Loading video...

Video Failed to Load

Go Home

🧬 Take a look inside a 3D tissue bioprinting lab! NIH postdoctoral fellow Dr. Cristina Antich Acedo demonstrates how cutting-edge bioprinting can recreate human tissue structure. By combining different cell types and biomaterials, researchers can mimic real biological environments with precision. 🔬 This technology helps accelerate the path from...

NIH's profile picture

NIH

1,743,292 subscribers

14,495 views • 3 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

⚡🎉 We are thrilled to introduce VORTEX, an AI-powered computational framework for predicting 3D Spatial Transcriptomics (ST) using 3D tissue images and minimal 2D ST! 🧬 By combining cutting-edge 3D non-destructive tissue imaging with AI, VORTEX imputes the 3D molecular landscape of large tissue samples in a cost-effective and scalable manner. 🧠💡Our approach: By pretraining on diverse 3D morphology–2D transcriptomic pairs from heterogeneous tissue samples, and then fine-tuning on minimal 2D ST data from a volume of interest, VORTEX leverages both generic tissue-specific and sample-specific morphomolecular correlates to predict 3D ST. Congratulations to our superstar co-leads Cristina Almagro Pérez and Andrew H. Song, this was an exciting collaboration with Jonathan Liu Sizun Jiang Ali Bashashati. Preprint: Demo: Read the excellent blog from our superstar grad student Cristina Almagro Pérez: Also see our previous work on 3D Computational Pathology from Andrew H. Song published in Cell last year: Stay tuned for more to come.
0:51

⚡🎉 We are thrilled to introduce VORTEX, an AI-powered computational framework for predicting 3D Spatial Transcriptomics (ST) using 3D tissue images and minimal 2D ST! 🧬 By combining cutting-edge 3D non-destructive tissue imaging with AI, VORTEX imputes the 3D molecular landscape of large tissue samples in a cost-effective and scalable manner. 🧠💡Our approach: By pretraining on diverse 3D morphology–2D transcriptomic pairs from heterogeneous tissue samples, and then fine-tuning on minimal 2D ST data from a volume of interest, VORTEX leverages both generic tissue-specific and sample-specific morphomolecular correlates to predict 3D ST. Congratulations to our superstar co-leads Cristina Almagro Pérez and Andrew H. Song, this was an exciting collaboration with Jonathan Liu Sizun Jiang Ali Bashashati. Preprint: Demo: Read the excellent blog from our superstar grad student Cristina Almagro Pérez: Also see our previous work on 3D Computational Pathology from Andrew H. Song published in Cell last year: Stay tuned for more to come.

Faisal Mahmood

17,991 views • 1 year ago

.Jay Bhattacharya, MD, PhD and Dr. @NKleinstreuer talk about NIH’s shift toward human-focused research and how NIH will no longer issue NOFOs exclusively for animal models. Watch the latest episode of The Director’s Desk to hear more:
1:29

.Jay Bhattacharya, MD, PhD and Dr. @NKleinstreuer talk about NIH’s shift toward human-focused research and how NIH will no longer issue NOFOs exclusively for animal models. Watch the latest episode of The Director’s Desk to hear more:

NIH

143,684 views • 1 year ago

NIH researchers are exploring how immature cells called stem cells develop into specialized cells like heart or lung cells. This research on how cells keep their DNA organized during that specialization process could help advance the development of lab grown organs for thousands of people waiting on a transplant. Watch the full video to learn more:
2:14

NIH researchers are exploring how immature cells called stem cells develop into specialized cells like heart or lung cells. This research on how cells keep their DNA organized during that specialization process could help advance the development of lab grown organs for thousands of people waiting on a transplant. Watch the full video to learn more:

NIH

19,895 views • 5 months ago

How does NIH’s Unified Funding Strategy strengthen scientific stewardship? 🔬 Dr. Nora Volkow, Director of the National Institute on Drug Abuse (NIDA), explains how the new plan allows us to identify research gaps while also identifying areas of redundancy, making it easier to fund the science most likely to bring about new benefits to human health. Hear more from NIH leadership at the upcoming webinar “Understanding NIH’s Unified Funding Strategy: What the Research Community Needs to Know” ➡️
0:39

