Calling Crunchers Worldwide to Contribute to Groundbreaking Research in Autoimmune Disease
Crunch Lab and The Eric and Wendy Schmidt Center invite you to join the Autoimmune Disease Machine Learning Challenge to design algorithms that will enable a more accurate diagnosis of inflammatory bowel disease (IBD), affecting millions of people worldwide.
In collaboration with
%20(2).png)
.png)
An extensive Dataset
A $50,000 Prize Pool
Transform
cancer treatment. Your code, patients' futures.
Our Cancer Immunotherapy Machine Learning Competition aims to harness the power of the immune system to combat cancer more effectively.
The challenge seeks to answer a critical question: How can we induce desired cell state changes in T cells?
With an expanded list of immune checkpoint targets, including PD-1, CTLA-4, LAG3, TIM3, and VISTA, our goal is to make immunotherapy a viable option for a broader range of patients and cancer types.
Over 2500 clinical trials underscore the potential of immune checkpoint inhibitors in revolutionizing cancer treatment.
To facilitate meaningful participation from crunchers across disciplines, we offer comprehensive educational resources.
Our recorded crash courses and MIT IAP course provide essential background in biomedical concepts relevant to the challenge.
These materials are designed to equip participants, regardless of their biological expertise, with the necessary knowledge to contribute effectively to this global initiative.
We encourage all interested researchers to review these courses as a first step towards engaging in this critical area of study.
Caroline Uhler and Nir Harcohen
Biology
Orr Ashenberg
Orr Ashenberg
Data
Orr Ashenberg
2025
Phases
The challenge is broken down into three Phases = Crunches, ordered by increasing complexity.
Crunch 1 – Oct 28 to Jan 31 –Predict gene expression in spatial transcriptomics data from matched pathology images
Crunchers will build a model to predict the expression of 460 genes in held-out patches of colon tissue using H&E pathology images and Xenium spatial transcriptomics training data. Hematoxylin and Eosin (H&E) images provide insight into cell organization, while Xenium data add information on gene expression and cellular pathways of disease.
Crunch 2 – Nov 18 to Jan 31 – Predicting Unseen Genes
In this phase, participants will predict the expression of all protein-coding genes, including those that were not measured in the spatial training data, using single-cell RNA-seq data as support. This Crunch focuses on leveraging cell transcriptional profiles to enhance the predictive model’s ability to infer the expression of unknown genes in spatial contexts.
Crunch 3 – Dec 9 to Jan 31 (submission deadline) / Feb 14 (peer review deadline) – Identifying Gene Markers for Pre-cancerous Regions
Participants will rank genes by their ability to distinguish between dysplasia (pre-cancerous) regions and noncancerous tissue in IBD patients, increasing our ability to detect cancer early. The final gene panel will be chosen based on participant performance in Crunch 2 and on peer review of participants' methods taking place after the submission deadline. The gene panel will be experimentally validated in a new colon tissue with dysplasia, and all participants' ranked gene lists will be scored.
Watch our lecture series for biology, technology, and data backgrounds needed to complete the challenge.
Each lecture guides participants through data handling, model training, and algorithm testing, emphasizing practical applications for advancing diagnosis, treatment prediction, and patient outcomes in autoimmune diseases.
It’s ideal for those participating in the challenge or interested in applying AI solutions in medical research.
The Schmidt Center is enabling a new field of interdisciplinary research at the intersection of the data and life sciences, aimed at improving human health. Our researchers and partners work together to make the biological questions of our time key drivers for foundational advances in machine learning — and vice versa.
Questions? Please email ericandwendyschmidtcenter@broadinstitute.org.
Crunch Lab is a quant boutique that helps large companies, investment firms, and financial institutions extract more value from their data. Crunch Lab works with data-rich companies to host Crunches, which are global ML competitions for the best and brightest in the CrunchDAO community.
CrunchDAO is an elite research community that develops alpha-generating insights through distributed ML competitions. The DAO consists of over 6,000 data scientists, quants and machine learning (ML) engineers, including 600 PhDs. DAO members can monetize their talents and expertise by competing in corporate Crunches.
-min.png)
