Related Experiment Video
Updated: Jul 9, 2025

Orthotopic Transplantation of Syngeneic Lung Adenocarcinoma Cells to Study PD-L1 Expression
Published on: January 19, 2019
Deep learning untangles the resistance mechanism of p53 reactivator in lung cancer cells
Soo Min Lee1, Younghyun Han1, Kwang-Hyun Cho1
1Laboratory for Systems Biology and Bio-inspired Engineering, Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, Republic of Korea.
Abstract:
Tumor suppressor p53 plays a pivotal role in suppressing cancer, so various drugs has been suggested to upregulate its function. However, drug resistance is still the biggest hurdle to be overcome. To address this, we developed a deep learning model called AnoDAN (anomalous gene detection using generative adversarial networks and graph neural networks for overcoming drug resistance) that unravels the hidden resistance mechanisms and identifies a combinatorial target to overcome the resistance. Our findings reveal that the TGF-β signaling pathway, alongside the p53 signaling pathway, mediates the resistance, with THBS1 serving as a core regulatory target in both pathways. Experimental validation in lung cancer cells confirms the effects of THBS1 on responsiveness to a p53 reactivator. We further discovered the positive feedback loop between THBS1 and the TGF-β pathway as the main source of resistance. This study enhances our understanding of p53 regulation and offers insights into overcoming drug resistance.
Insights
This study introduces AnoDAN, a deep learning model to overcome cancer drug resistance by identifying resistance mechanisms. It reveals THBS1 and the TGF-β pathway as key targets for enhancing p53 reactivator therapy.
Area of Science:
- Oncology
- Computational Biology
- Genetics
Background:
- The tumor suppressor p53 is crucial for cancer suppression, but drug resistance remains a significant challenge.
- Developing strategies to overcome drug resistance is essential for effective cancer therapy.
Purpose of the Study:
- To develop a deep learning model, AnoDAN, to identify mechanisms of drug resistance and discover combinatorial targets.
- To investigate the role of the TGF-β signaling pathway and THBS1 in mediating resistance to p53-targeting drugs.
Main Methods:
- Development of AnoDAN, a deep learning model integrating generative adversarial networks and graph neural networks.
- Analysis of signaling pathways involved in drug resistance.
- Experimental validation in lung cancer cells to assess the impact of THBS1 modulation.
Main Results:
- AnoDAN identified the TGF-β signaling pathway and THBS1 as key mediators of resistance to p53 reactivators.
- THBS1 was confirmed as a core regulatory target in both p53 and TGF-β pathways.
- A positive feedback loop between THBS1 and TGF-β was identified as a primary resistance mechanism.
Conclusions:
- The study enhances understanding of p53 regulation and drug resistance mechanisms.
- AnoDAN provides a novel approach for identifying combinatorial targets to overcome cancer drug resistance.
- Targeting THBS1 in conjunction with p53 reactivators shows promise for improving lung cancer treatment.
Related Concept Videos
Abnormal Proliferation
Treatment Resistant Cancers
DNA Damage can Stall the Cell Cycle
Negative Regulator Molecules

