Related Experiment Video
Updated: Jul 12, 2025
Using RNA-sequencing to Detect Novel Splice Variants Related to Drug Resistance in In Vitro Cancer Models
Published on: December 9, 2016
DELFOS-drug efficacy leveraging forked and specialized networks-benchmarking scRNA-seq data in multi-omics-based
Luiz Felipe Piochi1,2,3, António J Preto2,3,4, Irina S Moreira1,2,3
1Department of Life Sciences, University of Coimbra, Coimbra 3000-456, Portugal.
Motivation:
Cancer is currently one of the most notorious diseases, with over 1 million deaths in the European Union alone in 2022. As each tumor can be composed of diverse cell types with distinct genotypes, cancer cells can acquire resistance to different compounds. Moreover, anticancer drugs can display severe side effects, compromising patient well-being. Therefore, novel strategies for identifying the optimal set of compounds to treat each tumor have become an important research topic in recent decades.
Results:
To address this challenge, we developed a novel drug response prediction algorithm called Drug Efficacy Leveraging Forked and Specialized networks (DELFOS). Our model learns from multi-omics data from over 65 cancer cell lines, as well as structural data from over 200 compounds, for the prediction of drug sensitivity. We also evaluated the benefits of incorporating single-cell expression data to predict drug response. DELFOS was validated using datasets with unseen cell lines or drugs and compared with other state-of-the-art algorithms, achieving a high prediction performance on several correlation and error metrics. Overall, DELFOS can effectively leverage multi-omics data for the prediction of drug responses in thousands of drug-cell line pairs.
Availability And Implementation:
The DELFOS pipeline and associated data are available at github.com/MoreiraLAB/delfos.
Insights
A new algorithm, Drug Efficacy Leveraging Forked and Specialized networks (DELFOS), predicts cancer drug response using multi-omics data. This tool aids in identifying effective cancer treatments by analyzing diverse cell types and drug compounds for personalized medicine.
Area of Science:
- Oncology
- Bioinformatics
- Computational Biology
Background:
- Cancer poses a significant global health challenge, with high mortality rates and complex cellular heterogeneity leading to drug resistance.
- Current anticancer drug treatments can have severe side effects, necessitating personalized therapeutic strategies.
- Identifying optimal drug combinations for individual tumors is a critical area of research.
Purpose of the Study:
- To develop a novel computational algorithm for predicting drug response in cancer.
- To leverage multi-omics and structural data for accurate drug sensitivity prediction.
- To improve personalized cancer treatment strategies through advanced predictive modeling.
Main Methods:
- Developed Drug Efficacy Leveraging Forked and Specialized networks (DELFOS), a novel drug response prediction algorithm.
- Trained the model using multi-omics data from over 65 cancer cell lines and structural data from over 200 compounds.
- Incorporated single-cell expression data and validated the model on unseen cell lines and drugs, comparing performance against state-of-the-art methods.
Main Results:
- DELFOS demonstrated high prediction performance across multiple correlation and error metrics.
- The algorithm effectively utilizes multi-omics data for predicting drug responses in numerous drug-cell line pairs.
- Validation confirmed DELFOS's ability to generalize to new datasets, outperforming existing algorithms.
Conclusions:
- DELFOS provides an effective computational approach for predicting cancer drug efficacy.
- The algorithm facilitates personalized medicine by enabling the selection of optimal compounds for specific tumors.
- The DELFOS pipeline and data are publicly available, promoting further research and application in cancer treatment.
