Constant Field Values

Contents

• edu.msu.*

edu.msu.*

edu.msu.cme.rdp.classifier.Classifier

Modifier and Type	Constant Field	Value
public static final int	MAX_SEQ_LEN	5000
public static final int	MIN_BOOTSTRSP_WORDS	5
public static final int	MIN_GOOD_WORDS	42
public static final int	MIN_SEQ_LEN	50

edu.msu.cme.rdp.classifier.cli.CmdOptions

Modifier and Type	Constant Field	Value
public static final java.lang.String	BIOMFILE_DESC	"the input clluster biom file. The classification result will replace the taxonomy of the corresponding cluster id."
public static final java.lang.String	BIOMFILE_LONG_OPT	"biomFile"
public static final java.lang.String	BIOMFILE_SHORT_OPT	"m"
public static final java.lang.String	BOOTSTRAP_LONG_OPT	"conf"
public static final java.lang.String	BOOTSTRAP_OUTFILE_DESC	"the output file containing the number of matching assignments out of 100 bootstraps for major ranks. Default is null"
public static final java.lang.String	BOOTSTRAP_OUTFILE_LONG_OPT	"bootstrap_outfile"
public static final java.lang.String	BOOTSTRAP_OUTFILE_SHORT_OPT	"b"
public static final java.lang.String	BOOTSTRAP_SHORT_OPT	"c"
public static final java.lang.String	FORMAT_LONG_OPT	"format"
public static final java.lang.String	FORMAT_SHORT_OPT	"f"
public static final java.lang.String	GENE_LONG_OPT	"gene"
public static final java.lang.String	GENE_SHORT_OPT	"g"
public static final java.lang.String	HIER_OUTFILE_DESC	"tab-delimited output file containing the assignment count for each taxon in the hierarchical format. Default is null."
public static final java.lang.String	HIER_OUTFILE_LONG_OPT	"hier_outfile"
public static final java.lang.String	HIER_OUTFILE_SHORT_OPT	"h"
public static final java.lang.String	METADATA_DESC	"the tab delimited metadata file for the samples, with first row containing attribute name and first column containing the sample name"
public static final java.lang.String	METADATA_LONG_OPT	"metadata"
public static final java.lang.String	METADATA_SHORT_OPT	"d"
public static final java.lang.String	MIN_BOOTSTRAP_WORDS_LONG_OPT	"minWords"
public static final java.lang.String	MIN_BOOTSTRAP_WORDS_SHORT_OPT	"w"
public static final java.lang.String	MIN_WORDS_DESC	"minimum number of words for each bootstrap trial. Default(maximum) is 1/8 of the words of each sequence. Minimum is 5"
public static final java.lang.String	OUTFILE_DESC	"tab-delimited text output file for classification assignment."
public static final java.lang.String	OUTFILE_LONG_OPT	"outputFile"
public static final java.lang.String	OUTFILE_SHORT_OPT	"o"
public static final java.lang.String	QUERYFILE_DESC	"legacy option, no longer needed "
public static final java.lang.String	QUERYFILE_LONG_OPT	"queryFile"
public static final java.lang.String	QUERYFILE_SHORT_OPT	"q"
public static final java.lang.String	RANK_LONG_OPT	"rank"
public static final java.lang.String	RANK_SHORT_OPT	"r"
public static final java.lang.String	SAMPLE_LONG_OPT	"biomFile"
public static final java.lang.String	SHORTSEQ_OUTFILE_DESC	"the output file containing the sequence names that are too short to be classified"
public static final java.lang.String	SHORTSEQ_OUTFILE_LONG_OPT	"shortseq_outfile"
public static final java.lang.String	SHORTSEQ_OUTFILE_SHORT_OPT	"s"
public static final java.lang.String	TAXON_LONG_OPT	"taxon"
public static final java.lang.String	TAXON_SHORT_OPT	"n"
public static final java.lang.String	TRAINPROPFILE_DESC	"property file containing the mapping of the training files if not using the default. Note: the training files and the property file should be in the same directory."
public static final java.lang.String	TRAINPROPFILE_LONG_OPT	"train_propfile"
public static final java.lang.String	TRAINPROPFILE_SHORT_OPT	"t"

