scholarly journals PCN10 MACHINE LEARNING PREDICTION OF SURVIVAL IN DIFFUSE LARGE B-CELL LYMPHOMA BASED ON GENE-EXPRESSION PROFILING

2020 ◽  
Vol 23 ◽  
pp. S23-S24
Author(s):  
S. Merdan ◽  
K. Subramanian ◽  
T. Ayer ◽  
J. Weyenbergh ◽  
J. Koff ◽  
...  
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
B Cell ◽  
Gene Expression Profiling ◽  
Expression Profiling ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Large B Cell Lymphoma ◽  
Prediction Of Survival ◽  
Large B Cell

Machine learning prediction of survival in diffuse large B-cell lymphoma based on gene-expression profiling.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 8047-8047
Author(s):  
Selin Merdan ◽  
Kritika Subramanian ◽  
Turgay Ayer ◽  
Jean Louise Koff ◽  
Andres Chang ◽  
...  
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Prediction Model ◽  
B Cell ◽  
Gene Expression Profiling ◽  
Expression Profiling ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Large B Cell Lymphoma ◽  
Large B Cell

8047 Background: The current clinical risk stratification of Diffuse Large B-cell Lymphoma (DLBCL) relies on the International Prognostic Index (IPI) comprising a limited number of clinical variables but is imperfect in the identification of high-risk disease. Our study aimed to: (1) develop a risk prediction model based on the genetic and clinical features; and (2) evaluate the model’s biological implications in association with the estimated profiles of immune infiltration. Methods: Gene-expression profiling was performed on 718 patients with DLBCL for which RNA sequencing data and clinical covariates were available by Reddy et al (2017). Unsupervised and supervised machine learning methods were used to discover and identify the best set of survival-associated gene signatures for prediction. A multivariate model of survival from these signatures was constructed in the training set and validated in an independent test set. The compositions of the tumor-infiltrating immune cells were enumerated using CIBERSORT for deconvolution analysis. Results: A four gene-signature-based score was developed that separated patients into high- and low-risk groups with a significant difference in survival in the training, validation and complete cohorts (p < 0.001), independently of the IPI. The combination of the gene-expression-based score with the IPI improved the discrimination on the validation and complete sets. The area-under-the-curve at 2 and 5 years increased from 0.71 and 0.69 to 0.75 and 0.74 in the validation set, respectively. Conclusions: By analyzing the gene-expression data with a systematic approach, we developed and validated a risk prediction model that outperforms existing risk assessment methods. Our study, which integrated the profiles of immune infiltration with prognostic prediction, unraveled important associations that have the potential to identify patients who could benefit from the various therapeutic interventions, as well as highlighting possible targets for new drugs.

Cell-of-Origin in Diffuse Large B-Cell Lymphoma: Are the Assays Ready for the Clinic?

2015 ◽  
pp. e458-e466 ◽  
Author(s):  
David W. Scott
Keyword(s):  
Gene Expression ◽  
B Cell ◽  
Gene Expression Profiling ◽  
Expression Profiling ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Practical Implementation ◽  
Cell Of Origin ◽  
Large B Cell Lymphoma ◽  
Large B Cell

Diffuse large B-cell lymphoma (DLBCL) is the most common lymphoma worldwide and consists of a heterogeneous group of cancers classified together on the basis of shared morphology, immunophenotype, and aggressive clinical behavior. It is now recognized that this malignancy comprises at least two distinct molecular subtypes identified by gene expression profiling: the activated B-cell-like (ABC) and the germinal center B-cell-like (GCB) groups—the cell-of-origin (COO) classification. These two groups have different genetic mutation landscapes, pathobiology, and outcomes following treatment. Evidence is accumulating that novel agents have selective activity in one or the other COO group, making COO a predictive biomarker. Thus, there is now a pressing need for accurate and robust methods to assign COO, to support clinical trials, and ultimately guide treatment decisions for patients. The “gold standard” methods for COO are based on gene expression profiling (GEP) of RNA from fresh frozen tissue using microarray technology, which is an impractical solution when formalin-fixed paraffin-embedded tissue (FFPET) biopsies are the standard diagnostic material. This review outlines the history of the COO classification before examining the practical implementation of COO assays applicable to FFPET biopsies. The immunohistochemistry (IHC)-based algorithms and gene expression–based assays suitable for the highly degraded RNA from FFPET are discussed. Finally, the technical and practical challenges that still need to be addressed are outlined before robust gene expression–based assays are used in the routine management of patients with DLBCL.

scholarly journals Constitutive Nuclear Factor κB Activity Is Required for Survival of Activated B Cell–like Diffuse Large B Cell Lymphoma Cells

2001 ◽  
Vol 194 (12) ◽  
pp. 1861-1874 ◽  
Author(s):  
R. Eric Davis ◽  
Keith D. Brown ◽  
Ulrich Siebenlist ◽  
Louis M. Staudt
Keyword(s):  
Gene Expression ◽  
B Cell ◽  
Gene Expression Profiling ◽  
Expression Profiling ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Nuclear Factor ◽  
Large B Cell Lymphoma ◽  
Dlbcl Subtype ◽  
Large B Cell

