A machine learning model can improve genetic prediction of type 1 diabetes by as much as 10%, show results from a University of California, San Diego study.
The researchers used the machine‑learning model T1GRS to improve on a gold standard polygenic genetic risk score used to predict who is likely to develop the condition called GRS2.
Type 1 diabetes is an autoimmune condition that impacts around 2 million people in the U.S. While it is a multifactorial condition, genetics plays a big role and around 50% of a person’s susceptibility comes from genetics.
“The natural history of type 1 diabetes suggests that the disease occurs in genetically susceptible individuals exposed to environmental triggers, leading to the development of islet-specific autoantibodies and autoreactive T cells and progressive loss of insulin secretory function, although the underlying etiology is not fully understood,” write lead author Kyle Gaulton, PhD, associate professor of pediatrics at UC San Diego School of Medicine, and colleagues in Nature Genetics.
The GRS2 polygenic risk score has been widely tested and can be used to predict newborns who are at high risk of developing type 1 diabetes. While early prediction can’t necessarily stop the disease it can help to prevent emergencies like diabetic ketoacidosis at diagnosis, allow families time to prepare and could allow use of therapies to delay onset of the condition.
In this study, Gaulton and colleagues carried out a genome‑wide association study in 20,355 people with type 1 diabetes and 797,363 non‑diabetic Europeans, as well as a further analysis around the MHC region in 10,107 diabetic and 19,639 nondiabetic individuals.
“The MHC has ‘blocks’ of co-inherited genetic information that are very highly enriched in individuals with type 1 diabetes,” said co-first author Emily Griffin, PhD, a postdoctoral fellow in Gaulton’s lab. “If you have them, it doesn’t mean that you’re going to get diabetes, but if you don’t have them, it means you have a very low chance of getting diabetes.”
Overall 160 risk signals were identified, and the team trained their T1GRS model to predict who was likely to develop type 1 diabetes based on their genetics. The model was able to improve on the GRS2 model predictions by up to 10% in both populations of European and African American ancestry.
Overall the new score correctly flagged about 89 of 100 people with type 1 diabetes while correctly reassuring about 84 of 100 people without the disease.
“Our results highlight the value of combining the results of genetic association studies with machine learning methods to improve the prediction of complex diseases,” conclude the authors.
Researchers at UTHealth Houston have developed a patient-derived “tumor-on-a-chip” model designed to more precisely study pancreatic ductal adenocarcinoma (PDAC). The study, published in Advanced Science, details how the investigators designed the chip to integrate three-dimensional tumor organoids with components of the tumor microenvironment inside a microfluidic system to recreate interactions between cancer cells, stromal tissue, blood vessels, and immune cells.
“Our goal was to build a model that looks and behaves much more like a real pancreatic tumor than traditional lab models,” said Faraz Bishehsari, MD, PhD, professor and director of the Gastroenterology Research Center at McGovern Medical School at UTHealth Houston. “By recreating the tumor’s environment, we can better understand the disease and test treatments in a patient-specific way.”
Pancreatic cancer is difficult to treat because tumors exist within a dense and complex microenvironment that influences both tumor growth and drug response. Current in vitro methods to study the disease, such as two-dimensional cell cultures, as well as pancreatic cancer organoids, often fail to replicate these dynamics.
“Ex vivo models that replicate the tumor and its microenvironment can advance precision medicine in PDAC,” the researchers wrote, but noted that organoids alone “fall short in replicating the tumor microenvironment (TME), which includes various stromal and immune cells influencing tumor growth and chemoresistance.”
To address this, the UTHealth team combined patient-derived organoids with fibroblasts, endothelial cells, and immune cells in a microfluidic chip. The model was created using tumor and blood samples donated by consenting patients, which were used to grow organoids that retained the functional features of the original tumor. The organoids were then incorporated into a chip containing microfluidic channels that mimic blood flow and circulation to create a more dynamic interaction between cells types than current models.