edu.msu.cme.rdp.classifier.comparison.ComparisonCmd

Modifier and Type	Constant Field	Value
public static final java.lang.String	COMPARE_OUTFILE_DESC	"output file name for the comparsion results."
public static final java.lang.String	COMPARE_OUTFILE_LONG_OPT	"compare_outputFile"
public static final java.lang.String	COMPARE_OUTFILE_SHORT_OPT	"o"
public static final java.lang.String	QUERYFILE_DESC	"query file contains sequences in one of the following formats: Fasta, Genbank and EMBL."
public static final java.lang.String	QUERYFILE1_LONG_OPT	"queryFile1"
public static final java.lang.String	QUERYFILE1_SHORT_OPT	"q1"
public static final java.lang.String	QUERYFILE2_LONG_OPT	"queryFile2"
public static final java.lang.String	QUERYFILE2_SHORT_OPT	"q2"

edu.msu.cme.rdp.classifier.train.LineageSequenceParser

Modifier and Type	Constant Field	Value
public static final java.lang.String	delimiter	";"

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

Modifier and Type	Constant Field	Value
public final int	bins	11

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

Modifier and Type	Constant Field	Value
public static final int	NUM_OF_RUNS	100

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

Modifier and Type	Constant Field	Value
public static final int	MIN_BOOTSTRSP_WORDS	5
public static final long	seed	1L

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

Modifier and Type	Constant Field	Value
public static final java.lang.String	GENUS	"GENUS"

edu.msu.cme.rdp.classifier.train.validation.leaveoneout.LeaveOneOutTesterMain

Modifier and Type	Constant Field	Value
public static final java.lang.String	HIDETAXON_SHORT_OPT	"h"
public static final java.lang.String	LENGTH_DESC	"the default is to test the entire query sequence. if specifiy a length, a region of the query sequence with the specified length will be random choosen for testing"
public static final java.lang.String	LENGTH_LONG_OPT	"length"
public static final java.lang.String	LENGTH_SHORT_OPT	"l"
public static final java.lang.String	OUTFILE_DESC	"stat of leave-one-out testing including correctness rate at each rank, misclassified rate for each taxon "
public static final java.lang.String	OUTFILE_LONG_OPT	"outputFile"
public static final java.lang.String	OUTFILE_SHORT_OPT	"o"
public static final java.lang.String	QUERYFILE_DESC	"query file contains sequences, same format as the training sequence file"
public static final java.lang.String	QUERYFILE_LONG_OPT	"queryFile"
public static final java.lang.String	QUERYFILE_SHORT_OPT	"q"
public static final java.lang.String	TRAIN_SEQFILE_DESC	"training files in fasta format labelled with the lineage information. \nThe header of this fasta file starts with \'>\', followed by the sequence name, white space(s) and a list taxon names seperated by \';\' with highest rank taxon first\nex: Root;Bacteria;Proteobacteria;Gammaproteobacteria;Enterobacteriales;Enterobacteriaceae;Enterobacter"
public static final java.lang.String	TRAIN_SEQFILE_LONG_OPT	"trainSeqFile"
public static final java.lang.String	TRAIN_SEQFILE_SHORT_OPT	"s"
public static final java.lang.String	TRAIN_TAXONFILE_DESC	"contains the hierarchical taxonomy information, taxon name and rank together is unique. \nThe format looks like the following: taxid*taxon name*parent taxid*depth*rank Note taxid, the parent taxid and depth should be in integer format. depth indicates the depth from the root taxon."
public static final java.lang.String	TRAIN_TAXONFILE_LONG_OPT	"trainTaxonFile"
public static final java.lang.String	TRAIN_TAXONFILE_SHORT_OPT	"t"

edu.msu.cme.rdp.classifier.train.validation.movingwindow.FindWindowFrame

Modifier and Type	Constant Field	Value
public static final int	step	25
public static final int	window_size	200

edu.msu.cme.rdp.classifier.utils.ClassifierFactory

Modifier and Type	Constant Field	Value
public static final java.lang.String	FUNGALITS_unite_GENE	"fungalits_unite"
public static final java.lang.String	FUNGALITS_warcup_GENE	"fungalits_warcup"
public static final java.lang.String	FUNGALLSU_GENE	"fungallsu"
public static final java.lang.String	RRNA_16S_GENE	"16srrna"

edu.msu.cme.rdp.multicompare.taxon.MCTaxon

Modifier and Type	Constant Field	Value
public static final int	Count_Array_size	2