Cellular Intelligence has appointed Arjun Raj as chief scientific officer and named him scientific co-founder. Raj, a University of Pennsylvania professor, joined the company full-time in 2025 as head of computational biology and has now extended his leave to expand his role. The Boston-based AI company is building a foundation model of cell signalling. Raj co-developed a method for visualising RNA molecules in single cells and will lead the integration of experimental biology, computational biology, and machine learning. Cellular Intelligence has raised over $70 million from investors including Khosla Ventures and the Chan Zuckerberg Initiative. In May, the company acquired STEM-PD, an investigational Phase 2-ready Parkinson's disease cell therapy programme, from Novo Nordisk.

Cellular Intelligence names single-cell biology pioneer Arjun Raj, Ph.D., chief scientific officer and scientific co-founder. Renowned University of Pennsylvania professor takes on expanded leadership role to advance the company's science and scale its closed-loop cell signaling platform. BOSTON, Aug. 12, 2026 /PRNewswire/ - Cellular Intelligence, the AI company building a universal foundation model of cell signaling, today announced that Arjun Raj, Ph.D., has been appointed chief scientific officer and named scientific co-founder. Raj joined the company full-time in 2025 as head of computational biology while on leave from the University of Pennsylvania. Combining a background in mathematics and systems biology, Raj spent his first year architecting Cellular Intelligence's data engine and scientific program. He has now extended his leave and expanded his mandate to lead overall scientific strategy. Discover more Medical Facilities & Services Naming Raj scientific co-founder recognizes the foundational role he has played at the company, from the design of its experiments and data generation methodologies to the development and validation of its models. As chief scientific officer, he will lead the integration of experimental biology, computational biology, machine learning, and translational science into a closed-loop system built to understand, predict, and ultimately control cell behavior. "Arjun joined us because he saw the possibility of building something biology has never had: massive, context-rich, time-resolved perturbation datasets, and models purpose-built to learn from them. In his first year at the company, he helped turn that possibility into reality," said Micha Breakstone, Ph.D., co-founder and chief executive officer of Cellular Intelligence. "Arjun moves fluently between machine learning and experimental biology while remaining deeply grounded in fundamental science. Naming him scientific co-founder recognizes the company he has already helped build. As chief scientific officer, he will lead our efforts to scale the foundation model and unlock a new era of predictable cell engineering." Cellular Intelligence has developed a proprietary capsule-based platform that runs time-varying, sequential signaling combinations in parallel within a single experiment, expanding the scale of controlled perturbation experimentation by orders of magnitude. Rather than relying on static observations collected for other purposes, the company designs controlled, intervention-rich experiments that reveal how cells respond as signals, timing, and context change. The resulting data train models that identify gaps in their own understanding, guide the next generation of experiments, and improve with every cycle. "I have spent my career trying to understand how individual cells make decisions, and what has always limited the field is the data," said Arjun Raj, scientific co-founder and chief scientific officer of Cellular Intelligence. "Cellular Intelligence is building high-fidelity, time-resolved perturbation data generated expressly for learning. For the first time, I can see a path from observing cellular decisions to predicting and eventually controlling them." Discover more Academic Conferences & Publications Healthcare Raj is the Richard K. Lubin Professor of Bioengineering and Professor of Genetics at the University of Pennsylvania. A mathematician turned experimental systems biologist, he co-developed a foundational method for visualizing and counting individual RNA molecules inside single cells. His lab has since made influential contributions to understanding stochastic gene expression, cell identity, rare non-genetic states in cancer therapy resistance, and cellular memory. He received his bachelor's degree in physics and mathematics from the University of California, Berkeley, and his doctorate in mathematics from the Courant Institute at New York University. He completed postdoctoral training at the Massachusetts Institute of Technology and joined Penn's faculty in 2010. Engineering & Technology Raj's expanded role comes as Cellular Intelligence connects its foundation-model platform to a direct path to patients. In May, the company acquired STEM-PD, an investigational Phase 2-ready Parkinson's disease cell therapy program, from Novo Nordisk. STEM-PD is both a therapy the company is working to advance for patients and a proving ground for the company's technology, in which