Get your free personalized podcast brief

We scan new podcasts and send you the top 5 insights daily.

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.

Related Insights

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.

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.

Excalipoint accelerates R&D via a systematic process combining a pre-built library of molecular tools, deep disease-specific expertise, and a dual China/US clinical strategy for rapid validation. This repeatable 'human algorithm,' now being enhanced with AI, drastically shortens the timeline from concept to clinic.

Human genetics doesn't just provide a drug target; it often specifies the therapeutic approach required. Discovering a protective loss-of-function mutation immediately tells researchers to develop an inhibitor (like an antibody or siRNA), accelerating the path from target discovery to molecule design.

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.

Pharmaceutical companies like Pfizer have vast amounts of human genetic data (GWAS hits) linked to diseases but struggle to determine which are viable drug targets. Gordian's high-throughput in vivo screening directly tests the causal effects of hundreds of these targets, rapidly identifying the most promising candidates.

When the FDA approves a new biomarker-linked therapy, an in-house pathology lab actively queries its historical database of all prior NGS tests to identify past cases with the relevant genetic alteration. They then proactively contact the oncologists for these patients, uncovering new treatment options that were previously unavailable.

For patients with ultra-rare diseases, traditional drug development is too slow. AI platforms like Therna's can design a custom RNA molecule in days and complete the lab-testing cycle in under three months, compressing a multi-year process and making previously impossible treatments viable.

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.

The primary bottleneck in drug development isn't creating therapies but identifying the right targets. Regeneron built its massive genetics database to find rare, protective genetic mutations in humans, effectively de-risking the target identification process and aiming to improve the industry's low success rate.

A new MSH3 paper triggered a program in minutes | RiffOn