A gene expression signature distinguishes innate response and resistance to proteasome inhibitors in multiple myeloma

A. K. Mitra, T. Harding, U. K. Mukherjee, J. S. Jang, Y. Li, R. HongZheng, Jin Jen, P. Sonneveld, Shaji K Kumar, W. M. Kuehl, S Vincent Rajkumar, B. Van Ness

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Extensive interindividual variation in response to chemotherapy is a major stumbling block in achieving desirable efficacy in the treatment of cancers, including multiple myeloma (MM). In this study, our goal was to develop a gene expression signature that predicts response specific to proteasome inhibitor (PI) treatment in MM. Using a well-characterized panel of human myeloma cell lines (HMCLs) representing the biological and genetic heterogeneity of MM, we created an in vitro chemosensitivity profile in response to treatment with the four PIs bortezomib, carfilzomib, ixazomib and oprozomib as single agents. Gene expression profiling was performed using next-generation high-throughput RNA-sequencing. Applying machine learning-based computational approaches including the supervised ensemble learning methods Random forest and Random survival forest, we identified a 42-gene expression signature that could not only distinguish good and poor PI response in the HMCL panel, but could also be successfully applied to four different clinical data sets on MM patients undergoing PI-based chemotherapy to distinguish between extraordinary (good and poor) outcomes. Our results demonstrate the use of in vitro modeling and machine learning-based approaches to establish predictive biomarkers of response and resistance to drugs that may serve to better direct myeloma patient treatment options.

Original languageEnglish (US)
Pages (from-to)e581
JournalBlood Cancer Journal
Volume7
Issue number6
DOIs
StatePublished - Jun 30 2017
Externally publishedYes

Fingerprint

Proteasome Inhibitors
Multiple Myeloma
Transcriptome
Drug Therapy
High-Throughput Nucleotide Sequencing
Cell Line
Genetic Heterogeneity
Gene Expression Profiling
Drug Resistance
Therapeutics
Biomarkers
Learning
Survival
Neoplasms
Forests
Machine Learning
In Vitro Techniques

ASJC Scopus subject areas

  • Hematology
  • Oncology

Cite this

Mitra, A. K., Harding, T., Mukherjee, U. K., Jang, J. S., Li, Y., HongZheng, R., ... Van Ness, B. (2017). A gene expression signature distinguishes innate response and resistance to proteasome inhibitors in multiple myeloma. Blood Cancer Journal, 7(6), e581. https://doi.org/10.1038/bcj.2017.56

A gene expression signature distinguishes innate response and resistance to proteasome inhibitors in multiple myeloma. / Mitra, A. K.; Harding, T.; Mukherjee, U. K.; Jang, J. S.; Li, Y.; HongZheng, R.; Jen, Jin; Sonneveld, P.; Kumar, Shaji K; Kuehl, W. M.; Rajkumar, S Vincent; Van Ness, B.

In: Blood Cancer Journal, Vol. 7, No. 6, 30.06.2017, p. e581.

Research output: Contribution to journalArticle

Mitra, AK, Harding, T, Mukherjee, UK, Jang, JS, Li, Y, HongZheng, R, Jen, J, Sonneveld, P, Kumar, SK, Kuehl, WM, Rajkumar, SV & Van Ness, B 2017, 'A gene expression signature distinguishes innate response and resistance to proteasome inhibitors in multiple myeloma', Blood Cancer Journal, vol. 7, no. 6, pp. e581. https://doi.org/10.1038/bcj.2017.56
Mitra, A. K. ; Harding, T. ; Mukherjee, U. K. ; Jang, J. S. ; Li, Y. ; HongZheng, R. ; Jen, Jin ; Sonneveld, P. ; Kumar, Shaji K ; Kuehl, W. M. ; Rajkumar, S Vincent ; Van Ness, B. / A gene expression signature distinguishes innate response and resistance to proteasome inhibitors in multiple myeloma. In: Blood Cancer Journal. 2017 ; Vol. 7, No. 6. pp. e581.
@article{d0af9e5ade6747a0919b5170d5537edd,
title = "A gene expression signature distinguishes innate response and resistance to proteasome inhibitors in multiple myeloma",
abstract = "Extensive interindividual variation in response to chemotherapy is a major stumbling block in achieving desirable efficacy in the treatment of cancers, including multiple myeloma (MM). In this study, our goal was to develop a gene expression signature that predicts response specific to proteasome inhibitor (PI) treatment in MM. Using a well-characterized panel of human myeloma cell lines (HMCLs) representing the biological and genetic heterogeneity of MM, we created an in vitro chemosensitivity profile in response to treatment with the four PIs bortezomib, carfilzomib, ixazomib and oprozomib as single agents. Gene expression profiling was performed using next-generation high-throughput RNA-sequencing. Applying machine learning-based computational approaches including the supervised ensemble learning methods Random forest and Random survival forest, we identified a 42-gene expression signature that could not only distinguish good and poor PI response in the HMCL panel, but could also be successfully applied to four different clinical data sets on MM patients undergoing PI-based chemotherapy to distinguish between extraordinary (good and poor) outcomes. Our results demonstrate the use of in vitro modeling and machine learning-based approaches to establish predictive biomarkers of response and resistance to drugs that may serve to better direct myeloma patient treatment options.",
author = "Mitra, {A. K.} and T. Harding and Mukherjee, {U. K.} and Jang, {J. S.} and Y. Li and R. HongZheng and Jin Jen and P. Sonneveld and Kumar, {Shaji K} and Kuehl, {W. M.} and Rajkumar, {S Vincent} and {Van Ness}, B.",
year = "2017",
month = "6",
day = "30",
doi = "10.1038/bcj.2017.56",
language = "English (US)",
volume = "7",
pages = "e581",
journal = "Blood Cancer Journal",
issn = "2044-5385",
publisher = "Nature Publishing Group",
number = "6",