How does NIH’s Unified Funding Strategy strengthen scientific stewardship? 🔬 Dr. Nora Volkow, Director of the National Institute on Drug Abuse (NIDA), explains how the new plan allows us to identify research gaps while also identifying areas of redundancy, making it easier to fund the science most likely to bring about new benefits to human health. Hear more from NIH leadership at the upcoming webinar “Understanding NIH’s Unified Funding Strategy: What the Research Community Needs to Know” ➡️

NIH

18,171 views • 1 month ago

NEW episode! Drug development has never been more expensive, in terms of output per dollar spent. This trend, called Eroom’s law, is surprising, considering the incredible technological advances in drug discovery, from genome sequencing to engineering to microscopy. On a new episode of the Works in Progress podcast, Ben Southwood and I talk to Ruxandra Teslo 🧬 about why this has happened and what can be done about it. We discuss how: • AI isn’t a magic bullet for drug discovery. Predictive models lack the physical human data, like individual variation and rare side effects, that can only be generated by actually running real-world clinical trials. • As scientists invent more effective drugs, it becomes harder to discover new treatments that can surpass past successes. This is known as the "Better than the Beatles" problem. • Biotech companies are increasingly moving their "first-in-human" trials to Australia because its simpler regulations allow researchers to test drug safety faster and cheaper than in the US. • Clinical trials can be made more efficient with various reforms including: embracing platform trials, allowing researchers to select from independent ethics boards, expanding the funding and validation of surrogate endpoints, increasing transparency by releasing regulatory correspondence from failed companies, and much more. Timestamps: 00:00:00 Eroom’s law and the paradox of drug development 00:08:03 How clinical trials actually work 00:10:23 The power and controversy of surrogate endpoints 00:14:01 How historical patent laws influenced trial timelines 00:22:46 The Australia advantage and regulatory drag 00:29:08 Institutional review boards (IRBs) and bureaucratic drag 00:32:21 Open science and successful reforms 00:41:49 Our wishlist for clinical trial reforms, and which reforms we *don’t* like 00:53:48 Why AI isn’t a magic bullet for drug discovery
56:13

NEW episode! Drug development has never been more expensive, in terms of output per dollar spent. This trend, called Eroom’s law, is surprising, considering the incredible technological advances in drug discovery, from genome sequencing to engineering to microscopy. On a new episode of the Works in Progress podcast, Ben Southwood and I talk to Ruxandra Teslo 🧬 about why this has happened and what can be done about it. We discuss how: • AI isn’t a magic bullet for drug discovery. Predictive models lack the physical human data, like individual variation and rare side effects, that can only be generated by actually running real-world clinical trials. • As scientists invent more effective drugs, it becomes harder to discover new treatments that can surpass past successes. This is known as the "Better than the Beatles" problem. • Biotech companies are increasingly moving their "first-in-human" trials to Australia because its simpler regulations allow researchers to test drug safety faster and cheaper than in the US. • Clinical trials can be made more efficient with various reforms including: embracing platform trials, allowing researchers to select from independent ethics boards, expanding the funding and validation of surrogate endpoints, increasing transparency by releasing regulatory correspondence from failed companies, and much more. Timestamps: 00:00:00 Eroom’s law and the paradox of drug development 00:08:03 How clinical trials actually work 00:10:23 The power and controversy of surrogate endpoints 00:14:01 How historical patent laws influenced trial timelines 00:22:46 The Australia advantage and regulatory drag 00:29:08 Institutional review boards (IRBs) and bureaucratic drag 00:32:21 Open science and successful reforms 00:41:49 Our wishlist for clinical trial reforms, and which reforms we *don’t* like 00:53:48 Why AI isn’t a magic bullet for drug discovery

