Seattle-based ModernVivo is using AI to help scientists design preclinical studies for drug discovery. The goal: better experiments that are also faster, cheaper and less reliant on animals.
“You’d be shocked at the way scientists design their experiments,” co-founder Ian Levine told GeekWire. “It’s very manual.”
To design experiments, scientists typically enter keywords into PubMed or another database, receiving hundreds or thousands of results. They then go through each complex paper, typically 30 pages long, to find information relevant to the experiment they’re planning.
Levine spent thousands of hours manually combing through scientific papers as a research undergrad at Virginia Tech, and later as a Ph.D. student at the University of Michigan. He wanted a better way – and in 2022 co-founded ModernVivo with Colin Small, a fellow graduate student he’d met online while Small was pursuing a master’s in biotechnology at Brown University.
ModernVivo’s platform can analyze millions of peer-reviewed publications – cross-referenced with clinical trial and regulatory data – delivering highly detailed results in minutes. Researchers can filter papers by factors including animal model, experimental conditions, author affiliation and publication date, then drill down into more than 40 individual variables used in the experiments.
“We want to make experiments faster,” Levine said, “and help get better drugs to the clinic.”
For Levine, it’s personal: while studying to develop non-opioid pain therapeutics at Virginia Tech, he watched his mother live with a chronic pain disorder.
In the pharmaceutical industry, about 90% of drug candidates that reach human clinical trials go on to fail. Levine suspects part of the problem could lie in the many variables involved in how animal experiments are designed.
ModernVivo occupies a narrow niche in biotech software. Its closest analog is Trials.ai, another AI-driven platform tackling clinical trial design, founded in San Diego and acquired in 2023 by consulting firm ZS.
The Seattle company draws on the paper database of Semantic Scholar, a research tool developed by the Allen Institute for Artificial Intelligence, putting it in loose company with general-purpose research tools like Elicit and Consensus – though none of those are built specifically to extract in vivo protocol details the same way.
ModernVivo’s pitch is that it provides deeper insight than manual literature review or general-purpose AI tools. Ask a general AI chatbot about an experiment, Levine said, and it’ll return the high-level, commonly known approaches. Researchers want every relevant data point, including the obscure European study that might matter for their specific drug candidate but wouldn’t surface in a broad summary.
The software also surfaces contradictions in the literature: if 20 published studies point one way and five point another, ModernVivo flags this rather than picking a winner, since, as Levine puts it, scientists don’t want to be told what to do.
“They’re the people who suffer through the Ph.D. to be an expert in their field,” he said.
So far, the results are speed, confidence and lower animal use, Levine said. Tracking whether a study leads to a successful drug takes years, so he’s cautious about claiming translational impact. But customers have told him work that used to take about a month now takes as little as an hour.
Researchers who use ModernVivo report more trust in their initial study design, he said, and run fewer duplicate or follow-up animal experiments, which cuts down on animal use and the cost of housing and caring for animals.
ModernVivo has more than 20 customers ranging from small biotech firms to large pharmaceutical companies. It also offers ModernVivo Scholar, a version for academic researchers launched last October, with plans ranging from free to $50 a month.
The company has been through multiple accelerator programs: a WTIA founder cohort in 2023, Creative Destruction Lab’s Seattle program, which it graduated from in June 2025, and the Merck Digital Sciences Studio’s third cohort. The company has raised $1 million in a pre-seed round, and Levine said fundraising is going well as the company looks to expand.
ModernVivo’s attention is now shifting from the design phase of an experiment to execution. The company launched the ModernVivo Marketplace on Sept. 15, matching a finished study design against a network of pre-vetted contract research organizations, analytical labs and specialist dosing facilities. Suppliers of compounds and animal models are listed as coming soon.
Once a study is designed, researchers often don’t know which vendors have the right supplies or which contract research facilities are equipped to execute it, and tracking that down has meant manual search and outreach. ModernVivo wants to remove that ambiguity and connect scientists directly to the right vendor.
“The way we position ourselves in the future,” Levine said, “is helping scientists go from study design to study execution faster than ever before.”
