Lecture: 'Machine learning-driven modeling of immune receptors'
Deep learning has transformed protein science, enabling increasingly accurate structure prediction, protein language modeling, and generative protein design. Yet immune receptors remain a particularly difficult frontier: for antibodies and T cell receptors, accurate global folds are not sufficient. Binding specificity, cross-reactivity, and affinity are governed by flexible interfaces where current structure prediction models often have the lowest confidence.
In this talk, I will discuss our work developing machine learning approaches to model B and T cell receptor recognition. I will first introduce how molecular dynamics-informed generative models can capture TCR conformational ensembles beyond static structures, with implications for predicting peptide recognition and cross-reactivity. I will then describe graph-based models of antibody–antigen affinity that integrate structural representations with protein language model embeddings to improve generalization across antibody families and antigens. Finally, I will present ongoing work on the de novo design of peptides in the context of autoimmune diseases, as well as strategies for fine-tuning protein language models to improve zero-shot ranking of immune receptor–ligand interactions.
Together, these examples illustrate a central theme: the next generation of immune receptor modeling will require moving beyond static structure prediction toward models that integrate sequence, structure, dynamics, and biophysical constraints at the binding interface.
About the speaker
Prof. María Rodríguez Martínez is an Associate Professor of Biomedical Informatics & Data Science at Yale School of Medicine and a member of the Center for Systems and Engineering Immunology. Her research lies at the intersection of artificial intelligence and immunology, where she develops interpretable and generative deep learning approaches to model adaptive immune receptors. She integrates deep learning approaches for protein modeling, including protein language models and structure prediction, with experimental data such as high-throughput immune repertoire sequencing and multimodal datasets to decode sequence–structure–function relationships in T and B cell receptors. Her work has applications in autoimmune disease, vaccine design, and next-generation immunotherapies.
Before joining Yale, María spent a decade at IBM Research Europe, where she led the Computational Systems Biology team and coordinated large interdisciplinary consortia, including EU-funded initiatives in personalized cancer medicine. Her research during this period advanced machine-learning methods for modeling tumor evolution, drug response, and immune–tumor interactions.
María’s academic career spans physics and systems biology. She has published widely on machine learning for computational biology, immune repertoire dynamics, and structure-based prediction of biomolecular interactions. Her work bridges computational biology, machine learning, and immunology, with an emphasis on interpretable models that can accelerate biological discovery and translational applications.
Deep learning has transformed protein science, enabling increasingly accurate structure prediction, protein language modeling, and generative protein design. Yet immune receptors remain a particularly difficult frontier: for antibodies and T cell receptors, accurate global folds are not sufficient. Binding specificity, cross-reactivity, and affinity are governed by flexible interfaces where current structure prediction models often have the lowest confidence.
In this talk, I will discuss our work developing machine learning approaches to model B and T cell receptor recognition. I will first introduce how molecular dynamics-informed generative models can capture TCR conformational ensembles beyond static structures, with implications for predicting peptide recognition and cross-reactivity. I will then describe graph-based models of antibody–antigen affinity that integrate structural representations with protein language model embeddings to improve generalization across antibody families and antigens. Finally, I will present ongoing work on the de novo design of peptides in the context of autoimmune diseases, as well as strategies for fine-tuning protein language models to improve zero-shot ranking of immune receptor–ligand interactions.
Together, these examples illustrate a central theme: the next generation of immune receptor modeling will require moving beyond static structure prediction toward models that integrate sequence, structure, dynamics, and biophysical constraints at the binding interface.
About the speaker
Prof. María Rodríguez Martínez is an Associate Professor of Biomedical Informatics & Data Science at Yale School of Medicine and a member of the Center for Systems and Engineering Immunology. Her research lies at the intersection of artificial intelligence and immunology, where she develops interpretable and generative deep learning approaches to model adaptive immune receptors. She integrates deep learning approaches for protein modeling, including protein language models and structure prediction, with experimental data such as high-throughput immune repertoire sequencing and multimodal datasets to decode sequence–structure–function relationships in T and B cell receptors. Her work has applications in autoimmune disease, vaccine design, and next-generation immunotherapies.
Before joining Yale, María spent a decade at IBM Research Europe, where she led the Computational Systems Biology team and coordinated large interdisciplinary consortia, including EU-funded initiatives in personalized cancer medicine. Her research during this period advanced machine-learning methods for modeling tumor evolution, drug response, and immune–tumor interactions.
María’s academic career spans physics and systems biology. She has published widely on machine learning for computational biology, immune repertoire dynamics, and structure-based prediction of biomolecular interactions. Her work bridges computational biology, machine learning, and immunology, with an emphasis on interpretable models that can accelerate biological discovery and translational applications.
On-site event
Thursday, October 22, 2026
1792627200000
/events/lecture-machine-learning-driven-modeling-of-immune-receptors
events_en