Saloni

109,256 views • 4 months ago

Ranging in size from as small as a speck of pepper to the size of an apple seed, ticks can be hard to spot and remove, increasing the chance of exposure to tick-borne diseases. NIH researchers are exploring how to trigger a process found in animals, where molecules called cytokines activate the neurons that cause us to itch. This would allow humans to scratch off a tick before it can transmit disease. Watch the full video to learn more:
2:12

Ranging in size from as small as a speck of pepper to the size of an apple seed, ticks can be hard to spot and remove, increasing the chance of exposure to tick-borne diseases. NIH researchers are exploring how to trigger a process found in animals, where molecules called cytokines activate the neurons that cause us to itch. This would allow humans to scratch off a tick before it can transmit disease. Watch the full video to learn more:

NIH

11,519 views • 5 months ago

“Just the idea that 2-meter-long DNA can be wrapped up in a tiny cell is just mind-boggling” – Dr. Peter Park on how NIH-supported research led to key discoveries about DNA organization’s impact on health & disease. Watch the full video:
0:57

“Just the idea that 2-meter-long DNA can be wrapped up in a tiny cell is just mind-boggling” – Dr. Peter Park on how NIH-supported research led to key discoveries about DNA organization’s impact on health & disease. Watch the full video:

NIH

17,824 views • 1 year ago

🩺 Could our urine reveal more insights into how diabetes harms our kidneys? NIH researchers are studying tiny extracellular vesicles called exosomes found in urine to better understand how diabetes harms the kidneys. 🎥 Watch to learn more:
1:31

🩺 Could our urine reveal more insights into how diabetes harms our kidneys? NIH researchers are studying tiny extracellular vesicles called exosomes found in urine to better understand how diabetes harms the kidneys. 🎥 Watch to learn more:

NIH

26,800 views • 20 days ago

Why choose NIH for your clinical fellowship? Dr. Derek MacMath, a Clinical Fellow at the National Institute of Allergy and Infectious Diseases (NIAID), values the close proximity to the NIH Clinical Center and the unique opportunity to conduct translational research. See why NIH is an exceptional place to train, collaborate, and make an impact. Learn more about NIAID Clinical Fellowship opportunities:
1:25

Why choose NIH for your clinical fellowship? Dr. Derek MacMath, a Clinical Fellow at the National Institute of Allergy and Infectious Diseases (NIAID), values the close proximity to the NIH Clinical Center and the unique opportunity to conduct translational research. See why NIH is an exceptional place to train, collaborate, and make an impact. Learn more about NIAID Clinical Fellowship opportunities:

NIH

13,079 views • 23 days ago

Dr Anthony Fauci authorized over $200 million US taxpayer dollars for transgender animal testing and animal torture “Can you describe what exactly the American people's taxpayer dollars were spent on regarding transgender animal testing?” “Yeah: - In a lot of these cases, they involve mice, rats, monkeys who are being surgically mutilated and subjected to hormone therapies to mimic female to male or male to female gender transitions - Gender affirming hormone therapies, and then looking at the biological, psychological, and physiological effects of the gender transitions - Looking at the effects of taking vaccines after you've transitioned these animals from male to female or female to male - Looking at the size of their genitals changing after you've put them on estrogen or testosterone therapies to transition them - There was a $1.1 million grant to give female lab rats testosterone to mimic transgender male humans and then overdose them with this party drug to see if female animals taking testosterone were more likely to overdose on the sex party drug than animals who are not taking testosterone “Are many of these taxpayer funded animal studies shared with the public or is there a significant oversight of this research?” “You essentially needed a degree in information technology to navigate the federal spending databases to find any of this stuff.” “In our analysis, Dr. Fauci funded about 95% of the change-drender animal experiments” “What we are doing to test human effects is poisoning lab animals - Forcing them to breathe wildfire smoke simulated in a laboratory by burning different types of foliage and pumping into animals cages - Making them obese to simulate what it would be like for obese people to be exposed to wildfire smoke - Shooting off handguns and rifles and forcing animals to breathe the emissions and gun control experiments - and the list goes on and on”
3:14

