Building the world's largest in vivo, single-cell atlas of how chemistry perturbs biology
Mosaic: The first platform to generate high-resolution in vivo data at scale
Single-cell resolution
.png)
One experiment, many patients
In vivo
AI models trained on our in vivo atlas that capture the diversity of patients
To uncover novel targets and drug candidates, undetectable by today’s models.
Team
Investors
News
300 million single cell atlas now accessible to the scientific community comprised of Vevo's Tahoe-100M, mapping 60,000 drug-patient interactions, and Arc's AI-curated scBaseCamp 200 million cell dataset
Generated using Vevo's Mosaic platform, Tahoe-100M leveraged Parse Biosciences' GigaLab for single cell sample preparation and Ultima Genomics for sequencing.
PALO ALTO, Calif. and SOUTH SAN FRANCISCO, Calif., Feb. 25, 2025 -- In a landmark move to advance AI-driven biological research, Arc Institute and Vevo Therapeutics announced today that they have partnered on the first release of the Arc Virtual Cell Atlas—the largest and most biologically diverse public resource for single-cell transcriptomic data across species, tissues, and experimental and perturbation conditions, starting with data from over 300 million unique cells. This data is open source and freely accessible via Arc's website as of February 25, 2025.
The atlas currently includes single-cell gene expression data from two massive datasets:
- Vevo's Tahoe-100M, is the world's largest single-cell dataset, 50x larger than all public drug-perturbed data combined. It includes 100 million cells and maps 60,000 drug-patient interactions, measuring cellular response across 50 cancer cell lines to 1,200 drug perturbations. Tahoe-100M was generated using Vevo's Mosaic Technology, the first platform to make pan-cancer testing of drugs at single cell resolution scalable, and with support from Parse Biosciences' GigaLab leveraging its single-cell RNA sequencing capabilities.
- Arc's scBaseCamp is the first single-cell RNA sequencing data repository from public data to be curated and reprocessed at scale using AI agents. This gene expression data from another 200 million cells from 21 different species was sourced from public repositories and has been standardized to ensure interoperability for optimal use by machine learning models.
"What makes the Arc Virtual Cell Atlas particularly powerful is not just its scale, but that now researchers can analyze together both observational natural cell states and cells that have been deliberately perturbed by drugs or chemicals to see how they respond," says Dave Burke (@davey_burke) Arc Institute's Chief Technology Officer. "We're grateful to partner with Vevo on our first release of this resource, leveraging their large-scale Tahoe-100M cell dataset, which is crucial for developing predictive models that can simulate cellular responses to perturbations, potentially reducing years of laboratory work to computational queries that take minutes."
"Something extraordinary happened in the last few years: emergence of AI models that can predict protein structure and function," says Nima Alidoust (@nalidoust), Chief Executive Officer and Co-founder of Vevo Therapeutics. "Our mission at Vevo is to go a huge step further: build AI models of human cells to predict how diseased cells interact with potential drug molecules."
"These models need massive amounts of observational and drug-perturbed single-cell data, leaps beyond what is publicly available today," says Johnny Yu, Chief Scientific Officer at Vevo. "Our Mosaic platform overcomes this fundamental challenge; it can generate single-cell datasets such as Tahoe-100M at a scale that was not possible before."
"We are open sourcing Tahoe-100M to help start a new movement in biological modeling that goes beyond us," says Alidoust. "Releasing it on Arc's Virtual Cell Atlas is the obvious choice as it aims to precisely do that."
The Arc Virtual Cell Atlas is now accessible on this portal: https://arcinstitute.org/tools/virtualcellatlas.
Vevo's Tahoe-100M Preprint: https://www.biorxiv.org/content/10.1101/2025.02.20.639398v1
Arc's scBaseCamp Technical Report: https://arcinstitute.org/manuscripts/scBaseCamp
About the Arc Institute
The Arc Institute (@arcinstitute) is an independent nonprofit research organization located in Palo Alto, California, that aims to accelerate scientific progress and understand the root causes of complex diseases. Arc's model gives scientists complete freedom to pursue curiosity-driven research agendas and fosters deep interdisciplinary collaboration.
