# Statistical and Machine Learning Methods to Address Biomedical Challenges for Integrating Multi-view Data (Supplement)

> **NIH NIH R35** · UNIVERSITY OF MINNESOTA · 2024 · $230,604

## Abstract

Abstract
Advances in technology and data preprocessing have enabled the generation of diverse and complementary
multiomic, multimodal data, with rich information that offers remarkable opportunities to understand biological
processes involved in complex diseases and transform medicine. Analyzing multiomics and multimodal data
to obtain useful information and knowledge is challenging because the data are complex, heterogeneous, and
high-dimensional, requiring a considerable level of analytical sophistication. The amount of data to be handled
during training and real data applications can be massive, and traditional central processing units (CPUs) may
struggle to handle the size of the data. Graphical Processing Units (GPUs) are essential for handling big data
since they offer parallel processing capabilities that can significantly speed up training tasks. The Minnesota
Supercomputing Institute (MSI) addresses the high-performance computing needs of research groups at the
University of Minnesota, providing excellent resources with free CPU and GPU time, memory, and storage, up to
a certain limit. The resources at MSI are shared by the entire research community at the University of Minnesota
and have a queue system that limits the number of tasks that can be run, sometimes leading to job submission
failures and delays in job execution. Since our simulations for the parent grant are closely linked to real data
projects and our applications sometimes require loading large data into memory, we need computing resources
that are fast, parallelizable, have a large amount of memory and storage available, and can be executed without
delay to speed up our training and testing processes. We are requesting funds to purchase computing resources
from MSI specifically for our research group since the MSI allocation is not enough to meet our computational
needs. This will eventually improve our training and testing processes. Ultimately, our methods and algorithms to
be developed have the potential to narrow the gap from raw molecular data to biological insights, offer opportunity
to expand the definition of complex diseases, and allow to stratify patients and identify those who might benefit
from targeted interventions.

## Key facts

- **NIH application ID:** 11100974
- **Project number:** 3R35GM142695-04S1
- **Recipient organization:** UNIVERSITY OF MINNESOTA
- **Principal Investigator:** Sandra E Safo
- **Activity code:** R35 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2024
- **Award amount:** $230,604
- **Award type:** 3
- **Project period:** 2021-09-23 → 2026-06-30

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/11100974

## Citation

> US National Institutes of Health, RePORTER application 11100974, Statistical and Machine Learning Methods to Address Biomedical Challenges for Integrating Multi-view Data (Supplement) (3R35GM142695-04S1). Retrieved via AI Analytics 2026-05-26 from https://api.ai-analytics.org/grant/nih/11100974. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*