All posts by cpike

UCM/Google partnership in the news

By | News | No Comments

The research collaboration between Google and University of Chicago Medicine was profiled this week in Becker’s Hospital Review, which called our partnership “a data-driven duo to watch.”

The article highlights how UCM will take advantage of the CRI’s Clinical Research Data Warehouse as a base for Google’s predictive models. CRI Director Sam Volchenboum explains why the CRDW is a particularly important resource for the Google project: “We’ve taken a very rigorous approach to our data warehouse that is not necessarily the norm. We’ve been able to take our clinical data and standardize it and clean it up in a way that makes it much more easy to analyze and to perform this type of machine learning.”

“Our digital trail leaves many clues, both subtle and overt, to our overall health and well-being.”

By | News | No Comments

In Wired, CRI Director Sam Volchenboum shares a thought-provoking essay on the potential of social networks like Facebook and Google to predict disease. As our daily lives generate more and more trackable data through social media, wearables, GPS, etc., algorithms could become better and better at recognizing patterns that could point to health conditions — but the potential benefits of this are balanced with significant risks. Read Sam’s take on it here.

UCM and CRI partner with Google to explore machine learning in healthcare

By | News | No Comments

Google has announced announced a new partnership with University of Chicago Medicine which will take advantage of the CRI’s experience and expertise in working with biomedical data and predictive algorithms.

The Google team will work with University researchers to apply advanced machine learning techniques to de-identified patient data. These models may detect patterns that enable doctors to predict future health events — meaning they could anticipate patients’ needs before they arise, improve outcomes, and save lives. The partnership will expand on work in this area that is already in progress at UCM, such as the eCART model for predicting cardiac arrest.

Read more about the partnership in the Chicago Tribune and on Google’s blog.

CRI welcomes CTMS team leaders

By | CTMS, News | No Comments

We’re happy to announce that Alex Lapson and Don Starkey have joined the Center for Research Informatics to lead our newest major project, the management and development of a BSD-wide clinical trials management system.

Alex Lapson, Senior Program Manager, has more than twenty years of project and program management experience with a range of high-profile clients. In coordination with Don and our Manager of Programming Brian Furner, Alex is responsible for the daily direction of the CTMS project.

Don Starkey, Lead Web Applications Developer, is the technical lead for the project. Bringing more than twenty years of experience in programming, software architecture, and application development, he will design our software solution and guide a team of developers to bring this project to fruition.

Welcome, Alex and Don!

CRI to lead development of new BSD-wide clinical trials management system

By | CTMS, News | No Comments

Following a competitive proposal process, the Center for Research Informatics has been selected to lead the development of an enterprise clinical trials management system to be used for clinical research efforts across the University of Chicago Biological Sciences Division. The project was officially launched last week at a meeting led by Dean Kenneth Polonsky and attended by the Advisory Group for the project, a broad group of information technology leaders from across the University.

Over the coming months, the CRI will lead the process of designing and building a new system and integrating it with the BSD information systems already in place. We are now building our team for this project – see the job opening for a Senior Program Manager here. As the development phase is completed, this team will lead a new branch of the CRI dedicated to maintaining the system and supporting BSD clinical informatics as a whole.

The CRI is excited to be taking on this ambitious, high-impact project and we look forward to keeping you updated as our team grows and work on the system progresses.

Coming soon: Gardner, our new HPC cluster

By | News | No Comments

This fall, the CRI will launch our new high performance computing cluster, named Gardner. Available to all BSD/UCM researchers and their collaborators, the new cluster will allow us to accommodate more users and run analyses even more quickly and powerfully.

Gardner will feature:

  • 2.0 GHz Intel Haswell processors across all nodes
  • Infiniband FDR interconnect (56 Gbps)
  • 97 TFLOPs  Actual Performance (Rmax)
  • 88 standard compute nodes (2464 total cores;  128 GB RAM per node)
  • 28 mid-tier compute nodes (784 total cores; 512 GB RAM per node)
  • 4 large memory nodes (112 total cores; 1.28 TB RAM per node)
  • 5 GPU nodes with NVidia Tesla K80 GPUs
  • 1 Xeon Phi nodes with 2 Knight’s Corner coprocessors
  • 350 TB Scratch Space

Read More

“We are converging on a time when the whole world could become a big clinical trial”

By | News | No Comments

With a recent lawsuit drawing attention to inaccuracies in heart rate data gathered by Fitbits, do wearable health tracking devices have a place in clinical research? CRI Director Sam Volchenboum and Daphne Kis, writing in TechCrunch, look at both sides of the issue and advocate for a path forward that prioritizes both accuracy and usability.

Wearables and other forms of real-time tracking can transform large-scale studies of disease, giving researchers data that is more extensive and more accurate than what patients are able to remember weeks or months later. For example, this UChicago study of IBD patients uses Fitbits to track physical activity, allowing reseachers to find patterns and identify potential symptom triggers. But as Volchenboum and Kis note, “If we want better devices, we must do a better job of telling manufacturers what kinds of measurements and outputs we need. … Standards and data provenance aren’t sexy, but they are absolutely essential to any compelling future vision of clinical research.”

Science Life explores significance of CRI-enabled zebrafish research

By | News | No Comments

A story today in Science Life highlights the research on zebrafish antigen processing genes, conducted in part by the CRI Bioinformatics Core (read about our contribution here), that was recently published in the Proceedings of the National Academy of Sciences. Read the article to hear from the study’s lead author Sean McConnell, PhD, of the Department of Pediatrics about why these new discoveries are so exciting and how research on zebrafish may translate to advances in our understanding of the human immune system.

CRI Bioinformatics Core research published in PNAS

By | News | No Comments

A new publication in the Proceedings of the National Academy of Sciences highlights findings about novel antigen processing and presentation genes in zebrafish. This newly identified genetic diversity, discovered by de novo assembly, represents the most extensive diversity yet seen in the antigen processing genes of any species and fills in previously unrecognized knowledge gaps about the evolution of vertebrate adaptive immunity.

This research was enabled in part by our Bioinformatics Core. CRI Director of Bioinformatics Jorge Andrade, PhD, and Bioinformatician Kyle Hernandez, PhD, are co-authors on the paper. They produced the de novo assembly of the genome of a clonal line of zebrafish, using the CRI’s computing infrastructure for this complex data- and memory-intensive task. They then used many tools to determine which de novo scaffolds aligned near the chromosomal region being studied and aggregated these scaffolds to orient and order them across the region.

Read the full paper here, and see more publications enabled by the CRI here.

New publication highlights findings from 1,135 A. thaliana genomes

By | News | No Comments

A recent publication in the journal Cell details the findings of the first phase of the 1001 Genomes project, in which researchers sequenced and analyzed the genomes of 1,135 strains of Arabidopsis thaliana. This data has led to discoveries about the evolutionary and migratory history of A. thaliana and creates opportunities for new research about how genes and environment interact. Read about how CRI resources contributed to this study.