Plenary-07

Maria Rodriguez Martinez

Technical Leader of Computational Systems Biology

IBM Research – Zurich

Abstract:

In recent years, deep learning models have resulted in outstanding breakthrough performances. However, many models behave as black boxes that can hide data biases, incorrect hypotheses, or even software errors. In this talk, I will illustrate how interpretable deep learning models can achieve both high prediction accuracy and transparency. First, I will introduce multi-modal deep learning models that predict drug response while highlighting the genetic and chemical patterns that were more informative to make a prediction. I will also discuss how reinforcement learning approaches can facilitate the early phases of drug discovery and support the personalized design of new candidate compounds.

Shifting focus to T cell-based immunotherapies, I will present a model designed to predict the binding of T cell receptors and epitopes. This model can be coupled with an easy-to-use interpretable pipeline to extract the binding rules governing the T cell binding. These approaches are a first step towards the design and engineering of receptors of improved affinity. Furthermore, I will also illustrate how state-of-the-art large language models, applied to amino acid sequences and protein information, can substantially facilitate the prediction of immune receptor-related properties.

Finally, I will discuss the crucial need of integrating AI and mechanistic models to address current computational challenges and enable the personalized design of new therapeutic interventions. The fusion of AI and mechanistic understanding holds immense promise to revolutionize the field.