This course will introduce life scientists to practical data science methods increasingly used in research, with a particular focus on statistics and machine learning, using Python as the language of choice. Participants will learn how to prepare, process, and visualise some key biological datatypes, and gain hands-on experience in training and evaluating machine learning models using publicly available data. 

The course will combine morning lectures (supported by short practical exercises where relevant) with afternoons working on group projects, providing independent, hands-on experience in applying what is learnt to research questions. Trainers and mentors will be available throughout to guide participants and offer advice and feedback.

 

Group projects

A central part of the course is the group project. You will work in small groups, applying machine learning approaches to a biological question of interest. These projects will follow a framework suggested by the mentors, but be driven by participants, with as much support and input from mentors as you need.

During the application process, you will be asked to indicate your preferences from a list of biological applications for the group project work. During the course, following a framework provided by project mentors, each group will finalise their project aims, collect and process data, and apply machine learning approaches to address their research question. Groups will receive regular feedback and support from mentors, and are expected to take an active role in driving their projects forward collaboratively.

There will be daily opportunities to present progress so far and receive feedback, and the projects will end with a flash-talk session on the last day, giving participants the opportunity to present the data, methods, and insights they have developed during the training.