What's the one question we obsess over at Recursion? It's how do we harness the full power of AI to consistently and with urgency create better medicines for patients? And this quarter, we are continuing to make real and concrete progress against that. Let me share a few highlights. First, REC 1245, one of our potential first-in-class oncology programs, where both the biology and the molecule were discovered using our platform. The early clinical data shows a well-tolerated profile with no dose-limiting toxicities to date and encouraging PK-PD profile. This is an important and early step with more data coming in the second half of 2026. Second, REC 4881 in FAP, a serious disease with no approved treatments to date. We have already shown strong proof of concept with meaningful and durable impact, and we now have initiated FDA engagement on a potential registration on Path Forward. We expect to provide an update in the second half of 2026. Third, Rec4539, our best-in-class LSD1 inhibitor for small cell lung cancer and AML. This is a precision-designed molecule built to address class-limiting toxicity, such as thrombocytopenia, with the potential for improved safety and CNS penetration. Our update is that we've just dosed the first patient in our phase one trial. So look, this isn't just about one asset. It's about building a repeatable, AI-driven product engine starting to deliver across discovery and into the clinic. And we're just getting started.