About Vevo Therapeutics
Vevo Therapeutics is a biotechnology company using its in vivo drug discovery platform and next-generation AI models to uncover better drugs for more patients. The company's Mosaic platform is the first to make multi-patient drug screening data scalable, with single-cell precision, to better represent patient diversity in drug response. Vevo is using Mosaic to build the world's largest atlas of how drugs interact with patient cells and to train disease-relevant models of human cells for discovering novel targets and drugs undetectable by other technologies.
Located in South San Francisco, CA, Vevo was founded by a team of inventors and thought leaders who have discovered drugs for "undruggable" targets and invented novel methods in genomics, computational biology, and chemistry. Learn more at www.vevo.ai and follow us on LinkedIn and X.
Vevo Media Contact:
Peg Rusconi
Deerfield Group
peg.rusconi@deerfieldgroup.com
Tahoe-100M is the world's largest single-cell atlas of how drug molecules impact biology of patient cells
SOUTH SAN FRANCISCO, Calif., Jan. 13, 2025 -- Vevo Therapeutics, a biotechnology company using its Mosaic technology and next-generation AI to uncover better drugs for more patients, announced today that it will open source its historic Tahoe-100M dataset in collaboration with NVIDIA's biology foundation model research team. The NVIDIA team will contribute machine learning and data engineering expertise to train models on this data and package for use.
The Tahoe-100M data set is the world's largest atlas of single-cell transcriptomic data, mapping how drugs impact patient cells at scale. It comprises 100 million cells and 60,000 experiments, mapping 1,200 drug treatments across 50 different tumor models. It is larger than all public single-cell datasets combined, and 50x larger than all publicly available, drug-perturbed single-cell data put together.
"We are thrilled to collaborate with NVIDIA and to combine our ability to generate datasets with historic scale and information content with the capabilities of NVIDIA's large-scale AI models," said Nima Alidoust, Chief Executive Officer and Co-founder of Vevo Therapeutics. "Open sourcing a dataset of this magnitude is a momentous step towards creating a more open and collaborative community in biological research, which can ultimately help us design better therapeutics for patients. It further demonstrates our confidence in our ability to generate transformative datasets and reflects our commitment to enabling researchers worldwide to build innovative AI models."
About Vevo Therapeutics
Vevo Therapeutics is a biotechnology company using its in vivo drug discovery platform and next-generation AI models to uncover better drugs for more patients. The company's Mosaic platform is the first to make multi-patient drug screening data scalable, with single-cell precision, to better represent patient diversity in drug response. Vevo is using Mosaic to build the world's largest atlas of how drugs interact with patient cells and training AI models on its data to find novel targets and drugs undetectable by other technologies.
Located in South San Francisco, CA, Vevo was founded by a team of inventors and thought leaders who have discovered drugs for "undruggable" targets and invented novel methods in genomics, computational biology, and chemistry. Vevo is backed by leading investors at the intersection of life sciences and technology, including General Catalyst, Wing Venture Capital, Mubadala Capital, AIX Ventures, and Camford Capital. Learn more at www.vevo.ai and follow us on LinkedIn and Twitter.
Vevo Media Contact:
Peg Rusconi
Deerfield Group
Peg.rusconi@deerfieldgroup.com
Vevo's Mosaic platform is the first to make single-cell measurement of drug action across heterogeneous patients scalable
The Tahoe-100M dataset, generated using Mosaic in partnership with the GigaLab at Parse Biosciences, is larger than all public single-cell data combined and 50x larger than all other public drug treated single-cell data
SOUTH SAN FRANCISCO, Calif., Dec. 5, 2024 -- Vevo Therapeutics, a biotechnology company using its Mosaic technology and next generation AI to uncover better drugs for more patients, announced today that it has generated the world's largest single-cell atlas of how drugs interact with and affect tumor cells. The company's Mosaic platform is the first to make pan-cancer testing of drugs at single cell resolution scalable.
Vevo's approach combines data from the atlas with AI models to uncover novel targets and pathways and pair them with the best drug molecules in order to treat major cancer subtypes. Data collected will provide an unprecedented depth of information on how drug molecules perturb biology of patient cells.
"We are thrilled to reach this important milestone of creating a 100 million cell atlas of how chemistry perturbs biology, and we believe this will open new opportunities for drug discovery and development. This atlas is far beyond the scale of any existing datasets, and we plan to generate many more datasets through the Mosaic platform," said Johnny Yu, Chief Scientific Officer and Co-founder of Vevo Therapeutics.
