Get started
Work

Essential guidelines for computational method benchmarking

Year: 2019
Type: article
Abstract: In computational biology and other sciences, researchers are frequently faced with a choice between several computational methods for performing data analyses. Benchmarking studies aim to rigorously compare the performance of different methods using well-characterized benchmark datasets, to determine the strengths of each method or to provide recommendations regarding suitable choices of methods for an analysis. However, benchmarking studies must be carefully designed and implemented to provide accurate, unbiased, and informative results. Here, we summarize key practical guidelines and recommendations for performing high-quality benchmarking analyses, based on our experiences in computational biology.
DOI: 10.1186/s13059-019-1738-8
Authors: Weber, Lukas M, Saelens, Wouter, Cannoodt, Robrecht, Soneson, Charlotte, Hapfelmeier, Alexander, Gardner, Paul P, Boulesteix, Anne-Laure, Saeys, Yvan, Robinson, Mark D; https://orcid.org/0000-0002-3048-5518
Institutions: University of Zurich, VIB-UGent Center for Inflammation Research, SIB Swiss Institute of Bioinformatics, Technical University of Munich, University of Otago, Institut für Medizinische Informationsverarbeitung, Biometrie und Epidemiologie, Ludwig-Maximilians-Universität München
Language: English
Open Access status: green
Funders: Silicon Valley Community Foundation, Deutsche Forschungsgemeinschaft, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, Bundesministerium für Bildung und Forschung, Fonds Wetenschappelijk Onderzoek, Universität Zürich
Awards: Defining the identity and differentiation pathways of the immune-stimulating fibroblastic tumor stroma, G1386627085, G22550774, Beyond the average: computational tools for discovery in high-throughput single cell datasets, G3024871434, G3034827328, G6671980391
OpenAlex ID: W2951624434
FWCI: 24.47
Cites: 117
Cited by: 194
Related to: 10