Can't run classifier. #26

LuoPangpang · 2019-07-05T09:49:29Z

Dear Author,

I got the message as shown below when trying to run the final step run_isown.pl:

perl /workplace/Software/ISOWN/bin/run_isown.pl 181023001/ 181023001/181023001.isown.txt "-trainingSet /workplace/Software/ISOWN/training_data/UCEC_100_TrainSet.arff -sanityCheck false -classifier nbc"

Reformat files in '181023001' to emaf ...

WARNING: 18 variants with unknown annotation were removed
Total number of variants after filtering 3770

Running prediction using file '181023001/181023001.isown.txt.emaf' ...

...
Your working directory is 181023001
...
This file was chosen for classifier training: /workplace/Software/ISOWN/training_data/UCEC_100_TrainSet.arff
...
Total number of samples in your set is 1
...
Number of loaded nonsilent coding variants in test set is 808
...

Naive Bayes Classifier:
Option: supervised discretization (SD) is true
10-fold cross-validation

F1-measure: 98.12%.
Recall: 97.817%.
Precision: 98.425%.
False positive rate: 1.565%.
AUC: 99.77%.

Can't run classifier.
java.io.IOException: nominal value not declared in header, read Token[null], line 19
at weka.core.converters.ArffLoader$ArffReader.errorMessage(ArffLoader.java:240)
at weka.core.converters.ArffLoader$ArffReader.getInstanceFull(ArffLoader.java:578)
at weka.core.converters.ArffLoader$ArffReader.getInstance(ArffLoader.java:423)
at weka.core.converters.ArffLoader$ArffReader.readInstance(ArffLoader.java:391)
at weka.core.converters.ArffLoader$ArffReader.readInstance(ArffLoader.java:376)
at weka.core.converters.ArffLoader$ArffReader.(ArffLoader.java:138)
at weka.core.Instances.(Instances.java:126)
at main.Prediction.runClassifier(Prediction.java:233)
at main.runISOWN.main(runISOWN.java:90)

...
Total number of predicted somatic mutations 0
Final results are saved here: 181023001/181023001.isown.txt
...

Done

INTERESTINGLY, I got no error running both database_annotation.pl and run_isown.pl with the two vcf files provided in the test_data/ directory ...

I googled about the "nominal value not declared in header" and some said it is something to do with weka, so I checked:

java -jar /workplace/Software/ISOWN/bin/weka.jar

Exception in thread "main" java.lang.ExceptionInInitializerError
Caused by: java.awt.HeadlessException:
No X11 DISPLAY variable was set, but this program performed an operation which requires it.
at java.awt.GraphicsEnvironment.checkHeadless(GraphicsEnvironment.java:204)
at java.awt.Window.(Window.java:536)
at java.awt.Frame.(Frame.java:420)
at javax.swing.JFrame.(JFrame.java:233)
at weka.gui.LogWindow.(LogWindow.java:252)
at weka.gui.GUIChooser.(GUIChooser.java:215)

So did I miss anything? By the way, the weka.jar was already in the bin/ directory when I installed ISOWN, so I did not do any replacement of weka.jar since check_dependencies.pl said everything was installed.

Thank you very much!

Pang

amit21AIT · 2019-07-06T08:29:23Z

Can you send the first few lines of your annotated VCF file excluding headers ? I was getting an error after the database annotation process - "ArrayIndexOutOfBound 3 " , i just want to find where the error is .
Thanks
Amit

LuoPangpang · 2019-07-08T02:07:46Z

Can you send the first few lines of your annotated VCF file excluding headers ? I was getting an error after the database annotation process - "ArrayIndexOutOfBound 3 " , i just want to find where the error is .
Thanks
Amit

Hi Amit,

This is the output annotated vcf that I run through without errors using the "test_data/3d2edf87-6ec5-4c9f-9212-e8a751cc33e8.dkfz-snvCalling_1-0-132-1.20160126.vcf as input". Hope it helps.

