Related Experiment Video
Updated: Jun 14, 2025
Author Spotlight: Advancing Personalized Medicine in Ovarian Cancer
Published on: February 23, 2024
Artificial intelligence in ovarian cancer drug resistance advanced 3PM approach: subtype classification and
Cong Zhang1, Jinxiang Yang1, Siyu Chen1
1Department of Epidemiology and Health Statistics, School of Public Health, Chongqing Medical University, Yixue Road, Chongqing, 400016 China.
Background:
Ovarian cancer patients' resistance to first-line treatment posed a significant challenge, with approximately 70% experiencing recurrence and developing strong resistance to first-line chemotherapies like paclitaxel.
Objectives:
Within the framework of predictive, preventive, and personalized medicine (3PM), this study aimed to use artificial intelligence to find drug resistance characteristics at the single cell, and further construct the classification strategy and deep learning prognostic models based on these resistance traits, which can better facilitate and perform 3PM.
Methods:
This study employed "Beyondcell," an algorithm capable of predicting cellular drug responses, to calculate the similarity between the expression patterns of 21,937 cells from ovarian cancer samples and the signatures of 5201 drugs to identify drug-resistance cells. Drug resistance features were used to perform 10 multi-omics clustering on the TCGA training set to identify patient subgroups with differential drug responses. Concurrently, a deep learning prognostic model with KAN architecture which had a flexible activation function to better fit the model was constructed for this training set. The constructed patient subtype classifier and prognostic model were evaluated using three external validation sets from GEO: GSE17260, GSE26712, and GSE51088.
Results:
This study identified that endothelial cells are resistant to paclitaxel, doxorubicin, and docetaxel, suggesting their potential as targets for cellular therapy in ovarian cancer patients. Based on drug resistance features, 10 multi-omics clustering identified four patient subtypes with differential responses to four chemotherapy drugs, in which subtype CS2 showed the highest drug sensitivity to all four drugs. The other subtypes also showed enrichment in different biological pathways and immune infiltration, allowing for targeted treatment based on their characteristics. Besides, this study applied the latest KAN architecture in artificial intelligence to replace the MLP structure in the DeepSurv prognostic model, finally demonstrating robust performance on patients' prognosis prediction.
Conclusions:
This study, by classifying patients and constructing prognostic models based on resistance characteristics to first-line drugs, has effectively applied multi-omics data into the realm of 3PM.
Supplementary Information:
The online version contains supplementary material available at 10.1007/s13167-024-00374-4.
Insights
Ovarian cancer patients often develop resistance to chemotherapy. This study used AI to identify drug resistance traits, classifying patients into subtypes for personalized treatment and developing a deep learning model for prognosis.
Area of Science:
- Oncology
- Bioinformatics
- Artificial Intelligence
Background:
- Ovarian cancer exhibits high recurrence rates, with approximately 70% of patients developing resistance to first-line chemotherapies like paclitaxel.
- Addressing treatment resistance is crucial for improving patient outcomes in ovarian cancer.
Purpose of the Study:
- To leverage artificial intelligence for identifying single-cell drug resistance characteristics in ovarian cancer.
- To develop a classification strategy and deep learning prognostic models based on identified resistance traits to advance predictive, preventive, and personalized medicine (3PM).
Main Methods:
- Utilized the "Beyondcell" algorithm to predict cellular drug responses and identify drug-resistant cells by comparing expression patterns against drug signatures.
- Applied 10 multi-omics clustering on TCGA data using drug resistance features to define patient subgroups with differential drug responses.
- Developed and validated a deep learning prognostic model using KAN architecture on training and external validation datasets.
Main Results:
- Identified endothelial cells as resistant to paclitaxel, doxorubicin, and docetaxel, suggesting potential therapeutic targets.
- Discovered four patient subtypes with distinct chemotherapy responses; subtype CS2 demonstrated highest sensitivity to four tested drugs.
- The KAN-based deep learning model showed robust performance in predicting patient prognosis, outperforming traditional MLP structures.
Conclusions:
- Successfully classified ovarian cancer patients and developed prognostic models based on first-line drug resistance characteristics.
- Demonstrated the effective application of multi-omics data and AI in advancing predictive, preventive, and personalized medicine (3PM) for ovarian cancer.
