https://github.com/akensert/single-peak-integration-using-dl
https://github.com/akensert/single-peak-integration-using-dl
Last synced: 12 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/akensert/single-peak-integration-using-dl
- Owner: akensert
- Created: 2023-03-29T15:07:04.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2024-02-22T11:07:26.000Z (over 2 years ago)
- Last Synced: 2025-02-04T21:17:19.021Z (over 1 year ago)
- Language: Python
- Size: 58.6 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Peak integration using deep learning
## About
Single chromatographic peaks are extracted using convolutional neural networks; variances of the peaks can then be calcualted, and subsequently used to estimate protein diffusion coefficients.
## Requriements
- Python ~= 3.10
- Pip ~= 22.0.2
- Python packages, see `requirements.txt`
## Usage
### Training
Add chromatograms (containing single peaks) in `automatic_peak_integration/inputs/train_files/`. Each chromatogram should be an Excel file with four columns: time, signal, \[only first row\] start time of peak, \[only first row\] end time of peak.
Then navigate to `automatic_peak_integration/scripts/` and run, from terminal: `python train.py`.
When training is done, model is saved in `automatic_peak_integration/models/`.
### Predicting (integrating peaks)
Add chromatograms (containing single peaks) in `automatic_peak_integration/inputs/files/`. Each chromatogram should be a txt file with two columns (tab separated): time, signal.
Then navigate to `automatic_peak_integration/scripts/` and run, from terminal: `python integrate.py`
When finished, output is saved in `automatic_peak_integration/outputs/`.