- AutoGaitA simplifies, accelerates, and standardises gait analyses after body posture tracking with DeepLabCut and Simi Motion.
- AutoGaitA's first-level tools provide a wide range of automated kinematic analyses for each input video and AutoGaitA Group allows the comparison of up to six groups.
- AutoGaitA enables comparisons to be made across experimental conditions, species, disease states or genotypes.
- Despite being developed with gait data, AutoGaitA can be utilised for the analysis of any motor behaviour.
Note! Our documentation provides step-by-step walkthroughs of how to install autogaita for Windows and Mac
It is strongly recommended that a separate virtual environment for AutoGaitA is created (note that the approach below creates the virtual environment to your current directory):
-
Create the virtual environment
python -m venv env_gaita
-
After creation, activate the virtual environment via:
- Windows:
env_gaita\Scripts\activate - Mac:
source env_gaita/bin/activate
- Windows:
-
Once activated, install AutoGaitA in the virtual environment via pip:
pip install autogaita. -
Access the main user interface via
python -m autogaita. -
To update to the latest release (see the Releases panel on the right for the current version) activate your virtual environment & enter
pip install autogaita -U.
The AutoGaitA YouTube Channel provides tutorials for file preparation and instructions on how to use AutoGaitA
Please note that tutorial videos might not always reflect the most up-to-date version of our toolbox, especially in the beginning when things are regularly changing. We will make sure to record new videos whenever there are major changes, though.
We provide an example dataset in the example data folder of this repository, with a set of mice walking over differently wide beams and both the beam as well as body coordinates being tracked with DLC. Note that this dataset was used in our tutorial videos introducing AutoGaitA_DLC, AutoGaitA_Group and in our video explaining file preparation for AutoGaitA_DLC. We further provide a group folder there that can be used alongside the AutoGaitA_Group tutorial to confirm that users generate the same set of results following our instructions.
Annotation Table example and template files for AutoGaitA_DLC and AutoGaitA_Simi can be found in the annotation tables folder of this repository.
Users are advised to read the important note of that folder, use the template to enter their data's timestamp information and to then compare the resulting table with our example to check formatting. Users working with ImageJ/FIJI are encouraged to check out the AnnotationTable-Plugin developed by our contributor Luca Flemming.
The AutoGaitA Documentation provides complete guidelines on installation, file preparation, AutoGaitA GUIs, using AutoGaitA via the command line, installing FFmpeg for rotating 3D PCA videos, lists known issues and FAQ.
We strongly recommend users to pay attention to the custom joints and angles windows of AutoGaitA's first level toolboxes. Please see the relevant links below. These windows allow users to customise which columns of their data should be analysed and how angles should be computed.
By default, AutoGaitA DLC and AutoGaitA Simi implement standard values for mouse and human locomotion, respectively. If your analysis deviates from these standards (e.g. by focussing on another limb or a different species) you must change these values! You can find the window in the advanced configuration sections and once values are customised they remain for subsequent executions of AutoGaitA (i.e., until the program is closed).
Find out more about AutoGaitA's custom joints and angles:
- YouTube - AutoGaitA DLC Advanced Configuration
- YouTube - AutoGaitA Simi
- Documentation - AutoGaitA DLC
- Documentation - AutoGaitA Simi
Even though AutoGaitA's main focus is to automate and standardise gait analyses, our toolbox can be used to automate the analyses of any rhythmic behaviour of interest. For a proof-of-principle demonstration and an introduction of the general workflow of such analyses, see AutoCyclA - Automated Cycling Analysis with AutoGaitA.
If you use this code or data please cite our preprint.
AutoGaitA is licensed under GPL v3.0 and Forschungszentrum Jülich GmbH holds all copyrights.
The AutoGaitA software is provided without warranty of any kind, express or implied, including, but not limited to, the implied warranty of fitness for a particular purpose.
Luca Flemming - Undergraduate Student
Nicholas del Grosso - RSE Advisor
If you would like to contribute to the AutoGaitA toolbox, feel free to open a pull request or contact us at [email protected]!
We are looking forward to your input and ideas 😊