Headlines

Knee osteoarthritis (KOA) affects more than 1 in 10 people over 40 years of age, impairing patients' mobility and quality of life.

EAST LANSING, Mich. — Transitioning to regenerative agriculture can be a slow and complicated process, whether farms adopt no-till, cover crops, precision nutrient management, new crops or “everything but the kitchen sink.” Michigan State University’s Long-Term Agroecosystem Research (LTAR) site has taken the latter approach, and now, five years into a cropping systems experiment, scientists […] The post Upcoming LTAR Field Day to Highlight Five Years of Regenerative Agriculture Research appeared first on Morning Ag Clips.

Scientists are shedding new light on a little-known biological system that could help unlock the full potential of stem cell therapy, one of the most promising areas of modern medicine.

Vanderbilt will build an AI triage agent into its EHR to speed Alzheimer's patients to treatment. What it would do, and who is funding it.

Osteoarthritis (OA) is a chronic, painful joint disease and a leading cause of disability. Despite its prevalence, therapies for osteoarthritis are limited and focus on symptom management.

An AI foundation model extracted hidden physiological patterns from routine polysomnography and identified five patient groups with distinct long-term risks of mortality, cardiovascular disease, and neurological disorders. The approach outperformed apnea–hypopnea index severity categories for risk stratification and remained informative in an independent sleep cohort.

Gastroesophageal reflux disease is commonly associated with burning chest pain, regurgitation and irritation of the esophagus, but the disorder begins with changes that are far smaller than the symptoms they eventually produce. One of the earliest microscopic signs is the appearance of dilated intercellular spaces, or DIS, in the esophageal lining. These widened gaps between […]

The latest news and headlines from Yahoo! News. Get breaking news stories and in-depth coverage with videos and photos.

A new review in Genes & Diseases examines how T cell exhaustion may become both an obstacle and an opportunity in organ transplantation. The immune state, best known from chronic infections and cancer, arises when T cells are exposed to persistent antigen stimulation for extended periods. Rather than remaining fully functional, these cells gradually lose […]

Transplanted human interneurons, a type of nerve cell, formed working connections in the injured spinal cords of rats and improved breathing, supporting their potential as a possible treatment for spinal cord injuries in people. The post Engineered Human Interneuron Transplants Repair Respiratory Circuits in Injured Rats appeared first on GEN - Genetic Engineering and Biotechnology News.

Scientists are drawing attention to an underexplored molecular system that may determine how effectively stem cells repair damaged tissues, preserve their regenerative properties, and mature into specialized cell types. A new review in Genes & Diseases examines the role of PIWI proteins and PIWI-interacting RNAs, commonly known as piRNAs, in stem cell biology and therapy. […]

Experts at City of Hope, one of the nation's largest and most advanced cancer research and treatment organizations, are shining a spotlight on the risk of skin cancer faced by hematopoietic cell transplant (HCT) survivors, as well as the need for early detection. New City of Hope research published in Journal of the National Comprehensive Cancer Network shows how a cost-effective, scalable education program targeting survivors and their doctors can significantly improve screening.

Myotonic dystrophy type 1, or DM1, has long been recognized as a disease of defective RNA processing, but new research suggests that its damage begins even earlier in the formation of muscle fibers. In a study published in Nature Communications, V. Todorow, X. Lornage, S. Hayashi and colleagues report that depletion of the RNA-binding protein […]

Osteoarthritis (OA) is a chronic, painful joint disease and a leading cause of disability. Despite its prevalence, therapies for osteoarthritis are limited and focus on symptom management. Now, researchers are combining genetic studies of Utah families with AI-based molecular biology tools to find new medications that may ultimately help treat OA at its source.

Twenty-six total procedures have now been completed with the Jasper robotic surgical platform, allowing the surgical team to maintain standard clinical workflow.ForSight Robotics announced in a press release the completion of 14 more procedures by Alexey Rapoport, MD, with Robert Edward T. Ang, MD, as principal investigator. The company announced in April that Rapoport and Ang had completed the first in-human procedures with the Jasper platform.Surgeons completed all 26 procedures without having to switch to manual surgery, according to the release.The platform allowed the clinical team to

The identification of the cancer cell of origin is a fundamental issue in cancer biology. We used fluorescent lineage tracing of independent mouse skin stem cell populations, single-cell transcriptomics, and duplex sequencing to identify the origin of ...

