Predicting ovarian cancer patients' clinical response to platinum-based chemotherapy by their tumor proteomic signatures

Kun Hsing Yu, Douglas A. Levine, Hui Zhang, Daniel Wan-Yui Chan, Zhen Zhang, Michael Snyder

Research output: Contribution to journalArticle

Abstract

Ovarian cancer is the deadliest gynecologic malignancy in the United States with most patients diagnosed in the advanced stage of the disease. Platinum-based antineoplastic therapeutics is indispensable to treating advanced ovarian serous carcinoma. However, patients have heterogeneous responses to platinum drugs, and it is difficult to predict these interindividual differences before administering medication. In this study, we investigated the tumor proteomic profiles and clinical characteristics of 130 ovarian serous carcinoma patients analyzed by the Clinical Proteomic Tumor Analysis Consortium (CPTAC), predicted the platinum drug response using supervised machine learning methods, and evaluated our prediction models through leave-one-out cross-validation. Our data-driven feature selection approach indicated that tumor proteomics profiles contain information for predicting binarized platinum response (P < 0.0001). We further built a least absolute shrinkage and selection operator (LASSO)-Cox proportional hazards model that stratified patients into early relapse and late relapse groups (P = 0.00013). The top proteomic features indicative of platinum response were involved in ATP synthesis pathways and Ran GTPase binding. Overall, we demonstrated that proteomic profiles of ovarian serous carcinoma patients predicted platinum drug responses as well as provided insights into the biological processes influencing the efficacy of platinum-based therapeutics. Our analytical approach is also extensible to predicting response to other antineoplastic agents or treatment modalities for both ovarian and other cancers.

Original languageEnglish (US)
Pages (from-to)2455-2465
Number of pages11
JournalJournal of Proteome Research
Volume15
Issue number8
DOIs
StatePublished - Aug 5 2016

Fingerprint

Chemotherapy
Platinum
Proteomics
Ovarian Neoplasms
Tumors
Drug Therapy
Neoplasms
Carcinoma
Antineoplastic Agents
Pharmaceutical Preparations
Biological Phenomena
Recurrence
GTP Phosphohydrolases
Proportional Hazards Models
Learning systems
Feature extraction
Hazards
Therapeutics
Adenosine Triphosphate

Keywords

  • bioinformatics
  • cancer biomarkers
  • drug resistance
  • ovarian cancer
  • tandem mass spectrometry

ASJC Scopus subject areas

  • Biochemistry
  • Chemistry(all)

Cite this

Predicting ovarian cancer patients' clinical response to platinum-based chemotherapy by their tumor proteomic signatures. / Yu, Kun Hsing; Levine, Douglas A.; Zhang, Hui; Chan, Daniel Wan-Yui; Zhang, Zhen; Snyder, Michael.

In: Journal of Proteome Research, Vol. 15, No. 8, 05.08.2016, p. 2455-2465.

Research output: Contribution to journalArticle

@article{caeb81bfb90940649d2d0fd5bb816bf7,
title = "Predicting ovarian cancer patients' clinical response to platinum-based chemotherapy by their tumor proteomic signatures",
abstract = "Ovarian cancer is the deadliest gynecologic malignancy in the United States with most patients diagnosed in the advanced stage of the disease. Platinum-based antineoplastic therapeutics is indispensable to treating advanced ovarian serous carcinoma. However, patients have heterogeneous responses to platinum drugs, and it is difficult to predict these interindividual differences before administering medication. In this study, we investigated the tumor proteomic profiles and clinical characteristics of 130 ovarian serous carcinoma patients analyzed by the Clinical Proteomic Tumor Analysis Consortium (CPTAC), predicted the platinum drug response using supervised machine learning methods, and evaluated our prediction models through leave-one-out cross-validation. Our data-driven feature selection approach indicated that tumor proteomics profiles contain information for predicting binarized platinum response (P < 0.0001). We further built a least absolute shrinkage and selection operator (LASSO)-Cox proportional hazards model that stratified patients into early relapse and late relapse groups (P = 0.00013). The top proteomic features indicative of platinum response were involved in ATP synthesis pathways and Ran GTPase binding. Overall, we demonstrated that proteomic profiles of ovarian serous carcinoma patients predicted platinum drug responses as well as provided insights into the biological processes influencing the efficacy of platinum-based therapeutics. Our analytical approach is also extensible to predicting response to other antineoplastic agents or treatment modalities for both ovarian and other cancers.",
keywords = "bioinformatics, cancer biomarkers, drug resistance, ovarian cancer, tandem mass spectrometry",
author = "Yu, {Kun Hsing} and Levine, {Douglas A.} and Hui Zhang and Chan, {Daniel Wan-Yui} and Zhen Zhang and Michael Snyder",
year = "2016",
month = "8",
day = "5",
doi = "10.1021/acs.jproteome.5b01129",
language = "English (US)",
volume = "15",
pages = "2455--2465",
journal = "Journal of Proteome Research",
issn = "1535-3893",
publisher = "American Chemical Society",
number = "8",

