Anas Toma
Nature of Work
Academic
Profession
Vice President for Innovation and Artificial Intelligence
Email Address
[email protected]
Office Phone
(+970) 9 2345113 Ext. 2170

Anas Toma

Nature of Work
Academic
Profession
Vice President for Innovation and Artificial Intelligence
Email Address
[email protected]
Office Phone
(+970) 9 2345113 Ext. 2170
Machine Learning and Data Mining for Bioinformatics (Master) - 467708
Course Title
Machine Learning and Data Mining for Bioinformatics (Master)
Course Number
467708
Instructor Name
Anas Toma
Contact Information
[email protected]
Semester(s) and academic year(s)
First Semester 2025
Compulsory / Elective
Compulsory
Course Description

This course introduces the core concepts and techniques of data mining and machine learning, with applications in bioinformatics and health care. It covers the knowledge discovery process, data understanding and preprocessing, frequent pattern mining, supervised learning, model evaluation, ensemble methods, and neural networks. Students apply these techniques to biological and biomedical datasets using Orange and Python libraries such as Scikit-Learn, TensorFlow and Keras.

Course Outline

  1. Introduction and Fundamentals: the KDD process, mining functions (classification, association, clustering, outlier analysis), and learning types
  2. Data Representation and Understanding: data types, statistical description, similarity and visualization
  3. Data Preprocessing: cleaning, outlier handling, integration, reduction and transformation
  4. Frequent Patterns, Association and Correlations
  5. Supervised Learning and Classification: decision trees, rule-based classification, SVM, k-NN, genetic algorithms and linear regression
  6. Neural Networks and Deep Learning
  7. Model Evaluation and Selection
  8. Improving Classification Accuracy: ensembles, bagging, random forests, boosting and class imbalance
Course Objectives

This course introduces the main techniques of machine learning and data mining, with a focus on applications in bioinformatics. Students learn the complete workflow, from exploring and preprocessing biological data to building and evaluating models that learn from patterns in complex biological information. The course emphasizes practical skills in data cleaning, analysis, visualization and modeling. It uses Orange, a visual tool for building and testing workflows interactively, alongside Scikit-Learn, TensorFlow and Keras. By the end, students will be able to design, implement and evaluate computational models that support bioinformatics research and clinical decision-making.

Intended learning Outcomes and Competences

By the end of the course, students will be able to:

  1. Introduction and Fundamentals: Explain the fundamentals of data mining and machine learning, including the main mining functions such as classification, association and clustering, and their uses in bioinformatics and health care.
  2. Data Understanding and Preprocessing: Explore, preprocess and visualize biological and biomedical datasets, including detecting and handling outliers.
  3. Frequent Patterns and Association: Apply frequent pattern and association rule mining to biomedical data.
  4. Supervised Learning and Model Evaluation: Build, optimize and evaluate supervised and deep learning models for problems such as disease prediction.
  5. Tools and Implementation: Implement these techniques using Orange, Scikit-Learn, TensorFlow and Keras.
Textbook and References

Textbooks:

  • Aurélien Géron. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. 2nd Edition. O'Reilly Media, 2019. ISBN: 1492032646, 978-1492032649.
  • Jiawei Han, Jian Pei, Micheline Kamber. Data Mining: Concepts and Techniques. 3rd Edition. Elsevier, 2011. ISBN: 0123814804, 9780123814807.

Tools:

Assessment Criteria
Activity Percent (%)
Midterm 30%
HWs/Project 35%
Final 35%