{"id":461774,"date":"2026-05-27T01:15:13","date_gmt":"2026-05-27T01:15:13","guid":{"rendered":"https:\/\/www.newsbeep.com\/il\/461774\/"},"modified":"2026-05-27T01:15:13","modified_gmt":"2026-05-27T01:15:13","slug":"since-1987-covering-the-fastest-computers-in-the-world-and-the-people-who-run-them","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/il\/461774\/","title":{"rendered":"Since 1987 \u2013 Covering the Fastest Computers in the World and the People Who Run Them"},"content":{"rendered":"<p>May 26, 2026 \u2014 Have you ever taken a prescribed medicine to resolve a health issue, only for the treatment to fail? Perhaps you\u2019re among the unlucky low percentage of people on weight loss drugs who can\u2019t seem to lose a single pound. The lack of efficacy in your treatments may be due to your unique genetic profile. Our specific genes can have many subtle effects on our health that don\u2019t necessarily fit the average. Two researchers from Professor Hongyu Zhao\u2019s lab at Yale University are working on AI tools to change that, and they\u2019ve used <a href=\"https:\/\/www.ncsa.illinois.edu\/resources-and-services\/compute-resources\/delta\/\" rel=\"nofollow noopener\" target=\"_blank\">NCSA\u2019s Delta supercomputer<\/a> to support their projects.<\/p>\n<p>Decoding Your Unique Blueprint<\/p>\n<p>Tianyu Liu is a Ph.D. candidate at Yale University. He is working on a tool that can account for individual genetic variations when researching treatments and diseases. His work involves tackling how gene-expression-predictive models use genomic language models (gLMs). Liu\u2019s work was recently published in <a href=\"https:\/\/www.nature.com\/articles\/s44387-026-00103-4\" rel=\"nofollow noopener\" target=\"_blank\">npj Artificial Intelligence<\/a>.<\/p>\n<p><a href=\"https:\/\/www.hpcwire.com\/wp-content\/uploads\/2026\/05\/Liu-figure1.jpg\" rel=\"nofollow noopener\" target=\"_blank\"><img fetchpriority=\"high\" decoding=\"async\" aria-describedby=\"caption-attachment-191195\" class=\"wp-image-191195\" src=\"https:\/\/www.newsbeep.com\/il\/wp-content\/uploads\/2026\/05\/Liu-figure1-300x163.jpg\" alt=\"\" width=\"400\" height=\"217\"  \/><\/a><\/p>\n<p id=\"caption-attachment-191195\" class=\"wp-caption-text\">The model overview of UKBioBERT and UKBioFormer as Foundation Models for genetically precise medicine.<\/p>\n<p>Most current gLMs rely on the \u201creference genome,\u201d a standardized blueprint of human DNA assembled from multiple individuals. A different approach was needed to provide a better tool for individualized gene expression predictions.<\/p>\n<p>\u201cWe pre-trained a powerful genomic language model (UKBioBERT) based on human variants from biobanks, and demonstrated that the embeddings from our model can enhance different expert models in performing gene expression prediction across individuals or genes,\u201d said Liu. This language model was trained using real genetic variants from approximately 300,000 individuals in the UK Biobank, creating rich, function-aware representations of genomic sequences.<\/p>\n<p>Building on this, the researchers created UKBioFormer and UKBioZoi by combining UKBioBERT with state-of-the-art architectures to improve the science of treatment and discovery. With these new tools, doctors would be better able to understand how your individual genes might affect things like disease risk or drug response. Conditions like cancer, diabetes, Alzheimer\u2019s and autoimmune disorders are driven by subtle changes in gene expression rather than mutations in a single gene; these new tools help pinpoint those subtle regulatory effects. And, due to the broad dataset, results from these tools will be more applicable to a wider population with different ancestries than results based on a more limited reference genome, ensuring that treatments \u2013 from heart medication to weight-loss drugs \u2013 are tailored to the person, not the average.