Image-based profiling using deep learning
DeepProfiler is a set of tools that allow you to use deep learning for analyzing imaging data in high-throughput biological experiments. Please, see our Wiki documentation page for more details about how to use it.
Quick Guide
Clone or fork this repository and install it using:
pip install -e .
When running DeepProfiler you usually need to specify a root directory where your data is stored and a command that you want to run. For instance, to initialize your project, you can use:
python deepprofiler --root=/home/ubuntu/project setup
In the created directories, you will need to organize your input files, including metadata, images and single-cell locations. See more details about the project structure here.
Next, if you want to train a model, as specified in the configuration file, you can then run the following command:
python deepprofiler --root=/home/ubuntu/project/ train
And to extract single-cell embeddings, use:
python deepprofiler --root=/home/ubuntu/project/ profile
Find more information in the training and profiling section of our wiki.
Happy profiling!