Related Experiment Video
Updated: Apr 4, 2026
A Strategy to Identify Compounds that Affect Cell Growth and Survival in Cultured Mammalian Cells at Low-to-Moderate Throughput
Published on: September 22, 2019
Improved large-scale prediction of growth inhibition patterns using the NCI60 cancer cell line panel
Isidro Cortés-Ciriano1, Gerard J P van Westen2, Guillaume Bouvier1
1Unité de Bioinformatique Structurale, Institut Pasteur and CNRS UMR 3825, Structural Biology and Chemistry Department, 75 724 Paris, France.
Motivation:
Recent large-scale omics initiatives have catalogued the somatic alterations of cancer cell line panels along with their pharmacological response to hundreds of compounds. In this study, we have explored these data to advance computational approaches that enable more effective and targeted use of current and future anticancer therapeutics.
Results:
We modelled the 50% growth inhibition bioassay end-point (GI50) of 17,142 compounds screened against 59 cancer cell lines from the NCI60 panel (941,831 data-points, matrix 93.08% complete) by integrating the chemical and biological (cell line) information. We determine that the protein, gene transcript and miRNA abundance provide the highest predictive signal when modelling the GI50 endpoint, which significantly outperformed the DNA copy-number variation or exome sequencing data (Tukey's Honestly Significant Difference, P <0.05). We demonstrate that, within the limits of the data, our approach exhibits the ability to both interpolate and extrapolate compound bioactivities to new cell lines and tissues and, although to a lesser extent, to dissimilar compounds. Moreover, our approach outperforms previous models generated on the GDSC dataset. Finally, we determine that in the cases investigated in more detail, the predicted drug-pathway associations and growth inhibition patterns are mostly consistent with the experimental data, which also suggests the possibility of identifying genomic markers of drug sensitivity for novel compounds on novel cell lines.
Contact:
terez@pasteur.fr; ab454@ac.cam.uk
Supplementary Information:
Supplementary data are available at Bioinformatics online.
Insights
This study advances computational approaches for anticancer therapeutics by modeling compound response in cancer cell lines. Protein, gene transcript, and miRNA abundance best predict drug sensitivity, outperforming DNA-based omics data.
Area of Science:
- Computational biology
- Pharmacogenomics
- Cancer research
Background:
- Large-scale omics initiatives have generated extensive data on cancer cell line alterations and drug responses.
- Existing data offer opportunities to refine computational methods for targeted cancer therapy.
Purpose of the Study:
- To develop and validate advanced computational models for predicting anticancer drug efficacy.
- To identify key biological features that drive drug response in cancer cell lines.
Main Methods:
- Modeled the 50% growth inhibition (GI50) endpoint for 17,142 compounds across 59 NCI60 cancer cell lines.
- Integrated chemical and biological data, including protein, gene transcript, miRNA abundance, and DNA variation.
- Compared predictive performance against existing models and datasets like GDSC.
Main Results:
- Protein, gene transcript, and miRNA abundance were the strongest predictors of GI50, significantly outperforming DNA-based omics data.
- The developed approach demonstrated robust interpolation and extrapolation capabilities for compound bioactivities across cell lines and tissues.
- The model's predictions for drug-pathway associations and growth inhibition patterns were largely consistent with experimental findings.
Conclusions:
- Computational modeling integrating multi-omics data significantly enhances prediction of anticancer drug response.
- The findings support the potential for identifying genomic markers of drug sensitivity for novel compounds and cell lines.
- This approach offers a powerful tool for the targeted application of current and future anticancer therapeutics.
More Related Videos
06:19Author Spotlight: Exploring the Role of Ion Channels in Cancer: Characterization and Potential Treatment Approaches
Published on: June 16, 2023
13:34A Combined 3D Tissue Engineered In Vitro/In Silico Lung Tumor Model for Predicting Drug Effectiveness in Specific Mutational Backgrounds
Published on: April 6, 2016