}

TY - JOUR

T1 - A gene expression signature distinguishes innate response and resistance to proteasome inhibitors in multiple myeloma

AU - Mitra, A. K.

AU - Harding, T.

AU - Mukherjee, U. K.

AU - Jang, J. S.

AU - Li, Y.

AU - HongZheng, R.

AU - Jen, Jin

AU - Sonneveld, P.

AU - Kumar, Shaji K

AU - Kuehl, W. M.

AU - Rajkumar, S Vincent

AU - Van Ness, B.

PY - 2017/6/30

Y1 - 2017/6/30

N2 - Extensive interindividual variation in response to chemotherapy is a major stumbling block in achieving desirable efficacy in the treatment of cancers, including multiple myeloma (MM). In this study, our goal was to develop a gene expression signature that predicts response specific to proteasome inhibitor (PI) treatment in MM. Using a well-characterized panel of human myeloma cell lines (HMCLs) representing the biological and genetic heterogeneity of MM, we created an in vitro chemosensitivity profile in response to treatment with the four PIs bortezomib, carfilzomib, ixazomib and oprozomib as single agents. Gene expression profiling was performed using next-generation high-throughput RNA-sequencing. Applying machine learning-based computational approaches including the supervised ensemble learning methods Random forest and Random survival forest, we identified a 42-gene expression signature that could not only distinguish good and poor PI response in the HMCL panel, but could also be successfully applied to four different clinical data sets on MM patients undergoing PI-based chemotherapy to distinguish between extraordinary (good and poor) outcomes. Our results demonstrate the use of in vitro modeling and machine learning-based approaches to establish predictive biomarkers of response and resistance to drugs that may serve to better direct myeloma patient treatment options.

AB - Extensive interindividual variation in response to chemotherapy is a major stumbling block in achieving desirable efficacy in the treatment of cancers, including multiple myeloma (MM). In this study, our goal was to develop a gene expression signature that predicts response specific to proteasome inhibitor (PI) treatment in MM. Using a well-characterized panel of human myeloma cell lines (HMCLs) representing the biological and genetic heterogeneity of MM, we created an in vitro chemosensitivity profile in response to treatment with the four PIs bortezomib, carfilzomib, ixazomib and oprozomib as single agents. Gene expression profiling was performed using next-generation high-throughput RNA-sequencing. Applying machine learning-based computational approaches including the supervised ensemble learning methods Random forest and Random survival forest, we identified a 42-gene expression signature that could not only distinguish good and poor PI response in the HMCL panel, but could also be successfully applied to four different clinical data sets on MM patients undergoing PI-based chemotherapy to distinguish between extraordinary (good and poor) outcomes. Our results demonstrate the use of in vitro modeling and machine learning-based approaches to establish predictive biomarkers of response and resistance to drugs that may serve to better direct myeloma patient treatment options.

UR - http://www.scopus.com/inward/record.url?scp=85037554568&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037554568&partnerID=8YFLogxK

U2 - 10.1038/bcj.2017.56

DO - 10.1038/bcj.2017.56

M3 - Article

C2 - 28665416

AN - SCOPUS:85037554568

VL - 7

SP - e581

JO - Blood Cancer Journal

JF - Blood Cancer Journal

SN - 2044-5385

IS - 6

ER -