Hewlett Packard Enterprise Data Science Institute

Machine learning techniques are revolutionizing nuclear data evaluation and reactor design. Vladimir Sobes, assistant professor in the Department of Nuclear Engineering at the University of Tennessee, Knoxville, has dedicated his career to exploring the application of modern artificial intelligence and machine learning algorithms to current problems in nuclear engineering. 

In the realm of nuclear data evaluation, Sobes underscored the significance of ML algorithms in automating tasks such as hyper-parameter tuning and learning complex functions, particularly in the realm of uncertainty quantification. Sobes illustrated the structured nature of nuclear data, stressing the importance of automated feature identification—a task traditionally performed manually by experts. ML/AI, he argued, offers the promise of enhancing efficiency, reproducibility, and uncertainty quantification in nuclear data evaluation, thereby enabling experts to devote their time to more critical tasks. 

Transitioning to the topic of reactor design, AI has the potential surpass human capabilities in autonomous optimization, although Sobes cautioned against the indiscriminate use of surrogate models.  

Sobes demonstrated the effectiveness of the Gaussian Process Learning Algorithm for design optimization using a scenario related to the development of a spacecraft antenna. NASA engineers asked an AI algorithm to imagine an antenna. Despite an initial skepticism of its unintuitive design, rigorous testing demonstrated superior performance compared to human-designed alternatives. In 2006, the NASA ST5 spacecraft antenna, the same model proposed by an evolutionary computer design, was sent to space. 

AI/ML technologies are reshaping the landscape of nuclear engineering, from streamlining nuclear data evaluation processes to pushing the boundaries of reactor design beyond what was previously thought possible. Sobes' insights highlighted the symbiotic relationship between human expertise and AI, emphasizing the potential for collaboration to drive innovation in nuclear science. 

The presentation concluded with a quote by Arthur C. Clarke, adapted to signify the transformative potential of advanced optimization methodologies: "Any sufficiently advanced optimization methodology is going to be indistinguishable from intelligence."  

Sobes envisions a future where AI supplements human expertise, enabling breakthroughs in nuclear science and technology. 

Health disparities— differences in health attributable to one’s social, racial, economic and/or environmental status— affect many nationwide. Efforts have been made in recent years to identify the root causes of these disparities. The lab of Kumaraswamy Naidu Chitrala takes this search to a molecular level, focusing on health disparities linked to aging, cancer, and neurological disorders while analyzing key genetic, proteomic, and epigenetic mechanisms using bioinformatics, computational biology, and statistical approaches.

In his talk for the HPE Data Science Institute, Chitrala first introduced his research concerning DNA methylation (DNAm), an epigenetic modification closely linked with aging and disease. Using samples collected from the Healthy Aging in Neighborhoods of Diversity Across the Life Span (HANDLS) study at the National Institutes of Health (NIH), Chitrala was able to analyze participants’ socioeconomic differences and their influence on DNA methylation and age-associated diseases, such as breast cancer, cardiovascular disease and metabolic syndrome.

In his analysis pipeline, Chitrala utilized computational tools like the Infinum MethylationEPIC BeadChip and the minfi R package to perform genome-wide DNA methylation analysis. With this, he built linear regression models to predict differences in methylation for the sample. Chitrala examined the significant results, which he used to conduct an epigenome wide association study (EWAS).

In the second half of the webinar, Chitrala touched on various other diseases and genomics-related studies within his lab, including research on PTSD, obesity, and proteomics. Some of his current lab efforts include creating a deep learning neural network to study breast cancer and metabolic syndrome genes, investigating candidate genes driving disparities among Triple Negative Breast Cancer (TNBC) patients using transcriptome association studies (TWAS), and RNA sequencing studies.