Metagenomics Diagnosis for Inflammatory Bowel Disease Challenge (MEDIC)

Metagenomics Diagnosis for Inflammatory Bowel Disease Challenge (MEDIC)

 This challenge is directed towards finding the best classification algorithm that can be used in diagnosing Inflammatory Bowel Disease with data obtained from non-invasive clinical samples, and it comes with a prize-pool of $12,000. The finalists will also have the opportunity to collaborate with leading biologists and data scientists, and to publish their findings in peer-reviewed journals.


Currently open the Metagenomics Diagnosis for Inflammatory Bowel Disease Challenge, which is organized as part of the sbv IMPROVER project, aims to investigate the diagnostic potential of metagenomics data to classify patients with Inflammatory Bowel Disease (IBD) and non-IBD subjects. Futhermore, within the IBD category, the participants with have to attempt to classify Ulcerative Colitis (UC) and Crohn’s Disease (CD) subjects. 

So, here is our question to you: Can you predict IBD status using metagenomics data?


The Metagenomics Diagnosis for IBD Challenge (MEDIC) aims to verify that shotgun metagenomics sequencing data is sufficiently informativs to allow for accurate classification of human subjects (Figure 1) as:

    1. IBD vs. non-IBD
    2. UC vs. non-IBD
    3. CD vs. non-IBD
    4. UC vs. CD

    The Challenge is split into two sub-challenges:

    • In the first sub-challenge (“MEDIC RAW”), you are provided with shotgun metagenomics sequencing reads, so that you will have the possibility to process metagenomics data with your analysis pipeline to address the Challenge.
    • In the second sub-challenge (“MEDIC PROCESSED”), you are provided with pre-calculated taxonomic and pathway abundances matrices derived from the raw data. This will allow data scientists with no access to metagenomics analysis pipelines to solve the Challenge, as well as to compare the performance of classification methods beyond the role of pre-processing steps.


    Figure 1. Schematic representation of the challenge and its two sub-challenges. 

    Scientific Questions

    The Challenge aims to answer the following scientific questions:

    • Which predictive computational approaches are the most accurate across the four 2-class problems described above?
    • What do the most discriminative metagenomic features tell us?

    a) Are they rather based on taxonomy, functions/pathways and/or other types, e.g., k-mers?
    b) Are they distinct between UC vs non-IBD and CD vs non-IBD or do they show commonalities? 


    The Challenge was open until February 29th, 2020. This challenge is now closed.



    Leaflet, poster and other information sources can be found in the resources section. Feel free to share the electronic versions with your network and colleagues. If you also have the possibility to share a print version, please contact us, and we will be happy to send you reprints of the poster and leaflets.

    Stay tuned and contact us if you want to make sure receive timely information about this new challenge!

    Share this page