Clayton Mellina says Transcripta builds disease signatures from patient single-cell RNA-seq, then screens drugs in cells to create its Drug Gene Atlas. It matches those signatures before committing to one protein target, keeping target identification open until later and widening the therapeutic search. Chris Moxham adds this combines phenotypic screening with efficient target-based work.
Clayton Mellina describes a rare autism case where Transcripta found a cancer drug class that calmed hyperexcitability in patient neurons at lower doses. After clinical behavioral improvements in that single-patient cohort, the team found similar RNA signatures across broader genetic autism disorders, expanding the program.
Chris Moxham says when a Science paper showed MSH3 knockdown could delay Huntington's repeat expansion, Transcripta queried its internal data and found novel structures already being worked on within minutes. That existing data turned a fresh finding into a program aiming for the clinic next year.
Clayton Mellina says AI agents now help interpret transcriptomic data that measures roughly 20,000 gene-regulation events across doses and cell types. They can chase specific changes, connect them to prior literature, and let small teams run many disease-program hypotheses in parallel. He calls these agent swarms.
Chris Moxham says traditional de novo discovery costs about $25 million to reach an IND. Transcripta instead builds a tiered pipeline with novel molecules, clinical-stage assets already de-risked, and approved drugs repurposed for new indications, aiming for a more capital-efficient company. This mix reduces reliance on one costly path.
