HEMDAG2.7.4 package

Hierarchical Ensemble Methods for Directed Acyclic Graphs

adj.upper.tri

Binary upper triangular adjacency matrix

auprc

AUPRC measures

auroc

AUROC measures

build.ancestors

Build ancestors

build.children

Build children

build.consistent.graph

Build consistent graph

build.descendants

Build descendants

build.edges.from.hpo.obo

Parse an HPO obo file

build.parents

Build parents

build.scores.matrix

Build scores matrix

build.subgraph

Build subgraph

build.submatrix

Build submatrix

check.annotation.matrix.integrity

Annotation matrix checker

check.dag.integrity

DAG checker

compute.flipped.graph

Flip graph

constraints.matrix

Constraints matrix

create.stratified.fold.df

DataFrame for stratified cross validation

distances.from.leaves

Distances from leaves

example.datasets

Small real example datasets

find.best.f

Best hierarchical F-score

find.leaves

Leaves

fmax

Compute Fmax

full.annotation.matrix

Full annotation matrix

gpav.holdout

GPAV holdout

gpav.over.examples

GPAV over examples

gpav.parallel

GPAV over examples -- parallel implementation

gpav

Generalized Pool-Adjacent Violators (GPAV)

gpav.vanilla

GPAV vanilla

graph.levels

Build graph levels

HEMDAG-package

HEMDAG: Hierarchical Ensemble Methods for Directed Acyclic Graphs

hierarchical.checkers

Hierarchical constraints checker

htd.holdout

HTD-DAG holdout

htd

HTD-DAG

htd.vanilla

HTD-DAG vanilla

lexicographical.topological.sort

Lexicographical topological sorting

multilabel.F.measure

multilabel F-measure

normalize.max

Max normalization

obozinski.heuristic.methods

Obozinski heuristic methods

obozinski.holdout

Obozinski's heuristic methods -- holdout

obozinski.methods

Obozinski's heuristic methods calling

pxr

Precision-Recall curves

read.graph

Read a directed graph from a file

read.undirected.graph

Read an undirected graph from a file

root.node

Root node

scores.normalization

Scores normalization function

specific.annotation.list

Specific annotations list

specific.annotation.matrix

Specific annotation matrix

stratified.cross.validation

Stratified cross validation

tpr.dag.cv

TPR-DAG cross-validation experiments

tpr.dag.holdout

TPR-DAG holdout experiments

tpr.dag

TPR-DAG ensemble variants

transitive.closure.annotations

Transitive closure of annotations

tupla.matrix

Tupla matrix

unstratified.cv.data

Unstratified cross validation

weighted.adjacency.matrix

Weighted adjacency matrix

write.graph

Write a directed graph on file

An implementation of several Hierarchical Ensemble Methods (HEMs) for Directed Acyclic Graphs (DAGs). 'HEMDAG' package: 1) reconciles flat predictions with the topology of the ontology; 2) can enhance the predictions of virtually any flat learning methods by taking into account the hierarchical relationships between ontology classes; 3) provides biologically meaningful predictions that always obey the true-path-rule, the biological and logical rule that governs the internal coherence of biomedical ontologies; 4) 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; 5) scales nicely both in terms of the complexity of the taxonomy and in the cardinality of the examples; 6) provides several utility functions to process and analyze graphs; 7) provides several performance metrics to evaluate HEMs algorithms. (Marco Notaro, Max Schubach, Peter N. Robinson and Giorgio Valentini (2017) <doi:10.1186/s12859-017-1854-y>).

  • Maintainer: Marco Notaro
  • License: GPL (>= 3)
  • Last published: 2021-02-12