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

Anouk C. de Jong; Alexandra Danyi; Job van Riet; Ronald de Wit; Martin Sjöström; Felix Feng; Jeroen de Ridder; Martijn P. Lolkema

doi:10.1038/s41467-023-37647-x

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

Anouk C. de Jong, Alexandra Danyi, Job van Riet, Ronald de Wit, Martin Sjöström, Felix Feng, Jeroen de Ridder, Martijn P. Lolkema^*

^*Corresponding author for this work

Medical Oncology

Research output: Contribution to journal › Article › Academic › peer-review

10 Citations (Scopus)

39 Downloads (Pure)

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 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.

Original language	English
Article number	1968
Pages (from-to)	1968
Number of pages	1
Journal	Nature Communications
Volume	14
Issue number	1
DOIs	https://doi.org/10.1038/s41467-023-37647-x
Publication status	Published - Dec 2023

Bibliographical note

Funding Information:
This research was financially supported with an unrestricted grant by Johnson & Johnson (ML; 212082PCR3014) and Astellas Pharma (ML; Lolkema/NL-72-RG-11). In addition, we would like to acknowledge the Erasmus MC Cancer Computational Biology Center (CCBC) and Hartwig Medical Foundation (HMF) for sharing their expertise and computational resources.

Funding Information:
This research was financially supported with an unrestricted grant by Johnson & Johnson (ML; 212082PCR3014) and Astellas Pharma (ML; Lolkema/NL-72-RG-11). In addition, we would like to acknowledge the Erasmus MC Cancer Computational Biology Center (CCBC) and Hartwig Medical Foundation (HMF) for sharing their expertise and computational resources.

Publisher Copyright:
© 2023, The Author(s).

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1038/s41467-023-37647-xLicence: CC BY

Predicting response to enzalutamide and abiraterone in metastatic prostate cancer using whole-omics machine learningFinal published version, 2.65 MBLicence: CC BY

Cite this

@article{3d2260a119864903a2303c3e658aa446,

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

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 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.",

author = "{de Jong}, {Anouk C.} and Alexandra Danyi and {van Riet}, Job and {de Wit}, Ronald and Martin Sj{\"o}str{\"o}m and Felix Feng and {de Ridder}, Jeroen and Lolkema, {Martijn P.}",

note = "Funding Information: This research was financially supported with an unrestricted grant by Johnson & Johnson (ML; 212082PCR3014) and Astellas Pharma (ML; Lolkema/NL-72-RG-11). In addition, we would like to acknowledge the Erasmus MC Cancer Computational Biology Center (CCBC) and Hartwig Medical Foundation (HMF) for sharing their expertise and computational resources. Funding Information: This research was financially supported with an unrestricted grant by Johnson & Johnson (ML; 212082PCR3014) and Astellas Pharma (ML; Lolkema/NL-72-RG-11). In addition, we would like to acknowledge the Erasmus MC Cancer Computational Biology Center (CCBC) and Hartwig Medical Foundation (HMF) for sharing their expertise and computational resources. Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = dec,

doi = "10.1038/s41467-023-37647-x",

language = "English",

volume = "14",

pages = "1968",

journal = "Nature Communications",

issn = "2041-1723",

publisher = "Nature Research",

number = "1",

}

TY - JOUR

T1 - Predicting response to enzalutamide and abiraterone in metastatic prostate cancer using whole-omics machine learning

AU - de Jong, Anouk C.

AU - Danyi, Alexandra

AU - van Riet, Job

AU - de Wit, Ronald

AU - Sjöström, Martin

AU - Feng, Felix

AU - de Ridder, Jeroen

AU - Lolkema, Martijn P.

N1 - Funding Information: This research was financially supported with an unrestricted grant by Johnson & Johnson (ML; 212082PCR3014) and Astellas Pharma (ML; Lolkema/NL-72-RG-11). In addition, we would like to acknowledge the Erasmus MC Cancer Computational Biology Center (CCBC) and Hartwig Medical Foundation (HMF) for sharing their expertise and computational resources. Funding Information: This research was financially supported with an unrestricted grant by Johnson & Johnson (ML; 212082PCR3014) and Astellas Pharma (ML; Lolkema/NL-72-RG-11). In addition, we would like to acknowledge the Erasmus MC Cancer Computational Biology Center (CCBC) and Hartwig Medical Foundation (HMF) for sharing their expertise and computational resources. Publisher Copyright: © 2023, The Author(s).

PY - 2023/12

Y1 - 2023/12

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85151997862&partnerID=8YFLogxK

U2 - 10.1038/s41467-023-37647-x

DO - 10.1038/s41467-023-37647-x

M3 - Article

C2 - 37031196

AN - SCOPUS:85151997862

SN - 2041-1723

VL - 14

SP - 1968

JO - Nature Communications

JF - Nature Communications

IS - 1

M1 - 1968

ER -

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

Abstract

Bibliographical note

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this