<\/p>\n<p>\u201cNCSA resources provided valuable computation nodes for us to train a large model and conduct experiments efficiently,\u201d said Liu. \u201cPreviously, we needed to spend more than one month to train a model with 300 genes, but now we only need 10 days.\u201d<\/p>\n<p>Mapping the Biological Symphony<\/p>\n<p>Xinyi Lisa Chen is a third-year Ph.D. student who also works in Professor Zhao\u2019s lab. Chen is researching how genetic expression interacts with other parts of tissues. While Liu focuses on the unique \u2018letters\u2019 of an individual\u2019s genetic code, Chen looks at how those instructions are carried out in physical space.<\/p>\n<p>\u201cImagine watching the brain of a newborn mouse develop into adulthood,\u201d said Chen, \u201ccells gradually organizing into precise patterns, each performing distinct roles over time. To understand this biological symphony and discover how disruptions might lead to diseases like Alzheimer\u2019s or Parkinson\u2019s, scientists must piece together a puzzle involving not just what genes are active, but also where in the tissue they\u2019re active, when they\u2019re switched on, and how they interact with other biological processes.\u201d<\/p>\n<p>Scientists have recently been able to get unprecedented amounts of detailed information about cells during scans \u2013 sometimes they\u2019re even able to isolate tiny groups of cells no bigger than two to three together to study them. \u201cSpecifically, scientists can measure both gene activity (RNA, or transcriptomics) and gene regulation (chromatin accessibility, or epigenomics via ATAC-seq) within these spots, while also precisely pinpointing their locations in specific regions,\u201d Chen explained.<\/p>\n<p><a href=\"https:\/\/www.hpcwire.com\/wp-content\/uploads\/2026\/05\/Chen-STORM-fig-scaled-1.jpg\" rel=\"nofollow noopener\" target=\"_blank\"><img loading=\"lazy\" decoding=\"async\" aria-describedby=\"caption-attachment-191196\" class=\"wp-image-191196\" src=\"https:\/\/www.newsbeep.com\/il\/wp-content\/uploads\/2026\/05\/Chen-STORM-fig-scaled-1-300x74.jpg\" alt=\"\" width=\"700\" height=\"172\"  \/><\/a><\/p>\n<p id=\"caption-attachment-191196\" class=\"wp-caption-text\">STORM\u2019s integrated clustering result of postnatal mouse brain across 2 developmental timepoints, 21 days and 22 days after birth.<\/p>\n<p>However, these snapshots of gene activity within cells had limitations. \u201cUntil now, scientists lacked a method to combine all these layers \u2013 spatial location, timing and multiple types of genetic data \u2013 into a single clear picture,\u201d said Chen. To solve this, she created a tool called STORM (Spatial Temporal multi-Omics Representation Model). STORM uses graph neural networks to integrate these complex layers of information into one cohesive, biologically interpretable view.<\/p>\n<p>The hope is that this tool can be a valuable aid in personalized medicine. \u201cWhile our current research involves mouse models, applying STORM to human atlas data can illuminate crucial developmental trajectories in tissues, highlighting pivotal moments when developmental processes may deviate from the norm,\u201d Chen said. \u201cSuch insights could enable clinicians to administer targeted screenings or early interventions, significantly improving health outcomes. In elderly populations, STORM can help map the progression of neurodegenerative diseases like Alzheimer\u2019s and Parkinson\u2019s, potentially identifying critical windows for preventative strategies or therapeutic interventions, ultimately improving patient quality of life.