Talk Abstracts

Analyzing Big Data from Big Brains

KEYNOTE SPEAKER
Terrence Sejnowski, PhD, Francis Crick Professor, Computational Neurobiology Laboratory, Salk Institute for Biological Studies
As the BRAIN Initiative develops new neurotechniques that generate bigger and bigger data sets, new methods for analyzing these data are needed. We have developed new methods to analyze global brain states in large-scale recordings from humans.

Data Subject to Restrictions at MARCC

Jaime E. Combariza, PhD, Associate Research Professor, Department of Chemistry, Krieger School of Arts and Sciences, Johns Hopkins University; Director, Maryland Advanced Research Computing Center (MARCC)
The Maryland Advanced Research Computing Center (MARCC) completed its first year of operation on June 30, 2016. In this extremely successful first year, over 800 user accounts have been created with the involvement of over 190 Principal Investigators. The system currently boasts over 300 active users investigating a diverse range of scientific projects that range … Continued

How much cancer can we cure with the immune system?

KEYNOTE SPEAKER
Drew Pardoll, MD, PhD, Ableoff Professor of Oncology, Director, Cancer Immunology, Director, Bloomberg~Kimmel Institute for Cancer Immunotherapy, School of Medicine, Johns Hopkins University

In pursuit of DNA and RNA Amalgamations

Seed Fund Update
Sarah J. Wheelan, MD, PhD, Associate Professor, School of Medicine, Johns Hopkins University
Protein-coding sequences (genes) are not contiguous in the genome; rather, the pre-mRNA transcripts derived from these regions are cut into pieces and assembled into a final, mature mRNA that is exported from the nucleus and translated into a protein. The machinery that performs this cutting and pasting called splicing is thought to have very high … Continued

Metabolic Compass: A Mobile Health Platform for Understanding the Impact of Circadian Sleeping, Eating and Exercise Behaviors on Metabolic Syndrome, and Obesity

Seed Fund Update
Jeanne Clark, MD, MPH1 and Yanif Ahman, PhD2, [1] Director, Division of General Internal Medicine, School of Medicine, Johns Hopkins University; [2] Assistant Professor, Department of Computer Science, Johns Hopkins University
Circadian rhythms drive much of our health, but are not well understood. Our App, Metabolic Compass, is designed to collect information on when we eat, when we sleep, and when we exercise. These events are displayed for users to quickly see their daily behavior within a weekly context. Our long-term goal is an understanding of … Continued

Navigating tens of thousands of RNA-seq datasets with recount, SciServer and Jupyter

Ben Langmead, Department of Computer Science, Whiting School of Engineering, Johns Hopkins University
RNA sequencing is a ubiquitous tool for assaying gene expression. Public sequencing data archives such as the Sequence Read Archive now hold more than 50,000 human RNA-seq samples, and the size of the archive doubles approximately every 18 months. Many of these archived studies are valuable to biological researchers and methods developers. However, samples are … Continued

Opening Remarks

S. Alexander Szalay, PhD, Director of IDIES, Professor of Astrophysics & Computer Science, Johns Hopkins University

Optimization Challenges for Cost-Sensitive Model Prediction with Applications in Healthcare

Daniel P. Robinson, PhD, Assistant Professor, Applied Mathematics and Statistics, Whiting School of Engineering, Johns Hopkins University
I present a key challenge to incorporating user preferences into model prediction problems when the costs do not occur at the feature level of the underlying cost structure. Problems in healthcare, e.g., the prediction of adverse medical events such as Septic Shock, are important examples of such problems. During this talk I present a solution … Continued

Scalable Framework for Statistical Inference on Big Multimodal Data via Sketching and Concentration

Seed Fund Update
Vladimir Braverman, PhD, Assistant Professor, Department of Computer Science, Whiting School of Engineering, Johns Hopkins University
Our goal is to develop scalable frameworks for statistical inference of multimodal high dimensional, large and complex data. For example, community detection for large graphs can often be approximated on a sketched version of the given graph, in which the inherent dimension is much smaller than the number of vertices. We propose to develop efficient … Continued

SciServer Compute: Bringing Analysis Close to the Data

Mike Rippin, PhD, Institute for Data Intensive Engineering and Science, Johns Hopkins University
SciServer Compute is a recent addition to SciServer, a Big Data infrastructure project developed at Johns Hopkins University that provides a common environment for sharable, computationally-intensive research. SciServer Compute implements Jupyter notebooks in Docker containers to bring advanced analysis capabilities close to Terabyte-scale relational databases and Petabyte-scale file storage systems. In addition to real-time analysis … Continued

The ‘Sixth’ Factor — Social Media Factor Derived Directly from Tweet Sentiments

Jim Kyung-Soo Liew, PhD, Assistant Professor in Finance, Carey Business School, Johns Hopkins University
In this work, we document that the characteristics of securities derived from social media have significant power in explaining the time-series variation in daily stock returns. We examine the recent period from January 4, 2012 to October 30, 2015 in conjunction with direct tweet sentiments as provided by StockTwits. Notably, our “Social Media company-specific” factor … Continued

Towards the Johns Hopkins Ocean Circulation Database: Method Development and Prototype

Seed Fund Update
Thomas Haine, PhD, Morton K. Blaustein Chair and Professor of the Earth & Planetary Sciences Department, Krieger School of Arts and Sciences, Johns Hopkins University
Numerical ocean circulation models are getting more and more realistic, but tools to analyze the model output are still primitive. We are using our seed fund award to develop a prototype environment that will make ocean-model output analysis easy, fast, and (eventually) accessible to the general public. We envision tools to enable on-the-fly analysis of … Continued

Using Causal Inference to Make Sense of Messy Data

Ilya Shpitser, PhD, John C. Malone Assistant Professor, Department of Computer Science, Whiting School of Engineering, Johns Hopkins University
The mission of the Malone Center for Engineering in Healthcare is to catalyze and accelerate the development of research-based innovations that advance the effectiveness and efficiency of health care. In this talk I will discuss how my work on missing data and causal inference fits in with the Center’s mission by helping us make sense … Continued