Women may hold one of nature’s most important clues to the biology of aging, according to a new perspective published in Cell. The paper introduces the Reproductive Resilience Hypothesis, an evolutionary framework proposing that reproduction and longevity are not always opposing biological investments. Instead, in species where reproductive success depends on surviving, recovering, caregiving, or […]

Experts at City of Hope, one of the nation's largest and most advanced cancer research and treatment organizations, are shining a spotlight on the risk of skin cancer faced by hematopoietic cell transplant (HCT) survivors, as well as the need for early detection.

Intellia Therapeutics said it discovered a common link among the patients who faced the highest liver enzyme elevations after receiving its CRISPR gene editing treatment for ATTR amyloidosis. The gene editing ...

Why do women, on average, live longer than men yet often face a greater burden of chronic disease later in life? Why do some of the most fertile animals in nature, including queen bees and naked mole-rat queens, also live exceptionally long lives?

Robot-assisted surgery (RAS) is one of the most advanced tools in modern medicine. These systems give surgeons extreme precision, allowing procedures to be performed through small incisions that minimize both pain and recovery time. Yet even with this sophisticated technology, operations still depend on a human surgeon, who must stay intensely focused for hours while making medical decisions. With RAS increasingly adopted worldwide, understanding what it demands of surgeons is critical.

THURSDAY, Aug. 6, 2026 — Peanut allergies might be treatable by using a fecal transplant to introduce “good” bacteria into a person’s digestive tract, a new study says.Some young adults with peanut allergies wound up with a higher tolerance to...

Health systems and hospitals are widely adopting AI solutions in administrative and clinical workflows, but there are significant gaps in strategy, validation, testing environments and success measurement, according to a new report from the Center for Connected Medicine at UPMC and KLAS Research.

Robot-assisted surgery is often portrayed as the ultimate expression of precision medicine: a surgeon seated at a console, controlling miniature instruments that move through tiny incisions with extraordinary accuracy. But behind the technology, the procedure remains a demanding human performance. Surgeons must interpret three-dimensional images, control delicate instruments, anticipate complications, communicate with the operating team, […]

FDA and CMS held a closed-door clinical AI event with 10 tech companies. What is routine, what is disclosed, and why patient groups want access.

Robot-assisted surgery (RAS) is one of the most advanced tools in modern medicine. These systems give surgeons extreme precision, allowing procedures to be performed through small incisions that minimize both pain and recovery time.

The Gerontological Society of America (GSA) has announced a new slate of elected officers who will help guide one of the world’s largest interdisciplinary organizations devoted to aging. Chosen by more than 6,000 members—including researchers, educators, clinicians, and policy professionals—the incoming leaders will begin their terms on January 1, 2027. Their appointments arrive as population […]

arXiv:2608.04826v1 Announce Type: new Abstract: In pan-omics pan-cancer studies, it is critical to identify latent sources of variation that are shared across particular subsets. This task often requires bidimensionally linked data matrices to be decomposed into a sum of block-sparse, low-rank modules. Existing approaches often rely on pre-specified module numbers, ranks, or post-hoc thresholding and can be sensitive to model specification when the underlying sharing structure is complex. To address these issues, we propose GL-BIDIFAC+, a group-regularized matrix factorization framework for discovering partially shared modules. It requires only an upper bound on the latent dimension and encourages module selection through group regularization with theoretically-motivated tuning parameter selection and local support recovery analysis, providing both scalability and principled guidance for module discovery. It also admits a probabilistic interpretation that enables model-based

arXiv:2608.04215v1 Announce Type: new Abstract: The growing diversity of code clone types, from syntactic copies to cross-language semantic clones to AI-generated duplicates, has created a fragmentation crisis in clone detection. Current deep learning detectors are domain specialists that degrade significantly outside their training distribution, with F1 drops exceeding 70% across domains. Deploying multiple specialized models is impractical, yet training a single cross-domain detector requires simultaneous access to all training data. To address this, we investigate model merging, a family of post-hoc techniques that operate solely on trained checkpoints. We evaluate parameter merging with five task-vector methods, architecture merging via greedy layer stitching, and cross-tokenizer alignment across four code models, three benchmarks, and twelve configurations. Same-base TIES merging creates effective cross-domain detectors, validated across two model families and three random seeds,

