HAPIR: a refined Hallmark gene set-based machine learning approach for predicting immunotherapy response in cancer patients

Abstract Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment, yet the response rate remains limited, with only about 30% of solid tumor patients benefiting. Identifying reliable biomarkers to predict ICIs response remains a significant challenge. In this study, we proposed a ref...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengqin Yuan, Haizhou Liu, Yu-e Huang, Fei Hou, Lihong Wang, Quan Wang, Wei Jiang
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:npj Precision Oncology
Online Access:https://doi.org/10.1038/s41698-025-00992-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849686229431353344
author Mengqin Yuan
Haizhou Liu
Yu-e Huang
Fei Hou
Lihong Wang
Quan Wang
Wei Jiang
author_facet Mengqin Yuan
Haizhou Liu
Yu-e Huang
Fei Hou
Lihong Wang
Quan Wang
Wei Jiang
author_sort Mengqin Yuan
collection DOAJ
description Abstract Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment, yet the response rate remains limited, with only about 30% of solid tumor patients benefiting. Identifying reliable biomarkers to predict ICIs response remains a significant challenge. In this study, we proposed a refined Hallmark gene set-based Approach for Predicting Immunotherapy Response (HAPIR). Through comprehensive multi-cohort analyses encompassing six TIGER cohorts (n = 352) and TCGA-SKCM (n = 472), we validated the optimal performance of HAPIR. Using transcriptomic data from a training cohort, we firstly refined seven Hallmark gene sets enriched with differentially expressed genes between responder and non-responder patients. Then, a logistic regression model trained based on the activities of these gene sets demonstrated superior predictive performance (AUROC = 0.778) in ten-fold cross-validation, significantly outperforming 13 existing biomarkers, including PD-1 (AUROC = 0.678) and PD-L1 (AUROC = 0.54). HAPIR’s robustness was further validated in the validation set and four independent cohorts spanning multiple cancer types (melanoma, NSCLC, and STAD), consistently achieving average AUROC = 0.745. Beyond well-known biomarkers, HAPIR surpassed both gene-based and alternative gene set-based models. Importantly, HAPIR scores correlated significantly with patient survival and effectively recapitulated the immune microenvironment, enabling the prediction of potential drug targets and drug candidates to overcome immunotherapy resistance. In conclusion, HAPIR is a promising tool for predicting ICIs response and guiding the development of new immunotherapy strategies.
format Article
id doaj-art-4d8f8761d0ba4040b5a60ca9342b2f09
institution DOAJ
issn 2397-768X
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series npj Precision Oncology
spelling doaj-art-4d8f8761d0ba4040b5a60ca9342b2f092025-08-20T03:22:46ZengNature Portfolionpj Precision Oncology2397-768X2025-06-019111110.1038/s41698-025-00992-9HAPIR: a refined Hallmark gene set-based machine learning approach for predicting immunotherapy response in cancer patientsMengqin Yuan0Haizhou Liu1Yu-e Huang2Fei Hou3Lihong Wang4Quan Wang5Wei Jiang6Department of Biomedical Engineering, Nanjing University of Aeronautics and AstronauticsFujian Key Laboratory of Precision Medicine for Cancer, the First Affiliated Hospital, Fujian Medical UniversityInstitute of Precision Medicine, the Affiliated Hospital of Guizhou Medical UniversityDepartment of Biomedical Engineering, Nanjing University of Aeronautics and AstronauticsFujian Key Laboratory of Precision Medicine for Cancer, the First Affiliated Hospital, Fujian Medical UniversityDepartment of Biomedical Engineering, Nanjing University of Aeronautics and AstronauticsFujian Key Laboratory of Precision Medicine for Cancer, the First Affiliated Hospital, Fujian Medical UniversityAbstract Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment, yet the response rate remains limited, with only about 30% of solid tumor patients benefiting. Identifying reliable biomarkers to predict ICIs response remains a significant challenge. In this study, we proposed a refined Hallmark gene set-based Approach for Predicting Immunotherapy Response (HAPIR). Through comprehensive multi-cohort analyses encompassing six TIGER cohorts (n = 352) and TCGA-SKCM (n = 472), we validated the optimal performance of HAPIR. Using transcriptomic data from a training cohort, we firstly refined seven Hallmark gene sets enriched with differentially expressed genes between responder and non-responder patients. Then, a logistic regression model trained based on the activities of these gene sets demonstrated superior predictive performance (AUROC = 0.778) in ten-fold cross-validation, significantly outperforming 13 existing biomarkers, including PD-1 (AUROC = 0.678) and PD-L1 (AUROC = 0.54). HAPIR’s robustness was further validated in the validation set and four independent cohorts spanning multiple cancer types (melanoma, NSCLC, and STAD), consistently achieving average AUROC = 0.745. Beyond well-known biomarkers, HAPIR surpassed both gene-based and alternative gene set-based models. Importantly, HAPIR scores correlated significantly with patient survival and effectively recapitulated the immune microenvironment, enabling the prediction of potential drug targets and drug candidates to overcome immunotherapy resistance. In conclusion, HAPIR is a promising tool for predicting ICIs response and guiding the development of new immunotherapy strategies.https://doi.org/10.1038/s41698-025-00992-9
spellingShingle Mengqin Yuan
Haizhou Liu
Yu-e Huang
Fei Hou
Lihong Wang
Quan Wang
Wei Jiang
HAPIR: a refined Hallmark gene set-based machine learning approach for predicting immunotherapy response in cancer patients
npj Precision Oncology
title HAPIR: a refined Hallmark gene set-based machine learning approach for predicting immunotherapy response in cancer patients
title_full HAPIR: a refined Hallmark gene set-based machine learning approach for predicting immunotherapy response in cancer patients
title_fullStr HAPIR: a refined Hallmark gene set-based machine learning approach for predicting immunotherapy response in cancer patients
title_full_unstemmed HAPIR: a refined Hallmark gene set-based machine learning approach for predicting immunotherapy response in cancer patients
title_short HAPIR: a refined Hallmark gene set-based machine learning approach for predicting immunotherapy response in cancer patients
title_sort hapir a refined hallmark gene set based machine learning approach for predicting immunotherapy response in cancer patients
url https://doi.org/10.1038/s41698-025-00992-9
work_keys_str_mv AT mengqinyuan hapirarefinedhallmarkgenesetbasedmachinelearningapproachforpredictingimmunotherapyresponseincancerpatients
AT haizhouliu hapirarefinedhallmarkgenesetbasedmachinelearningapproachforpredictingimmunotherapyresponseincancerpatients
AT yuehuang hapirarefinedhallmarkgenesetbasedmachinelearningapproachforpredictingimmunotherapyresponseincancerpatients
AT feihou hapirarefinedhallmarkgenesetbasedmachinelearningapproachforpredictingimmunotherapyresponseincancerpatients
AT lihongwang hapirarefinedhallmarkgenesetbasedmachinelearningapproachforpredictingimmunotherapyresponseincancerpatients
AT quanwang hapirarefinedhallmarkgenesetbasedmachinelearningapproachforpredictingimmunotherapyresponseincancerpatients
AT weijiang hapirarefinedhallmarkgenesetbasedmachinelearningapproachforpredictingimmunotherapyresponseincancerpatients