The significance this new lab-on-a-chip lies in its ability to more closely replicate the tumor microenvironment as it would exist in humans more accurately than existing approaches. The design of the chip allows researchers to observe how tumors evolve over time, how stromal and immune components influence cancer behavior, and, perhaps most importantly, how potential drugs and therapies perform under conditions that more closely resemble human disease.
The researchers wrote that their chip “successfully recapitulated the in vivo cancer-stroma interaction of PDAC.” This included the formation of desmoplastic stroma, a dense, scar-like tissue known to limit drug effectiveness. This feature is difficult to reproduce in current PDAC models, but is known to be a major contributor to treatment resistance.
The chip allowed the team to test both chemotherapy and immunotherapies targeting PDAC. They showed that when stromal components were targeted in the model, the effectiveness of standard chemotherapy increased. For immune response, the team studied the effects of pembrolizumab to see how immune cells interacted with the tumor and showed that the drug enhanced T cell infiltration and tumor cell kill. Their observations that lower doses were less effective mirror patterns that have emerged in other clinical studies.
Based on these findings, the researchers noted that chip could serve as a tool for testing new drugs, studying mechanisms of resistance, and evaluating combination therapies tailored to individual patients. Because of its ability to closely recreate the way a tumor would react in vivo, the chip could serve as an important tool to identify the preclinical candidates most likely to effectively treat PDAC.
The implications for developing more precise PDAC therapies are significant. By incorporating organoids and tissues collected directly from individual patients, the chip could allow testing of individualized treatments to account for tumor heterogeneity. Further, it could help find ways to overcome drug resistance driven by stromal interactions and immune suppression.
Next steps for the research include improving the platform’s scalability and reproducibility to support broader use. Future work will also focus on incorporating additional immune components and refining the model to better reflect patient-specific tumor biology.
“This study shows that we can faithfully recreate key features of human pancreatic tumors, including interactions with stromal and immune cells,” Bishehsari said. “The next step is making these systems more practical so they can be widely used in research and drug development.”
Researchers have found a novel therapeutic target to enhance the effects of cancer immunotherapy. A study published today in Science Immunology reveals how a metabolite known as citraconate can reduce T cell exhaustion and enhance the ability of these immune cells to live longer, multiply, and effectively fight tumors.
Despite the widespread success of checkpoint inhibitor immunotherapies, a substantial proportion of patients still do not respond to these treatments. One contributing factor is metabolic dysregulation within the tumor microenvironment (TME), which compromises the antitumor activity of tumor-infiltrating T cells and limits their proliferation, reducing the efficacy of immunotherapy.
“Emerging evidence highlights the TME as a formidable metabolic barrier to immune cell function, attributable, in part, to the accumulation of immunosuppressive metabolites, which collectively promote T cell exhaustion and resistance to immunotherapy,” writes Lianjun Zhang, PhD, professor at the Suzhou Institute of Systems Medicine and senior author of the study. “Although tumor-derived metabolites are increasingly recognized as key modulators of T cell dysfunction and antitumor immunity, the critical metabolic circuits and specific metabolites that shape and sustain T cell phenotypes remain incompletely characterized.”
Citraconate is known to have antioxidative and antiviral properties, as well as being involved in T cell exhaustion. However, the exact signaling pathways it activates and immunological functions it plays in the context of cancer still remain poorly understood.
Zhang’s team uncovered a previously unreported role for this metabolite in antitumor immunity, by reducing T cell exhaustion and preserving their ability to replicate. In tumor tissue samples from patients, the researchers found that citraconate was depleted within exhausted T cells. In cultured human cells and mouse models, supplementation with citraconate increased the activation of tumor-infiltrating T cells, promoted their division, and reduced exhaustion, boosting their antitumor activity.
Further examination revealed that citraconate triggers these effects by increasing intracellular levels of cAMP, which in turn represses the ALOX5 enzyme involved in the oxidation of fatty acids such as arachidonic acid. This signaling cascade reduces the vulnerability of T cells to ferroptosis, a form of cell death driven by the accumulation of oxidized lipids on the cell membrane.
