Presented at AACR Annual Meeting 2026
Jeannette Fuchs1, Kenneth To2, Christopher Jackson2, Lawrence Schöbs2, Rohan Lyons2, Rafay Azhar2
1 Debiopharm International S.A., Switzerland
2 ViewsML Technologies Inc., Canada
Summary
The purpose of this study was to develop and validate a virtual immunohistochemistry (vIHC) algorithm capable of predicting Cyclin E1 (CCNE1) protein expression levels from hematoxylin and eosin (H&E)-stained whole-slide images in gynecological malignancy encompassing primarily high-grade serous ovarian carcinoma (HGSOC) and uterine serous carcinoma (USC). CCNE1 is a key cell-cycle regulator whose gene amplification (copy number ≥6) strongly correlates with protein overexpression (H-score >50) and enhanced sensitivity to WEE1 inhibitors and their combination with PKMYT1 inhibitors – see MYTHIC clinical trial zedoresertib+lunresertib1. Conventional IHC requires precious tissue and additional, timeconsuming wetlab processing. The ViewsML virtual biomarker platform derived from routinely available H&E slides provides a scalable alternative to wetlab IHC with a strong potential of accelerating patient selection for targeted therapies.
1T. Yap et al., First data disclosure of Phase I trial of the first in class combination of WEE1 inhibitor zedoresertib with PKMYT1 inhibitor lunresertib in patients with advanced solid tumors harboring CCNE1, FBXW7 or PPP2R1A genomics alterations, Clinical Trial Plenary Session CT022, AACR 2026