Dr Anthony Fauci authorized over $200 million US taxpayer dollars for transgender animal testing and animal torture “Can you describe what exactly the American people's taxpayer dollars were spent on regarding transgender animal testing?” “Yeah: - In a lot of these cases, they involve mice, rats, monkeys who are being surgically mutilated and subjected to hormone therapies to mimic female to male or male to female gender transitions - Gender affirming hormone therapies, and then looking at the biological, psychological, and physiological effects of the gender transitions - Looking at the effects of taking vaccines after you've transitioned these animals from male to female or female to male - Looking at the size of their genitals changing after you've put them on estrogen or testosterone therapies to transition them - There was a $1.1 million grant to give female lab rats testosterone to mimic transgender male humans and then overdose them with this party drug to see if female animals taking testosterone were more likely to overdose on the sex party drug than animals who are not taking testosterone “Are many of these taxpayer funded animal studies shared with the public or is there a significant oversight of this research?” “You essentially needed a degree in information technology to navigate the federal spending databases to find any of this stuff.” “In our analysis, Dr. Fauci funded about 95% of the change-drender animal experiments” “What we are doing to test human effects is poisoning lab animals - Forcing them to breathe wildfire smoke simulated in a laboratory by burning different types of foliage and pumping into animals cages - Making them obese to simulate what it would be like for obese people to be exposed to wildfire smoke - Shooting off handguns and rifles and forcing animals to breathe the emissions and gun control experiments - and the list goes on and on”

Wall Street Apes

237,297 views • 1 year ago

What if scientists knew how to stop or slow the spread of cancer cells to other parts of the body? This process, also known as cancer metastasis, is responsible for the majority of cancer deaths. NIH researchers are studying this process with hopes of preventing it from happening. 🎥 Watch the full video to learn more:
0:55

What if scientists knew how to stop or slow the spread of cancer cells to other parts of the body? This process, also known as cancer metastasis, is responsible for the majority of cancer deaths. NIH researchers are studying this process with hopes of preventing it from happening. 🎥 Watch the full video to learn more:

NIH

12,677 views • 2 months ago

Chronic inflammation plays a role in some of today’s biggest health challenges, including Alzheimer’s, cancer, and heart disease. NIH researchers are developing new medications designed to boost the body’s natural anti-inflammatory responses and potentially help millions of people living with chronic inflammation. Learn more in this video:
2:06

Chronic inflammation plays a role in some of today’s biggest health challenges, including Alzheimer’s, cancer, and heart disease. NIH researchers are developing new medications designed to boost the body’s natural anti-inflammatory responses and potentially help millions of people living with chronic inflammation. Learn more in this video:

NIH

10,407 views • 3 months ago

NIH researchers studied more than 11,000 Americans and found that many people think healthy foods like fruits and vegetables are tasty too. The findings offer new insights into how our attitudes toward food may influence what we eat. 🎥 Watch the video to learn more: #EatRealFood
1:54

NIH researchers studied more than 11,000 Americans and found that many people think healthy foods like fruits and vegetables are tasty too. The findings offer new insights into how our attitudes toward food may influence what we eat. 🎥 Watch the video to learn more: #EatRealFood

NIH

17,508 views • 1 month ago

Every breakthrough begins with curiosity. Every discovery brings us one step closer to better treatments and brighter futures. Learn more about NIH vision science at
0:30

Every breakthrough begins with curiosity. Every discovery brings us one step closer to better treatments and brighter futures. Learn more about NIH vision science at

NIH

20,285 views • 25 days ago

It is because of the gold standard research conducted at NIH that children with rare diseases are provided the opportunity of lifesaving therapies and treatments. We are proud of our friends at U.S. FDA launching a framework for accelerating the development of individualized therapies for ultra rare diseases. Read more about FDA’s plan to accelerate cures here ➡️ HHS
1:58

