Back to All Awardees

Classification Tool for Diffuse Large B Cell Lymphoma to Guide Treatment and Improve Prognostic Accuracy

  • Diagnostics
  • 2024

Diffuse Large B-cell Lymphoma (DLBCL), the most common adult lymphoid malignancy, is known for its molecular heterogeneity, despite being a single diagnosis under the microscope. While over 60% of patients respond well to standard R-CHOP immunochemotherapy, the remainder either fail to respond or experience recurrence. The molecular heterogeneity of the cancer complicates treatment, necessitating a robust molecular classifier to better inform prognosis and therapeutic decisions. Toward that goal, a project led by Margaret Shipp, MD, Douglas Miller Chair in Lymphoma and Professor of Medicine at Harvard Medical School, has developed a new diagnostic tool aimed at improving DLBCL’s molecular diagnosis, prognostic accuracy, and treatment strategy for the disease. The project received funding from the Dana-Farber Accelerator Program in the 2024 cycle. 

Focusing on Five Genetic Subtypes 

In earlier research, Shipp and her team collaborated with colleagues from the lab of Gad Getz, PhD, director of the Cancer Genome Computational Analysis Group at the Broad Institute, to define five distinct genetic subtypes of DLBCL, each with unique biological characteristics and varying responses to standard chemotherapy. This framework, published in Nature Medicine 1 in 2018, laid thefoundation for the development of a robust molecular classifier known as DLBclass by characterizing genetic alterations in DLBCL and identifying five distinct subtypes that could provide physicians with crucial insights into overall prognosis and treatment strategies. 

As described in a recent paper in Blood  2, the team further validated the DLBclass taxonomy and developed a probabilistic molecular classifier, using a dataset of 699 primary DLBCL samples. They employed machine learning models to achieve high accuracy in classifying these subtypes, demonstrating 91% accuracy in training/validation sets and 89% in independent test sets. The classifier has potential for widespread clinical application, positioning it as a best-in-class diagnostic tool for DLBCL. 

Outperforms Existing Classification Tools 

The benefits of DLBclass are substantial. It enables precise classification of DLBCL subtypes, critical for enrolling patients in genetically guided clinical trials and optimizing treatment strategies. This classifier outperforms existing tools like the NIH’s LymphGen, which only classified 58% of cases into a significant portion of a significant portion of patients without clear subtype identification. In contrast, DLBclass successfully classified all samples, providing actionable genetic information for a larger number of patients. 

The Accelerator award recognizes a pivotal moment for the project, enabling the team to transition from research to clinical application. The goal of the project is to develop the test under CLIA guidelines, ensuring that it produces consistent and accurate results across different conditions and equipment. Achieving CLIA certification would allow the classifier to be used in translational research and prospective clinical trials and practice, enabling oncologists to make informed treatment decisions based on a patient’s specific genetic subtype. 

The DLBclass project has been a testament to the power of sustained collaboration. The Shipp team worked closely with the Getz group at the Broad Institute, building on their previous work to define the genetic framework of DLBCL.

Team Members: Margaret Shipp, MD, Gad Getz, PhD, Bjorn Chapuy, MD, PhD, Chip Stewart, PhD, Timothy Wood, Eleonora Calabretta, MD, Sumbul Khan, PhD 

Team Members

Gad Getz, PhD

Director, Cancer Genome Computational Analysis at the Broad Institute of MIT and Harvard

Director of bioinformatics in the Krantz Family Center for Cancer Research and Department of Pathology at Massachusetts General Hospital.