Research institute · Science policy · Palo Alto, California · Est. 2021
Arc Institute is an independent nonprofit research organization headquartered in Palo Alto, California, focused on accelerating scientific progress and understanding the root causes of complex diseases. Its approach combines multi-year, no-strings-attached funding for investigators with institute-wide development of experimental and computational tools, positioned at the intersection of biology and artificial intelligence.
Arc operates in partnership with Stanford University, UC Berkeley, and UCSF, and it organizes its work around two institute initiatives: the Virtual Cell Initiative (focused on building predictive ML models of how cells respond to chemical and genetic perturbations) and the Alzheimer’s Disease Initiative (focused on identifying underlying drivers of Alzheimer’s disease and developing new drug candidates). Arc also emphasizes technology-building through specialized Technology Centers that aim to advance platforms such as its Virtual Cell efforts and related biomedical AI tooling, and it hosts community benchmarking efforts such as the Virtual Cell Challenge.
No curated programs yet. Check the careers page ↗.
We knew we had something interesting with T3p, a single small RNA found in breast cancer but absent from normal tissue. After being described in 2018, this molecule took our team on a six-year journey to systematically map orphan non-coding RNAs (oncRNAs) across all major cancer
Yusuf Roohani, Arc’s Associate Director of Machine Learning, on designing the architecture behind a virtual cellYusuf Roohani spent his PhD making machine learning models to predict how cells respond to genetic perturbations. Long before the term “virtual cell” was in vogue, Roohani was building tools to simulate and steer cellular behavior in industry and then in academia.
Arc Institute’s first virtual cell model: <span style="font-variant: small-caps">S<span style="font-weight: bolder">tate</span></span>Today, Arc is releasing its first generation virtual cell model, called State. The model is designed to predict how various stem cells, cancer cells, and immune cells respond to drugs, cytokines, or genetic perturbations.
Arc Institute launches its inaugural “virtual cell” competition using AI to solve one of biology’s biggest challengesThe competition, hosted by Arc Institute at virtualcellchallenge.org and sponsored by NVIDIA, 10x Genomics, and Ultima Genomics, is focused on accelerating progress in AI modeling of biology. Entrants will create models that will predict effects of single gene perturbations in ce
Virtual Cell Challenge 2025 Wrap-Up: Winners and ReflectionsThank you to every participant who made the inaugural Virtual Cell Challenge a success. The response far exceeded our expectations: over 5,000 people registered across 114 countries, over 1,200 teams submitted results, and over 300 teams made final submissions. We saw remarkable
Researchers reveal key differences in STING inhibition between humans and miceResearchers have long focused on the STING (Stimulator of Interferon Genes) pathway as a way to harness the immune system’s natural defenses against cancer. This pathway, which plays a key role in helping the body defend against potential pathogens, can be leveraged to trigger an
Proof-of-concept innate immune checkpoint inhibitor shows promise against solid tumors in rodentsBiochemist Lingyin Li has been pioneering a new direction for immunotherapy, searching for drugs that would turn these “cold” environments “hot”. Instead of stimulating T cells in the adaptive immune system, she focuses on harnessing cGAMP, one of the fast-acting inflammatory mol
Paul Datlinger, Arc’s Associate Director of Genome Engineering, on inventing the technologies needed to train a virtual cellOne of Arc’s Institute Initiatives is to build a highly predictive, single-cell foundation model that can help drug discovery efforts or assist biologists in their research. Released in June 2025, our first virtual model of a human cell, called STATE, can predict resulting shifts
Nianzhen Li, Arc’s Senior Director of Multi-omics Technology Development, on developing the experimental platform for a virtual cellIn a sense, Li’s team is building the experimental backbone for Arc’s most ambitious ideas. They may not be making new chips or devices from scratch, but they are stitching together tools—wet lab, automation, and software—into workflows that actually work at scale.
Meet Arc Science Fellow Maya Arce, who is unlocking the genetic underpinnings of autoimmune diseasesArce discusses her personal interest in tackling autoimmune diseases, her genomics-focused approach to immunology, and how Arc's emphasis on AI and complex diseases offered a supportive environment for her research goals.
Meet John Pluvinage, Arc’s 9th Core Investigator and first physician-scientistJohn Pluvinage (X: @jvpluv), Arc’s 9th Core Investigator and first physician-scientist, has arrived and is now setting up his lab. Pluvinage investigates the overlap between autoimmunity and neurodegeneration, aiming to decipher mechanisms and design targeted treatments for undia
Meet Arc Core Investigator Isha Jain, who is decoding how oxygen and nutrients shape our physiologyOn June 9, Arc welcomed Isha Jain as our eighth Core Investigator. Jain has spent more than a decade studying how the human body senses, and responds to, external molecules—especially oxygen and vitamins.
Arc announced the 2026 Virtual Cell Challenge with a zero-shot setting, expanded evaluation scope, and stated grand-prize and sponsor information.
Announcing the Arc AIxBio Fellows Program for UndergradsArc launched its Arc AIxBio Fellows Program for undergraduates, structured as a team-driven, project-owned research experience at the intersection of AI and life sciences.
Arc Institute launches its inaugural “virtual cell” competition using AI to solve one of biology’s biggest challengesArc announced the inaugural Virtual Cell Challenge (hosted with a public competition site and sponsored by NVIDIA, 10x Genomics, and Ultima Genomics), including dataset description and prize information.
Arc Institute’s first virtual cell model: S tateArc released its first-generation virtual cell model, S tate, describing model structure, training data scale (observational and perturbational), and release terms for noncommercial use.
10x Genomics and Ultima Genomics partner with Arc Institute to accelerate development of the Arc Virtual Cell AtlasArc announced partnerships with 10x Genomics and Ultima Genomics to scale perturbational single-cell data generation supporting the Arc Virtual Cell Atlas.
Arc Virtual Cell Atlas launches, combining data from over 300 million cellsArc launched the Arc Virtual Cell Atlas portal, describing initial dataset components (including Tahoe-100M and scBaseCount) and planned expansion focus.