}

TY - JOUR

T1 - Predicting ovarian cancer patients' clinical response to platinum-based chemotherapy by their tumor proteomic signatures

AU - Yu, Kun Hsing

AU - Levine, Douglas A.

AU - Zhang, Hui

AU - Chan, Daniel Wan-Yui

AU - Zhang, Zhen

AU - Snyder, Michael

PY - 2016/8/5

Y1 - 2016/8/5

N2 - Ovarian cancer is the deadliest gynecologic malignancy in the United States with most patients diagnosed in the advanced stage of the disease. Platinum-based antineoplastic therapeutics is indispensable to treating advanced ovarian serous carcinoma. However, patients have heterogeneous responses to platinum drugs, and it is difficult to predict these interindividual differences before administering medication. In this study, we investigated the tumor proteomic profiles and clinical characteristics of 130 ovarian serous carcinoma patients analyzed by the Clinical Proteomic Tumor Analysis Consortium (CPTAC), predicted the platinum drug response using supervised machine learning methods, and evaluated our prediction models through leave-one-out cross-validation. Our data-driven feature selection approach indicated that tumor proteomics profiles contain information for predicting binarized platinum response (P < 0.0001). We further built a least absolute shrinkage and selection operator (LASSO)-Cox proportional hazards model that stratified patients into early relapse and late relapse groups (P = 0.00013). The top proteomic features indicative of platinum response were involved in ATP synthesis pathways and Ran GTPase binding. Overall, we demonstrated that proteomic profiles of ovarian serous carcinoma patients predicted platinum drug responses as well as provided insights into the biological processes influencing the efficacy of platinum-based therapeutics. Our analytical approach is also extensible to predicting response to other antineoplastic agents or treatment modalities for both ovarian and other cancers.

AB - Ovarian cancer is the deadliest gynecologic malignancy in the United States with most patients diagnosed in the advanced stage of the disease. Platinum-based antineoplastic therapeutics is indispensable to treating advanced ovarian serous carcinoma. However, patients have heterogeneous responses to platinum drugs, and it is difficult to predict these interindividual differences before administering medication. In this study, we investigated the tumor proteomic profiles and clinical characteristics of 130 ovarian serous carcinoma patients analyzed by the Clinical Proteomic Tumor Analysis Consortium (CPTAC), predicted the platinum drug response using supervised machine learning methods, and evaluated our prediction models through leave-one-out cross-validation. Our data-driven feature selection approach indicated that tumor proteomics profiles contain information for predicting binarized platinum response (P < 0.0001). We further built a least absolute shrinkage and selection operator (LASSO)-Cox proportional hazards model that stratified patients into early relapse and late relapse groups (P = 0.00013). The top proteomic features indicative of platinum response were involved in ATP synthesis pathways and Ran GTPase binding. Overall, we demonstrated that proteomic profiles of ovarian serous carcinoma patients predicted platinum drug responses as well as provided insights into the biological processes influencing the efficacy of platinum-based therapeutics. Our analytical approach is also extensible to predicting response to other antineoplastic agents or treatment modalities for both ovarian and other cancers.

KW - bioinformatics

KW - cancer biomarkers

KW - drug resistance

KW - ovarian cancer

KW - tandem mass spectrometry

UR - http://www.scopus.com/inward/record.url?scp=84981313253&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84981313253&partnerID=8YFLogxK

U2 - 10.1021/acs.jproteome.5b01129

DO - 10.1021/acs.jproteome.5b01129

M3 - Article

C2 - 27312948

AN - SCOPUS:84981313253

VL - 15

SP - 2455

EP - 2465

JO - Journal of Proteome Research

JF - Journal of Proteome Research

SN - 1535-3893

IS - 8

ER -