Related Experiment Video
Updated: Aug 13, 2026

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization
Published on: October 3, 2025
Drug sensitivity prediction across cancer types using graph isomorphism networks and biological pathway features: A
Shuang Li1,2,3,4, Quanzhong Yang1, Feifei Shen1
1Institute of Medical Technology, Luoyang Polytechnic, Luoyang, Henan, China.
Abstract:
Drug sensitivity prediction is an important issue within the precision medicine field. IC50, which is the molar drug dose needed to decrease the viability of cells by half compared to the drug-free control, is the main pharmacodynamics parameter used for drug sensitivity analysis in large-scale pharmacogenomics screenings. Computational estimation of IC50s based on molecular and genomic factors significantly reduces costs associated with experiments for measuring cell viability and allows for accelerating the process of drug discovery. Traditional methods of IC50 calculation do not allow integrating the three-dimensional chemical structure of drugs and the biological context of particular cell lines, resulting in suboptimal model performance when using different pharmacogenomics data sources. In this work, we propose an innovative dual-branch approach based on Graph Isomorphism Network (GIN) drug representations coupled with a Multilayer Perceptron (MLP) for 50-dimensional ssGSEA pathway activities calculated from CCLE gene expression. After training on cell-line-drug pair combinations from the Genomics of Drug Sensitivity in Cancer 2 (GDSC2) dataset across various cancers, the proposed GIN+Pathway MLP model attains an R2 of 0.8553 and a Pearson Correlation Coefficient (PCC) of 0.9249 on the testing split of the same dataset. In a variant ablation study of six variants, we find that eliminating the pathway MLP component lowers the R2 value by more than 0.15, thus proving the importance of biological features in the two-branch model. The performance of our proposed model exceeds benchmark scores for models such as GraphDRP (PCC = 0.870, R2 = 0.756) and DeepCDR (PCC = 0.847, R2 = 0.720) when tested on the same GDSC2 dataset.
Insights
This study introduces a novel dual-branch model combining Graph Isomorphism Network (GIN) for drug structures and Multilayer Perceptron (MLP) for pathway activities to predict drug sensitivity (IC50). The model significantly improves accuracy, outperforming existing benchmarks in precision medicine.
Area of Science:
- Bioinformatics
- Computational Biology
- Pharmacogenomics
Background:
- Drug sensitivity prediction is crucial for precision medicine.
- Accurate estimation of IC50 values accelerates drug discovery.
- Existing methods struggle to integrate drug 3D structures and cell line biological context.
Purpose of the Study:
- To develop an innovative dual-branch model for enhanced drug sensitivity prediction.
- To integrate molecular drug features with biological pathway information from cell lines.
- To improve the accuracy of IC50 estimation in large-scale pharmacogenomics.
Main Methods:
- Utilized Graph Isomorphism Network (GIN) for drug molecular representations.
- Employed a Multilayer Perceptron (MLP) for 50-dimensional ssGSEA pathway activities from CCLE gene expression.
- Trained and tested the model on the Genomics of Drug Sensitivity in Cancer 2 (GDSC2) dataset.
Main Results:
- The proposed GIN+Pathway MLP model achieved an R2 of 0.8553 and a PCC of 0.9249 on the GDSC2 testing set.
- Ablation studies confirmed the critical contribution of the pathway MLP component, with its removal decreasing R2 by over 0.15.
- The model's performance surpassed established benchmarks like GraphDRP and DeepCDR on the same dataset.
Conclusions:
- The dual-branch approach effectively integrates drug chemical structures and cell line biological context for superior drug sensitivity prediction.
- Biological pathway information is essential for enhancing the performance of computational drug sensitivity models.
- This approach offers a promising computational tool for accelerating precision medicine and drug discovery.
Related Concept Videos
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Treatment Resistant Cancers