Key Investor Signals
Selected for Y Combinator Fall 2025
Anto Biosciences joined 's Fall 2025 batch
Founders combine repeat-startup experience with research at MIT, Broad, and Harvard Medical School.
Arvid E. Gollwitzer researches in MIT's Traverso Lab and at the , and co-founded before Anto. David de Gruijl researched at , Harvard Medical School, and was Chief Technology Officer of Nook Biosciences, a drug-microbiota company.
Co-founder published peer-reviewed microbiome research in Clinical Pharmacology & Therapeutics.
David de Gruijl co-authored a paper arguing that drug development should account for the microbiome. It was published in 2025 in Clinical Pharmacology & Therapeutics, a peer-reviewed medical journal.
Other Positive Signals
- Presented two papers at the 2025 AI for Science workshop.
- Filtering method increases the usable share of public sequence data from 5% to 40%.
Team
Arvid E. Gollwitzer
Co-Founder
- Graduate researcher in the Traverso Lab at MIT, and a researcher at the Broad Institute of MIT and Harvard.
- Co-developed and in Onur Mutlu's SAFARI group at , published at 2022 and 2024.
- First author of , a metagenomic classifier reported at 3.9 times the speed of without accuracy loss.
- Co-founded NextGuide, an AI assistance product for visually impaired users.
David de Gruijl
Co-Founder
- Researcher in the Gastroenterology Department at Brigham and Women's Hospital, Harvard Medical School.
- Chief Technology Officer of Nook Biosciences from 2024 to 2025, a company working on drug-microbiota interactions.
- Worked in data science at Janssen Pharmaceuticals, part of , after engineering degrees at Delft University of Technology.
- Co-authored a 2025 paper on microbiome-aware drug development in Clinical Pharmacology & Therapeutics.
Product
Anto Biosciences is building a prediction platform for pharmaceutical R&D rather than developing its own therapeutic. Its foundation models analyse microbial communities to estimate how differences in the gut microbiome may affect a drug's efficacy and toxicity across patient populations.
Starting with oral drugs
Anto initially focuses on orally administered drugs because gut bacteria can act on these molecules before absorption. This creates a direct link between microbiome variation and how a drug behaves in the body.
Preparing microbiome data
Public sequence archives contain large volumes of sparse and low-quality data. Anto filters out noise before training its models so that the remaining data carries stronger predictive signal.
Modelling molecules and communities
The platform models how a drug behaves within individual samples and how microbial species interact as a community. Its predictions are intended to help drug developers identify microbiome-related risks earlier and design molecules that work across broader populations.
Market Overview
Gut bacteria can alter how oral drugs are metabolized, affecting their efficacy and toxicity across patient populations. Large-scale studies have shown that these interactions are common, yet conventional drug-development models mainly account for human metabolism rather than differences between microbial communities.
The challenge is turning microbiome research into reliable predictions. Microbiome data is sparse, noisy, and difficult to model, preventing pharmaceutical teams from assessing microbiome-related effects before clinical trials. A predictive layer that makes this data usable would enter a large pharmaceutical R&D market that is already adopting AI-based drug-discovery tools.
Share of 271 tested oral drugs metabolized by at least one human gut bacterial strain.
Share of tested human-targeted drugs that inhibited at least one commensal gut bacterial strain.
Research and development spending by PhRMA member companies in 2019.
Projected global market growth from 2024 to 2029, representing a 29.9% compound annual growth rate.
Comparable Outcomes
Nimbus Therapeutics
Nimbus used computational chemistry and predictive modelling to develop NDI-034858, an oral TYK2 inhibitor for immune-mediated diseases. Takeda acquired the Nimbus subsidiary holding the program in 2023 for $4 billion in cash. Two additional $1 billion payments were tied to the drug reaching annual sales of $4 billion and $5 billion, taking the potential value to $6 billion.
Isomorphic Labs
Isomorphic Labs provides AI-based prediction and drug-design capabilities to pharmaceutical partners. Eli Lilly paid $45 million upfront, with up to $1.7 billion in milestones. Novartis paid $37.5 million upfront, with up to $1.2 billion in milestones plus research funding. Together, the agreements represent $82.5 million upfront and up to $2.9 billion in potential milestones.
Seres Therapeutics
Seres developed VOWST, the first oral microbiome therapy approved by the FDA, for recurrent Clostridioides difficile infection. Nestlé paid $175 million upfront for US and Canadian commercial rights. The agreement included $125 million upon FDA approval, $10 million upon Canadian approval and up to $225 million in sales milestones.
Have a question about Anto Biosciences?
Ask DealBio. We may research the answer or share selected questions with the company.
Sources
This profile was built from public company materials, ecosystem sources, market references, and professional profiles.