Exonic is building unsupervised biological AI, training biological foundation models on heterogeneous, unstructured, and noisy datasets. Its first application is the design of safer gene therapies, and in 2025 the company reported state-of-the-art results in liver cancer targeted gene therapy validated in vitro in its San Francisco lab. The company says it has trained a model with unprecedented zero-shot generalization on genomic regulatory expression. Exonic was founded in 2025 and is part of Y Combinator's Fall 2025 batch.
Exonic
ActiveUnsupervised Biological AI
Total raised
$500K
1 round
Stage
Seed
Jan 2025
Team
1-10
since 2025
Pricing
—
Founded
2025
San Francisco, United States
Agent-ready
—
Unsupervised biological foundation models for life sciences
Trained on heterogeneous, unstructured, and noisy biological datasets
First application focused on designing safer gene therapies
Reported state-of-the-art in vitro results in liver cancer targeted gene therapy
Model with zero-shot generalization on genomic regulatory expression
In-house wet-lab validation at its San Francisco facility
Genomic and regulatory sequence modeling
Research-stage platform aimed at therapeutic design
12/100
Early
MCP server
Public API
Webhooks
OAuth 2.0
SDKs
No public agent surfaces detected yet.
Jan 2025 Seed $500K ● Y Combinator
Capital network
$500K raised ·1 backer·10 network links
- Backers1
- Shared portfoliocompanies these backers also fund
- Extended networkfunds that co-invest alongside them
Pearl Health
AI value-based care platform for primary care providers
AI AnalyticsAI Healthcare
Commure
AI Healthcare
Innovaccer
AI Healthcare
Truveta
AI Healthcare
Terray Therapeutics
Generative AI and ultra-high-throughput chemistry for small-molecule drug discovery
AI HealthcareDrug Discovery
Genesis Molecular AI
Generative AI for small-molecule drug discovery
AI HealthcareDrug Discovery
- What is Exonic building?
- Exonic trains unsupervised biological foundation models on heterogeneous, unstructured, and noisy biological datasets, with a first application in designing safer gene therapies.
- What results has Exonic reported?
- In 2025 the company reported state-of-the-art in vitro results in liver cancer targeted gene therapy, validated in its San Francisco lab, and a model with zero-shot generalization on genomic regulatory expression.
- Is Exonic a product I can use?
- No. It is an early-stage research company founded in 2025, focused on building foundation models and therapeutic applications rather than a self-serve product.
- Why unsupervised learning for biology?
- Much biological data is unstructured and noisy. Unsupervised foundation models can learn from these large datasets without requiring extensive manual labeling.
- How mature are the reported results?
- The liver cancer results are in vitro, an early validation stage. In vitro success does not guarantee in vivo or clinical outcomes, which require further research and trials.
Discussion
Sign in to join the discussion.
Sign inExplore more around Exonic
Contextual paths to related AI startups, deals and rankings.