Systems Immunology: an intro to multi-omics data integration and machine learning course

Date

March 28/29th 2022

Instructor

Adriana Tomic, PhD
Systems Immunology, University of Oxford Oxford, UK

Email: info@adrianatomic.com

About

In this course, we will learn what is AI and how to apply it to biomedical research. Also, we will learn how to use SIMON – our recently developed open-source software for the application of machine learning to biological and clinical data.

Why SIMON: In SIMON, analysis is performed using an intuitive graphical user interface and standardized, automated machine learning approach allowing non-technical researchers to identify patterns and extract knowledge from high-dimensional data and build thousands of high-quality predictive models using 180+ machine learning algorithms. With an easy-to-use graphical user interface, standardized pipelines, and automated approach for machine learning and other statistical analysis methods, SIMON helps to identify optimal algorithms and provides a resource that empowers non-technical and technical researchers to identify crucial patterns in biomedical data.

If you plan to use machine learning to identify patterns in your data and want to learn more about SIMON and how to use it, you are all invited to join this Oxford Medical Science Division course.

Pre-read and prerequisite for the course

• Installation instructions: SIMON repository
• Step-by-step analysis instructions:SIMON manuscript
• Feature Engineering and Selection: A Practical Approach for Predictive Models by Max Kuhn and Kjell Johnson

Training course overview

Part 1 - SIMON, pattern recognition and knowledge extraction platform (March 28th 2022)

• Theoretical part - intorduction to machine learning

  • Machine learning and AI – what is all the fuss about?
  • What is SIMON?
  • Case study – example 1 - FluPRINT project

  Dealing with missing values, overfitting and evaluation of model performance

• Hands-on - introduction to SIMON software

  • analysis using provided dataset ('Cyclists')
  • performance metrics, evaluation, and selection of high-quality models
  • feature selection

Part 2 - Exploratory analysis using SIMON hands-on session (March 29th 2022)

• Hands-on

  • Perform SIMON analysis using provided dataset ('VAST')
  • Unsupervised ML

• Theoretical part - introduction to multi-omics data integration

  • Feature processing methods to avoid ‘curse of dimensionality'
  • Case study – example 2 (Multi-omics data integration) - COMBAT project