IC Colloquium: Learning hidden signatures in biomedical data across space and time
By: David van Dijk - Yale University
Video of his talk
Abstract
New biomedical measurement technologies, including single-cell sequencing and imaging modalities, contain a wealth of information that promise unparalleled insight into biology. However, our ability to model and analyze this information is currently limited by the high dimensionality and large sample numbers inherent to these datasets. In this talk, I will present a number of recently developed algorithms that can discover hidden signatures in large biomedical datasets, including brain imaging recordings and single-cell sequencing data. These algorithms are inspired by ideas from manifold learning, graph-signal processing, computer vision, and natural language processing, and provide new representations of spatiotemporal data that allow meaningful insight into the underlying biology.
Bio
Dr. David van Dijk is an Assistant Professor in the departments of Computer Science and Internal Medicine at Yale University where he leads a research group focusing on the development of ML/AI algorithms for large biomedical datasets. Dr. van Dijk completed his PhD in Computer Science at the University of Amsterdam and the Weizmann Institute of Science where he used ML to decipher links between DNA sequence and gene activity. Dr. van Dijk moved on to postdoctoral fellow positions at Columbia University and Yale University where he developed manifold learning and machine learning algorithms for single-cell genomic data. His current research focus is in developing machine learning algorithms, inspired by ideas from computer vision and natural language processing, that are capable of discovering underlying principles of biological functioning from large biomedical datasets, including single-cell RNA sequencing, health records, medical imaging, and brain activity recordings. Dr. van Dijk is recipient of the Dutch Research Council Rubicon fellowship and the NIH R35 Maximizing Investigators' Research Award.
More information
Video of his talk
Abstract
New biomedical measurement technologies, including single-cell sequencing and imaging modalities, contain a wealth of information that promise unparalleled insight into biology. However, our ability to model and analyze this information is currently limited by the high dimensionality and large sample numbers inherent to these datasets. In this talk, I will present a number of recently developed algorithms that can discover hidden signatures in large biomedical datasets, including brain imaging recordings and single-cell sequencing data. These algorithms are inspired by ideas from manifold learning, graph-signal processing, computer vision, and natural language processing, and provide new representations of spatiotemporal data that allow meaningful insight into the underlying biology.
Bio
Dr. David van Dijk is an Assistant Professor in the departments of Computer Science and Internal Medicine at Yale University where he leads a research group focusing on the development of ML/AI algorithms for large biomedical datasets. Dr. van Dijk completed his PhD in Computer Science at the University of Amsterdam and the Weizmann Institute of Science where he used ML to decipher links between DNA sequence and gene activity. Dr. van Dijk moved on to postdoctoral fellow positions at Columbia University and Yale University where he developed manifold learning and machine learning algorithms for single-cell genomic data. His current research focus is in developing machine learning algorithms, inspired by ideas from computer vision and natural language processing, that are capable of discovering underlying principles of biological functioning from large biomedical datasets, including single-cell RNA sequencing, health records, medical imaging, and brain activity recordings. Dr. van Dijk is recipient of the Dutch Research Council Rubicon fellowship and the NIH R35 Maximizing Investigators' Research Award.
More information
Practical information
- General public
- Free
- This event is internal
Contact
- Host: Maria Brbic