# Calculate heuristically maximum scoring subnetwork

### Description

The function uses an heuristic approach to calculate the maximum scoring subnetwork. Based on the given network and scores the positive nodes are in the first step aggregated to meta-nodes between which minimum spanning trees are calculated. In regard to this, shortest paths yield the approximated maximum scoring subnetwork. This function can be used if a CPLEX license is not available to calculate the optimal solution.

### Usage

1 | ```
runFastHeinz(network, scores)
``` |

### Arguments

`network` |
A graph in |

`scores` |
A named vector, containing the scores for the nodes of the network. All nodes need to be scored in order to run the algorithm. |

### Value

A subnetwork in the input network format.

### Author(s)

Daniela Beisser

### See Also

`writeHeinzEdges`

, `writeHeinzNodes`

, `readHeinzTree`

, `readHeinzGraph`

, `runHeinz`

### Examples

1 2 3 4 5 6 7 8 9 10 11 12 13 | ```
library(DLBCL)
# load p-values
data(dataLym)
# load graph
data(interactome)
# get induced subnetwork for all genes contained on the chip
interactome <- subNetwork(dataLym$label, interactome)
p.values <- dataLym$t.pval
names(p.values) <- dataLym$label
bum <- fitBumModel(p.values, plot=TRUE)
scores <- scoreNodes(network=interactome, fb=bum, fdr=0.0001)
module <- runFastHeinz(network=interactome, scores=scores)
## Not run: plotModule(module)
``` |

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker. Vote for new features on Trello.