models help sharpen protocol optimization, manufacturing scalability, comparability, potency, and dosing, and in which clinical and manufacturing insights flow back into those models. The result is a continuous learning system - described in a recent white paper, "From Model to Medicine - and Back" - in which better science aims to yield a better therapy, and the therapy in turn strengthens the science. About Cellular Intelligence Cellular Intelligence is building a universal foundation model for cell signaling to understand, predict, and ultimately control how cells behave, transforming biology from trial and error into an engineering discipline. A clinical-stage AI company, Cellular Intelligence holds the global rights to STEM-PD, an investigational Phase 2-ready cell therapy for Parkinson's disease with FDA Fast Track designation, acquired from Novo Nordisk. The company's founding team includes repeat AI entrepreneur Dr. Micha Breakstone (Chorus.ai, acquired for $575M), the Head of the Fundamental AI Group at MIT, and five professors from Harvard Medical School, the University of Pennsylvania, and the University of Washington, collectively holding five National Academy memberships. Based in Boston, Cellular Intelligence has raised over $70M from Khosla Ventures, the Chan Zuckerberg Initiative, Novo Nordisk, AMD Ventures, and others. STEM-PD is an investigational therapy. Its safety and efficacy have not been established. SOURCE Cellular Intelligence

Virtual cells go multiscale to predict complex biology. Posted on July 24, 2026 By News Staff Virtual cell models that enable the prediction of cell behavior across scales and biological contexts are rapidly emerging at the forefront of drug discovery. Tom Sercu, PhD, vice president of AI and engineering at Biohub, points to a clinician-scientist studying a rare autoimmune disease as an example of how AI models could reshape translational medicine. Starting from a patient's genome, researchers could use virtual cells to predict how major immune cell types behave in disease versus healthy states. The result offers an invaluable tool across target and mechanism-of-action discovery, patient stratification, toxicity prediction, and therapeutic development. Yet, building a virtual cell is not an easy feat. "Transformative AI in biology does not come from algorithms alone, but when models are trained on large-scale, high-quality, openly accessible datasets," says Sercu. To capture complex biology, such data must span model systems and organisms, interventional and observational methods, and diverse cellular states. To support this mission, Biohub announced a $500 million commitment to the Virtual Biology Initiative in April. The five-year campaign will accelerate the generation of technologies and multi-modal datasets needed to power virtual cell models. Similar to how more than 253,000 experimentally determined molecular structures in the Protein Data Bank (PDB), assembled over five decades, became foundational training data for modern AI protein-structure prediction, Sercu sees an analogous moment for cellular biology. "We do not yet have the equivalent of the PDB for cells," he emphasized. "The Virtual Biology Initiative seeks to change that." Today's virtual cell developers reflect on what's needed for these models to predict complex biology and overhaul drug discovery. Single or bulk. Much of the industry has defined the virtual cell as transcriptome models that predict how perturbations alter gene expression across cellular contexts. Among the increasingly crowded ecosystem, Arc Institute's first-generation virtual cell model, STATE, predicts how stem cells, cancer cells, and immune cells respond to drugs, cytokines, or genetic perturbations. In March, billion-dollar-backed, Xaira Therapeutics unveiled X-Cell, the first scaling law demonstrator in the virtual cell domain, sizing up to a whopping 4.9 billion parameters. These models aim to generalize to unseen biological contexts by training on causal single-cell RNA sequencing (scRNA-seq) data. To train X-Cell, Xaira has spent its initial years building what the company describes as "the largest genome-wide CRISPRi Perturb-seq dataset ever reported." Named X-Atlas/Pisces, the dataset is composed of 25.6 million cells across seven screens and 16 biological contexts. Ginkgo Datapoints, the AI platform division of Ginkgo Bioworks, looks toward bulk transcriptomics rather than a single-cell approach. "Just like how models benefit from diversity in training data, we as an industry benefit from having diversity of approaches," said John Androsavich, PhD, general manager at Ginkgo Datapoints. The Datapoints team applies high-throughput automation to create diverse biological datasets, including cell perturbations, antibody developability, and ADME small molecule developability data, to support AI model training for life science partners. In March, Ginkgo Datapoints delivered the first data release of the Virtual Cell Pharmacology Initiative (VCPI). Approximately 2,280 small molecules were profiled in full dose response using DRUG-seq, a scalable arrayed transcriptomics assay measuring chemical perturbations. In contrast to scRNA-seq, which covers approximately 