Deep learning-based prediction of gene expression from histopathology identifies NR5A1 as a candidate biomarker and druggable target in high-grade serous ovarian carcinoma
Prakash Lingasamy, Marta Ostrowska-Leśko, Pantelis Tsakalis, Naisarg Patel, Ilias Chamatidis, Sajitha Lulu Sudhakaran, Joanna Kubik, Marcin Bobiński, Nikos D. Lagaros, Andres Salumets, Vijayachitra Modhukur · 2026
Read Deep learning-based prediction of gene expression from histopathology identifies NR5A1 as a candidate biomarker and druggable target in high-grade serous ovarian carcinoma by Prakash Lingasamy, Marta Ostrowska-Leśko, Pantelis Tsakalis, Naisarg Patel, Ilias Chamatidis, Sajitha Lulu Sudhakaran, Joanna Kubik, Marcin Bobiński, Nikos D. Lagaros, Andres Salumets, Vijayachitra Modhukur (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13262399.txt.
Description
Prakash Lingasamy leads a 2026 journal article on reading gene activity from tumor images in ovarian cancer. The cancer type is high-grade serous ovarian carcinoma, the most deadly form, often found late and prone to resist platinum drugs. Gene tests can guide care but are costly, so the team used routine stained slide images instead.
Their computer model was trained on paired slide images and gene data and predicted activity for about 6,400 genes. Average accuracy was modest, but more than 300 genes were predicted more strongly. In a small check with ten tumors, one gene, NR5A1, varied most and ran higher in tumors that responded to platinum. Computer docking tests suggested a plant compound could bind its protein.
Catalog record
| CREATOR | Prakash Lingasamy, Marta Ostrowska-Leśko, Pantelis Tsakalis, Naisarg Patel, Ilias Chamatidis, Sajitha Lulu Sudhakaran, Joanna Kubik, Marcin Bobiński, Nikos D. Lagaros, Andres Salumets, Vijayachitra Modhukur |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67841 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |