This method supports for Windows, Linux and macOS operating systems (recommended for Windows).
CPUs: Minimum 2 cores
Memory (RAM): Minimum 4GB
swap (in docker setting): Minimum 8GB
For installing the Docker, please follow the instructions from each link depending on your operating system:
- Windows: https://docs.docker.com/docker-for-windows/install/
- macOS: https://docs.docker.com/docker-for-mac/install/
- CentOS: https://docs.docker.com/engine/install/centos/
- Debian: https://docs.docker.com/engine/install/debian/
- Fedora: https://docs.docker.com/engine/install/fedora/
- Ubuntu: https://docs.docker.com/engine/install/ubuntu/
The LigEGFR_docker.tar.gz
file provides at https://zenodo.org/record/4362561 and then extract file by
tar -xzvf LigEGFR_docker.tar.gz
Basically, the organization of LigEGFR_docker
folder contains files and directories as below.
A valid organization of a directory:
├── cdk-2.3.jar
├── DockerFile
├── examples
│ ├── structure*.sdf
├── models
│ ├── __init__.py
│ ├── applicabilityDomain.py
│ ├── cleanSmiles.py
│ ├── csgen.py
│ ├── fingerprint.py
│ ├── knnpickle_file
│ ├── longlist.py
│ ├── model.py
│ ├── model256.model
│ ├── mydataset.py
│ └── tobject.py
└── run_predict.py
This step will build docker image based-on CentOS7, it will be taken time ~6 mins and storage ~5.26GB.
cd LigEGFR_docker
docker build -t ligegfr .
For prediction, please add input qeury.sdf
file, this file consists of multi-compounds in sdf format.
docker run -it --cpus="2" --memory="4g" --memory-swap="8g" --name lig1 --rm -i --mount type=bind,source=%cd%,target=/ligegfr ligegfr python3 run_predict.py query.sdf
docker run -it --cpus="2" --memory="4g" --memory-swap="8g" --name lig1 --rm -i --mount type=bind,source=$(pwd),target=/ligegfr ligegfr python3 run_predict.py query.sdf
Hardware specification is depends on your computer performance, it can be adjusted as appropriate. When the script is computed to finish, returning a LigEGFR_output.csv
file for prediction results. By the way, swap memory is normally adjusted by 2 times of RAM setting e.g. RAM = 4GB, swap = 8GB.
docker run -it --cpus="2" --memory="4g" --memory-swap="8g" --name lig1 --rm -i --mount type=bind,source=%cd%,target=/ligegfr ligegfr python3 run_predict.py examples/structure10.sdf
docker run -it --cpus="2" --memory="4g" --memory-swap="8g" --name lig1 --rm -i --mount type=bind,source=$(pwd),target=/ligegfr ligegfr python run_predict.py examples/structure250.sdf