\u201d<\/p>\n<p>Liu and Chen were able to get time on NCSA\u2019s Delta supercomputer through an allocation from the U.S. National Science Foundation\u00a0<a href=\"https:\/\/access-ci.org\/\" rel=\"nofollow noopener\" target=\"_blank\">ACCESS<\/a>\u00a0program. ACCESS helped connect these researchers to the computing power needed to turn complex AI theories into real biological discoveries. \u201cLeveraging NCSA\u2019s powerful H100 GPU, we successfully processed extensive datasets encompassing five timepoints and two modalities within just over 24 hours \u2013 a task previously infeasible even with other advanced GPUs like the A100,\u201d said Chen. \u201cThis tremendous computational acceleration has allowed us to conduct research at a pace previously unattainable, rapidly advancing our understanding of complex biological processes.\u201d<\/p>\n<p>About Delta\u00a0and\u00a0DeltaAI<\/p>\n<p><a href=\"http:\/\/www.ncsa.illinois.edu\/\" rel=\"nofollow noopener\" target=\"_blank\">NCSA<\/a>\u2019s\u00a0<a href=\"http:\/\/www.ncsa.illinois.edu\/enabling\/delta\" rel=\"nofollow noopener\" target=\"_blank\">Delta<\/a>\u00a0and\u00a0<a href=\"https:\/\/delta.ncsa.illinois.edu\/deltaai-allocations\/\" rel=\"nofollow noopener\" target=\"_blank\">DeltaAI<\/a>\u00a0are part of the national cyberinfrastructure ecosystem through the\u00a0<a href=\"https:\/\/www.nsf.gov\/\" rel=\"nofollow noopener\" target=\"_blank\">U.S. National Science Foundation<\/a><a href=\"https:\/\/access-ci.org\/\" rel=\"nofollow noopener\" target=\"_blank\">ACCESS<\/a>\u00a0program. Delta (<a href=\"https:\/\/www.nsf.gov\/awardsearch\/showAward?AWD_ID=2005572&amp;HistoricalAwards=false\" rel=\"nofollow noopener\" target=\"_blank\">OAC 2005572<\/a>) is a powerful computing and data-analysis resource combining next-generation processor architectures and NVIDIA graphics processors with forward-looking user interfaces and file systems. The Delta project partners with the\u00a0<a href=\"https:\/\/sciencegateways.org\/\" rel=\"nofollow noopener\" target=\"_blank\">Science Gateways Community Institute<\/a>\u00a0to empower broad communities of researchers to easily access Delta and with the University of Illinois\u00a0<a href=\"https:\/\/www.disability.illinois.edu\/\" rel=\"nofollow noopener\" target=\"_blank\">Division of Disability Resources &amp; Educational Services<\/a>\u00a0and the\u00a0<a href=\"https:\/\/ischool.illinois.edu\/\" rel=\"nofollow noopener\" target=\"_blank\">School of Information Sciences<\/a>\u00a0to explore and reduce barriers to access. DeltaAI (<a href=\"https:\/\/www.nsf.gov\/awardsearch\/showAward?AWD_ID=2320345\" rel=\"nofollow noopener\" target=\"_blank\">OAC 2320345<\/a>) maximizes the output of artificial intelligence and machine learning (AI\/ML) research. Tripling NCSA\u2019s AI-focused computing capacity and greatly expanding the capacity available within ACCESS, DeltaAI enables researchers to address the world\u2019s most challenging problems by accelerating complex AI\/ML and high-performance computing applications running terabytes of data. Additional funding for DeltaAI comes from the State of Illinois.<\/p>\n<p><a href=\"https:\/\/www.ncsa.illinois.edu\/2026\/05\/26\/new-frontiers-in-precision-medicine\/\" rel=\"nofollow noopener\" target=\"_blank\">Source<\/a>: Megan Meave Johnson, NCSA<\/p>\n","protected":false},"excerpt":{"rendered":"May 26, 2026 \u2014 Have you ever taken a prescribed medicine to resolve a health issue, only for&hellip;\n","protected":false},"author":2,"featured_media":461775,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[85,46,141],"class_list":["post-461774","post","type-post","status-publish","format-standard","has-post-thumbnail","category-science","tag-il","tag-israel","tag-science"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/461774","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/comments?post=461774"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/461774\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media\/461775"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media?parent=461774"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/categories?post=461774"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/tags?post=461774"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}