Presenter: Roni Rosenfeld, PhD

Epidemics can and should be forecast, to improve decision making by governments, institutions and individuals.  The goal of the Delphi group at Carnegie Mellon University is to make epidemiological forecasting as universally accepted and useful as weather forecasting is today.

Presenter: Charles Jonassaint, PhD

The overarching goal of Dr. Jonassaint’s program of research is to improve behavioral and physical health and reduce health disparities by using mobile multimedia technology to deliver evidence-based interventions to underserved populations.

Presenter: Maria Chikina, PhD

Genome scale molecular datasets are often highly structured, with many correlated observations. This general phenomenon can be related to the underlying data generating process.

Presenter: Hyun Jung Park, PhD, MS

Cancer is often associated with aberrant gene expression at the post-transcriptional level. However, it has not been fully understood how post-transcriptional regulation alters gene expression for cancer. Since hundreds RNAs interact with otherhundreds RNAs simultaneously at the level, their tumorigenic mechanisms need to be understood in consideration of the interactions.

Presenter: Shyam Visweswaran, MD, PhD & Jonathan Silverstein, MD, MS
Presenter: Vanathi Gopalakrishnan, PhD

The PRoBE laboratory for Pattern Recognition from Biomedical Evidence has been studying genomic, proteomic,  imaging, microbiome and metabolomics data for early detection and monitoring of diverse diseases including cancers of the lung, breast and esophagus, as well as adverse cardiovascular events.

Presenter: Victoria Khersonsky
Presenter: Joel Saltz, PhD

In this presentation, I will survey the development of Digital Pathology methodology beginning with the 1997 virtual microscope prototype at Hopkins to current tools, methods and algorithms designed to display, analyze and classify whole slide imaging data.  I will describe methods, tools and algorithms to extract information from Pathology images.  These tools include ability to traverse whole slide images, segment nuclei, carry out deep learning r

Presenter: Lifan Liang, MS & Menna Abaye, BA

Lifan's Abstract:  Integrating multiple sources of biological data has great potential to provide a better understanding of how genes function together. This study adopted the multiplex framework to integrate different high-throughput data for functional module identification. Our results showed that, with appropriate clustering algorithms, the multiplex formulation achieved a better accuracy for functional module identification.

Presenter: Yifan Xue, MS & Pritika Dasgupta, MS

Yifan's Abstract: Somatic genome alterations (SGAs) are one of the major causes of cancer. Among all the genetic alterations observed in a cancer cell, only a small fraction, known as drivers, directly contribute to tumor growth. The set of drivers in each tumor preserves most of the tumor-specific oncogenic information.