Phyllox discovers novel herbicide modes of action for the resistant weeds breaking modern agriculture — molecules superweeds have never seen.


Independent science researcher (TRP pain-receptor channels). 1st, IFT Nutmeg & PepsiCo Engineering Awards. 1st at HackPrinceton. YC Startup School '26. Leads strategy, science, and the raise.

3× Regeneron ISEF Grand Award winner. 1st at JSHS '25, National STEM Champion '26. Published co-author in the Journal of Biological Chemistry; holds a provisional patent. YC Startup School '26. Runs operations and partnerships.

IEEE-published AI/ML researcher (youngest author). 3M Young Scientist International GENIUS Olympiad — 1st Place Gold Medal – Science. 3rd @ JSHS 25'. YC Startup School '26. Builds the discovery platform.
Superweeds now shrug off entire classes of herbicides across the world's biggest cash crops.
Roughly a quarter of a $40B global market is breaking down as existing chemistry stops working.
No new herbicide mode of action has reached the market in three decades. The pipeline has run dry.
We point the AI at the GLR3.4 binding pocket — a new, unexploited herbicide target class.
Protein-language models predict which novel molecules bind, across billions of candidates in silico.
Candidates are scored and shortlisted by predicted binding, selectivity, and synthesizability.
Top hits are confirmed in the wet lab — predictions become real, working chemistry.
Validated modes of action are licensed to the major agriculture companies that need them.
A pre-seed round to take Phyllox from validated targets to confirmed, licensable hits — capital goes straight into compound synthesis, wet-lab assays, and field validation.