Snyder’s talk, “Big Data and Health,” will take place at noon in room 101-102 at the Kosair Charities Clinical & Translational Research Building, 505 S. Hancock St. Snyder will focus on how information in large databases, or big data, can be used to develop improved and more individualized approaches to predicting, diagnosing and treating common diseases. 

, PhD, is an international leader in the fields of functional genomics and proteomics and is the director of the Center of Genomics and Personalized Medicine at Stanford University, where he is the Stanford W. Ascherman Professor and Chair of Genetics.

He wrote “Genomics & Personalized Medicine: What Everyone Needs to Know,” a book that explores the prospects and realities of genomics and personalized medicine for consumers. He was a key participant in the Encyclopedia of DNA Elements (ENCODE) project, which identified functional elements in the human genome.

Snyder’s research group was the first to perform a large-scale functional genomics project in any organism. Genomics is a branch of molecular biology that focuses on the structure, function, evolution and mapping of genomes in an organism’s complete set of DNA.

 has made several groundbreaking findings, including the discovery that much more of the human genome is either transcribed or contains regulatory elements than previously known, and that a high diversity of binding of transcription factors – gene products that participate in regulating what genes are active – occurs between and within species.

Snyder also has combined different advanced “omics” technologies to perform the first longitudinal Integrative Personal Omics Profile (iPOP) of an individual and used the information to assess disease risk and monitor disease states for personalized medicine. He co-founded several biotechnology companies, including Protometrix (now part of Life Technologies), Affomix (now part of Illumina), Excelix, Personalis and Q Bio.

Snyder received his PhD at the California Institute of Technology and postdoctoral training at Stanford University.

The lecture is sponsored by the  at the UofL School of Medicine. For more information, contact Janice Ellwanger at 502-852-5217 or David Samuelson at 502-852-7797.

Professors Stephanie Philipp from the College of ����ֱ�� and Human Development and Olfa Nasraoui from the earlier this year won a three-year, $600,000 Research Experience for Teachers (RET) grant from the National Science Foundation to train the educators.

Ten teachers from Jefferson, Carroll and Bullitt counties are on Belknap Campus through the end of July learning about big data and data science, plus getting practical help developing lesson plans to teach the concepts to their students. 

“The teachers in our cohort are a diverse group with a diverse population of students,” said Philipp, who teaches in CEHD’s Department of Middle and Secondary ����ֱ��.

Philipp and Nasraoui are also focused on introducing computer science to groups historically underrepresented in the field: women, people of color and those with disabilities.

“This is a form of professional development that Kentucky teachers seek out but, in a time of limited resources, have trouble finding,” said CEHD Dean Ann Larson. “With this grant, the university continues its longstanding tradition of supporting local educators through science, technology, engineering and math (STEM) partnerships and career and workforce readiness opportunities in STEM fields for high school students, including underrepresented groups.”

The project will have an impact beyond STEM teachers, said Nasraoui, who is professor and endowed chair of e-commerce in the Department of Computer Engineering and Computer Science and director of the .

“Its impact will be significant as these teachers go back to their classrooms and pass on the knowledge to their students. Thousands of students will be exposed to these concepts,” she said.

Kevin Walsh, associate dean of research and facilities in the Speed School, said the grant was “a huge win” for UofL and local high school students.

“NSF only awarded nine such grants throughout the entire country.” Walsh said. “Big data science is such an important field these days, as it is being used to solve real-world problems in numerous fields.”

Philipp added the project will support “active, long-term collaborative partnerships between teachers and university faculty and students to enhance the knowledge and capacity of teachers through participation in authentic research experiences. We also predict that the university faculty will learn more about how high school teachers support students to think computationally and prepare students for college and career.”

To avoid information overload, computer scientists have created algorithms and systems to help humans sort through all of that data. The algorithms recommend products and articles you might like, or tell you what information other people already searched for.

“The world is simply drowning in information,” said Dr. Olfa Nasraoui, a professor of computer engineering and computer science at the University of Louisville. “Our brains couldn’t handle the volumes of information and number of options, especially on social media, so these systems emerged out of necessity — not luxury.”

But while these algorithms may make our lives easier, there’s a problem: they can become biased.

Nasraoui, director of the UofL Knowledge Discovery and Web Mining Lab at the J.B. Speed School of Engineering, is studying this bias— and, possibly, how to fix it. Her research is backed by the National Science Foundation.

First, it’s important to note that these algorithms don’t necessarily start out biased. But, through machine learning — where computers analyze data examples to “learn” how to make decisions — they learn what humans like and don’t like and show us that.

“It’s possible that you perpetuate your biases as a human being because the algorithm can act as a filter,” she said. “It will filter the world for you.”

This, she said, creates “filter bubbles,” where we only see information that reinforces or strengthens our preexisting beliefs. This can increase polarization and division.