A healing colon does not simply switch genes on and off. Its cells appear to follow a complex daily timetable, with different populations activating distinct genetic programs at different times. A new study by V. Carmona-Alcocer, C. Gobet, J. MacDonald and colleagues introduces a “chrono-atlas” designed to chart these cell-type-specific rhythms during colon regeneration, offering […]

Food allergy researchers at Boston Children’s Hospital have reported early evidence that changing the gut microbiome may increase tolerance to peanuts, offering a potential new strategy for people living with severe and potentially life-threatening reactions. In a small clinical trial, participants who received fecal microbiota transplantation from healthy donors showed signs of improved peanut tolerance […]

The cerebral cortex is densely packed with different nerve cells that enable us to perceive, think and act. Yet how these cell types arise while the brain develops is still not fully understood.

Digestion is hard on the cells that line the human gut, and they are constantly being shed and replaced. This renewal is driven by a population of tireless stem cells.

Hong Kong’s redevelopment policy is approaching an institutional turning point. Recent government proposals – pilot schemes for additional plot ratios and cross-district plot ratio transfers – are presented as new instruments to stimulate redevelopment in ageing districts. Yet they extend the same paradigm that shaped policy for decades: incentivising redevelopment through floor-area bonuses, relying on land premium as the financial logic and assuming more buildable area will automatically...

NHS HRT prescribing has doubled in 5 years, but pharmacists warn that rising demand is straining an already stretched supply chain.

Researchers at The University of Texas MD Anderson Cancer Center have discovered that immunosuppressed patients with non-melanoma skin cancer are not missing the key cancer-fighting immune cells found in immunocompetent patients, but those cells – known as macrophages – have lost the ability to communicate effectively.

Cells become senescent throughout life, because of stress or damage or reaching the Hayflick limit on replication, but senescent cells only begin to accumulate with age. When a cell becomes senescent, it grows in size, ceases to replicate, and turns its energies to creating signals promoting inflammation and growth. The immune system is responsible for destroying senescent cells after they have served their purpose, which is usually to attract the attention of immune cells to locations where they are needed to prevent or repair issues. While clearance of senescent cells is efficient in young people, it becomes much less efficient with age, allowing a population of lingering senescent cells to grow over time in tissues throughout the body. The pro-growth, pro-inflammatory signals that are helpful […]

Some 33 million Americans have severe food allergies. Now, researchers at Boston Children's Hospital may have found a promising solution. In a small clinical trial, Rima Rachid, M.D., director of the Food Allergy Program and the Allergen Immunotherapy Program, and Talal Chatila, M.D., director of translational immunology, and their colleagues found that some participants with peanut allergies experienced a higher tolerance to peanuts months after receiving a fecal transplant from a healthy donor without food allergies. Their findings are published in Science Translational Medicine.

A contract manufacturer running multiple adeno-associated virus (AAV) programs says early engagement between key stakeholders, proactive risk assessments and platform knowledge is core to the successful delivery of gene therapies. The post Seamless Integration in Gene Therapy Process Development appeared first on GEN - Genetic Engineering and Biotechnology News.

Steven Levy / Wired: Jeff Dean and three other Google execs are leaving to launch Discovery Loop, which will seek AI-powered breakthroughs in drug discovery, chip design, and more  —  Jeff Dean and other high-profile Google executives have founded Discovery Loop, a startup that will seek AI-powered breakthroughs …

Researchers from the Rolf Luft Research Center for Diabetes and Endocrinology at Karolinska Institutet have developed a targeted RNA technology to prepare pancreatic islet cells for transplantation. The technology briefly boosts a gene that drives blood vessel growth, prompting grafts to re-establish their blood supply sooner and shortening the vulnerable, low-oxygen window that normally follows transplantation. In studies using both mouse and human islets, treated cells engrafted more effectively and required fewer donor islets to restore normal blood sugar control.

Matt Walker couldn't pet a dog without sneezing—until he and other scientists used a gene editing technique to produce a hypoallergenic beagle named Bailey.

WEDNESDAY, Aug. 5, 2026 — Vanessa Barahona received a call this past spring from Angelica at Kern Family Health Care in Bakersfield, California, telling her it was time to renew her coverage under Medi-Cal, the state’s version of Medicaid.Angelica...

