The Multiple Myeloma Channel is supported with funding from AbbVie (Platinum), Sanofi (Gold), Legend Biotech (Bronze), and through an educational grant from Alexion Pharma GmbH.
VJHemOnc is an independent medical education platform. Supporters, including channel supporters, have no influence over the production of content. The levels of sponsorship listed are reflective of the amount of funding given to support the channel.
IMS 2026 | CoxBoost six-gene proliferation signature: ML approach to improve myeloma risk stratification
Shahzad Raza, MD, Cleveland Clinic, Cleveland, OH, shares insights into the CoxBoost six-gene proliferation signature, identified using a TP53-anchored machine learning (ML) approach, to improve multiple myeloma (MM) risk stratification. Dr Raza explains that the model analyzed differential gene expression profiles and identified key pathways and gene signatures associated with drug sensitivity, highlighting the importance of considering combinations of genetic mutations, rather than single mutations, to explain variability in patient responses. This interview took place at the 23rd International Myeloma Society (IMS) Annual Meeting in Glasgow, UK.
These works are owned by Magdalen Medical Publishing (MMP) and are protected by copyright laws and treaties around the world. All rights are reserved.
Transcript
So this is a project that I did with a high school student, actually, and he and I, and we both worked together on that. We first looked at the MMRF database and found out how many patients have a TP53 mutation. Then we looked at the differential gene expression profile. So we identified around 256 genes and then we looked at the five major pathways which these genes travel through, and then we used the clinical factors and five gene pathways and then used the machine learning algorithms to find out which one does better, so we found out the CoxBoost gene model is the best one, then we incorporated those five gene signatures using a volcano plot and looked at each as a drug sensitivity to find out which drug sensitivity is higher...
So this is a project that I did with a high school student, actually, and he and I, and we both worked together on that. We first looked at the MMRF database and found out how many patients have a TP53 mutation. Then we looked at the differential gene expression profile. So we identified around 256 genes and then we looked at the five major pathways which these genes travel through, and then we used the clinical factors and five gene pathways and then used the machine learning algorithms to find out which one does better, so we found out the CoxBoost gene model is the best one, then we incorporated those five gene signatures using a volcano plot and looked at each as a drug sensitivity to find out which drug sensitivity is higher. I think it’s still preliminary to assess that whether what you are seeing now should be seen in clinical practice too. But it’s important to understand the concept that once you have a TP53 mutation, it’s not the only TP53 mutation, it may be the combination of other genes as well, because two patients with identical features can have totally different outcomes, so I think with the drug sensitivity data that we have now, we can apply them to the clinical trials and see whether this really holds true or not.
This transcript is AI-generated. While we strive for accuracy, please verify this copy with the video.
Read more...
