Machine learning uncovers previously undetectable genetic deletions in cancer panel sequencing
Missed genetic deletions can prevent cancer patients from receiving effective targeted therapy. Standard pipelines, such as TSO500, use bin count averaging for copy number variation detection but often overlook focal events. To address this, we developed a machine learning (ML) pipeline for deletion detection and zygosity evaluation within the MASTERsg precision oncology program. We focused on the tumor suppressor gene PTEN, whose loss confers sensitivity to mTOR/Akt inhibition. An Extreme Gradient Boosting model trained on PTEN-deleted and wild-type tumor samples identified focal deletions missed by the TSO500 pipeline and CNVkit that were associated with concordant PTEN protein loss by immunohistochemistry. Importantly, the model detected PTEN deletions in 33/204 profiled samples that were classified as PTEN wild-type by TSO500; 75% (15/20) of stainable cases showed absent or reduced PTEN protein expression. These findings demonstrate the potential of ML to enhance panel sequencing, uncovering therapeutically relevant alterations missed by established diagnostic methods.
Authors
- Irina A. Kerle (ORCID: https://orcid.org/0000-0002-3650-488X)
- Sascha Brückmann
- Karsten Wendt (ORCID: https://orcid.org/0000-0001-9373-6751)
- Daniela Richter (ORCID: https://orcid.org/0009-0004-8958-140X)
- Lino Möhrmann (ORCID: https://orcid.org/0000-0003-4650-6827)
- Evelin Schröck (ORCID: https://orcid.org/0000-0002-3377-1704)
- Anja Kögler (ORCID: https://orcid.org/0000-0003-4270-4762)
- Daniela Ellen Aust (ORCID: https://orcid.org/0000-0002-4867-8852)
- Nicole Pfarr (ORCID: https://orcid.org/0000-0002-5977-5375)
- Dorothea Hanf (ORCID: https://orcid.org/0000-0001-9636-5378)
- Christoph Heining (ORCID: https://orcid.org/0000-0002-1256-8387)
- Hanno Glimm (ORCID: https://orcid.org/0000-0003-4104-1135)
- Doreen William (ORCID: https://orcid.org/0000-0001-7824-5073)
- Carolin Mogler (ORCID: https://orcid.org/0000-0003-3400-7254)
- Maximilian Werner (ORCID: https://orcid.org/0000-0003-0252-5057)
- Andreas Hartig
- Rebecca Prause
- Oleksandr Husak
- Thomas Gross
Institutions
- Boston Children's Hospital (US)
- Harvard University (US)
- Heidelberg University (DE)
- Universitätsmedizin Greifswald (DE)
- Helmholtz-Zentrum Dresden-Rossendorf (DE)
- University Hospital Heidelberg (DE)
- Universität Greifswald (DE)
- National Center for Tumor Diseases (DE)
- University Hospital Carl Gustav Carus (DE)
- Nationales Centrum für Tumorerkrankungen Dresden (DE)
- Technical University of Munich (DE)
- Technische Universität Dresden (DE)
Publication Details
- Journal
- npj Precision Oncology
- Published
- 2026-10-16
- DOI
- https://doi.org/10.1038/s41698-026-01756-9
- Primary Topic
- Cancer Genomics and Diagnostics
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Technische Universität München
- Deutschen Konsortium für Translationale Krebsforschung