CAFA-evaluator: a Python tool for benchmarking ontological classification methods.

Autor:	Piovesan D; Department of Biomedical Sciences, University of Padova, 35121 Padova, Italy., Zago D; Program in Bioinformatics and Computational Biology, Iowa State University, Ames, IA 50011, United States., Joshi P; Program in Bioinformatics and Computational Biology, Iowa State University, Ames, IA 50011, United States.; Department of Veterinary Microbiology and Preventive Medicine, Iowa State University, Ames, IA 50011, United States., De Paolis Kaluza MC; Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115, United States., Mehdiabadi M; Department of Biomedical Sciences, University of Padova, 35121 Padova, Italy., Ramola R; Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115, United States., Monzon AM; Department of Information Engineering, University of Padova, 35121 Padova, Italy., Reade W; Kaggle, San Francisco, CA, United States., Friedberg I; Department of Veterinary Microbiology and Preventive Medicine, Iowa State University, Ames, IA 50011, United States., Radivojac P; Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115, United States., Tosatto SCE; Department of Biomedical Sciences, University of Padova, 35121 Padova, Italy.
Jazyk:	angličtina
Zdroj:	Bioinformatics advances [Bioinform Adv] 2024 Mar 14; Vol. 4 (1), pp. vbae043. Date of Electronic Publication: 2024 Mar 14 (Print Publication: 2024).
DOI:	10.1093/bioadv/vbae043
Abstrakt:	We present CAFA-evaluator, a powerful Python program designed to evaluate the performance of prediction methods on targets with hierarchical concept dependencies. It generalizes multi-label evaluation to modern ontologies where the prediction targets are drawn from a directed acyclic graph and achieves high efficiency by leveraging matrix computation and topological sorting. The program requirements include a small number of standard Python libraries, making CAFA-evaluator easy to maintain. The code replicates the Critical Assessment of protein Function Annotation (CAFA) benchmarking, which evaluates predictions of the consistent subgraphs in Gene Ontology. Owing to its reliability and accuracy, the organizers have selected CAFA-evaluator as the official CAFA evaluation software. Availability and Implementation: https://pypi.org/project/cafaeval. Competing Interests: None declared. (© The Author(s) 2024. Published by Oxford University Press.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu