Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Predicting response to enzalutamide and abiraterone in metastatic prostate cancer using whole-omics machine learning

de Jong, Anouk C ; Danyi, Alexandra ; van Riet, Job ; de Wit, Ronald ; Sjöström, Martin LU ; Feng, Felix ; de Ridder, Jeroen and Lolkema, Martijn P (2023) In Nature Communications 14(1).
Abstract

Response to androgen receptor signaling inhibitors (ARSI) varies widely in metastatic castration resistant prostate cancer (mCRPC). To improve treatment guidance, biomarkers are needed. We use whole-genomics (WGS; n = 155) with matching whole-transcriptomics (WTS; n = 113) from biopsies of ARSI-treated mCRPC patients for unbiased discovery of biomarkers and development of machine learning-based prediction models. Tumor mutational burden (q < 0.001), structural variants (q < 0.05), tandem duplications (q < 0.05) and deletions (q < 0.05) are enriched in poor responders, coupled with distinct transcriptomic expression profiles. Validating various classification models predicting treatment duration with ARSI on our internal and... (More)

Response to androgen receptor signaling inhibitors (ARSI) varies widely in metastatic castration resistant prostate cancer (mCRPC). To improve treatment guidance, biomarkers are needed. We use whole-genomics (WGS; n = 155) with matching whole-transcriptomics (WTS; n = 113) from biopsies of ARSI-treated mCRPC patients for unbiased discovery of biomarkers and development of machine learning-based prediction models. Tumor mutational burden (q < 0.001), structural variants (q < 0.05), tandem duplications (q < 0.05) and deletions (q < 0.05) are enriched in poor responders, coupled with distinct transcriptomic expression profiles. Validating various classification models predicting treatment duration with ARSI on our internal and external mCRPC cohort reveals two best-performing models, based on the combination of prior treatment information with either the four combined enriched genomic markers or with overall transcriptomic profiles. In conclusion, predictive models combining genomic, transcriptomic, and clinical data can predict response to ARSI in mCRPC patients and, with additional optimization and prospective validation, could improve treatment guidance.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; and
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Male, Humans, Prostatic Neoplasms, Castration-Resistant/drug therapy, Androstenes/therapeutic use, Phenylthiohydantoin/therapeutic use, Nitriles/therapeutic use, Biomarkers, Tumor/genetics, Treatment Outcome, Benzamides
in
Nature Communications
volume
14
issue
1
article number
1968
publisher
Nature Publishing Group
external identifiers
  • scopus:85151997862
  • pmid:37031196
ISSN
2041-1723
DOI
10.1038/s41467-023-37647-x
language
English
LU publication?
no
additional info
© 2023. The Author(s).
id
20747565-d74b-4336-be52-5f99ba7484c5
date added to LUP
2026-02-20 13:37:02
date last changed
2026-02-21 04:00:58
@article{20747565-d74b-4336-be52-5f99ba7484c5,
  abstract     = {{<p>Response to androgen receptor signaling inhibitors (ARSI) varies widely in metastatic castration resistant prostate cancer (mCRPC). To improve treatment guidance, biomarkers are needed. We use whole-genomics (WGS; n = 155) with matching whole-transcriptomics (WTS; n = 113) from biopsies of ARSI-treated mCRPC patients for unbiased discovery of biomarkers and development of machine learning-based prediction models. Tumor mutational burden (q &lt; 0.001), structural variants (q &lt; 0.05), tandem duplications (q &lt; 0.05) and deletions (q &lt; 0.05) are enriched in poor responders, coupled with distinct transcriptomic expression profiles. Validating various classification models predicting treatment duration with ARSI on our internal and external mCRPC cohort reveals two best-performing models, based on the combination of prior treatment information with either the four combined enriched genomic markers or with overall transcriptomic profiles. In conclusion, predictive models combining genomic, transcriptomic, and clinical data can predict response to ARSI in mCRPC patients and, with additional optimization and prospective validation, could improve treatment guidance.</p>}},
  author       = {{de Jong, Anouk C and Danyi, Alexandra and van Riet, Job and de Wit, Ronald and Sjöström, Martin and Feng, Felix and de Ridder, Jeroen and Lolkema, Martijn P}},
  issn         = {{2041-1723}},
  keywords     = {{Male; Humans; Prostatic Neoplasms, Castration-Resistant/drug therapy; Androstenes/therapeutic use; Phenylthiohydantoin/therapeutic use; Nitriles/therapeutic use; Biomarkers, Tumor/genetics; Treatment Outcome; Benzamides}},
  language     = {{eng}},
  month        = {{04}},
  number       = {{1}},
  publisher    = {{Nature Publishing Group}},
  series       = {{Nature Communications}},
  title        = {{Predicting response to enzalutamide and abiraterone in metastatic prostate cancer using whole-omics machine learning}},
  url          = {{http://dx.doi.org/10.1038/s41467-023-37647-x}},
  doi          = {{10.1038/s41467-023-37647-x}},
  volume       = {{14}},
  year         = {{2023}},
}