Innovative benchmarking approaches to improve computational methods for big data analysis in health

If analysed correctly, real health data is a valuable tool. COMETH develops a framework for assessing benchmarks to analyse health data and then trains health professionals to use that framework.


COMETH targets the need to evaluate novel computational methods and apply them directly to real health data sets, while also offering training to help professionals meet this need.

The programme will produce a benchmarking framework that can be used with the data that health professionals handle every day. To prove the usefulness of the benchmarking framework, the programme will apply it to quantification of cell heterogeneity in cancer, an area of study that can guide creation of improved cancer treatment strategies.

The COMETH programme also provides a digital platform containing statistical methods to be benchmarked and data sets to be developed by health data scientists, as well as a web application dedicated to direct use of these tools on novel clinical data sets provided by health professionals. These resources will be disseminated through training.

The COMETH course

To help professionals use the programme’s framework and online tools, COMETH will organise a two-day training course for clinicians and cancer pathologists on the application of these statistical methods.

Course overview

Course dates: 16-17 February 2021.

Hours of commitment: Fifteen hours of training over two days.

Price: Free of charge.

Mode of presentation: Online.

Is it for me?

The course especially targets clinicians, anatomopathologists, bioinformaticians and is open to all health professionals, research scientists and students with a general background in omics data.

Course curriculum

Day 1, 15 February 2020

9-9:30 am, Lecture: Introduction of COMETH project in brief: COMETH objectives, aim of the course.

9:30 -10:30 am, Lecture: Clinician’s point of view: Why does tumour heterogeneity quantification matter?

11am-noon, Lecture: Bioinformatician’s point of view: How to quantify tumour heterogeneity; overview of unsupervised/supervised computational methods.

2-3 pm, Practical work: Formatting and pre-treatment of the data.

3-5pm, Practical work: Presentation of the user-friendly COMETH web interface: Quantification of tumour heterogeneity using a model example provided by the trainers.

Day 2, 16 February 2020

9-10 am, Practical work: Selection of the computational methods of interest for each participant.

10am-noon, Practical work: Tumour heterogeneity quantification on participant’s datasets using selected algorithms.

2-2:45 pm, Lecture: Visualisation and interpretation of the results.

2:45-4 pm Practical work: Biological interpretation of participants results and discussions.

4-5 pm, Lecture: From scientific research to clinical usage: needs and perspectives.

Registration and information

See the course website for more information.

Register for the course by 17 December 2020.

Magali Richard
| Activity Lead | UGA