Personalized prediction of anticancer potential of non-oncology drugs through learning from genome derived molecular pathways
Abstract Advances in cancer genomics have significantly expanded our understanding of cancer biology. However, the high cost of drug development limits our ability to translate this knowledge into precise treatments. Approved non-oncology drugs, comprising a large repository of chemical entities, of...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | npj Precision Oncology |
| Online Access: | https://doi.org/10.1038/s41698-025-00813-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823863423394381824 |
|---|---|
| author | Xiaobao Dong Huanhuan Liu Ting Tong Liuxing Wu Jianhua Wang Tianyi You Yongjian Wei Xianfu Yi Hongxi Yang Jie Hu Haitao Wang Xiaoyan Wang Mulin Jun Li |
| author_facet | Xiaobao Dong Huanhuan Liu Ting Tong Liuxing Wu Jianhua Wang Tianyi You Yongjian Wei Xianfu Yi Hongxi Yang Jie Hu Haitao Wang Xiaoyan Wang Mulin Jun Li |
| author_sort | Xiaobao Dong |
| collection | DOAJ |
| description | Abstract Advances in cancer genomics have significantly expanded our understanding of cancer biology. However, the high cost of drug development limits our ability to translate this knowledge into precise treatments. Approved non-oncology drugs, comprising a large repository of chemical entities, offer a promising avenue for repurposing in cancer therapy. Herein we present CHANCE, a supervised machine learning model designed to predict the anticancer activities of non-oncology drugs for specific patients by simultaneously considering personalized coding and non-coding mutations. Utilizing protein–protein interaction networks, CHANCE harmonizes multilevel mutation annotations and integrates pharmacological information across different drugs into a single model. We systematically benchmarked the performance of CHANCE and show its predictions are better than previous model and highly interpretable. Applying CHANCE to approximately 5000 cancer samples indicated that >30% might respond to at least one non-oncology drug, with 11% non-oncology drugs predicted to have anticancer activities. Moreover, CHANCE predictions suggested an association between SMAD7 mutations and aspirin treatment response. Experimental validation using tumor cells derived from seven patients with pancreatic or esophageal cancer confirmed the potential anticancer activity of at least one non-oncology drug for five of these patients. To summarize, CHANCE offers a personalized and interpretable approach, serving as a valuable tool for mining non-oncology drugs in the precision oncology era. |
| format | Article |
| id | doaj-art-63daef0a1f5d42729d4bdd0243ae4223 |
| institution | Kabale University |
| issn | 2397-768X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Precision Oncology |
| spelling | doaj-art-63daef0a1f5d42729d4bdd0243ae42232025-02-09T12:09:27ZengNature Portfolionpj Precision Oncology2397-768X2025-02-019111510.1038/s41698-025-00813-zPersonalized prediction of anticancer potential of non-oncology drugs through learning from genome derived molecular pathwaysXiaobao Dong0Huanhuan Liu1Ting Tong2Liuxing Wu3Jianhua Wang4Tianyi You5Yongjian Wei6Xianfu Yi7Hongxi Yang8Jie Hu9Haitao Wang10Xiaoyan Wang11Mulin Jun Li12Department of Genetics, The Province and Ministry Co-sponsored Collaborative Innovation Center for Medical Epigenetics, Precision Medicine Research Center, The Second Hospital of Tianjin Medical University; Tianjin Medical UniversityDepartment of Bioinformatics, Tianjin Key Laboratory of Inflammation Biology, School of Basic Medical Sciences, Tianjin Medical UniversityDepartment of Gastroenterology, The Third Xiangya Hospital, Hunan Key Laboratory of Non-resolving Inflammation and Cancer, Central South UniversityDepartment of Bioinformatics, Tianjin Key Laboratory of Inflammation Biology, School of Basic Medical Sciences, Tianjin Medical UniversityDepartment of Bioinformatics, Tianjin Key Laboratory of Inflammation Biology, School of Basic Medical Sciences, Tianjin Medical UniversityDepartment of Bioinformatics, Tianjin Key Laboratory of Inflammation Biology, School of Basic Medical Sciences, Tianjin Medical UniversityDepartment of Bioinformatics, Tianjin Key Laboratory of Inflammation Biology, School of Basic Medical Sciences, Tianjin Medical UniversityDepartment of Bioinformatics, Tianjin Key Laboratory of Inflammation Biology, School of Basic Medical Sciences, Tianjin Medical UniversityDepartment of Bioinformatics, Tianjin Key Laboratory of Inflammation