It is because of the gold standard research conducted at NIH that children with rare diseases are provided the opportunity of lifesaving therapies and treatments. We are proud of our friends at U.S. FDA launching a framework for accelerating the development of individualized therapies for ultra rare diseases. Read more about FDA’s plan to accelerate cures here ➡️ HHS

NIH

22,498 views • 6 months ago

From 1975 to 2020, prevention and screening efforts averted 4.75 million deaths from five cancer types: breast, cervical, colorectal, lung, and prostate. A new NIH study emphasizes just how much prevention and screening contributes to reductions in mortality.
0:49

From 1975 to 2020, prevention and screening efforts averted 4.75 million deaths from five cancer types: breast, cervical, colorectal, lung, and prostate. A new NIH study emphasizes just how much prevention and screening contributes to reductions in mortality.

NIH

11,660 views • 1 year ago

Excited to share our new work on building a multimodal atlas of human skin in health and inflammatory disease — a project I’m especially proud of, bringing together AI, high-throughput genomics, and clinical science to accelerate discovery. Over the past decade, single-cell genomics has transformed how we map cells in human tissues. But a major challenge remains: can we systematically decode how cells organize into functional niches in situ — including those invisible to standard histopathology? To address this, we integrated large-scale scRNA-seq, spatial transcriptomics, histopathology, and AI-driven modeling frameworks to build an in situ atlas of human skin across health and disease. Led by Lloyd Steele, an MD/PhD student working between Haniffa Lab and my lab at Wellcome Sanger Institute and Cambridge University . Another amazing collaboration with Muzz Haniffa, the mastermind behind the work as part of Human Cell Atlas. A key part of this study is that we didn’t build everything from scratch — we leveraged and combined AI methods that actually work! and showed how they can be used together to extract biological insight at scale. We used: • scArches to build and map into a reference scRNA-seq atlas of human skin: • NicheCompass to identify and characterize spatial niches: • MINT-Flow to extract microenvironment-induced cell states and gene programs: Together, these enabled an end-to-end workflow from atlas construction to spatial mapping, niche discovery, and cell state decoding. At scale, we integrated ~5 million cells and 100+ spatial sections, enabling a systematic view of tissue organization. Using this framework, we identified 26 niches in skin, including known histopathologic structures as well as hidden disease-associated niches not visible on H&E. Among the most striking findings were a resident memory T cell-rich sebaceous gland niche and a plasma cell-rich sweat gland niche, suggesting that appendageal structures act as active immunological microenvironments and may contribute to inflammatory memory and disease persistence. Importantly, this atlas is not just descriptive — it is usable. It can support mapping of new datasets, resolve finer cell types and niches, extract microenvironment-driven programs, and enable predictive analyses at scale. More broadly, this work shows what becomes possible when AI, spatial genomics, and atlas-scale data are integrated end-to-end: not just mapping tissues, but systematically decoding them. This was a massive collaboration, and I’m very grateful to the amazing scientists April Foster, Kenny Roberts, and Chloe Admane. Lloyd is an amazing scientist, and I’m especially excited for the community to see more of his work soon — stay tuned. The data and pre-trained models will be released soon. Preprint:
1:09

