ahujalab/camage repository overview

This is the repo of the official Docker image⁠ for CamAge.

You can find instructions for installing and running Docker on any PC using the following links⁠

1. Windows⁠
2. MacOS⁠
3. Linux⁠

⁠Pulling the CamAge Image

Pull the CamAge image from Docker Hub by running the following command in your terminal:

$ docker pull ahujalab/camage:latest

⁠Verifying the Image

Verify the new image has been created using the docker images command.

$ docker images

⁠Accessing the Docker Image Terminal

To access the terminal of a Docker container, use the docker run command with the -it option.

$ docker run -it <image-name> bash

⁠Managing Containers

Replace <image-name> with the name or ID of the Docker image of CamAge.

Find the ID of the currently running container for input and output.

$ docker ps -a

To start the container again, access its terminal.

$ docker start <container-ID>
$ docker exec -it <container-ID> bash

⁠Input/Output

⁠Input

Find the ID of the running container using the docker ps -a command.

$ docker ps -a

To write a file to the container, use the docker cp command to copy it from the host to the container.

$ docker cp file container_id:WDir/

This command will copy the folder from the host's current directory to the CamAge container with ID container_id at the WDir/ directory inside the container.

⁠Output

Find the ID of the running container using the docker ps -a command.

$ docker ps -a

To write a file from the container, use the docker cp command to copy it to the host.

$ docker cp container_id:WDir/file-name .

This command will copy the folder from the CamAge container with ID container_id under the WDir/ directory inside the container to the host's current directory.

⁠Running CamAge

There are two CamAge Docker images available: one optimized for GPU usage and the other for CPU. Users can select the appropriate image based on their specific requirements.

⁠1. Segmenter

This command segments yeast cell images.

$ segmenter -id raw_input_folder -od segmenter_output_folder

Additional arguments:

Returns:

~ masks: segmented file for the raw images
~ preprocessed_images: preprocessed images of raw yeast cells
~ compressed_masks.csv: compressed masked .csv for raw yeast cells

⁠2. Predictor

This command processes raw yeast images, converts them into single-cell yeast images, and provides CamAge predictions.

Basic Usage

$ predictor -id raw_input_folder -od prediction_output -segmented segmenter_output_folder -SCImages sc_output_folder

Advanced Usage

$ predictor -id raw_input_folder -od prediction_output -segmented segmenter_output_folder -SCImages sc_output_folder explainability -image_features -num_features 3 -bio_prediction

Additional arguments:

Returns:
~ Single-cell yeast images
~ Morphometric features
~ A .csv file containing CamAge predictions and bioactivity predictions
~ Explainability plots for predictions of each image

⁠1. Scripts

Detailed instructions on using the CamAge scripts are available at CamAge_Scripts⁠

⁠2. Datasets

The datasets used for developing CamAge can be downloaded from Zenodo⁠