Biology, School of Basic Medical Sciences, Tianjin Medical UniversityBiobank of Hefei Cancer Hospital, Chinese Academy of SciencesDepartment of Oncology, Tianjin Institute of Urology, The Second Hospital of Tianjin Medical UniversityDepartment of Gastroenterology, The Third Xiangya Hospital, Hunan Key Laboratory of Non-resolving Inflammation and Cancer, Central South UniversityDepartment of Genetics, The Province and Ministry Co-sponsored Collaborative Innovation Center for Medical Epigenetics, Precision Medicine Research Center, The Second Hospital of Tianjin Medical University; Tianjin Medical UniversityAbstract Advances in cancer genomics have significantly expanded our understanding of cancer biology. However, the high cost of drug development limits our ability to translate this knowledge into precise treatments. Approved non-oncology drugs, comprising a large repository of chemical entities, offer a promising avenue for repurposing in cancer therapy. Herein we present CHANCE, a supervised machine learning model designed to predict the anticancer activities of non-oncology drugs for specific patients by simultaneously considering personalized coding and non-coding mutations. Utilizing protein–protein interaction networks, CHANCE harmonizes multilevel mutation annotations and integrates pharmacological information across different drugs into a single model. We systematically benchmarked the performance of CHANCE and show its predictions are better than previous model and highly interpretable. Applying CHANCE to approximately 5000 cancer samples indicated that >30% might respond to at least one non-oncology drug, with 11% non-oncology drugs predicted to have anticancer activities. Moreover, CHANCE predictions suggested an association between SMAD7 mutations and aspirin treatment response. Experimental validation using tumor cells derived from seven patients with pancreatic or esophageal cancer confirmed the potential anticancer activity of at least one non-oncology drug for five of these patients. To summarize, CHANCE offers a personalized and interpretable approach, serving as a valuable tool for mining non-oncology drugs in the precision oncology era.https://doi.org/10.1038/s41698-025-00813-z |
| spellingShingle | Xiaobao Dong Huanhuan Liu Ting Tong Liuxing Wu Jianhua Wang Tianyi You Yongjian Wei Xianfu Yi Hongxi Yang Jie Hu Haitao Wang Xiaoyan Wang Mulin Jun Li Personalized prediction of anticancer potential of non-oncology drugs through learning from genome derived molecular pathways npj Precision Oncology |
| title | Personalized prediction of anticancer potential of non-oncology drugs through learning from genome derived molecular pathways |
| title_full | Personalized prediction of anticancer potential of non-oncology drugs through learning from genome derived molecular pathways |
| title_fullStr | Personalized prediction of anticancer potential of non-oncology drugs through learning from genome derived molecular pathways |
| title_full_unstemmed | Personalized prediction of anticancer potential of non-oncology drugs through learning from genome derived molecular pathways |
| title_short | Personalized prediction of anticancer potential of non-oncology drugs through learning from genome derived molecular pathways |
| title_sort | personalized prediction of anticancer potential of non oncology drugs through learning from genome derived molecular pathways |
| url | https://doi.org/10.1038/s41698-025-00813-z |
| work_keys_str_mv | AT xiaobaodong personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways AT huanhuanliu personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways AT tingtong personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways AT liuxingwu personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways AT jianhuawang personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways AT tianyiyou personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways AT yongjianwei personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways AT xianfuyi personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways AT hongxiyang personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways AT jiehu personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways AT haitaowang personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways AT xiaoyanwang personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways AT mulinjunli personalizedpredictionofanticancerpotentialofnononcologydrugsthroughlearningfromgenomederivedmolecularpathways |