edu.msu.cme.rdp.classifier.train.validation.distance

Class TaxaSimilarityMain

java.lang.Object

edu.msu.cme.rdp.classifier.train.validation.distance.TaxaSimilarityMain

public class TaxaSimilarityMain
extends java.lang.Object

Field Summary

Fields

Modifier and Type	Field and Description
static java.lang.String[]	RANKS

Constructor Summary

Constructors

Constructor and Description
TaxaSimilarityMain(java.util.List<java.lang.String> selectedRanks)

Method Summary

Methods

Modifier and Type	Method and Description
void	calPairwiseSimilaritye(java.lang.String taxonFile, java.lang.String trainSeqFile, java.lang.String testSeqFile)
void	calSabSimilarity(java.lang.String taxonFile, java.lang.String trainSeqFile, java.lang.String testSeqFile)
void	createPlot(java.lang.String plotTitle, java.io.File outdir)
java.util.HashMap<java.lang.String,HierarchyTree>	getAncestorNodes(HierarchyTree root, java.lang.String seqName, java.util.List<java.lang.String> ancestors)
static void	main(java.lang.String[] args) This calculates the average similarity (Sab score or pairwise alignment) between taxa at given ranks and plot the box and whisker plot and accumulation curve.
static java.util.List<java.lang.String>	readRanks(java.lang.String rankFile)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

RANKS

public static java.lang.String[] RANKS

Constructor Detail

TaxaSimilarityMain

public TaxaSimilarityMain(java.util.List<java.lang.String> selectedRanks)

Method Detail

readRanks

public static java.util.List<java.lang.String> readRanks(java.lang.String rankFile)
                                                  throws java.io.IOException

Throws:

java.io.IOException

getAncestorNodes

public java.util.HashMap<java.lang.String,HierarchyTree> getAncestorNodes(HierarchyTree root,
                                                                 java.lang.String seqName,
                                                                 java.util.List<java.lang.String> ancestors)

calSabSimilarity

public void calSabSimilarity(java.lang.String taxonFile,
                    java.lang.String trainSeqFile,
                    java.lang.String testSeqFile)
                      throws java.io.IOException

Throws:

java.io.IOException

calPairwiseSimilaritye

public void calPairwiseSimilaritye(java.lang.String taxonFile,
                          java.lang.String trainSeqFile,
                          java.lang.String testSeqFile)
                            throws java.io.IOException,
                                   edu.msu.cme.rdp.alignment.pairwise.rna.OverlapCheckFailedException

Throws:

java.io.IOException

edu.msu.cme.rdp.alignment.pairwise.rna.OverlapCheckFailedException

createPlot

public void createPlot(java.lang.String plotTitle,
              java.io.File outdir)
                throws java.io.IOException

Throws:

java.io.IOException

main

public static void main(java.lang.String[] args)
                 throws java.io.IOException,
                        edu.msu.cme.rdp.alignment.pairwise.rna.OverlapCheckFailedException

This calculates the average similarity (Sab score or pairwise alignment) between taxa at given ranks and plot the box and whisker plot and accumulation curve. The distances associate to a given rank contains the distances between different child taxa. It does not include the distances within the same child taxa. For example, if a query and it's closest match are from the same genus, the distance value is added to that genus. If there are from different genera but the same family, the distance value is added to that family, etc.

Parameters:

args -

Throws:

java.io.IOException

edu.msu.cme.rdp.alignment.pairwise.rna.OverlapCheckFailedException