AstraZeneca

New Capabilities

Maker of osimertinib (Tagrisso), the drug whose resistance the models replicate

Every year, hundreds of thousands of lung cancer patients start treatment with osimertinib, the leading targeted therapy for tumors driven by mutations in the EGFR gene. Most of them will respond. Nearly all of them will eventually stop responding, as their cancers evolve resistance through a dozen different molecular escape routes. Until now, researchers trying to understand those escape routes had to work with messy, inconsistent lab models that made it difficult to pin down which genetic change caused which failure. On April 20, 2026, the American Type Culture Collection (ATCC) and the Broad Institute of MIT and Harvard released a panel of 13 precisely engineered cancer cell lines, each genetically identical except for a single, defined resistance mechanism, giving researchers clean, standardized tools to study exactly how and why treatments stop working.

Updated Yesterday

New Capabilities

Manufacturer of acalabrutinib (Calquence); sponsor of the AMPLIFY trial

For decades, patients diagnosed with chronic lymphocytic leukemia—the most common adult leukemia in Western countries, affecting roughly 23,000 Americans each year—faced a difficult choice: endure rounds of intravenous chemotherapy with harsh side effects, or take targeted pills indefinitely, sometimes for life. On February 20, 2026, the Food and Drug Administration (FDA) approved a combination of two oral drugs, venetoclax and acalabrutinib, that eliminates both burdens. Patients take pills for roughly one year, then stop. In a trial of 867 patients, 77% remained cancer-free at three years.

Updated Feb 20

New Capabilities

Developing AI-powered oncology drug development infrastructure

For decades, cancer drug trials have failed at a rate exceeding 95%—burning through $50-60 billion annually on treatments tested in patients who were never likely to respond. On April 17, 2025, researchers from AstraZeneca and Tempus AI published results in Cancer Cell showing that the Predictive Biomarker Modeling Framework (PBMF)—a machine learning system using contrastive learning—can identify, from existing clinical data, which cancer patients will survive longer on immunotherapy versus chemotherapy. Applied retrospectively to completed phase 3 trials, the system improved survival outcomes by 15% compared to traditional patient selection.

Updated Feb 11