Click here to read the Healio Exclusive, “Embrace the future’ of robotics in ophthalmology.”I wrote an earlier perspective on the application of robotics to eye surgery in the April 25, 2024, issue of Healio | OSN.Since that time, significant progress has been made, including completion of the first in-human robot-assisted cataract surgery by two leading companies in the field, Horizon Surgical Systems and ForSight Robotics. In addition, I have participated in several meetings in which the application of robotics to eye surgery has been discussed and debated in the main sessions and between

A growing body of scientific insight is drawing attention to cellular senescence as a central force in the progression of intervertebral disc degeneration (IDD), a leading contributor to chronic low back pain worldwide.

Scientists at a biotech company have used gene editing to create two hypoallergenic beagles that don't trigger allergiesMatt Walker couldn’t pet a dog without sneezing – until he and other scientists used a gene editing technique to produce a hypoallergenic beagle named Bailey. Now, he can feed Bailey spoons of peanut butter while she lies on his lap and play fetch with her in Central Park. His allergies didn’t go away: Bailey’s saliva and hair no longer contain a key allergy-causing protein. Continue reading...

A new lipid nanoparticle system has enabled researchers to genetically modify human haematopoietic stem and progenitor cells (HSPCs) inside humanized mice, addressing one of the most difficult challenges in gene therapy: reaching rare, quiescent stem cells without compromising their ability to produce blood cells over the long term. The study, published in Nature Biomedical Engineering, […]

Vanessa Barahona received a call from Angelica at Kern Family Health Care in Bakersfield, California, telling her it was time to renew her coverage under Medi-Cal, the state's version of Medicaid.

A comprehensive new review highlights the expanding importance of Lgr6, a member of the G protein-coupled receptor family, as a critical regulator of tissue homeostasis, injury repair, and disease development across multiple organ systems.

Gene-edited beagles may offer a future option for people with dog allergies  AP NewsSee more headlines & perspectives on Google News

Gene-edited beagles may offer a future option for people with dog allergies  AP NewsSee more headlines & perspectives on Google News

The puppies represent a key first step towards addressing canine allergenicity and mark potentially a significant advance in veterinary biotechnology. The post Fur Real: Biotech Startup Eliminates Major Dog Allergen in Beagle Pups Using CRISPR appeared first on GEN - Genetic Engineering and Biotechnology News.

Among patients with primary CNS lymphoma who respond to induction therapy, high-dose chemotherapy with stem cell transplant improves survival compared with nonmyeloablative chemotherapy.

The latest news and headlines from Yahoo! News. Get breaking news stories and in-depth coverage with videos and photos.

Kern Family Health Care uses an AI agent to call Medi-Cal members about renewals. Here is what it does, what it costs, and what oversight is in place.

A startup has created beagles without the gene that causes runny noses and watery eyes for allergy sufferers.

British barley growers will receive premium payments to adopt regenerative farming methods under a Heineken UK programme expected to supply ...

Food labels and messaging that lead with environmental claims only resonate with about 30% of US consumers. The post Economics trump environment when it comes to commercializing regenerative ag: report appeared first on AgFunderNews.

arXiv:2608.02866v1 Announce Type: new Abstract: Recent AI advances have enabled protein structure prediction at near-experimental accuracy, largely solving the problem of identifying a dominant conformation from sequence. Many proteins, however, function as dynamic systems populating multiple conformational states with activity emerging from shifts in relative occupancy--an incomplete picture when reduced to one structure. Here, we argue that structure prediction should be reformulated as a state-space inference problem: recovering not one conformation's coordinates but accessible states, their energetic and kinetic relationships, context dependence, and responses to perturbations. We review emerging strategies--deep learning ensemble generators, physics-based simulations, and experimental constraints--and outline a roadmap toward state-space prediction.

arXiv:2608.03017v1 Announce Type: cross Abstract: There has been significant interest in using machine learning algorithms to predict kidney transplant outcomes, such as the number of years until a graft inevitably fails. These prediction algorithms could possibly be used for pre-transplant donor-recipient matching to identify more compatible donors and recipients and thus improve post-transplant outcomes. In this study, we explore the use of survival prediction models trained on deceased donor kidney transplant data from the Scientific Registry of Transplant Recipients (SRTR). We propose a novel paired recipient-based evaluation framework that compares graft outcomes between two recipients who received kidneys from the same deceased donor, allowing us to evaluate the counterfactual benefit of changing the recipient for a certain donor. We find that five different survival prediction models, ranging in complexity from linear to deep learning-based models, all result in ~60% paired

