Skip to content

New contentCHPC has a new page summarizing machine learning and artifical intelligence resources.

Center for High Performance Computing

Research Computing and Data Support for the University

In addition to deploying and operating high-performance computational resources and providing advanced user support and training, CHPC serves as an expert team to broadly support the increasingly diverse research computing and data needs on campus. These needs include support for big data, big data movement, data analytics, security, virtual machines, Windows science application servers, protected environments for data mining and analysis of protected health information, advanced networking, and more.

If you are new to the CHPC, the best place to learn about CHPC resources and policies is our Getting Started page.

Have a question? Please check our Frequently Asked Questions page and contact us if you require assistance or have further questions or concerns.

Upcoming Events:

CHPC PE DOWNTIME: Partial Protected Environment Downtime  -- Oct 24-25, 2023

Posted October 18th, 2023


CHPC INFORMATION: MATLAB and Ansys updates

Posted September 22, 2023


CHPC SECURITY REMINDER

Posted September 8th, 2023

CHPC is reaching out to remind our users of their responsibility to understand what the software being used is doing, especially software that you download, install, or compile yourself. Read More...

News History...

image 1

Stratifying Risk for Onset of Type 1 Diabetes Using Islet Autoantibody Trajectory Clustering

By Sejal Mistry, Ramkiran Gouripeddi, Vandana Raman, Julio C. Facelli

Department of Biomedical Informatics, Center for Clinical and Translational Science, Division of Pediatric Endocrinology, Department of Pediatrics University of Utah

Aims/Hypothesis:

Islet autoantibodies can be detected prior to the onset of type 1 diabetes and are important tools for disease screening. Current risk models rely on positivity status of islet autoantibodies alone. This work aimed to determine if a data-driven model incorporating characteristics of islet autoantibody development, including timing, type, and titer, could stratify risk for type 1 diabetes onset. 

Methods:

Glutamic acid decarboxylase (GADA), tyrosine phosphatase islet antigen-2 (IA-2A), and insulin (IAA) islet autoantibodies were obtained for 1,415 children enrolled in The Environmental Determinants of Diabetes in the Young study. Unsupervised machine learning algorithms were trained to identify clusters of autoantibody development based on islet autoantibody timing, type, and titer. 

Results:

We identified 2 – 4 clusters in each year cohort that differed by autoantibody timing, titer, and type. During the first 3 years of life, risk for type 1 diabetes was driven by membership in clusters with high titers of all three autoantibodies. Type 1 diabetes risk transitioned to type-specific titers during ages 4 – 8, as clusters with high titers of IA-2A showed faster progression to diabetes compared to high titers of GADA. The importance of high GADA titers decreased during ages 9 – 12, with clusters containing high titers of IA-2A alone or both GADA and IA-2A demonstrating increased risk. 

Conclusions/Interpretation:

This unsupervised machine learning approach provides a novel tool for stratifying type 1 diabetes risk using multiple autoantibody characteristics. Overall, this work supports incorporation of islet autoantibody timing, type, and titer in risk stratification models for etiologic studies, prevention trials, and disease screening.

 









 



 



 






 

System Status

General Environment

last update: 2024-10-17 19:41:02
General Nodes
system cores % util.
kingspeak 958/972 98.56%
notchpeak 2400/3148 76.24%
lonepeak 1745/1932 90.32%
Owner/Restricted Nodes
system cores % util.
ash Status Unavailable
notchpeak 13526/21940 61.65%
kingspeak 1664/4092 40.66%
lonepeak 136/416 32.69%

Protected Environment

last update: 2024-10-17 19:40:05
General Nodes
system cores % util.
redwood 549/628 87.42%
Owner/Restricted Nodes
system cores % util.
redwood 2803/6440 43.52%


Cluster Utilization

Last Updated: 9/3/24