Genetic and pharmacologic inhibition of ALOX5 enhanced antitumor immunity mediated by T cells, confirming these findings. In mouse models of cancer, supplementation with citraconate was shown to boost the effects of immune checkpoint therapy
Taken together, these findings unveil a critical metabolic checkpoint regulating the performance of tumor-infiltrating T cells, presenting a clinically actionable target to enhance the efficacy of immune checkpoint inhibitors. Going forward, the team plans to dive deeper into the signaling pathways that citraconate employs to modulate T cell activity, its role in metabolic regulation, and the potential contributions of epigenetics to the whole process.
Cytiva and Rockwell Automation launched the figurate supervisory control and data acquisition (SCADA) system designed to remove digital bottlenecks during biopharmaceutical manufacturing. Working across multiple instrument vendors and modalities, Figurate SCADA provides the connectivity needed to enable digital integration to advance modern bioprocessing, according to Matt Weaver, vice president of global industry life sciences at Rockwell.
“Biopharma teams are under pressure to move more quickly, but their systems are often not built to keep up,” says Weaver. “This collaboration with Cytiva marks a pivotal step in our mission to democratize digital manufacturing, enabling biopharma innovators to deploy SCADA faster, smarter and more affordably.”
Many biopharma teams have long juggled proprietary systems that cannot communicate with one another, creating operational silos, manual workarounds, and data integrity risks. The new system directly addresses this roadblock by having an open architecture, allowing for third-party instrument integration, and real-time oversight of integration capable unit operations from a single interface, notes a Cytiva spokesperson, who explains that the platform features include:
Native interoperability: The platform is natively integrated with Cytiva bioprocessing equipment and Rockwell Automation’s FactoryTalk software suite, enabling seamless interoperability across systems.
Scalable growth: A single platform expands from process development to commercial manufacturing without system redesign.
Cost-effective compliance: A streamlined digital manufacturing system reduces capital and operational costs and enables cGMP compliance.
Rapid implementation: Pre-engineered templates and modular design shorten deployment and validation timelines.
Enhanced operational insight: Centralized alarms, real-time monitoring, process intensification and batch reporting tailored to bioprocess workflows.
“This collaboration is designed to empower the next generation of biomanufacturers,” says Nicolas Pivet, manufacturing and digital solutions at Cytiva.
Industry data shows increasing demand for next generation process control systems as organizations transition toward data driven process intensification and continuous manufacturing. Equipment fragmentation remains one of the top pain points cited by biomanufacturers, particularly those advancing programs from R&D to clinical scale. By giving teams a unified digital control layer, the Figurate SCADA reduces the risk of human error, accelerates tech transfer, and supports reliable scaleup as workloads grow in complexity, points out the Cytiva spokesperson.
Cybersecurity was already under strain before AI entered the stack. Now, as AI expands the attack surface and adds new complexity, the limits of legacy approaches are becoming harder to ignore. This session from MIT Technology Review’s EmTech AI conference explores why security must be rethought with AI at its core, not layered on after the fact.
About the speaker
Tarique Mustafa, Cofounder, CEO, and CTO, GC Cybersecurity
Tarique Mustafa is Cofounder and CEO/CTO of two AI-powered cybersecurity companies: GCCybersecurity, Inc. and its data compliance spinout, Chorology, Inc. A prolific inventor and internationally recognized authority in knowledge representation, inference calculus, and AI planning, Tarique has spent his career applying autonomously collaborative AI to solve complex, ultra-high-scale challenges across cybersecurity, data security, and compliance — with deep expertise spanning Data Classification, DLP, and DSPM industries. His groundbreaking innovations and multiple USPTO patents have earned him global recognition, including frequent invitations to deliver keynote addresses at prestigious international security conferences and forums.
At GCCybersecurity, Tarique architected the core AI algorithms powering the company’s 4th and 5th generation fully autonomous data leak protection and exfiltration platform — among the most advanced platform of its kind. Prior to founding GCCybersecurity and Chorology, he served as founding CEO/CTO of NexTier Networks, a Silicon Valley provider of award-winning Data Leak Prevention solutions. With over 20 years of technical leadership experience, Tarique has held senior roles at Symantec, DHL Airways IT, MCI WorldCom, EDS, Andes Networks, and Nevis Networks, where he served as Principal Architect and built industry-leading security products leveraging next-generation security monitoring, event correlation, IDS/IPS, and SSL/IPSec technologies.