Gene expression profiling has revealed that diffuse large B cell lymphoma (DLBCL) consists of at least two distinct diseases. Patients with one DLBCL subtype, termed activated B cell–like (ABC) DLBCL, have a distinctly inferior prognosis. An untapped potential of gene expression profiling is its ability to identify pathogenic signaling pathways in cancer that are amenable to therapeutic attack. The gene expression profiles of ABC DLBCLs were notable for the high expression of target genes of the nuclear factor (NF)-κB transcription factors, raising the possibility that constitutive activity of the NF-κB pathway may contribute to the poor prognosis of these patients. Two cell line models of ABC DLBCL had high nuclear NF-κB DNA binding activity, constitutive IκB kinase (IKK) activity, and rapid IκBα degradation that was not seen in cell lines representing the other DLBCL subtype, germinal center B-like (GCB) DLBCL. Retroviral transduction of a super-repressor form of IκBα or dominant negative forms of IKKβ was toxic to ABC DLBCL cells but not GCB DLBCL cells. DNA content analysis showed that NF-κB inhibition caused both cell death and G1-phase growth arrest. These findings establish the NF-κB pathway as a new molecular target for drug development in the most clinically intractable subtype of DLBCL and demonstrate that the two DLBCL subtypes defined by gene expression profiling utilize distinct pathogenetic mechanisms.

Gene Expression Profiling of Diffuse Large B-Cell Lymphomas Supervised by CD5 Expression

Blood ◽  
2010 ◽  
Vol 116 (21) ◽  
pp. 4164-4164
Author(s):  
Kana Miyazaki ◽  
Motoko Yamaguchi ◽  
Hiroshi Imai ◽  
Satoshi Tamaru ◽  
Tohru Kobayashi ◽  
...  
Keyword(s):  
Gene Expression ◽  
B Cell ◽  
Gene Expression Profiling ◽  
Expression Profiling ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Gene Set ◽  
Large B Cell Lymphoma ◽  
The Difference ◽  
Large B Cell

Abstract Abstract 4164 Diffuse large B-cell lymphoma (DLBCL) is the most common non-Hodgkin lymphoma and is composed of heterogeneous groups of lymphoma with pathophysiological, genetic and clinical features. Gene expression profiling identified two distinct forms of DLBCL: activated B cell-like (ABC) and germinal center B-cell-like (GCB) types. ABC DLBCL shows more activated phenotype characterized with high activity of the NF-kappa B pathway and worse prognosis than GCB DLBCL. CD5-positive (CD5+) DLBCL comprises 5 to 10% of DLBCL and is one of the immunohistochemical subgroups in the 2008 WHO classification. It shows many distinct clinical characteristics with elderly onset, advanced stage at diagnosis, high serum lactate dehydrogenase level and frequent involvement of extranodal sites. Despite the use of rituximab, CD5+ DLBCL shows a poor prognosis and high incidence of central nervous system (CNS) relapse. More than 80% of patients with CD5+ DLBCL are classified as non-GCB subgroup by Hans' method; however, few molecular studies have been reported. To clarify the difference between CD5+ DLBCL and CD5-negative (CD5-) DLBCL in the gene expression profile, total RNA from 90 patients with de novo DLBCL including 33 CD5+ DLBCLs and 57 CD5- DLBCLs was examined using Agilent 44K human oligo-microarrays (Agilent 4112F). The expression of CD5 in tumor cells was confirmed by means of immunohistochemistry using frozen sections. Cases of primary mediastinal large B-cell lymphoma, intravascular large B-cell lymphoma and primary DLBCL of the CNS were excluded from the present study. Supervised hierarchical clustering of the expression data could separate the DLBCL cases into the two groups, CD5+ DLBCL and CD5- DLBCL. A signature gene set supervised by CD5 expression included some of the same genes (SH3BP5, CCND2, LMO2) in the predictor gene set to discriminate between GCB and ABC DLBCLs. To classify the difference between CD5+ ABC DLBCL and CD5- ABC DLBCL in the gene expression profile, the 90 DLBCLs were analyzed by the Rosenwald's gene set (NEJM, 2002). Those cases were separated with 78 ABC DLBCLs and 12 GCB DLBCLs. Incidence of CD5+ cases was 42% (33/78) in ABC DLBCLs and 0% in GCB DLBCLs. A classifier based on gene expression at supervised analysis also correctly identified CD5 expression in ABC DLBCL. Signature genes to distinguish between CD5+ ABC DLBCL and CD5- ABC DLBCL were as follows: SNAP25, SYCP3, CCNA1, MAPK4, CCNA1, LMO3, NLGN3, GRIN2A, AQP4, FGFR2, NEUROD1, KL, FGF1, SYT5, etc., were overexpressed in CD5+ ABC DLBCL, and CYP4Z1, MDM2, IL7R, GRLF1, TNFRSF9, CD1A etc., were overexpressed in CD5- ABC DLBCL. Enriched Gene Ontology (GO) categories in CD5+ ABC DLBCL were synapse, multicellular organismal process, fibroblast growth factor receptor signaling pathway, cell projection, alcohol dehydrogenase activity and glucuronosyltransferase activity. Among them, synapse was the top GO category (P=6.1E-05). In conclusion, our current study confirmed that most of CD5+ DLBCLs are classified as ABC DLBCL by gene expression profiling. Our results suggest that neurological component- and function-related genes in the CD5+ ABC DLBCL signature gene set may be related to the high frequency of CNS relapse in CD5+ DLBCL. Disclosures: No relevant conflicts of interest to declare.

Sign in / Sign up

Export Citation Format

Share Document