On Friday, May 2, 2014 in Distler Performance Hall,  Tufts University’s Office of the Vice Provost for Research held its 10th Research Day on Data Science. The objective of the day was to raise awareness of data science within the university community and to highlight current resources and research in this emerging interdisciplinary field. Data Science aims to make sense of the enormous amounts of data currently being created by modern technologies, such as sequencing techniques, electronic medical records, and social media outlets.

The event included a digital poster session and three lightning talk sessions with sixteen speakers highlighting techniques and applications of data science from across the University. Speakers and attendees joined in on the conversation on Twitter using the hashtag #JumboData throughout the day. 

 

Welcome Remarks & Program Overview

Video Presentation
Kirby Johnson on behalf of Diane L. Souvaine, Vice Provost for Research, Tufts University
Soha Hassoun, Associate Professor and Chair of Computer Science, School of Engineering 

 

Session I: Big Data Analysis: From Fundamentals to Engineering Applications 

Redefining Class Definitions Using Constraint-Based Clustering — Carla Brodley
Big Data Visual Analytics: A User-Centric Approach — Remco Chang
Big Data for Big Floods: Can We Break the Predictability Limits? — Shafiqul Islam
Computational Sensing: Bringing Physics to Big Data — Eric L. Miller
 

Session II: Data-Driven Discoveries

Harnessing Big Data in Psycholinguistics: Design and Data — Ariel Goldberg
MODIS Satellite Data and GAM models to Examine Urbanization as an Independent Predictor of Endothelial Dysfunction in a Large Southeast Asia Population — Kevin Lane
Virtual Cohorts and Big Data Analytics in Epidemiology — Elena Naumova
Using GIS, Spatial Epidemiology, and Hot Spot Analysis to Target  Nutrition Services —Thomas J. Stopka
Using Big Data to Study Urban Sentiments: Twitter Data vs. Published Meeting Minutes —Justin Hollander
Finding – and Not Crossing – The Ethics and Privacy Line in Using Big Data — Lisa Gualtieri
 

Session III: Data Enabling Medicine

Impact of Obesity on Intestinal Tumorigenesis – Searching for Answers in the Microbiome, Metabolome and Transcriptome: Studies by the HNRCA Cancer Cluster and Tufts Computational Biology Initiative — Jimmy W. Crott
Data Problems in Gut Microbiota Metabolomics — Kyongbum Lee
High-throughput Genetic Analysis of a Bacterial Pathogen — Andrew Camilli
Large Scale EEG Monitoring:  Is Dynamic Seizure Sensing Possible? — Chris Dulla
Understanding the Wiring of the Brain: Genome-Wide Analysis of Local Protein Synthesis — Joshua Ainsley
Loopfinder: Comprehensive Analysis of Hot Loops at Protein Interfaces as Targets for Macrocycle Inhibitors — Joshua Kritzer
 

Panel Presentation

Video Presentation
Infrastructural and Education Needs for Data Science at Tufts — Carla Brodley, Ariel Goldberg, Shafiqul Islam, and Thomas J. Stopka 
Moderator  Paul Stark, Professor and Director of Statistics, School of Dental Medicine

 

Session I: Big Data Analysis: From Fundamentals to Engineering Applications

Redefining Class Definitions Using Constraint-Based Clustering
Carla Brodley, Professor of Computer Science, School of Engineering
 
Big Data Visual Analytics: A User-Centric Approach
Video Presentation
Remco Chang, Assistant Professor of Computer Science, School of Engineering 
 
Big Data for Big Floods: Can We Break the Predictability Limits?
Video Presentation
Shafiqul Islam, Director of the Water Diplomacy Program, Professor of Civil and Environmental Engineering, School of Engineering, Professor of Water Diplomacy, The Fletcher School 
 
Computational Sensing: Bringing Physics to Big Data
Video Presentation
Eric L. Miller, Professor and Chair of Electrical and Computer Engineering, School of Engineering 
 
 
Moderator: Sergio Fantini, Professor of Biomedical Engineering, School of Engineering