Tarique holds multiple approved and pending patents with the USPTO and has authored numerous research publications spanning Information & Data Security, Computer & Network Security, Software Architecture, Database Technologies, and Artificial Intelligence. A recipient of the prestigious Rotary International Scholarship for doctoral studies in Computer Science at the University of Southern California (USC), Tarique also holds master’s degrees in engineering and computer science from USC, and a bachelor’s degree in mechanical engineering from NED University of Engineering & Technology.
Companies are taking control of their own data to tailor AI for their needs. The challenge lies in balancing ownership with the safe, trusted flow of high‑quality data needed to power reliable insights. This conversation from MIT Technology Review’s EmTech AI conference examines how AI factories unlock new levels of scale, sustainability, and governance—positioning data control as a strategic imperative for governments and enterprises.
About the speakers
Chris Davidson, Vice President, HPC & AI Customer Solutions, HPE
Chris Davidson is Vice President of HPC & AI Customer Solutions at Hewlett Packard Enterprise. He leads HPE’s global strategy for AI Factory solutions and Sovereign AI, working with governments, enterprises, and research institutions to build secure, scalable national- and enterprise-grade AI capabilities.
He also directs Product Management and Performance Engineering across HPE’s HPC and AI portfolio, including large-model training platforms and Cray exascale systems. His teams define product strategy, performance architecture, and deployment models that position HPE at the forefront of high-performance and AI computing.
During his nine years at HPE, Chris has led key initiatives across Performance Engineering, AI Cloud, and Professional Services, shaping how HPE delivers optimized, cloud-native, and globally deployed high-performance systems. He previously held technical and leadership roles in the biotech and medical diagnostics sectors.
Chris holds an M.B.A. in Entrepreneurship and Finance and a B.S. in Biology from Loyola University Chicago.
Arjun Shankar, Division Director, National Center for Computational Science, Oak Ridge National Laboratory
Mallikarjun (Arjun) Shankar is the Division Director for the National Center for Computational Science at the Oak Ridge National Laboratory. His research focuses on the interdisciplinary bridge between computer science and large-scale scientific discovery campaigns that rely on scalable computing and data science. He is a joint faculty appointee at the University of Tennessee’s Bredesen Center, a senior member of the IEEE and a senior member of the ACM.
Posted on
<![CDATA[The SPAN survey underscores gaps in schizophrenia care access as new treatments emerge, citing coverage and continuity challenges.]]>
Posted on
<![CDATA[New data shows stable symptoms when switching from atypical antipsychotics to Cobenfy using cross-titration.]]>
Posted on
<![CDATA[In the wake of the FDA fast-track of psychedelic therapies, we want to hear your clinical pearls for our May theme.]]>
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology.
A new US phone network for Christians aims to block porn and gender-related content
A new US-wide cell phone network marketed to Christians is set to launch next week. It blocks porn using network-level controls that can’t be turned off—even by adult account owners.
It’s also rolling out a filter on sexual content aimed at blocking material related to gender and trans issues, optional but turned on by default across all plans.
The trouble is, many websites don’t fit neatly into one category. That leaves its maverick founder with broad, subjective control over what is allowed or banned. Read the full story.
—James O’Donnell
This startup’s new mechanistic interpretability tool lets you debug LLMs
The San Francisco–based startup Goodfire has released a new tool, Silico, that lets researchers peer inside an AI model and adjust its parameters during training. It could give users more control over how this technology is built than was once thought possible.
The goal is to make building AI models less like alchemy and more like a science. Using a technique called mechanistic interpretability, Silico maps the neurons and pathways inside a model and lets developers tweak them to reduce unwanted behaviors or steer outputs.
By exposing the “knobs and dials,” Goodfire hopes to bring AI training closer to traditional software engineering. Read the full story.
