It all started in my kitchen. After eating a homemade carrot salad one evening, I noticed that the inside of my mouth had become swollen. Later, I learned that pollen-related food allergies can sometimes trigger such reactions. The experience left me wondering: could we know in advance whether a food might trigger an allergic reaction?

Around the same time, Merlin and I joined Prof. Kjell Jorner’s Digital Chemistry course at ETH out of curiosity about AI in the life sciences. Over lunch, we began exploring whether AI could help predict allergenic proteins beyond those already catalogued. Encouraged by early conversations with allergy researcher Katja Bärenfaller at the Swiss Institute of Allergy and Asthma Research (SIAF), we decided to pursue the idea.

This grew into XAllergen, a model designed to predict protein allergenicity accurately while providing interpretable explanations. Yet one question remained: what exactly do these AI explanations capture, and how closely do they align with established immunological knowledge?

To investigate this further, we continued the project through an ETH Studios internship at SIAF. Arriving in Davos, we found ourselves surrounded not only by snow-covered mountains, but also by a welcoming scientific community.

Through weekly institute meetings and conversations over lunch, we met researchers working across different areas of immunology. These interactions helped us better understand the immunological context of our project and ask more meaningful biological questions.

We were particularly grateful to our supervisors, Katja Bärenfaller and Damir Zhakparov, who encouraged us to challenge assumptions and explore uncertain directions. This open and supportive environment gave us the confidence to continue working on a challenging problem at the intersection of AI and immunology.

We found that the regions highlighted by current AI models often captured signals that were useful for prediction, but did not consistently match the parts of proteins that immunologists believe are responsible for triggering allergic responses. This matters because such models are increasingly used for safety screening of new food proteins and could one day help develop foods like carrots that no longer cause allergy. Our results suggest that strong predictive performance does not necessarily imply alignment with established biological mechanisms.

Looking back, this experience taught us that curiosity-driven research often follows an unpredictable path. A simple observation in a student kitchen led to a course project at ETH, an internship in Davos, and ultimately a scientific finding. The project will continue beyond Davos through presentations and discussions with the international machine learning and computational biology community, but it has already reinforced a lesson we will carry forward: even when the answer is uncertain, follow a simple question and see where it leads. You may discover something you never expected to find.

Further reading

• Yao J., Song A., Baerenfaller K., Zhakparov D. Residue-Level Attributions in Protein Language Models Do Not Recover Allergen Epitopes. arXiv:2606.22181 (2026). https://doi.org/10.48550/arXiv.2606.22181

Allegra! My name is Laura. I am a Computational Biologist currently finishing up my Master’s degree at ETH. For the past three months, I have been based at SIAF (Schweizer Institut für Allergie- und Asthmaforschung) working on an ETH Studio Davos project: building an isoform-specific database of the human proteome.

A Deep Dive into Immunology

Before the project even really started, I was invited to attend the World Immune Regulations Meeting (WIRM) organised by SIAF. It was an intense, whirlwind week of absorbing research from world-class immunologists, enjoying fantastic food, and networking with more people than I could keep track of. Especially the Gala Dinner on the last night was a lot of fun. I could not believe that a hundred immunologists would get up as soon as the music starts and dance for hours. I’m very grateful to my supervisor, Katja Baerenfaller, for inviting me to my first-ever scientific conference.

Life in the Alps

SIAF is located outside of the already remote mountain village of Davos. I was really excited to spend three months in the spring here to enjoy the change of seasons. I saw the mountains go from deep winter snow to the slow thaw that turns the landscape vibrant green. The Swiss Alps are one of my favorite places on earth and I think everybody should come here once in their life to go hiking and biking in the summer or skiing in the winter. During my time here, I managed to squeeze in some skiing with friends and went on some runs to explore Davos as the weather warmed up. The view from my office has gone from snowstorms in the middle of a really cold winter to beautiful snowy mountain tops and flowers blooming in the spring and early summer.

The Project

While the landscape was breathtaking, I spent the majority of my time in front of my computer. I was tasked with setting up a protein database—a challenge, considering I started with very little experience in database management. It was a steep but rewarding learning curve, offering me deep insights into how databases are structured and the nuances of proteomics data.

Once the database was ready, we re-ran data from previous lab experiments. The results are looking quite promising! I’m very happy with how the project has turned out and grateful for the time I’ve spent here.