Machine learning in life sciences

what is it, when should it be used and how to avoid common pitfalls

Workshop Description:

This workshop will provide a high-level introduction to machine learning: what it is, its advantages and disadvantages compared to traditional modelling approaches and the types of scenarios where it may be the right tool for the job. We’ll contrast a few commonly used algorithms for constructing predictive models and explore some of their trade-offs. We will discuss common pitfalls in how machine learning is applied and evaluated, with a focus on its application in the life-sciences, to help participants recognize overly optimistic results. We will discuss how and why such errors arise and strategies to avoid them. We will make use of simulated and publicly available genomics and demographics data. However, the contents of the workshop will be directly applicable across a wide range of application areas.

Learning objectives:

At the end of the workshop, you will be able to:

• Understand some of the core concepts of machine learning
• Describe the different stages required to implement a machine learning solution
• Implement a basic machine learning pipeline in Python using scikit-learn
• Critically evaluate the use of machine learning in the life sciences literature

Trainers:

Ben Goudey (The University of Melbourne)

Target audience:

This workshop is aimed at participants who have some programming experience in Python as the workshop will involve writing and running commands in Python in a Jupyter notebook interface. No prior machine learning or statistical knowledge will be assumed.

Eligibility:

This free workshop is available to staff and students at The University of Melbourne and its affiliated institutes only. When registering for this event you must provide an email address for an affiliated institution, or your registration may be cancelled.

Required:

This is an in person, hands-on workshop and attendees must bring their own computers (and chargers) with access to WiFi. The workshop material is executed in a Jupyter notebook using Google Colab and a Google account is required (free).

Access

If you require any further information, or have any access requirements in order to participate in this workshop, please contact the workshop organiser Melbourne Bioinformatics as soon as possible to discuss your requirements: bioinformatics-training@nullunimelb.edu.au