Proteomic alterations in ovarian cancer—Predicting residual disease status using artificial intelligence and SHAP-based biomarker interpretation

IntroductionHigh-grade serous ovarian cancer (HGSOC) is the most aggressive and prevalent subtype of ovarian Treatment outcomes are significantly influenced by residual disease status following neoadjuvant chemotherapy (NACT). Predicting residual disease before surgery can improve patient stratifica...

Full description

Saved in:
Bibliographic Details
Main Authors: Seyma Yasar, Rauf Melekoglu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1562558/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849303733161164800
author Seyma Yasar
Rauf Melekoglu
author_facet Seyma Yasar
Rauf Melekoglu
author_sort Seyma Yasar
collection DOAJ
description IntroductionHigh-grade serous ovarian cancer (HGSOC) is the most aggressive and prevalent subtype of ovarian Treatment outcomes are significantly influenced by residual disease status following neoadjuvant chemotherapy (NACT). Predicting residual disease before surgery can improve patient stratification and personalized treatment strategies.MethodsThis study analyzed pre-NACT proteomic data from 20 HGSOC patients treated with NACT. Patients were categorized into two groups based on surgical outcomes: no residual disease (R0, n = 14) and suboptimal residual disease (R1, n = 6). From an initial set of 97 differentially expressed proteins, 18 significant proteins were selected using the BORUTA feature selection method. Three machine learning models-Random Forest (RF), Support Vector Machine (SVM), and Bootstrap Aggregation with Classification and Regression Trees (BaggedCART)-were developed and evaluated.ResultsThe Random Forest model achieved the best performance with an AUC of 0.955, accuracy of 0.830, sensitivity of 0.904, specificity of 0.763, and F1-score of 0.839. SHapley Additive exPlanations (SHAP) analysis identified five proteins (P48637, O43491, O95302, Q96CX2, and P49189) as the most influential predictors of residual disease. These proteins, including glutathione synthetase and peptidyl-prolyl cis-trans isomerase FKBP9, are associated with chemotherapy resistance mechanisms.DiscussionThe findings demonstrate the potential of integrating proteomic data with machine learning techniques for predicting surgical outcomes in HGSOC. Identified protein signatures may serve as valuable biomarkers for anticipating NACT response and informing clinical decision-making, ultimately contributing to personalized patient care.
format Article
id doaj-art-5b146047fbdb4aeaa3f803333fce5e9c
institution Kabale University
issn 2296-858X
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-5b146047fbdb4aeaa3f803333fce5e9c2025-08-20T03:55:59ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-07-011210.3389/fmed.2025.15625581562558Proteomic alterations in ovarian cancer—Predicting residual disease status using artificial intelligence and SHAP-based biomarker interpretationSeyma Yasar0Rauf Melekoglu1Department of Biostatistics, and Medical Informatics, Medicine Faculty, Inonu University, Malatya, TürkiyeDepartment of Obstetrics and Gynecology, Faculty of Medicine, Inonu University, Malatya, TürkiyeIntroductionHigh-grade serous ovarian cancer (HGSOC) is the most aggressive and prevalent subtype of ovarian Treatment outcomes are significantly influenced by residual disease status following neoadjuvant chemotherapy (NACT). Predicting residual disease before surgery can improve patient stratification and personalized treatment strategies.MethodsThis study analyzed pre-NACT proteomic data from 20 HGSOC patients treated with NACT. Patients were categorized into two groups based on surgical outcomes: no residual disease (R0, n = 14) and suboptimal residual disease (R1, n = 6). From an initial set of 97 differentially expressed proteins, 18 significant proteins were selected using the BORUTA feature selection method. Three machine learning models-Random Forest (RF), Support Vector Machine (SVM), and Bootstrap Aggregation with Classification and Regression Trees (BaggedCART)-were developed and evaluated.ResultsThe Random Forest model achieved the best performance with an AUC of 0.955, accuracy of 0.830, sensitivity of 0.904, specificity of 0.763, and F1-score of 0.839. SHapley Additive exPlanations (SHAP) analysis identified five proteins (P48637, O43491, O95302, Q96CX2, and P49189) as the most influential predictors of residual disease. These proteins, including glutathione synthetase and peptidyl-prolyl cis-trans isomerase FKBP9, are associated with chemotherapy resistance mechanisms.DiscussionThe findings demonstrate the potential of integrating proteomic data with machine learning techniques for predicting surgical outcomes in HGSOC. Identified protein signatures may serve as valuable biomarkers for anticipating NACT response and informing clinical decision-making, ultimately contributing to personalized patient care.https://www.frontiersin.org/articles/10.3389/fmed.2025.1562558/fullhigh-grade serous ovarian cancer (HGSOC)neoadjuvant chemotherapy (NACT)machine learningproteomic biomarkersSHAP analysis
spellingShingle Seyma Yasar
Rauf Melekoglu
Proteomic alterations in ovarian cancer—Predicting residual disease status using artificial intelligence and SHAP-based biomarker interpretation
Frontiers in Medicine
high-grade serous ovarian cancer (HGSOC)
neoadjuvant chemotherapy (NACT)
machine learning
proteomic biomarkers
SHAP analysis
title Proteomic alterations in ovarian cancer—Predicting residual disease status using artificial intelligence and SHAP-based biomarker interpretation
title_full Proteomic alterations in ovarian cancer—Predicting residual disease status using artificial intelligence and SHAP-based biomarker interpretation
title_fullStr Proteomic alterations in ovarian cancer—Predicting residual disease status using artificial intelligence and SHAP-based biomarker interpretation
title_full_unstemmed Proteomic alterations in ovarian cancer—Predicting residual disease status using artificial intelligence and SHAP-based biomarker interpretation
title_short Proteomic alterations in ovarian cancer—Predicting residual disease status using artificial intelligence and SHAP-based biomarker interpretation
title_sort proteomic alterations in ovarian cancer predicting residual disease status using artificial intelligence and shap based biomarker interpretation
topic high-grade serous ovarian cancer (HGSOC)
neoadjuvant chemotherapy (NACT)
machine learning
proteomic biomarkers
SHAP analysis
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1562558/full
work_keys_str_mv AT seymayasar proteomicalterationsinovariancancerpredictingresidualdiseasestatususingartificialintelligenceandshapbasedbiomarkerinterpretation
AT raufmelekoglu proteomicalterationsinovariancancerpredictingresidualdiseasestatususingartificialintelligenceandshapbasedbiomarkerinterpretation