Welcome to HEMDAG R package!

	Bioconda Badges	CRAN Badges
License
Last Version
Last Updated
Read the Docs
Total Downloads
Code Coverage

---

Brief Description

HEMDAG package:

• implements several Hierarchical Ensemble Methods (HEMs) for Directed Acyclic Graphs (DAGs);
• reconciles flat predictions with the topology of the ontology;
• can enhance predictions of virtually any flat learning methods by taking into account the hierarchical relationships between ontology classes;
• provides biologically meaningful predictions that obey the true-path-rule, the biological and logical rule that governs the internal coherence of biomedical ontologies;
• is specifically designed for exploiting the hierarchical relationships of DAG-structured taxonomies, such as the Human Phenotype Ontology (HPO) or the Gene Ontology (GO), but can be safely applied to tree-structured taxonomies as well (as FunCat), since trees are DAGs;
• scales nicely both in terms of the complexity of the taxonomy and in the cardinality of the examples;
• provides several utility functions to process and analyze graphs;
• provides several performance metrics to evaluate HEMs algorithms.

Documentation

Please get a look to the documentation to know how to download, install and make experiments with the HEMDAG package.

Cite HEMDAG

If you use HEMDAG, please cite our Bioinformatics article or BMC Bioinformatics article:

Marco Notaro, Marco Frasca, Alessandro Petrini, Jessica Gliozzo, Elena Casiraghi, Peter N Robinson, Giorgio Valentini
HEMDAG: a family of modular and scalable hierarchical ensemble methods to improve Gene Ontology term prediction,
Bioinformatics, Volume 37, Issue 23, 1 December 2021, Pages 4526–4533

M. Notaro, M. Schubach, P. N. Robinson, and G Valentini.
Prediction of Human Phenotype Ontology terms by means of hierarchical ensemble methods.
BMC Bioinformatics, 18(1):449, 2017