Posts

Ritambhara Singh Gives A Keynote At The International Caparica Conference On Prescriptomics And Precision Medicine

None
Click the links that follow for more news about Ritambhara Singh, other Brown CS recipients of this award, and other recent accomplishments by our faculty.

On May 11, Brown CS faculty member Ritambhara Singh gave a keynote address at the 1st International Caparica Conference on Prescriptomics and Precision Medicine, a biomedical conference on safety for precision medicine, which in its first iteration, focused on how researchers can develop models that leverage the properties of different biological or clinical data types that should be integrated to make accurate diagnostic predictions. Prescriptomics is an emerging field focusing on the complex interplay within genetics and their impact on the effectiveness, safety, and response to precision medicine.

In her talk, Ritambhara discussed how data integration has become crucial to understanding diseases, given the large-scale efforts to collect different measurements in genomics and biomedicine. Her initial work emphasized the piecing together of the many factors governing gene expression to understand how all of the parts can function as a whole. Ritambhara’s research has expanded to developing and applying data-aware deep learning models to genomics and clinical datasets to bring these pieces together effectively while modeling the underlying structures and relationships in the data.

“The conference successfully brought together a diverse set of researchers from the computational and mathematical domains to biologists to chemists to clinicians, all motivated to tackle diseases from different perspectives,” Ritambhara says. She adds that this resulted in interesting conversations about promising collaborations and associated challenges to making precision medicine a reality.

In her talk, Ritambhara introduced an advanced attention-based deep learning framework, which is designed to meticulously analyze and learn the intricate patterns found in various types of clinical information from Alzheimer’s patients. By leveraging these patterns, the framework aims to enhance the accuracy of diagnoses, integrating data from different sources, such as medical histories, cognitive test results, and imaging studies, to provide a comprehensive assessment. 

She also mentioned her work using graph-based deep learning architecture that captures the underlying 3D organization of DNA to integrate different genomic signals and connect them to gene expression via the prediction task.

Her keynote address slide deck can be found here and the book of abstracts for the conference can be found here.

For more information, click the link that follows to contact Brown CS Communications Manager Jesse C. Polhemus.