About this seminar Artificial Intelligence approaches for personalized medicine
Speker: María Rodríguez Martínez, IBM Research – Zurich.read more
About this seminar Artificial Intelligence approaches for personalized medicineIn recent years, AI has become a very active area of research in computer science, and models with astounding performances in a broad area of scientific disciplines have been developed. In computational biology, the recent availability of large amounts of data generated by large international consortia has made possible the application of deep learning and machine learning approaches to a vast set of problems.
In this talk, I will present current activities at the Computational Systems Biology group in IBM Research, Zurich that illustrate the application of AI approaches with the goal of unraveling disease mechanisms and developing personalized patient models. For instance, as a first example, I will show how deep learning models can be used to characterize tumor heterogeneity in single-cell proteomic data and define new quantitative measures of tumor progression. Next, I will illustrate how multi-modal neural networks can be trained to ingest disparate data types, predict drug sensitivity in cancer cell lines and enable personalized drug design.
3 recent publications:
- A single-cell atlas of tumor and immune cell heterogeneity in human breast cancer. Wagner et all, Cell, 11 April (2019). https://doi.org/10.1016/j.cell.2019.03.005
- PIMKL: Pathway Induced Multiple Kernel Learning. Manica et al. npj Systems Biology and Applications, 2019. https://www.nature.com/articles/s41540-019-0086-3
- Towards Explainable Anticancer Compound Sensitivity Prediction via Multimodal Attention-based Convolutional Encoders. Manica et al. 2019. In revision at Molecular Pharmaceutics. https://arxiv.org/abs/1904.11223
Friday 13 September 2019, 09:30 - 10:30 hrs.
Figdor Lecture Theatre, route 289
Registration not applicable
Michiel Vermeulen PhD