Biomarker Identification via RFE on the Grid
Created: 2013-08-13 17:18:58
Last updated: 2013-09-24 08:17:01
The first two components split the original data set into several sub-sampling sets. The RFE component performs the machine learning approach by executing several instances of a SVM, each of which consuming one sub-sample data set. The execution of the SVM takes place in a distributed computing environment, using the UNICORE-Taverna Plugin. The calc_objFunc component calculates the F-measure of the ranked gene list compared to a 'gold standard'.
Preview
Run
Run this Workflow in the Taverna Workbench...
Workflow Components
Authors (0)
Titles (0)
Descriptions (0)
Dependencies (0)
Inputs (6)
Name |
Description |
Input_file |
|
number_iterations |
|
gold_standard |
|
RFE_Remove_Percentage |
|
RFE_Cost |
|
RFE_Epsilon_Tolerance |
|
Processors (15)
Name |
Type |
Description |
DataSplit_And_Seed |
externaltool |
|
ExtractSeeds_and_Input |
beanshell |
ScriptString a = in1;
int d= a.indexOf("Seed values:");
int f= a.indexOf("Importing and splitting completed.")-2;
String b=a.substring(d+13,f);
String [] seeds= b.split(" ");
int e= a.indexOf("Done.");
int g= a.indexOf("total")-1;
String file_path=a.substring(e+6,g)+File.separator+"data.ser";
|
RFE |
activity |
|
out_folder_value |
stringconstant |
Value. |
Kernel_Type |
stringconstant |
Value0 |
Cache_Size |
stringconstant |
Value100 |
Epsilon_Loss |
stringconstant |
Value0.1 |
Kernel_coef0 |
stringconstant |
Value0 |
Kernel_Degree |
stringconstant |
Value3 |
Kernel_Gamma |
stringconstant |
Value0.25 |
propability |
stringconstant |
Value0 |
Shrink |
stringconstant |
Value1 |
SVM_nu |
stringconstant |
Value0.5 |
SVM_Type |
stringconstant |
Value0 |
calc_ObjFunc_2 |
activity |
|
Beanshells (1)
Name |
Description |
Inputs |
Outputs |
ExtractSeeds_and_Input |
|
in1
|
seeds
file_path
|
Datalinks (22)
Source |
Sink |
Input_file |
DataSplit_And_Seed:file |
number_iterations |
DataSplit_And_Seed:number_iterations |
out_folder_value:value |
DataSplit_And_Seed:out_folder |
DataSplit_And_Seed:STDOUT |
ExtractSeeds_and_Input:in1 |
ExtractSeeds_and_Input:seeds |
RFE:Seed |
ExtractSeeds_and_Input:file_path |
RFE:Input |
RFE_Remove_Percentage |
RFE:Remove_Percentage |
RFE_Cost |
RFE:Cost |
Kernel_Type:value |
RFE:Kernel_Type |
Cache_Size:value |
RFE:Cache_Size |
Kernel_coef0:value |
RFE:Kernel_coef0 |
Kernel_Degree:value |
RFE:Kernel_Degree |
Kernel_Gamma:value |
RFE:Kernel_Gamma |
propability:value |
RFE:propability |
Shrink:value |
RFE:Shrink |
SVM_nu:value |
RFE:SVM_nu |
SVM_Type:value |
RFE:SVM_Type |
Epsilon_Loss:value |
RFE:Epsilon_Loss |
RFE_Epsilon_Tolerance |
RFE:Epsilon_Tolerance |
RFE:RFEOutput |
calc_ObjFunc_2:Input_files |
gold_standard |
calc_ObjFunc_2:Gold_standard |
calc_ObjFunc_2:SimpleES |
ES_out |
Uploader
License
All versions of this Workflow are
licensed under:
Version 2 (latest)
(of 2)
Credits (1)
(People/Groups)
Attributions (1)
(Workflows/Files)
Shared with Groups (0)
None
Featured In Packs (0)
None
Log in to add to one of your Packs
Attributed By (1)
(Workflows/Files)
Favourited By (0)
No one
Statistics
Other workflows that use similar services
(0)
There are no workflows in myExperiment that use similar services to this Workflow.
Comments (0)
No comments yet
Log in to make a comment