—Will Douglas Heaven
With mass firing, Trump deals a fresh blow to American science
This past week delivered another gut punch for science in the US. This time, the target was the National Science Foundation—a federal agency that funds major research projects to the tune of around $9 billion. On Friday, the 22 scientists overseeing those efforts were all fired.
Since 2025, the NSF has faced budget cuts, grant terminations, and mass firings, with staff numbers down sharply and many ambitious projects grinding to a halt. The result is a major shift in how American science is funded and governed. Discover what it means, and what’s next.
—Jessica Hamzelou
This article first appeared in The Checkup, MIT Technology Review’s weekly biotech newsletter. To receive it in your inbox every Thursday, and read articles like this first, sign up here.
China’s open-source bet: 10 Things That Matter in AI Right Now
Silicon Valley AI companies follow a familiar playbook: keep the models behind an API and charge for access. China’s leading AI labs are playing a different game, releasing “open-weight” models that developers can download, adapt, and run on their own hardware.
That approach went mainstream after DeepSeek open-sourced its R1 model, which matched top US systems at a fraction of the cost. It also won something subtler: goodwill with developers. A growing cohort of Chinese labs is now following the same blueprint.
As AI shifts from hype to deployment, open-source models are making the future of AI more multipolar than Silicon Valley expected. Read the full story.
—Caiwei Chen
China’s open-source bet is one of the 10 Things That Matter in AI Right Now, our list of the biggest ideas, trends, and advances in AI today. We’re unpacking one item from the list each day here in The Download, so stay tuned.
The must-reads
I’ve combed the internet to find you today’s most fun/important/scary/fascinating stories about technology.
1 Elon Musk has admitted that xAI trained Grok on OpenAI models “Distillation” is standard practice in AI, despite being legally dubious. (Wired $) + The White House has accused Chinese firms using distillation of theft. (BBC) + American labs are widely assumed to use similar techniques. (TechCrunch)
2A “de-extinction” startup wants to resurrect a long-lost antelope Colossal Biosciences wants to bring back the bluebuck. (Axios) + The company is using genomic editing to revive the animal. (Gizmodo) + It previously claimed to have cloned red wolves. (MIT Technology Review)
3 An OpenAI model outperformed ER doctors at diagnosing patients By analyzing health records data and information provided to physicians. (NPR) + But it still must be proven in real-world clinical trials. (Vox)
4Scientists are trying to power AI data centers with tiny nuclear reactors They could provide a new way to meet AI’s energy demands. (Gizmodo) + We did the math on AI’s energy footprint. (MIT Technology Review)
5Spotify has started verifying human artists A new badge will distinguish them from AI. (The Guardian) + Spotify has faced criticism for its handling of AI. (BBC)
6The US is backing a Congolese railway to break China’s grip on critical minerals The old railroad is key to the race for critical metals in Africa. (Rest of World) + The US is also searching for alternative sources. (MIT Technology Review)
7Huawei is set to overtake Nvidia in China’s AI chip market It’s expected to capture the largest market share this year. (FT $)
8Japan is building cardboard drones for the battlefield The flatpack designs are cheap, disposable, and built at scale. (404 Media)
9 The more young people use AI, the more they hate it Research shows that Gen Z doesn’t trust GenAI. (The Verge)
10 A new organoid can menstruate—and show how tissue repairs itself It’s revealing how the uterus can shed without scarring. (Nature)
Quote of the day
“I suspect that there are a number of people who do not want to put the future of humanity in Mr Musk’s hands.But we’re not going to get into that.”
—Judge Gonzalez Rogers rebukes attempts by Elon Musk’s lawyer to focus on AI’s existential risks as part of his lawsuit against OpenAI, the New York Times reports.
One More Thing
TMY350 VIA WIKIMEDIA COMMONS
This rare earth metal shows us the future of our planet’s resources
The materials we need to power our world are shifting from fossil fuels to energy sources that don’t produce greenhouse gas emissions.
Take neodymium, a rare earth metal used in powerful magnets that power everything from smartphones to wind turbines. Its story reveals many of the challenges we’ll likely face across the supply chain in the coming century and beyond.