- Course overview
- Search within this course
- What is machine learning?
- ML in drug discovery: why now?
- ML in the drug discovery pipeline
- Hands-on with WEKA
- Identifying targets for cancer using gene expression profiles
- Other tools utilising ML or NLP for drug discovery
- Summary
- Your feedback
- Learn more
- References
All materials are free cultural works licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) license, except where further licensing details are provided.
Getting started in ML using WEKA
Machine learning models can be developed using Python (e.g., Scikit-learn, TensorFlow, Keras, PyTorch), R, Matlab, and WEKA among many others. Here we will look at WEKA for an in-depth hands-on tutorial.
WEKA [12] is an easy-to-use java-based toolbox that provides a graphical user interface for the development of machine learning models and visualisation of data sets. It includes most of the functions necessary to perform a variety of machine learning tasks, such as classification, clustering, association rules mining, features selection, linear regression, gaussian processes and others.
WEKA is a useful tool for quick prototyping of ML models since it does not require writing code, and it is particularly suitable for learning ML principles without prior programming experience. However, it is also possible to write java code to programmatically run WEKA, and use the command line interface (explained later in this section) to run WEKA commands.Additionally, WEKA offers integration with popular programming languages including Python and R.
Variations on WEKA are available for other specialised purposes such as MEKA (multi-label classification) and deep learning with WEKA.
Let’s get started by downloading and installing WEKA to your computer.
To run WEKA, use the command line (e.g. iTerm or Terminal):
- Go to the directory where WEKA is stored
- Run the command: java -jar weka.jar
Alternatively, for Windows users, WEKA can be launched via the Program Menu.