Excited to share our new work on building a multimodal atlas of human skin in health and inflammatory disease — a project I’m especially proud of, bringing together AI, high-throughput genomics, and clinical science to accelerate discovery. Over the past decade, single-cell genomics has transformed how we map cells in human tissues. But a major challenge remains: can we systematically decode how cells organize into functional niches in situ — including those invisible to standard histopathology? To address this, we integrated large-scale scRNA-seq, spatial transcriptomics, histopathology, and AI-driven modeling frameworks to build an in situ atlas of human skin across health and disease. Led by Lloyd Steele, an MD/PhD student working between Haniffa Lab and my lab at Wellcome Sanger Institute and Cambridge University . Another amazing collaboration with Muzz Haniffa, the mastermind behind the work as part of Human Cell Atlas. A key part of this study is that we didn’t build everything from scratch — we leveraged and combined AI methods that actually work! and showed how they can be used together to extract biological insight at scale. We used: • scArches to build and map into a reference scRNA-seq atlas of human skin: • NicheCompass to identify and characterize spatial niches: • MINT-Flow to extract microenvironment-induced cell states and gene programs: Together, these enabled an end-to-end workflow from atlas construction to spatial mapping, niche discovery, and cell state decoding. At scale, we integrated ~5 million cells and 100+ spatial sections, enabling a systematic view of tissue organization. Using this framework, we identified 26 niches in skin, including known histopathologic structures as well as hidden disease-associated niches not visible on H&E. Among the most striking findings were a resident memory T cell-rich sebaceous gland niche and a plasma cell-rich sweat gland niche, suggesting that appendageal structures act as active immunological microenvironments and may contribute to inflammatory memory and disease persistence. Importantly, this atlas is not just descriptive — it is usable. It can support mapping of new datasets, resolve finer cell types and niches, extract microenvironment-driven programs, and enable predictive analyses at scale. More broadly, this work shows what becomes possible when AI, spatial genomics, and atlas-scale data are integrated end-to-end: not just mapping tissues, but systematically decoding them. This was a massive collaboration, and I’m very grateful to the amazing scientists April Foster, Kenny Roberts, and Chloe Admane. Lloyd is an amazing scientist, and I’m especially excited for the community to see more of his work soon — stay tuned. The data and pre-trained models will be released soon. Preprint:

Mo Lotfollahi

11,819 views • 4 months ago

Excited to share TERRA, a tissue world model 🧬 Over ~1.5 years we ran a large data-generation + modelling effort to build a world model for human tissues, pretrained on 112M cells from spatial transcriptomics (mostly Xenium 5000-plex + public data). It's built on one of the largest human spatial transcriptomics corpora assembled to date, spanning 20 tissues across development, health and 26 disease conditions, ~two-thirds newly generated in-house. Why a "world model" for tissue? Images have universal representations (ViT/DINOv3), so do proteins (ESM, Alex Rives) and pathology (UNI, Faisal Mahmood). We've worked hard to build something similar for human tissue: one model that captures its multi-scale logic, genes → cells → their native microenvironments. Like the JEPA approach Yann LeCun has championed, TERRA learns by prediction in embedding space, but for human tissue. How it works: it tokenises each cell together with its nearest neighbours into one sequence while keeping every gene's identity, then masks part of a neighbourhood and predicts the representation of the hidden part, not raw noisy counts. From one backbone it reads out three scales, gene embeddings (what a gene is doing in a cell and its niche), cell embeddings (cell type and state) and neighbourhood embeddings (the niche), and because it keeps gene-level resolution it can knock a gene out in silico and predict the response. Applied entirely zero-shot, TERRA maps and perturbs human tissue across unseen organs, diseases and technologies, outperforming existing spatial approaches. Three take-homes: 1️⃣ One model, any tissue. A single pretrained backbone provides tissue representations zero-shot, handling genes, cells and niches across organs and platforms, off the shelf. 2️⃣ New biology, development to clinic. We built a new spatial atlas of the developing human pancreas and found an islet-associated capillary state that looks like a precursor of mature islet vasculature. In kidney, TERRA's in silico knockouts predicted the tissue-injury programme from cancer immunotherapy (checkpoint blockade), confirmed in treated kidneys, detected in blood, and linked to declining kidney function. 3️⃣ A grammar of tissue architecture. By coupling each cell's state to its niche, TERRA defines recurring cross-organ "archetypes" of macrophage neighbourhoods, including a tumour-boundary niche that tracks poor survival in kidney cancer. TERRA is already in use: it powered our recent skin atlas of hidden immune-memory niches ( with more studies coming soon. This was an amazing collaboration between clinicians, machine-learning scientists and cell biologists 🙏 Led by Sebastian Birk, Vali Sanian Amirhosein Vahidi, Samuel Ogden, Daniyal Jafree, Adib Miraki, Carlo Leonardi and Arpit Merchant, with Lassi Paavolainen, Menna Clatworthy, Omer Ali Bayraktar, Muzlifah Haniffa, Tom Mitchell and Mostafa Bakhti. Huge thanks too to everyone who shared data and helped along the way. What excites me most is seeing how the community builds on this. The model, code and tutorials are all public, so anyone can run TERRA on their own tissues, extend it, or build new models on top. Huge thanks to the whole team across Wellcome Sanger Institute and our many collaborators. 📄 Paper: 💻 Code: 🤗 Model: #SpatialTranscriptomics #SpatialGenomics #FoundationModels #AI4Science #MachineLearning #ComputationalBiology #SingleCell #WorldModels
2:15