arXiv:2608.03835v1 Announce Type: new Abstract: Tomographic emissivity reconstruction from plasma diagnostics data relies on a synthetic model mapping the plasma emissivity to the measured signals. The model, referred to as a geometry matrix in the plasma imaging community, is often built using the line-of-sight (LoS) approximation. This approximation neglects the finite width of the detector viewing beams and can therefore introduce systematic errors. Physically correct volume-of-sight (VoS) models remove this inaccuracy by accounting for the full 3D extent of the viewing beams. Their adoption, however, is sometimes hindered by the difficulty of independently validating them. We present an intuitive and easily inspectable voxel-to-detector (V2D) approach for computing physically accurate VoS geometry matrices, based on discretizing the tokamak vessel into voxels and estimating the contribution of each voxel to the measurements of each detector. We apply the V2D approach to the soft

Kern Family Health Care uses an AI agent to call Medi-Cal members about renewals. Here is what it does, what it costs, and what oversight is in place.

Hepatocellular carcinoma, the most common primary cancer of the liver, is notoriously difficult to treat once it becomes advanced. Even when chemotherapy or targeted treatment initially slows tumor growth, a resilient population of cancer cells can survive, adapt and eventually return in a more aggressive form. A study by Xu, Huang, Zhang and colleagues, published […]

© seekingalpha.com. Use of this feed is limited to personal, non-commercial use and is governed by Seeking Alpha's Terms of Use (https://about.seekingalpha.com/terms). Publishing this feed for public or commercial use and/or misrepresentation by a third party is prohibited.

Parkinson’s disease research is increasingly turning its attention away from neurons alone. A new study by Smits, Magni, Grzyb and colleagues reports that the Parkinson’s-associated LRRK2-G2019S mutation may disrupt the development of astrocytes, the star-shaped support cells that help maintain the brain’s chemical balance, protect neurons and regulate local inflammation. The findings, published in npj […]

Authors argue that uncritical AI adoption in women’s health may encode reductive views of sex and gender, expand surveillance, and reproduce existing inequities. They call for greater scrutiny across the AI pipeline, community involvement, and structural change alongside carefully selected technologies.

Penn researchers found that TRF2, long known for protecting chromosome ends, also preserves muscle stem cell identity during injury repair in mice.

© seekingalpha.com. Use of this feed is limited to personal, non-commercial use and is governed by Seeking Alpha's Terms of Use (https://about.seekingalpha.com/terms). Publishing this feed for public or commercial use and/or misrepresentation by a third party is prohibited.

A Banner Phoenix cardiologist built an inpatient prehab gym for heart transplant candidates after watching bed rest disqualify them from surgery.

Learn more about the medical treatments CRISPR could improve and the ethical concerns it raises. 

FSMB leaders say AI should not be licensed as a separate practitioner, as bills in Idaho and Iowa and a Utah pilot push the question to states.

The question is no longer whether young people are using AI for mental health care, but the soundness of the advice they receive, health officials say.

Insilico Medicine ("Insilico"), a clinical-stage generative artificial intelligence (AI)-driven biotechnology company, today announced the publication of a collaborative study in the journal npj Precision Oncology.

CAMBRIDGE, Mass. — Aug. 4, 2026 — A new study is showing how artificial intelligence and multi-omic biology can expose therapeutic opportunities in one of the world’s rarest and least understood cancers. Published in npj Precision Oncology, the research provides the first comprehensive molecular characterization of inverted papilloma-associated sinonasal squamous cell carcinoma, or IP-SNSCC, an […]

A one-size-fits-all approach likely isn't the best strategy when designing artificial intelligence systems that assist users in disease diagnosis.

Researchers have demonstrated that AI tools could play an important part in developing simpler, lower-cost technologies for monitoring foot health, particularly in settings where access to specialized equipment may be limited. The research is published in Sensors.

Transposable elements, once dismissed as genomic “junk,” are emerging as active regulators of cell identity, stress responses and disease. A new study published in Cell Death Discovery examines how these mobile DNA sequences are expressed and regulated in an adult stem cell with major physiological and clinical importance. The work, led by Fu, Cai, Zhao […]

A year ago, the concept of an “AI doctor” was brand new. Now there are several startups using artificial intelligence to handle patient intake for medical visits and suggest potential diagnoses and treatment plans — though ...