Session II: Data-Driven Discoveries

Harnessing Big Data in Psycholinguistics: Design and Data
Video Presentation
Ariel Goldberg, Assistant Professor of Psychology, School of Arts and Sciences 
 
MODIS Satellite Data and GAM Models to Examine Urbanization as an Independent Predictor of Endothelial Dysfunction in a Large Southeast Asia Population
Video Presentation
Kevin Lane, Doctoral Candidate of Environmental Health, Boston University School of Public Health 
 
Virtual Cohorts and Big Data Analytics in Epidemiology
Video Presentation
Elena Naumova, Associate Dean for Research, Professor of Civil and Environmental Engineering, School of Engineering, Professor of Public Health and Community Medicine, School of Medicine 
 
Using GIS, Spatial Epidemiology, and Hot Spot Analysis to Target Nutrition Services
Video Presentation
Thomas J. Stopka, Assistant Professor of Public Health and Community Medicine, School of Medicine 
 
Using Big Data to Study Urban Sentiments: Twitter Data vs. Published Meeting Minutes
Video Presentation
Presented by Dibyendu Das on behalf of Justin Hollander, Associate Professor of Urban and Environmental Policy and Planning, School of Arts and Sciences 
 
Finding – and Not Crossing – The Ethics and Privacy Line in Using Big Data
Video Presentation
Lisa Gualtieri, Assistant Professor of Public Health and Community Medicine, School of Medicine
 
Moderator: Larry Parnell, Computational Biologist, United States Department of Agriculture, Agriculture Research Service, Nutritional Genomics Laboratory, Jean Mayer USDA Human Nutrition Center on Aging

Session III: Data Enabling Medicine

Impact of Obesity on Intestinal Tumorigenesis – Searching for Answers in the Microbiome, Metabolome and Transcriptome: Studies by the HNRCA Cancer Cluster and Tufts Computational Biology Initiative
Video Presentation
Jimmy W. Crott, Scientist I, Vitamins and Carcinogen Lab, Jean Mayer USDA Human Nutrition Research Center on Aging
 
Data Problems in Gut Microbiota Metabolomics
Kyongbum Lee, Associate Professor and Chair of Chemical and Biological Engineering, School of Engineering 
 
High-throughput Genetic Analysis of a Bacterial Pathogen
Video Presentation
Andrew Camilli, Professor of Molecular Biology and Microbiology, School of Medicine 
 
Large Scale EEG Monitoring: Is Dynamic Seizure Sensing Possible?
Video Presentation
Chris Dulla, Assistant Professor of Neuroscience, School of Medicine 
 
Understanding the Wiring of the Brain: Genome-Wide Analysis of Local Protein Synthesis
Video Presentation
Joshua Ainsley, Postdoctoral Scholar, Neuroscience, School of Medicine 
 
Loopfinder: Comprehensive Analysis of Hot Loops at Protein Interfaces as Targets for Macrocycle Inhibitors
Video Presentation
Joshua Kritzer, Assistant Professor of Chemistry, School of Arts and Sciences 
 
Moderator: Misha Eliasziw, Associate Professor of Public Health and Community Medicine, School of Medicine

TitleAuthor(s)

Data Science and the Data Management Lifecyle: A Library Perspective

 

Kelehan, Raboin, Vagts

The Computational Biology Initiative

 

Iyer and members of the Computational Biology Initiative

Conflated Constructs: The Case for Abandoning Social Support As an Evaluation Criterion for Transplantation

 

Ladin and Daniels

Using a Dental Data Repository to Test the Relationship between Periodontal Disease and Heart Attack: A Comparison of Data from NHANES and Big Mouth

 

Park, Stark, Tran, Walji

Mitochondrial and Plasma Associated Metabolic Perturbations Due to Low Dose, Chronic Exposure to the Organochlorine Pesticide Endosulfan I

 

Walker, Pennell, Caudle, Roede, Jones

Reduced Ventricular Contractility Is Associated with Reduced Cardiovascular Fractal Dimension

 

