We work in tight interdisciplinary teams each focusing on a single goal at a time.

We are trying to expand our modeling prowess with each model we release similar to how the team behind the Apollo program built up their moon landing capability (see NASA SP 287 page 8): we always try something new with each model release, but always build on the accumulated knowledge of what came before.

All groups are interdisciplinary and work standalone in a concerted push towards one goal, one model release trying to fragment their attention as little as possible. So we welcome collaborating around your computational biology "moonshots" as well, especially if they are aligned with our current open problems.

Drug Combination Group

Lead: Robert Sipos

Members: Dana Zemel Kristof Galambos Murat Cem Kose

We optimize models for drug combinations to predict possible synergies in a vast search space. Predicting synergy is a much more difficult task compared to predicting responses for mono treatments due to the worse signal-to-noise ratio. This also makes data harmonization more crucial.

Another focus is modeling advanced modalities, like antibody-drug conjugates (ADCs). Similarly to combinations in general, we developed solutions to match the antibodies with the best payload.

In vivo Biology Group

Lead: Imre Gaspar

Members: Valér Kaszas Balint Pfliegel Lucie Studena

In vivo data is scarce as it is expensive to generate. The in vivo biology team focuses on the transfer learning problem of using in vitro perturbation data (CRISPR, small molecule, etc., mainly from HT screens) to build in vivo predictive ML/AI models. Our approach is  to harmonize the different biosample domains through decomposition and in-model resynthesis that allows the model to learn from sample similarities while still being capable of distinguishing between the in vivo and in vitro domains.

Multimodal Learning Group

Lead: Laszlo Mero

Members: Csaba Gor Milan Sztilkovics Zsolt Gyüre Alex Sliz-Nagy Peter Frendl

In vitro data is diverse with multiple perturbation modalities and many possible endpoint measurements. We focus on enabling models to learn the underlying biology with high fidelity by combining datasets from different modalities. Our current project is creating a model for target discovery that combines CRISPR screens, PerturbSeq screens and drug modifier CRISPR data.

Beyond Oncology Team

Lead: Bence Szalai

Members: Bence Czako Gema Sanz Gerold Csendes

The Beyond oncology team specializes in applying virtual assay capabilities to new therapeutic areas beyond oncology, with a particular focus on immune system.

Our work is grounded in the idea that (perturbation) RNA-seq - bulk, single-cell, and spatial - provides a robust, scalable representation of cellular state, even outside traditional oncology settings. This approach is reflected in our participation in the Virtual Cell Challenge, where our "Mean Predictors" team achieved top-tier performance. 

TRAIL leadership

Scientific lead:

Kristof Szalay

CTO @ Turbine

Operations lead:

Gabor Kovacs

VP AI @ Turbine