|
Gene expression profiles of adult acute myeloid leukemia patients. Contains 116 samples and 1571 genes. The follow-up data also included.
● Data Source:
BioConductor
● Keywords:
● Alias: BullingerLeukemia
●
0 images
|
EnvioPlot
(Package: HCsnip) :
Visualize cluster's molecular entropy by violin plot
This function first calculates the entopy of each sample in the given partition, and make a violin plot for each cluster. If clusters are different in term of their molecular profiles, then one may expect density differences in the violin plot.
● Data Source:
BioConductor
● Keywords:
● Alias: EnvioPlot
●
1 images
|
HCsnip-package
(Package: HCsnip) :
Semi-supervised adaptive-height snipping of the Hierarchical Clustering tree
This package contain functions for extracting meaningful clusters from a HC tree. Rather than cutting the HC tree at a fixed highest (as existing methods do), it snips the tree at variable heights to extract hidden clusters. Cluster extraction process uses both the data type from which HC tree is derived and the available patients follow-up information. Functions for testing the significance of extracted clusters and cluster visualization using sample's molecular entropy are also given. If two HC trees are presented which maybe corresponding to the two treatment groups, this package also includes functions for optimally assigning new patients to one of the two HC trees and calculate the expected gain in terms of follow-up.
● Data Source:
BioConductor
● Keywords:
● Alias: HCsnip-package
●
0 images
|
|
This function snips given hierarchical clustering (HC) at variable heights to extract all possible partitions. Each partition (clustering) is composed of non-overlapping clusters.
● Data Source:
BioConductor
● Keywords:
● Alias: HCsnipper
●
0 images
|
RSF_eval
(Package: HCsnip) :
Function to calculate error rate using the Random Survival Forest
This function constructs survival forest using training sample's follow-up as response and cluster labels as covariate. Constructed forest is used to calculate cumulative hazard function (CHF) for each new sample based its cluster label. CHFs are compared with new samples' actual survival time to calculate the error rate. Error rate ranges from 0 to 1, with 0 representing perfect.
● Data Source:
BioConductor
● Keywords:
● Alias: RSF_eval
●
0 images
|
TcgaGBM
(Package: HCsnip) :
Glioblastoma multiforme gene expression data
The subset of latest version of TCGA glioblastoma (GBM) level 3 gene expression data with partial clinical info. Contains expression profiles of 120 samples measured on 3000 genes. Clinical data includes follow-up and type of drugs patients have been administered.
● Data Source:
BioConductor
● Keywords:
● Alias: TcgaGBM
●
0 images
|
TwoHC_assign
(Package: HCsnip) :
Function to assign new samples to one of the two given hierarchical clustering trees in a semi-supervised way
For given molecular data sets from two non-overlapping groups of patients, this functions constructs two independent HC trees and assigns new samples to one of them in semi-supervised way. See details.
● Data Source:
BioConductor
● Keywords:
● Alias: TwoHC_assign
●
0 images
|
TwoHC_perm
(Package: HCsnip) :
Function to assess the significance of group assignmetn from code{link{TwoHC_assign
Function to evaluate the significance of the group assignments generated by TwoHC_assign.
● Data Source:
BioConductor
● Keywords:
● Alias: TwoHC_perm
●
0 images
|
cluster_pred
(Package: HCsnip) :
Semi-supervised clustering
For a given partition, this function assigns new samples to one of the clusters in the partition. Partition (clustering) is composed of non-overlapping clusters
● Data Source:
BioConductor
● Keywords:
● Alias: cluster_pred
●
0 images
|
|
Function to evaluate the overall quality of a parition (composed of non-overlapping clusters) by user defined criteria.
● Data Source:
BioConductor
● Keywords:
● Alias: measure
●
0 images
|
providing 
.