The Mosaic platform is the key technology that enabled the atlas. In a single in vitro or in vivo experiment, Mosaic can measure how a drug impacts cells from tens to hundreds of patients, generating millions of datapoints on drug-induced changes in gene expression.
"Traditionally, drugs are discovered by searching for molecules that bind to single, isolated protein targets in test tubes. With this data, we now have the ability to search for drug molecules that actually treat cells from heterogeneous patients and can uncover how the drug molecule does that at single-gene, single-cell precision," said Yu. "This accelerates the path towards building clinical products at a fraction of the cost and allows us to pick the best drug molecules, identify the best drug combinations to increase efficacy, and find the patients that are most likely to respond to them - all in one experiment."
Generated and delivered in five weeks using the Mosaic technology, the Tahoe-100M data set comprises 100 million cells and 60,000 experiments, mapping 1,200 drug treatments across 50 different tumor models. The platform leverages single-cell RNA sequencing capabilities from Parse Biosciences' GigaLab that leverages Evercode combinatorial barcoding technology for scalable single cell analysis. High-throughput sequencing was provided by Ultima Genomics' UG100 instrument. The Tahoe-100M atlas will enable deep profiling of drugs across multiple tumor types allowing for identification of mechanisms of action and novel target discovery.
"The Tahoe-100M atlas sets a new standard, eclipsing currently available single-cell datasets. Most public datasets contain observational data from healthy cells, but Tahoe-100M consists entirely of drug-perturbed datapoints from diseased cells. It is 50X larger than all public drug-perturbed single cell data generated to date, which makes it much more suitable for drug discovery purposes," said Nima Alidoust, Chief Executive Officer and Co-founder of Vevo Therapeutics.
"Efforts to train an AI model of human cells have been hampered by the paucity of large-scale datasets that measure cells across diverse states. The Tahoe-100M atlas entirely changes the game, allowing us to train much larger AI models that can better learn the language of the cell," added Hani Goodarzi, Vevo Co-founder, Associate Professor at University of CA, San Francisco and Core Investigator at Arc Institute.
Vevo will announce additional collaborations around this dataset in Q1 2025.
About Vevo Therapeutics
Vevo Therapeutics is a biotechnology company using its in vivo drug discovery platform and next generation AI models to uncover better drugs for more patients. The company's Mosaic platform is the first to make multi-patient drug screening data scalable, with single-cell precision, to better represent patient diversity in drug response. Vevo is using Mosaic to build the world's largest atlas of how drugs interact with patient cells and training AI models on its data to find novel targets and drugs undetectable by other technologies.
Located in South San Francisco, CA, Vevo was founded by a team of inventors and thought leaders who have discovered drugs for "undruggable" targets and invented novel methods in genomics, computational biology, and chemistry. Vevo is backed by leading investors at the intersection of life sciences and technology, including General Catalyst, Wing Venture Capital, Mubadala Capital, AIX Ventures, and Camford Capital. Learn more at www.vevo.ai and follow us on LinkedIn and Twitter.
Vevo Media Contact:
Peg Rusconi
Deerfield Group
Peg.rusconi@deerfieldgroup.com
Mosaic drug discovery platform is the first to make in vivo data generation scalable, with single-cell precision; resulting datasets will be the world’s largest atlas of how drugs interact with patient cell
Approach combines atlas with AI models to capture in vivo context of disease early in discovery and better represent patient diversity in drug response over current in vitro assays
Company backed by prominent investors and founded by pioneers at the intersection of life sciences and technology, including co-founder Kevan Shokat
SAN FRANCISCO, Calif., December 8, 2022 – Vevo Therapeutics, a biotechnology company using its Mosaic in vivo drug discovery platform and next generation AI models to uncover better drugs for more patients, launched today with an oversubscribed and upsized $12M seed financing round. Wing Venture Capital and General Catalyst co-led the round with participation from Mubadala Capital, AIX Ventures, and Camford Capital.