1,500 genes per cell, DRUG-seq captures nearly 10,000 genes per condition with higher signal-to-noise to optimize insights for pharmacology. Notably, VCPI has exclusively focused on THP-1, a human monocytic cell line widely used across immunology, oncology, and inflammatory disease research, to understand drug action. Across space. While the crowding around scRNA-seq has largely been driven by the pursuit of scale, "a cell is not only its RNA," tempers Hani Goodarzi, PhD, core investigator at Arc Institute. He emphasizes that cells are complex systems shaped by multiple layers of biology beyond gene expression alone, including protein abundance, chromatin state, spatial organization, metabolism, and post-translational regulation. A useful analogy comes from large language models (LLMs), which became powerful as text provided an exceptionally scalable substrate for training trillions of tokens. Yet, text alone is an incomplete representation of human communication. "The lesson is not that one modality is sufficient forever," says Goodarzi, "but that a single high-quality, scalable modality can support general representations when the training corpus is large." Emma Lundberg, PhD, co-founder and CSO at GenBio AI, is worried about the "streetlight effect." "We're scaling what we can and not necessarily what we should," she says. GenBio AI seeks to develop world models that cross multiscale biology. Instead of concentrating on one data modality, the company's so-called "AI-Driven Digital Organism" grows expertise in embedding, tokenizing, and training models across scales, from the molecular layer to regulatory networks. Rather than undergo internal data generation, GenBio AI focuses on public data and partnerships to power the company's models. Lundberg, who is also associate professor of bioengineering and pathology at Stanford University, argues that models can guide the field to which data modalities to pursue. As an example, models that incorporate biological priors, such as protein-protein interactions, can achieve noticeable improvements in predictive performance. Spatial and temporal data also capture critical dimensions of biological function that sequence data alone cannot resolve. According to the Human Protein Atlas, roughly 60% of human genes encode proteins that localize to multiple cellular compartments, often carrying out distinct functions depending on context. In a May preprint posted on bioRxiv, Lundberg and colleagues introduced ProtiCelli, a deep generative model that visualizes the spatial organization of nearly the entire proteome within individual cells. By training on 1.23 million images from the Human Protein Atlas, the model simulates microscopy images for 12,800 human proteins while also generalizing to unseen cell types and drug perturbations absent from training. Through time. Cellular Intelligence is developing a universal virtual cell signaling model designed to simulate cell-state transitions over time, with the goal of expanding the possibilities of regenerative medicine. By learning the underlying "grammar" through which sequences of signaling cues drive cell differentiation, these models aspire to enable the on-demand generation of any cell type. Less than one percent of known human cell types can be reliably produced for downstream applications in cell therapy. As only 20 fundamental molecular signaling pathways give rise to thousands of cell states, researchers face an unfathomably large search space when engineering a particular cell type. "Every cell that we discover or optimize opens a slew of potential applications," said Micha Breakstone, CEO and co-founder of Cellular Intelligence. "One could spend a decade and tens of millions of dollars on painstaking trial-and-error to differentiate a new cell type, or solve this problem in one fell swoop, much like AlphaFold for the protein folding challenge." The company's platform leverages a semi-permeable capsule technology, which selectively retains cells and large analytes while being freely accessible to media, enzymes, and reagents. The method enables high-throughput assays combining live-cell culture with genome-wide readouts. Millions of time-varying signal combinations are tested on human stem cell differentiation in parallel, providing 1,000 times higher efficiency than traditional methods. In May, Cellular Intelligence advanced as a Phase II-ready clinical company after entering an agreement with Novo Nordisk to acquire STEM-PD, an allogeneic cell therapy program for Parkinson's disease with Fast Track Designation. The deal comes six months after Novo announced its strategic exit from the cell therapy space. The start-up's AI cell signaling models will address protocol development, one of the biggest obstacles preventing cell therapies from clinical impact. "Novo selected Cellular Intelligence as the right partner because the next major challenge for complex cell therapy programs is not only the biology," says Breakstone. "It is manufacturing scale-up, comparability, clinical logistics, and commercial readiness." As the diversity of virtual cell models targets new dimensions of complex biology, every approach takes another step closer toward clinical impact.