An Australian-first study of twins will seek to find out why two genetically similar people respond differently to infections, diseases and treatments.

An Australian-first twin study is set to investigate why people with highly similar genetic backgrounds can respond very differently to infections, immune-mediated diseases and medical treatments. Researchers from the Snow Centre for Immune Health and the University of Melbourne’s Twins Research Australia will recruit 100 pairs of identical and non-identical twins between the ages of […]

Ученые Томского политехнического университета вместе с коллегами из Санкт-Петербурга, Гамбурга, Лондона провели исследование, в котором впервые показали, что полимерные и гибридные микрокапсулы с покрытиями из наноразмерного слоя двуокиси кремния могут с высокой эффективностью применяться при редактировании генома с использованием технологии CRISPR-Cas9. В перспективе совместная разработка ученых ТПУ и их коллег сможет существенно упростить и повысить эффективность процедуры редактирования генома, которая в будущем поможет врачам лечить ранее неизлечимые наследственные заболевания, такие как болезнь Альцгеймера, гемофилия и многие другие, сообщает пресс-служба ТПУ. Результаты исследования опубликованы в журнале Nanomedicine: Nanotechnology, Biology and Medicine (IF 5,72; Q1). Авторами научной статьи стали ученые лаборатории новых лекарственных форм Центра RASA на базе Томского политехнического университета (ТПУ), Первого государственного

arXiv:2608.02547v1 Announce Type: new Abstract: Action chunking---predicting and executing multiple actions instead of a single action---has proven to be a critical component for learning effective robotic control policies. However, our precise understanding of why action chunking improves performance has remained limited. In this work we seek to close this gap. Through rigorous experimental evaluations in both simulated and real-world settings, we show that existing hypotheses for the success of action chunking---temporal consistency, horizon reduction, and representation learning---fail to explain the success of action chunking. Instead, we find that action chunking benefits from greater non-Markovian expressivity and reduced compounding error compared to Markovian policies, but, in many settings of interest, these effects can be fully captured by delayed policies, which at each step predict a single action based on the observation $k$ steps in the past. We then show that there

arXiv:2608.02238v1 Announce Type: new Abstract: Ensuring trust in AI systems is essential for the safe and ethical integration of machine learning systems into high-stakes domains such as digital health. Key dimensions, including robustness, explainability, fairness, accountability, and privacy, need to be addressed throughout the AI lifecycle, from problem formulation and data collection to model deployment and human interaction. While various contributions address different aspects of trustworthy AI, a focused synthesis on robustness and explainability, especially tailored to the healthcare context, remains limited. This review addresses that need by organizing recent advancements into an accessible framework, highlighting both technical and practical considerations. We present a structured overview of methods, challenges, and solutions, aiming to support researchers and practitioners in developing reliable and explainable AI solutions for digital health. This review article is

arXiv:2608.01686v1 Announce Type: new Abstract: In recent years, generative AI has attracted significant public attention, and its use has been rapidly expanding across a wide range of domains. From creative tasks such as text summarization, idea generation, and source code generation, to the streamlining of medical support tasks like diagnostic report generation and summarization, AI is now deeply involved in many areas. Today's breadth of AI applications is clearly distinct from what was seen before generative AI gained widespread recognition. Representative generative AI services include DALL-E 3 (OpenAI, California, USA) and Stable Diffusion (Stability AI, London, England, UK) for image generation, ChatGPT (OpenAI, California, USA), and Gemini (Google, California, USA) for text generation. The rise of generative AI has been influenced by advances in deep learning models and the scaling up of data, models, and computational resources based on the scaling laws. Moreover, the

arXiv:2608.01669v1 Announce Type: new Abstract: Gene perturbation analysis plays a critical role in drug discovery by enabling researchers to investigate how interventions on specific genes influence global gene expression patterns within cells. Recent advances in artificial intelligence-driven virtual cell models have made it possible to predict gene expression outcomes for a wide range of perturbation strategies in silico, substantially reducing reliance on costly and time-consuming biological experiments. However, effectively exploring and interpreting the high-dimensional perturbation spaces produced by these models remains challenging because of the combinatorial nature of perturbations and the complex cell-specific gene expression responses they generate. In this work, we present CellPrism, a visual analytics system designed to support the systematic exploration of gene perturbation strategies for drug discovery. Specifically, CellPrism integrates clustering-based overviews to