The company’s Mosaic platform is the first to make in vivo data generation scalable, with single-cell precision, while capturing patient diversity in drug response. In a single in vivo experiment, Mosaic can measure how a drug impacts cells from hundreds of patients, generating millions of datapoints on drug-induced changes in gene expression. With the seed funding, Vevo will perform thousands of Mosaic experiments to create what is deemed impossible today: an in vivo atlas of how chemistry perturbs biology. Vevo’s AI models will be trained on this atlas to uncover novel targets and drugs undetectable by other technologies.
Vevo’s platform builds on technology developed by two of its co-founders, Hani Goodarzi, Ph.D., Associate Professor at the University of California, San Francisco (UCSF), and Johnny Yu, Ph.D., Chief Scientific Officer of Vevo Therapeutics. The company holds an exclusive license to the technology from UCSF's Innovation Ventures office, which leads licensing and business development on behalf of the university.
“We founded Vevo to address the key challenge in drug discovery – that drugs discovered in in vitro models are failing patients,” said Nima Alidoust, Ph.D., Chief Executive Officer and Co-founder of Vevo. “Drug discovery is only as powerful as the data that fuels it, and today that data is generated out of context from how disease occurs in living organisms while also failing to account for the diverse mosaic of genetic backgrounds across patients – each with the potential to react differently to any one drug. By starting and guiding drug discovery with high-resolution in vivo data, we are flipping the script on traditional discovery methods.”
Despite being the gold standard of disease modeling, in vivo models are not scalable or precise enough for early-stage discovery. Limited to in vitro-based assays, early discovery efforts often overlook valuable targets that would only be detectable in vivo. Even when novel targets and drugs are found in vitro, many will be irrelevant when tested in vivo or in humans.
“Most first-generation small molecule drugs will work with limited efficacy in a small number of patients, with improvements made slowly over the course of second and third generation advances,” said Kevan Shokat, Ph.D., Co-founder of Vevo Therapeutics and Professor at UCSF. “Our ability to test drugs across many patients and generate single-cell data using in vivo models at the start of drug discovery will finally allow us to bypass generations of incremental improvements to get better medicines to patients faster.”
“The advent of AI in drug discovery has done little to improve the failure rate of drugs in clinical trials, because many are using AI to paper over the cracks in a flawed system,” said Gaurav Garg, Partner at Wing Venture Capital and a member of Vevo’s Board of Directors. “Vevo has made it possible to train AI on the best-known data from the start, creating an entirely new way of doing drug discovery.”
“I believe the best drug discovery innovations of our time will be the ones that can be used to rethink the discovery process while augmenting traditional drug hunting efforts,” said Deep Nishar, Managing Director at General Catalyst. “This is what we believe is most extraordinary about Vevo’s technology and ambition. It is no wonder that they have found novel oncology targets that have gone undetected by traditional methods despite years of research and investment in the field – all before they’ve even deployed their computational and AI pipelines.”
“Vevo’s platform addresses key limitations in drug discovery, namely, the poor predictive power of preclinical models, their lack of generalizability across patients, and the limited understanding of a drug’s mechanism of action,” said Ayman AlAbdallah, Partner at Mubadala Capital. “Vevo’s technology, combined with the drive and caliber of its team, position it to reshape how drugs are discovered and to benefit patients with unmet needs.”
About Vevo Therapeutics
Vevo Therapeutics is a biotechnology company using its in vivo drug discovery platform and next generation AI models to uncover better drugs for more patients. The company’s Mosaic platform is the first to make in vivo data generation scalable, with single-cell precision, to capture in vivo context of disease at the first step of drug discovery and to better represent patient diversity in drug response over current in vitro assays. Vevo is using Mosaic to build the world’s largest in vivo atlas of how drugs interact with patient cells and training AI models on its data to find novel targets and drugs undetectable by other technologies.
Located in San Francisco, CA, Vevo was founded by a team of inventors and thought leaders who have discovered drugs for “undruggable” targets and invented novel methods in genomics, computational biology, and chemistry. Vevo is backed by leading investors at the intersection of life sciences and technology, including General Catalyst, Wing Venture Capital, Mubadala Capital, AIX Ventures, and Camford Capital. Learn more at www.vevo.ai and follow us on LinkedIn and Twitter.
###
Vevo Therapeutics Media Contact
Peg Rusconi, Verge Scientific: prusconi@vergescientific.com