Excited to share TERRA, a tissue world model 🧬 Over ~1.5 years we ran a large data-generation + modelling effort to build a world model for human tissues, pretrained on 112M cells from spatial transcriptomics (mostly Xenium 5000-plex + public data). It's built on one of the largest human spatial transcriptomics corpora assembled to date, spanning 20 tissues across development, health and 26 disease conditions, ~two-thirds newly generated in-house. Why a "world model" for tissue? Images have universal representations (ViT/DINOv3), so do proteins (ESM, Alex Rives) and pathology (UNI, Faisal Mahmood). We've worked hard to build something similar for human tissue: one model that captures its multi-scale logic, genes → cells → their native microenvironments. Like the JEPA approach Yann LeCun has championed, TERRA learns by prediction in embedding space, but for human tissue. How it works: it tokenises each cell together with its nearest neighbours into one sequence while keeping every gene's identity, then masks part of a neighbourhood and predicts the representation of the hidden part, not raw noisy counts. From one backbone it reads out three scales, gene embeddings (what a gene is doing in a cell and its niche), cell embeddings (cell type and state) and neighbourhood embeddings (the niche), and because it keeps gene-level resolution it can knock a gene out in silico and predict the response. Applied entirely zero-shot, TERRA maps and perturbs human tissue across unseen organs, diseases and technologies, outperforming existing spatial approaches. Three take-homes: 1️⃣ One model, any tissue. A single pretrained backbone provides tissue representations zero-shot, handling genes, cells and niches across organs and platforms, off the shelf. 2️⃣ New biology, development to clinic. We built a new spatial atlas of the developing human pancreas and found an islet-associated capillary state that looks like a precursor of mature islet vasculature. In kidney, TERRA's in silico knockouts predicted the tissue-injury programme from cancer immunotherapy (checkpoint blockade), confirmed in treated kidneys, detected in blood, and linked to declining kidney function. 3️⃣ A grammar of tissue architecture. By coupling each cell's state to its niche, TERRA defines recurring cross-organ "archetypes" of macrophage neighbourhoods, including a tumour-boundary niche that tracks poor survival in kidney cancer. TERRA is already in use: it powered our recent skin atlas of hidden immune-memory niches ( with more studies coming soon. This was an amazing collaboration between clinicians, machine-learning scientists and cell biologists 🙏 Led by Sebastian Birk, Vali Sanian Amirhosein Vahidi, Samuel Ogden, Daniyal Jafree, Adib Miraki, Carlo Leonardi and Arpit Merchant, with Lassi Paavolainen, Menna Clatworthy, Omer Ali Bayraktar, Muzlifah Haniffa, Tom Mitchell and Mostafa Bakhti. Huge thanks too to everyone who shared data and helped along the way. What excites me most is seeing how the community builds on this. The model, code and tutorials are all public, so anyone can run TERRA on their own tissues, extend it, or build new models on top. Huge thanks to the whole team across Wellcome Sanger Institute and our many collaborators. 📄 Paper: 💻 Code: 🤗 Model: #SpatialTranscriptomics #SpatialGenomics #FoundationModels #AI4Science #MachineLearning #ComputationalBiology #SingleCell #WorldModels

Mo Lotfollahi

50,313 views • 18 days ago