Related Experiment Video
Updated: Jul 1, 2025
A Combined 3D Tissue Engineered In Vitro/In Silico Lung Tumor Model for Predicting Drug Effectiveness in Specific Mutational Backgrounds
Published on: April 6, 2016
A deep learning model of tumor cell architecture elucidates response and resistance to CDK4/6 inhibitors
Sungjoon Park1, Erica Silva2, Akshat Singhal3
1Department of Medicine, University of California, San Diego, La Jolla, CA, USA.
Abstract:
Cyclin-dependent kinase 4 and 6 inhibitors (CDK4/6is) have revolutionized breast cancer therapy. However, <50% of patients have an objective response, and nearly all patients develop resistance during therapy. To elucidate the underlying mechanisms, we constructed an interpretable deep learning model of the response to palbociclib, a CDK4/6i, based on a reference map of multiprotein assemblies in cancer. The model identifies eight core assemblies that integrate rare and common alterations across 90 genes to stratify palbociclib-sensitive versus palbociclib-resistant cell lines. Predictions translate to patients and patient-derived xenografts, whereas single-gene biomarkers do not. Most predictive assemblies can be shown by CRISPR-Cas9 genetic disruption to regulate the CDK4/6i response. Validated assemblies relate to cell-cycle control, growth factor signaling and a histone regulatory complex that we show promotes S-phase entry through the activation of the histone modifiers KAT6A and TBL1XR1 and the transcription factor RUNX1. This study enables an integrated assessment of how a tumor's genetic profile modulates CDK4/6i resistance.
Insights
Deep learning models predict response to cyclin-dependent kinase 4 and 6 inhibitors (CDK4/6is) in breast cancer. Identifying key protein assemblies reveals mechanisms of CDK4/6 inhibitor resistance.
Area of Science:
- Oncology
- Molecular Biology
- Computational Biology
Background:
- Cyclin-dependent kinase 4 and 6 inhibitors (CDK4/6is) are vital in breast cancer treatment.
- Limited patient response and acquired resistance to CDK4/6is necessitate understanding underlying mechanisms.
Purpose of the Study:
- To develop an interpretable deep learning model predicting response to palbociclib, a CDK4/6 inhibitor.
- To identify key multiprotein assemblies associated with CDK4/6 inhibitor sensitivity and resistance.
Main Methods:
- Constructed a deep learning model using a reference map of cancer multiprotein assemblies.
- Integrated genetic alterations across 90 genes to stratify cell lines.
- Validated model predictions in patient-derived xenografts and used CRISPR-Cas9 for functional genetic disruption.
Main Results:
- Identified eight core multiprotein assemblies that predict palbociclib sensitivity versus resistance.
- Model predictions correlated with clinical outcomes, outperforming single-gene biomarkers.
- Validated assemblies involved cell-cycle control, growth factor signaling, and histone modification (KAT6A, TBL1XR1, RUNX1) promoting S-phase entry.
Conclusions:
- An interpretable deep learning model effectively predicts CDK4/6 inhibitor response and resistance in breast cancer.
- Multiprotein assemblies, not single genes, are crucial for stratifying treatment response.
- Understanding these assemblies offers insights into therapeutic resistance and potential therapeutic strategies.
More Related Videos
Related Concept Videos
02:34Inhibition of Cdk Activity
02:56Treatment Resistant Cancers