T20S Proteasome: Topaz Particle Picking Tutorial

Topaz particle picking tutorial via the Topaz wrapper available in CryoSPARC.

Step 1 - Preprocess Data

Preprocess the T20S subset by completing steps 1-12 in the tutorial found in the Cryo-EM Data Processing in CryoSPARC: Introductory Tutorial section found here:

Ensure that the Inspect Picks, and Select 2D jobs from the linked tutorial are completed as they will be required for training the Topaz model. The ouputs from these two jobs will be used as inputs for the Topaz-related jobs.

Step 2 - Create Training Job

Select Topaz Train (BETA) from the Job Builder. Drag and drop the micrographs output from the completed Inspect Picks job and the particles_selected output from the completed Select 2D job into the micrographs and particles inputs respectively.
Use the file browser (activated by clicking the folder icon) to locate the Topaz executable path found in the Deep Picking section for the Path to Topaz Executable field. Instructions on how to find the Topaz executable path can be found above.
Modify the Downsampling factor parameter to 16. This parameter reduces the size of the input micrographs by the factor input and is often necessary to conform to a system's memory constraints.
Modify the Expected number of particles parameter to 300.
Queue the job.
The job is training a Topaz model on the subset of 20 micrographs from the T20S tutorial. It is highly recommended to train deep picker models on subsets of micrographs as acquiring training picks for all micrographs takes time and is not required. Once the Topaz model learns on a sufficient subset of the micrographs, it can pick particles from the entire dataset.

Step 3 - Create Topaz Extract Job

Select Topaz Extract (BETA) from the Job Builder. Drag and drop both the topaz_model and micrographs outputs from the Topaz Train job into the corresponding inputs on the Job Builder.
Use the file browser (activated by clicking the folder icon) to locate the Topaz executable path found earlier for the Path to Topaz Executable field.
Queue the job.
The job is using the trained Topaz model to infer picks from the input micrographs. Even though in this tutorial, the job is picking from the same micrographs used to train the model, a properly trained model will infer picks that were not used as training picks from the micrographs.

Step 4 - Acquire Particles from Topaz Extract

Select Extract from Micrographs from the Job Builder. Drag and drop both the micrographs and the particles outputs from the Topaz Extract job into the corresponding inputs on Job Builder.
Queue the job.
This job will update the particle picks with information required for further processing.
Select 2D Classification from the Job Builder. Drag and drop the particles output from the Extract from Micrographs job into the particles input of the 2D Classification job.
Queue the job.
Select Select 2D classes from the Job Builder. Drag and drop both outputs of the 2D Classification job into their corresponding inputs in the Select 2D classes job.
Queue the job.
Wait for the job status to change to "Waiting" and then select the particle templates that should be kept for further processing.
The 2D Classification and Select 2D classes jobs serve to filter out unwanted particles from the particle picking. Once the Select 2D classes job is complete, the particles output from the job can be used as particle picks to process further into the pipeline.

Next Steps

Now that a basic Topaz pipeline has been completed, the more advanced aspects of particle picking with Topaz can be explored. The following are some of these aspects:

Ideally, deep picking models are trained on a subset of micrographs and then perform inference on an entire dataset, as mentioned before. The Topaz model trained in this tutorial can be applied to the entire T20S dataset rather than the subset used in this tutorial. Potential refinement results will improve with the resultant increased number of picks.
The Topaz Train and Topaz Cross Validation jobs has many training parameters that can be fine tuned to affect the quality of the model.

PreviousTopaz (Bepler, et al)NextT20S Proteasome: Topaz Micrograph Denoising Tutorial

Last updated 2 years ago

Step 1 - Preprocess Data

Preprocess the T20S subset by completing steps 1-12 in the tutorial found in the Cryo-EM Data Processing in CryoSPARC: Introductory Tutorial section found here:

Ensure that the Inspect Picks, and Select 2D jobs from the linked tutorial are completed as they will be required for training the Topaz model. The ouputs from these two jobs will be used as inputs for the Topaz-related jobs.

Step 2 - Create Training Job

Select Topaz Train (BETA) from the Job Builder. Drag and drop the micrographs output from the completed Inspect Picks job and the particles_selected output from the completed Select 2D job into the micrographs and particles inputs respectively.

Use the file browser (activated by clicking the folder icon) to locate the Topaz executable path found in the Deep Picking section for the Path to Topaz Executable field. Instructions on how to find the Topaz executable path can be found above.

Modify the Downsampling factor parameter to 16. This parameter reduces the size of the input micrographs by the factor input and is often necessary to conform to a system's memory constraints.

Modify the Expected number of particles parameter to 300.

Queue the job.

The job is training a Topaz model on the subset of 20 micrographs from the T20S tutorial. It is highly recommended to train deep picker models on subsets of micrographs as acquiring training picks for all micrographs takes time and is not required. Once the Topaz model learns on a sufficient subset of the micrographs, it can pick particles from the entire dataset.

Step 3 - Create Topaz Extract Job

Select Topaz Extract (BETA) from the Job Builder. Drag and drop both the topaz_model and micrographs outputs from the Topaz Train job into the corresponding inputs on the Job Builder.

Use the file browser (activated by clicking the folder icon) to locate the Topaz executable path found earlier for the Path to Topaz Executable field.

Queue the job.

The job is using the trained Topaz model to infer picks from the input micrographs. Even though in this tutorial, the job is picking from the same micrographs used to train the model, a properly trained model will infer picks that were not used as training picks from the micrographs.

Step 4 - Acquire Particles from Topaz Extract

Select Extract from Micrographs from the Job Builder. Drag and drop both the micrographs and the particles outputs from the Topaz Extract job into the corresponding inputs on Job Builder.

Queue the job.

This job will update the particle picks with information required for further processing.

Select 2D Classification from the Job Builder. Drag and drop the particles output from the Extract from Micrographs job into the particles input of the 2D Classification job.

Queue the job.

Select Select 2D classes from the Job Builder. Drag and drop both outputs of the 2D Classification job into their corresponding inputs in the Select 2D classes job.

Queue the job.

Wait for the job status to change to "Waiting" and then select the particle templates that should be kept for further processing.

The 2D Classification and Select 2D classes jobs serve to filter out unwanted particles from the particle picking. Once the Select 2D classes job is complete, the particles output from the job can be used as particle picks to process further into the pipeline.

Next Steps

Now that a basic Topaz pipeline has been completed, the more advanced aspects of particle picking with Topaz can be explored. The following are some of these aspects:

Ideally, deep picking models are trained on a subset of micrographs and then perform inference on an entire dataset, as mentioned before. The Topaz model trained in this tutorial can be applied to the entire T20S dataset rather than the subset used in this tutorial. Potential refinement results will improve with the resultant increased number of picks.

The Topaz Train and Topaz Cross Validation jobs has many training parameters that can be fine tuned to affect the quality of the model.