**DOCUMENTATION OUTDATED** The documentation has moved to https://cryolo.readthedocs.io ===== Picking filaments - Using a model trained for your data ===== When picking filaments, it is important to identify each filament individually. This allows specific spacing of the boxes (i.e., the helical rise) to maximize the number of particles. CrYOLO supports this method of picking filaments. Filament mode on actin: {{:pipeline:window:action_tracing_2.png?300|}} {{:pipeline:window:action_traceing_1.png?300|}} Filament mode on MAVS (EMPIAR-10031) : {{:pipeline:window:filament_tracing_02.png?300|}} {{:pipeline:window:filament_tracing_03.png?300|}} ==== 1. Data preparation ==== {{ :pipeline:window:cryolo:settings_e2helixboxer_arrow.png?300|}} The first step is to create the training data for your model. Right now, you have to use the e2helixboxer.py for this: e2helixboxer.py --gui train_image/*.mrc After tracing your training data in e2helixboxer, export them using //File -> Save//. Unfortunately you have to do that with each image separately. **Adapt the file saving options** Make sure that you uncheck the boxes "Write Helices" and "Particle Images" and check the box "Particle Coordinates", as this the only format supported right now (see screenshot). Also remove the "_helix_ptcl_coords" suffix in the path field. The coordinate files have to have the same name as the micrographs. In the following example, it is expected that you exported into a folder called "train_annot". For projects with roughly 20 filaments per image we successfully trained on 40 images (=> 800 filaments). ==== 2. Start crYOLO ==== If you followed the installation instructions, you now have to activate the crYOLO virtual environment with source activate cryolo {{page>pipeline:window:cryolo:start_cryolo}} ==== 3. Configuration ==== {{page>pipeline:window:cryolo:configuration}}
► You can now press the [Start] button to create your configuration file.
Alternative: Create the configuration file using the command line
{{page>pipeline:window:cryolo:configuration_cmdl_normal}}
==== 4. Training ==== {{page>pipeline:window:cryolo:training}} ==== 5. Picking ==== Select the action prediction and fill all arguments in the “Required arguments” tab: {{ :pipeline:window:cryolo:cryolo_prediction_202003.png?700 |}} Now select the "Filament options" tab and check "Activate filament mode", specifiy the filament width (e.g. 100) and define the box distance (e.g. 20 for 90% overlap when using a box size if 200): {{ :pipeline:window:cryolo:cryolo_filament_202003.png?700 |}} The directory ''output_boxes'' will be created and all results are saved there. The format is the eman2 helix format with particle coordinates. **Import into Relion** You can find a detailed description [[:cryolo_filament_import_relion|how to import crYOLO filament coordinates into Relion here]].
► Press the [Start] button to start the picking.
Alternative: Run prediction in commmand line
Let's assume you want to pick a filament with a width of 100 pixels (-fw 100). The box size is 200x200 and you want a 90% overlap (-bd 20). Moreover, you wish that each filament has at least 6 boxes (-mn 6). The micrographs are in the ''full_data'' directory. Than the picking command would be: cryolo_predict.py -c config_cryolo.json -w cryolo_model.h5 -i full_data --filament -fw 100 -bd 20 -o boxes/ -g 0 -mn 6
==== 6. Visualize the results ==== {{page>pipeline:window:cryolo:visualize}}