
Healthcare
|
Biotechnology
|
YC W26
|
Valuation:
Undisclosed

Last Updated:
March 24, 2026

Develops AI-driven "evolutionary therapies" for autoimmune diseases by mining parasite genomes for immunomodulatory proteins, leveraging a proprietary computational biology platform to discover, predict, and engineer novel protein therapeutics.
AI platform mining 1M+ parasite-derived proteins across primate-infecting viruses, ticks, and parasitic worms. Tissue biobank built using YC founder blood drives for immunogenicity mapping. Thousands of candidate proteins discovered with drug-like binding affinities (1-2 nM). Early experiments show proteins acting on high-value targets for immune diseases. Over 98% of viral and parasite proteins remain uncharacterized, representing a vast unexplored design space. Seeking immunologist and biologics developer collaborations.
Protein language models and host-parasite computational genomics in development. Tissue biobank signals preparation for IND-enabling immunogenicity studies. The three founders previously worked together at Arcadia Science for 3 years, providing deep collaborative chemistry and shared research publication history. GitHub repos show active development on blood drive logistics and benchmarking tools. Likely Demo Day fundraise Q2 2026.
AI-powered large-scale mining of parasite genomes to discover novel immunomodulatory proteins as autoimmune disease drug candidates.
A computer scans millions of proteins that parasites use to hide from the immune system and picks out the ones most likely to work as medicines for autoimmune diseases.
It's like hiring a million-year-old parasite as your drug design consultant—it already figured out how to calm down the immune system, and the AI just translates its notes.
Machine learning-guided optimization of parasite-derived protein candidates for improved drug-like properties, stability, and therapeutic efficacy.
An AI acts like a protein personal trainer, tweaking and improving parasite proteins until they're strong enough, stable enough, and safe enough to become real medicines.
It's like using AI to speed-run evolution—instead of waiting a million years for nature to perfect a protein, you get the optimized version by Friday.
AI-driven immunogenicity prediction using a proprietary tissue biobank that maps real-world immune memory to parasite-derived protein candidates, enabling safer drug design.
An AI cross-references a library of real human immune tissue samples against candidate drug proteins to predict whether a patient's body would reject the medicine before it's ever tested in people.
It's like checking if your body's bouncers will recognize and kick out the new drug before you even send it to the club—saving everyone a very expensive night out.
Three co-founders with 40+ years of combined PhD-level expertise in computational biology, evolutionary biology, and host-parasite interactions across Harvard, Berkeley, UCSF, and UCSD. They worked together for 3 years as early scientists at another startup before founding Ditto, giving them rare team cohesion. Their approach, mining parasite genomes for molecules that already work in humans, sidesteps the 90% clinical trial failure rate by starting with biologically validated candidates rather than synthetic designs.