When a cell becomes cancerous, various abnormal alterations of cellular proteins can be observed by mass spectrometry. The OncoProteomics laboratory at Cancer Center Amsterdam received funding and research support to use innovative Artificial Intelligence to investigate their large datasets of specific cancer-associated protein alterations. The team aims to identify new biomarkers and potential drug targets to improve cancer diagnosis and treatment.

Detecting protein alterations in cancer
The OncoProteomics laboratory, encompassing the mass spectrometry (MS) facility at Cancer Center Amsterdam, has collected data on thousands of proteins in cancerous cells. MS cannot only identify the type and abundance of cellular proteins, it can also analyze protein-modifications that change functional properties and drive cancer. In this new project, ‘Transformer-based deep learning for next generation mass spectrometry-based phosphoproteomics’, the scientists will focus on a type of protein modification called phosphorylation: the addition of one or more phospho-groups to a protein that may act as switch to turn activity on or off. Professor Connie R. Jiménez, founder and head of the OncoProteomics Laboratory, explains: “Many genes that drive cancer are encoding proteins that place phospho-groups on other cellular proteins. This aberrant signaling changes the cell’s behavior and is already being exploited by various approved cancer medicines.”

A collaboration between protein and software experts
Professor Jiménez and Dr. Pham submitted a project proposal to the Netherlands eScience Center, an independent foundation promoting innovative software solutions in academic research initiated by the Dutch Research Council NWO and SURF, a cooperative association of Dutch educational and research institutions. The eScience Center offers funding for research in four categories including ‘Life Sciences and eHealth’ with grants up to € 500,000, plus the research support of specialized software engineers.

The project, which got underway in September this year, aims to apply state-of-the-art Artificial Intelligence technologies to a unique collection of phosphoproteomics data. Dr. Thang Pham, a specialist in machine learning at the OncoProteomics lab adds: “Phosphoproteomics by mass spectrometry provides a global view of cellular protein phosphorylation, making it highly relevant to cancer research. When successful, this project will change current practice in advanced data-independent acquisition-MS analysis, and catalyze both cancer-signaling research and biomarker and target discoveries to ultimately improve cancer diagnosis and treatment.”

People involved at Cancer Center Amsterdam:
Connie R. Jiménez, Thang V. Pham, Alex A. Henneman

For more information, contact Thang V. Pham (t.pham@amsterdamumc.nl).

Text by Henri van de Vrugt