Time to Treatment Prediction in Chronic Lymphocytic Leukemia Based on New Transcriptional Patterns

Abstract

Chronic lymphocytic leukemia (CLL) is the most frequent lymphoproliferative syndrome in western countries. CLL evolution is frequently indolent, and treatment is mostly reserved for those patients with signs or symptoms of disease progression. In this work, we used RNA sequencing data from the International Cancer Genome Consortium CLL cohort to determine new gene expression patterns that correlate with clinical evolution.We determined that a 290-gene expression signature, in addition to immunoglobulin heavy chain variable region ( IGHV ) mutation status, stratifies patients into four groups with notably different time to first treatment. This finding was confirmed in an independent cohort. Similarly, we present a machine learning algorithm that predicts the need for treatment within the first 5 years following diagnosis using expression data from 2,198 genes. This predictor achieved 90% precision and 89% accuracy when classifying independent CLL cases. Our findings indicate that CLL progression risk largely correlates with particular transcriptomic patterns and paves the way for the identification of high-risk patients who might benefit from prompt therapy following diagnosis.

Aberrant Expression of TLR2, TLR7, TLR9, Splicing Variants of TLR4 and MYD88 in Chronic Lymphocytic Leukemia Patients

“…Chronic lymphocytic leukemia (CLL) is a disease with the accumulation of aberrant B cells in peripheral blood as well as proliferation and accumulation of CLL cells in the bone marrow and peripheral lymphoid organs. CLL patients are characterized by different prognoses, as well as profound molecular and immune defects [ 1 , 2 , 3 ]. Immune deregulations result in high susceptibility to infections as well as a failure to improve effective antitumor immune responses [ 4 , 5 , 6 ].…”

Machine learning and multi-omics data in chronic lymphocytic leukemia: the future of precision medicine?

“…The genes associated with time to treatment were used for a ML classifier from BigML (BigML, 2011) and showed high accuracy in predicting the need for treatment within the first 5 years following diagnosis. (Mosquera Orgueira et al, 2019). This application paves the way for the identification of high-risk patients using ML.…”

Temporal variation in lymphocyte proteomics

“…Mutations in the immunoglobulin heavy-chain variable region gene (IGHV) are correlated with better outcomes 6,7 , while mutations in NOTCH1, SF3B1, and BIRC3 are all correlated with poorer outcomes 8 . Transcriptomic profiling has been used to identify predisposition to the disease, severity, and time to treatment [9][10][11] . Relatively few studies have explicitly looked at longitudinal evolution of CLL; however, one recent genomic study showed that when sampled at multiple time points, many CLL patients have minimal genetic subclonal evolution during early disease development 12 .…”