The current algorithms for filtering or sorting information for us typically fall into one of two categories: search engines and recommender systems.

Search engines allow you to sift through the available information to find what you want after you submit a search query. Recommender systems on the other hand, which are used increasingly such as on online shopping sites and on apps, learn about us over time and recommend information they think we might like.

As the algorithms analyze our data and look for trends, they can become biased in several ways.

For example, they might notice that people of a certain age group or who live in a certain area like or dislike certain things. This is sample set bias, and it’s why the recommendations in a hip urban neighborhood might look different from those you get in a small town.

Another type is iterative bias, which is common in online shopping platforms. If you search for the same kinds of things over and over, the algorithm will begin to make assumptions about what you like and start limiting what you can see by filtering information results.

Aside from just researching this bias, Nasraoui and her team of UofL students, ranging from undergraduates to doctoral candidates, are trying to prevent it.

Say, by creating an algorithm that can “tune” results according to the user’s wishes for exploring outside the filter bubble or finding ways to make the algorithms more transparent.

“Hopefully, as more people become aware of Big Data algorithmic biases, these algorithms will evolve for the better,” she said. “We must be aware.”

The proposals, which include representatives from nearly every school and college at UofL, were selected from 15 submissions after an intense, months-long process that included internal and external review. 

As part of the 21^st Century University Initiative, UofL was seeking to enhance up to three programs that show potential to address critical or emerging issues of national significance and that will help define the university as a national leader in these fields. Successful proposals also had to be interdisciplinary, encouraging participation from a variety of units across campus; be innovative and socially significant; provide opportunities for undergraduate and graduate research; and include financial support from the departments in which the proposal originated.

“We were pleased with the quality and quantity of proposals submitted from across the Belknap and Health Sciences campuses,” Acting President Neville Pinto said. “These three proposals clearly stood out as emerging areas in which we can play a lead role on a national level. Also important, faculty and students from every corner of the university will have the opportunity to play a role in their success.”

Each proposal will receive up to $250,000 per year for up to three years. Principal investigators will submit annual reports on the programs, which will be used to assess their development and determine future funding. The full reports are available on the web site.

The programs selected for this round of funding are:

Big Data Analysis in Medicine

Co-principal investigators Rob Keynton and Ayman El Baz of the Department of Bioengineering will lead a team in developing new models and learning approaches to analyze and integrate multiple data types to aid clinicians in early diagnosis and identification of high-risk patients for human diseases and disorders. The team will include a number of departments, faculty and students from the J.B. Speed School of Engineering and the School of Medicine.

Currently, a vast amount of data, ranging from medical images and pathology reports to qualitative clinical data produced through observations by physicians and other medical professionals, exists. The team proposes developing a platform that integrates information from a specific case with global data to help determine better diagnoses or treatment options for the patient.

While the proposed approach should apply to any clinical problem, the team will focus first on three areas in which UofL collaborations already exist: autism, heart failure and retinal disease.

Program in Metagenomics and Health

Recent research has established a link between indigenous microbiota, or micro-organisms such as bacteria that live on and in the human body, and health. The investigators hypothesize that these microbiota and their impact on the body are affected by factors such as a patient’s genetic profile, environment and lifestyle. The proposal supports studying the relationship between these social determinants, microbiota and the prevalence of specific diseases.

By combining the efforts of various UofL clinics and studies, the investigators plan to generate large data sets that may help determine a relationship between specific environmental factors, microbial profiles and disease.

The project will draw on research and clinical work from the Kent School, School of Medicine, James Graham Brown Cancer Center, School of Dentistry, School of Public Health and Information Sciences and others.

It will be led by co-principal investigators Nejat Egilmez, microbiology; Richard Lamont, oral immunology and infectious diseases; and Riaan Van Zyl, Kent School of Social work.

Cooperative Consortium for Transdisciplinary Social Justice Research

Many UofL departments and centers already conduct research and activities in social justice, diversity and equity. This program will promote transdisciplinary research to complement current projects. It also will provide a social justice hub to bring faculty, students and the community together on issues of social and racial justice.

Initial research focus areas will include community justice, environmental justice and emerging social justice issues. A fourth project area will focus on social justice issues in West Louisville, ensuring collaboration between the consortium and the Office of Community Engagement’s Signature Partnership. More than 45 faculty and 31 offices, units, centers, institutes and departments will participate in the initiative.

Co-Principal Investigators are Cate Fosl, associate professor, women and gender studies, and director, Anne Braden Institute for Social Justice Research, in the College of Arts and Sciences; and Enid Trucios-Haynes, professor in the Brandeis School of Law and director, Muhammad Ali Institute for Peace and Justice.

Previously funded programs

Three other programs have been funded as part of the 21^st Century University Initiative. Projects in cancer, restorative medicine, and advanced manufacturing and sustainability were selected for investment in 2014. Updates on all six programs will appear periodically in UofL News.