicrographName\n' >> micrographs.star | ls Micrographs/*.mrc >> micrographs.star
- Upload this directory to COSMIC² using Globus.
- Note: in order to upload this directory, you will need to select the directory named micrographs_for_cosmic2 in the above example
- If successful, you will see a new data file within your data page
- For this example, it will be named micrographs_for_cosmic2/micrographs.star
- Submit to COSMIC² – you will need to click Input parameters but no parameters are required.
- This job will be finished within 3-10 minutes.
Outputs from COSMIC²
When finished, you will see the following files listed in the output page for your task:
STAR file output
- This is an edited version of the original micrographs STAR file you uploaded to only contain the ‘good’ micrographs
- This file is ready to be used for subsequent processing in RELION or other programs
Good and bad micrograph JPG files
- This is a .zip file containing all micrographs grouped into two directories for bad (“pred_bad”) or good (“pred_good”) predications. The micrographs are .jpg files so you can download and display these images easily on your computer.
How do I cite MicAssess?
Please cite our preprint if you find this useful for your work:
Li et al. (2019) High-throughput cryo-EM enabled by user-free preprocessing routines. doi: https://doi.org/10.1101/2019.12.20.885541
Example groupings into ‘good’ and ‘bad’ categories