ADAP-BIG-V2 is a software that detects peaks in mass spectrometry data using object detection and image processing through the YOLOv5 algorithm and preprocessing blocking methods.
Model training notebook: https://colab.research.google.com/drive/1Zfc0K-rSsAA366ymqeoTUNEbx3bATYP8?usp=sharing
Labeling website: hasty.ai
Export YoloV5 Pytorch formatted data: roboflow.com
CD to the folder with requirements.txt and run this command in the terminal:
pip install requirements.txt
python adap_3d_main.py
Navigate to params.py in the adap-3d-cli directory and adjust parameters in this module
YoloV5 inferences stored in the cloned repo runs folder.
Exports one .csv
file to user specified results path
(user can specify in params.py
) containing:
- Block # peak is located in
- M/Z value of peak
- Retention Time value of peak
- M/Z and Retention Time ranges
- Confidence of model on specified peak
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Please make sure to update tests as appropriate.