Shapiro, Tolman, Joshi, Schumann, Lanchulev, Cobey, Stukowski

Evaluating Management Alternatives for Free-Roaming Cat Populations Across a Range of Landscapes: An Individual-Based, Demographic Simulation Modeling Approach 

 

Boone, Briggs, Lawler, Levy, Miller, Nutter, Slater, Zawistowski

Hierarchical Conditional Random Fields for Outlier Detection: An Application to Detecting Epileptogenic Cortical Malformations

 

Ahmed and Brodley

The Effect of Protective Factors on Shifting Caries Risk Classification

 

Midle, Alghanem, Stark

Mental Workload Classification with Functional Near-Infrared Spectroscopy: Model-Based and Data-Driven Approaches

 

Tgavalekos, Sassaroli, Kainerstorfer, Fantini, Hincks, Afergan, Peck, Shibata, Yuksel, Jenkins, Jacob

The Nutritional Genomics Laboratory at the HNRCA – Summary of Current Research Activities

 

Parnell

Living in an Urban Environment Is Associated with Increased Blood Pressure and Arterial Stiffness

 

Corlin, Woodin, Lane, Brugge, Thanikachalam, Vanzan, Sunderarajan, Thanikachalam

Ultra Short-Term Heart Rate Variability As a Predictor of CABG Outcomes: A Retrospective Case-Controlled Study

Ursprung, Dave, Cobey, Ursprung, Warner

Poster Session II

TitleAuthor(s)

Data Science and the Data Management Lifecyle: A Library Perspective

 

Kelehan, Raboin, Vagts

Regulatory Network of Astroglia in Synapse Formation

 

Iyer and Yang

Hypothesize, Visualize, Analyze, Scrutinize, and Generalize: The Multi-Faceted Challenges of Examining Big Data

 

Liss, Wu, Naumova, Chui

Building Data Science Competencies into Nutrition Science Training

 

Obin

Stochastic Curtailment of Health Questionnaires: A Computer-Based Approach to Reducing Respondent Burden

 

Finkelman, Kim, He, Lai

Comparison of Traffic-Related Ultrafine Particle Number Concentrations on Roads and at Nearby Residential Locations in Boston, Massachusetts (USA)

 

Simon, Bob, Patton, Durant, Brugge

Assessing the Utilization and Validity of a Standardized Dental Diagnostic Code System

 

Stark, Park, Walji, Kalenderian, McClellan, White

Multilinear Data Analytics: Methods and Applications

 

Aeron, Zhang, Pothier, Kilmer, Kernfeld

Evaluation of Dental Students Clinical Performance

 

Alghanem, Park, Midle, Stark

Using Social Media to Crowdsource Control Strategies for Soft-bodied Robots

 

Crooks, Rogers, Trimmer

Addressing Human Subjectivity via Transfer Learning: An Application to Predicting Disease Outcome in Multiple Sclerosis Patients

 

Zhao, Brodley, Chitnis, Healy

Longitudinal Analysis of the Gut Microbiota in Children with and without Stunting in India

 

Dinh, Ward, Ramadass, Kattula, Kang, Chatterjee, Wanke, Kane, Naumova

Social Networks and Labor Markets

Gee, Jones, Burke

Soha Hassoun, Committee Chair
Associate Professor and Chair of Computer Science, School of Engineering

Misha Eliasziw
Associate Professor of Public Health and Community Medicine, School of Medicine

Sergio Fantini
Professor of Biomedical Engineering, School of Engineering

Yannis Ioannides
Professor of Economics, School of Arts & Sciences

Anne Kane
CTSI Navigator, Director of Phoenix Lab, Tufts Medical Center

Phyllis Mann
Associate Professor of Biomedical Sciences, Cummings School of Veterinary Medicine

Larry Parnell
Computational Biologist, United Stated Department of Agriculture, Agriculture Research Service, Nutritional Genomics Laboratory, Jean Mayer USDA Human Nutrition Research Center on Aging

Paul Stark
Professor and Director of Statistics, School of Dental Medicine