Sponsored by:
Presented by:

Machine learning helps reveal altered signaling pathways
in blood cancers

This webcast has been produced for the sponsor, Cytobank, a part of Beckman Coulter Life Sciences, who retains sole responsibility for content.

Your details:

Our registration process uses cookies, by submitting this registration form you agree to our cookie policy.

(*) denotes required form field(s)



Myelofibrosis (MF) belongs to a class of blood cancers called Myeloproliferative Neoplasms (MPNs) that are characterized by anemia, an enlarged spleen, bone marrow fibrosis, and inflammatory cytokine production. The goal of this study is to better define the relationship between dysregulated cytokines and downstream signaling in MF, with the goal of determining how these pathways can be manipulated for therapeutic benefit.

Dr. Oh and his team employed mass cytometry analysis to interrogate altered signaling in MF by conducting quantitative analysis of more than 40 parameters at the single-cell level and then applied machine learning (ML) algorithms to identify NFkB pathway hyperactivation widely distributed across multiple hematopoietic cell populations, including both clonal (stem/progenitor cells) and non-clonal (T-cells) populations.

Plasma cytokine levels (including TNF) were elevated in these patients, suggesting that excessive production of inflammatory cytokines may result in activation of NFκB in a non-cell-autonomous fashion.

Investigators extended their mass cytometry and algorithmic approach to study the cellular distribution of cytokine production in MF. In patient samples, 14/15 cytokines were found to be constitutively overproduced, with the principal cellular source for most cytokines being monocytes, implicating a non-cell-autonomous role for monocyte-derived cytokines impacting disease-propagating stem/progenitor cells in MF.

These studies highlight the potential to leverage hyperactivated NFkB pathway signaling for therapeutic benefit in MPN patients.

In this webcast, you will learn:

  • How investigators can leverage machine learning and single-cell analysis methods to reveal dysregulated signaling pathways.
  • How top researchers established a high-dimensional data analysis pipeline
  • How applying machine learning algorithms to high-dimensional data output can help accelerate results

For research use only. Not for diagnostic purposes.

This webcast has been produced for Cytobank, a part of Beckman Coulter Life Sciences, by Nature Research Custom Media. The sponsor retains sole responsibility for content. About this content.


Dr. Stephen Oh
Co-Head, Immunomonitoring Laboratory, Bursky Center for Human Immunology and Immunotherapy Programs
Washington University School of Medicine
View Biography
Qianjun Zhang
Senior Field Applications Scientist
View Biography
Moderator: Sarah Hiddleston
Science Journalist
Nature Research for Nature Middle East
View Biography