{"id":511362,"date":"2026-06-26T01:54:13","date_gmt":"2026-06-26T01:54:13","guid":{"rendered":"https:\/\/www.newsbeep.com\/il\/511362\/"},"modified":"2026-06-26T01:54:13","modified_gmt":"2026-06-26T01:54:13","slug":"ai-framework-surfaces-new-car-t-target-with-multi-cancer-potential","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/il\/511362\/","title":{"rendered":"AI Framework Surfaces New CAR T Target with Multi\u2011Cancer Potential"},"content":{"rendered":"

\"CAR-T<\/a>Credit: NEMES LASZLO\/SCIENCE PHOTO LIBRARY\/ Getty Images<\/p>\n

A new study in Cell describes an AI\u2011enabled strategy that could accelerate the search for next\u2011generation CAR T cell targets\u2014an enduring bottleneck in expanding the therapy beyond blood cancers. The work, titled \u201cAI\u2011driven discovery of GPNMB CAR T cells as a multi\u2011cancer therapy<\/a>,\u201d was led by researchers at the Perelman School of Medicine at the University of Pennsylvania and Penn\u2019s Abramson Cancer Center, with collaborators at the Icahn School of Medicine at Mount Sinai and RWTH Aachen University.<\/p>\n

The Penn team developed a human\u2011in\u2011the\u2011loop AI framework designed to systematically nominate antigens suitable for CAR T cell therapy. Rather than replacing expert judgment, the system integrates large language models (LLMs) with single-cell RNA sequencing datasets from human skin cancer and healthy tissue to generate and refine target lists that scientists then evaluate experimentally. <\/p>\n

The challenge is well known: while CAR T therapies have transformed treatment for several hematologic malignancies, identifying safe, selective targets in solid tumors remains slow and labor\u2011intensive. \u201cDiscovering a good CAR target is like trying to find a needle in a haystack, except the haystack keeps growing as more sequencing data becomes available,\u201d said lead author Daniel Baker, PhD, who completed the work under the mentorship of Carl June, MD<\/a>, and Zoltan Arany, MD, PhD. LLMs, Baker added, excel at scanning broad datasets, while human experts \u201cgo deep\u201d\u2014a complementary pairing the team sought to formalize.<\/p>\n

To test the framework, the researchers focused on skin cancer, integrating four publicly available single\u2011cell RNA\u2011seq datasets with additional public resources. More than 10,000 potential antigens were filtered using criteria relevant to CAR T design, including tumor composition, tissue specificity, and clinical feasibility. Multiple LLMs then repeatedly simulated target nomination\u20141,000 independent runs\u2014to reduce noise and mitigate hallucinations. The resulting consensus list was reviewed by the team, who selected Glycoprotein non-metastatic melanoma protein B (GPNMB) as the top candidate.<\/p>\n

The researchers then engineered a GPNMB\u2011directed CAR T cell and validated its activity across several preclinical models. In mouse studies, the CAR T cells eliminated tumors not only in melanoma\u2014the original focus of the dataset\u2014but also in monoblastic leukemia and colorectal adenocarcinoma, suggesting broader therapeutic potential. These findings align with the paper\u2019s highlight that GPNMB is expressed across a wide range of tumor types.<\/p>\n

The full framework is included in the methods section to enable adoption by other groups. The Penn team plans to apply the approach to additional cancer types and continue advancing the GPNMB CAR T candidate toward potential clinical translation.<\/p>\n

According to June, \u201cthis study represents one of the first uses of large language models in the field of cell and gene therapy, including CAR T cell therapy.\u201d The framework is intentionally modular and disease\u2011agnostic, designed to accommodate new datasets and future LLMs as they evolve. Arany emphasized the broader implications: \u201cThis is only the tip of the iceberg, as agentic AI is on the rise.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"Credit: NEMES LASZLO\/SCIENCE PHOTO LIBRARY\/ Getty Images A new study in Cell describes an AI\u2011enabled strategy that could…\n","protected":false},"author":2,"featured_media":511363,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[10],"tags":[343,165,163,234698,85,46,43,7648,22124,76394],"class_list":["post-511362","post","type-post","status-publish","format-standard","has-post-thumbnail","category-health","tag-artificial-intelligence","tag-cancer","tag-health","tag-hematologic-and-lymphatic-cancer","tag-il","tag-israel","tag-news","tag-single-cell-rna-sequencing","tag-skin-cancer","tag-t-cell-immunotherapy"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/511362","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=511362"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/511362\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media\/511363"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media?parent=511362"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/categories?post=511362"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/tags?post=511362"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}