A community effort to assess and improve drug sensitivity prediction algorithms

By James C. Costello, Laura M. Heiser, Elisabeth Georgii, Mehmet Gönen, Michael P. Menden, Nicholas J. Wang, Mukesh Bansal, Muhammad Ammad-ud-din, P. Hintsanen, Suleiman A. Khan and 12 more. Nature Biotechnology, 2014

728 citations recorded by the source corpus.

Predicting the best treatment strategy from genomic information is a core goal of precision medicine. Here we focus on predicting drug response based on a cohort of genomic, epigenomic and proteomic profiling data sets measured in human breast cancer cell lines. Through a collaborative effort between the National Cancer Institute (NCI) and the Dialogue on Reverse Engineering Assessment and Methods (DREAM) project, we analyzed a total of 44 drug sensitivity prediction algorithms. The top-performing approaches modeled nonlinear relationships and incorporated biological pathway information. We found that gene expression microarrays consistently provided the best predictive power of the individual profiling data sets; however, performance was increased by including multiple, independent data sets. We discuss the innovations underlying the top-performing methodology, Bayesian multitask MKL, and we provide detailed descriptions of all methods. This study establishes benchmarks for drug sensitivity prediction and identifies approaches that can be leveraged for the development of new methods.

Subfields: Computational Theory and Mathematics, Immunology, Toxicology

View Paper: https://www.semanticscholar.org/paper/3d4a87f3eaa4f56d1cc41c7e7b74cf92ce2c94a6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Immunology

Citations in the corpus

Big Data for Health (2015, background): “These include cancer cell line databases of nonspecific cancer cell types [35], [36] or a specific cancer cell type such as breast cancer [37].”
Functional random forest with applications in dose-response predictions (2019, background): “Figure 10 shows two representative cases of Curve(1) and Curve(2) that has same IC50 values and similar AUC values but their dose-response profiles are significantly different.”
A Landscape of Pharmacogenomic Interactions in Cancer (2016, methodology): “The small number of pathway signatures had a disproportionately large effect in the logic models, showing that basal pathway activation scores provide relevant information to predict drug response beyond the genomic CFEs (Costello et al., 2014) (Figure S5D).”
The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology (2016, background): “As recently reviewed in [20, 21], the application in oncology of various types of knowledge-based in silico methods for predicting drug responses that require multiple kinds of -omics data for training has lead to the development and maintenance of large public databases containing curated data…”
Artificial Intelligence Transforms the Future of Health Care. (2019, background): “For example, Costello J. C. et al. 39 analyzed 44 drug sensitivity prediction algorithms on 53 breast cancer cell lines with available genomic information to fulfill dose-response values of growth inhibition for each cell line exposed to 28 therapeutic compounds.”
Machine learning and feature selection for drug response prediction in precision oncology applications (2018, methodology): “In the NCI/ DREAM7 Challenge, the BEMKL method demonstrated improved predictive performance as it enabled capturing common signal among multiple omics profiles, resulting in an increased signal-to-noise ratio (Costello et al. 2014).”
Multimodal data fusion for cancer biomarker discovery with deep learning (2023, positive): “Additionally, for therapy response and drug combination predictions, multi-omics ML methods have proved their value over traditional unimodal models 97–100 .”