Pang

##fileformat=VCFv4.1
##fileDate=20160129
##pancancerversion=1.0
##reference=<ID=hs37d5,Source=ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/phase2_reference_assembly_sequence/hs37d5.fa.gz>;
##center="DKFZ"
##workflowName=DKFZ_SNV_workflow
##workflowVersion=1.0.0
##INFO=<ID=SOMATIC,Number=0,Type=Flag,Description="Indicates if record is a somatic mutation">
##INFO=<ID=GERMLINE,Number=0,Type=Flag,Description="Indicates if record is a germline mutation">
##INFO=<ID=UNCLEAR,Number=0,Type=Flag,Description="Indicates if the somatic status of a mutation is unclear">
##INFO=<ID=VT,Number=1,Type=String,Description="Variant type, can be SNP, INS or DEL">
##INFO=<ID=AF,Number=.,Type=Float,Description="Allele Frequency in primary data, for each ALT allele, in the same order as listed">
##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership">
##INFO=<ID=MQ,Number=1,Type=Integer,Description="RMS Mapping Quality">
##INFO=<ID=1000G,Number=0,Type=Flag,Description="Indicates membership in 1000Genomes">
##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read depth at this position in the sample">
##FORMAT=<ID=DP4,Number=4,Type=Integer,Description="Number of high-quality ref-forward, ref-reverse, alt-forward and alt-reverse bases">
##FILTER=<ID=RE,Description="variant in UCSC_27Sept2013_RepeatMasker.bed.gz region and/or SimpleTandemRepeats_chr.bed.gz region, downloaded from UCSC genome browser and/or variant in segmental duplication region, annotated by annovar">
##FILTER=<ID=BL,Description="variant in DAC-Blacklist from ENCODE or in DUKE_EXCLUDED list, both downloaded from UCSC genome browser">
##FILTER=<ID=DP,Description="<= 5 reads total at position in tumor">
##FILTER=<ID=SB,Description="Strand bias of reads with mutant allele = zero reads on one strand">
##FILTER=<ID=TAC,Description="less than 6 reads in Tumor at position">
##FILTER=<ID=dbSNP,Description="variant in dbSNP135">
##FILTER=<ID=DB,Description="variant in 1000Genomes, ALL.wgs.phase1_integrated_calls.20101123.snps_chr.vcf.gz or dbSNP">
##FILTER=<ID=HSDEPTH,Description="variant in HiSeqDepthTop10Pct_chr.bed.gz region, downloaded from UCSC genome browser">
##FILTER=<ID=MAP,Description="variant overlaps a region from wgEncodeCrgMapabilityAlign100mer.bedGraph.gz:::--breakPointMode --aEndOffset=1 with a value below 0.5, punishment increases with a decreasing mapability">
##FILTER=<ID=SBAF,Description="Strand bias of reads with mutant allele = zero reads on one strand and variant allele frequency below 0.1">
##FILTER=<ID=FRQ,Description="variant allele frequency below 0.05">
##FILTER=<ID=TAR,Description="Only one alternative read in Tumor at position">
##FILTER=<ID=UNCLEAR,Description="Classification is unclear">
##FILTER=<ID=DPHIGH,Description="Too many reads mapped in control at this region">
##FILTER=<ID=DPLOWC,Description="Only 5 or less reads in control">
##FILTER=<ID=1PS,Description="Only two alternative reads, one on each strand">
##FILTER=<ID=ALTC,Description="Alternative reads in control">
##FILTER=<ID=ALTCFR,Description="Alternative reads in control and tumor allele frequency below 0.3">
##FILTER=<ID=FRC,Description="Variant allele frequency below 0.3 in germline call">
##FILTER=<ID=YALT,Description="Variant on Y chromosome with low allele frequency">
##FILTER=<ID=VAF,Description="Variant allele frequency in tumor < 5 times allele frequency in control">
##FILTER=<ID=BI,Description="Bias towards a PCR strand or sequencing strand">
##SAMPLE=<ID=CONTROL,SampleName=control_NA,Individual=NA,Description="Control">
##SAMPLE=<ID=TUMOR,SampleName=tumor_NA,Individual=NA,Description="Tumor">
##TARGET_FILE:SureSelectHumanAllExonV4=file:///oicr/data/genomes/homo_sapiens_mc/Agilent/SureSelectHumanAllExonV4/S03723314_Regions.merged.sorted.bed.gz
##VCF_FILE:dbSNP151=file:///workplace/Software/ISOWN/bin/../external_databases/dbsnp_151.hg19.All.modified.vcf.gz
##VCF_FILE:COSMIC_77=file:///workplace/Software/ISOWN/bin/../external_databases/Cosmic-All-Muts.vcf.gz
##VCF_FILE:ExAC.r0.3_20150421=file:///workplace/Software/ISOWN/bin/../external_databases/ExAC.r0.3.1.database.vcf.gz
##VCF_FILE:2015_12_31_MA=file:///workplace/Software/ISOWN/bin/../external_databases/2015_12_31_MA_r3.vcf.gz
#TAB_DELIMITED_HEADER=sample_name chr pos reference alternative genotype totalReadDepth %readDepthAlt in.dbSNP.or.not in.dbSNP.COMMON.or.not in.COSMIC.or.not MA_functional_impact MA_score is.SOMATIC in.ExAC ExAC_NCC FLANKING_STR POLYPHEN VARIANT_CLASS LENGTH CHROM POS ID REF ALT QUAL FILTER INFO FORMAT TUMOR

Guofengyu · 2019-07-18T07:54:11Z

Hi, Pang

Could you send several actual variants in your annotated vcf ? ANNOVAR can also annotate PolyPhen, Mutation Assessor, etc. I want to change the annotated vcf by ANNOVAR into the ISOWN annotated vcf and then test. Thanks.

Guofengyu · 2019-07-24T06:47:12Z

Hi, Pang

I have completed the test with reference to the process. I didn't encountered your problem. But I have another promblem like "Exception in thread "main" java.lang.IncompatibleClassChangeError: Found interface weka.core.Instance, but class was expected" until I replace the weka.jar to the origin file. I realize the weka.jar was already in the bin/ directory througth your issue. Thank you all the same.

Guo.

yueyangtime · 2019-12-30T02:42:09Z

Dear Author,

I got the message as shown below when trying to run the final step run_isown.pl:

perl /workplace/Software/ISOWN/bin/run_isown.pl 181023001/ 181023001/181023001.isown.txt "-trainingSet /workplace/Software/ISOWN/training_data/UCEC_100_TrainSet.arff -sanityCheck false -classifier nbc"

Reformat files in '181023001' to emaf ...

WARNING: 18 variants with unknown annotation were removed
Total number of variants after filtering 3770

Running prediction using file '181023001/181023001.isown.txt.emaf' ...

...
Your working directory is 181023001
...
This file was chosen for classifier training: /workplace/Software/ISOWN/training_data/UCEC_100_TrainSet.arff
...
Total number of samples in your set is 1
...
Number of loaded nonsilent coding variants in test set is 808
...

Naive Bayes Classifier:
Option: supervised discretization (SD) is true
10-fold cross-validation

F1-measure: 98.12%.
Recall: 97.817%.
Precision: 98.425%.
False positive rate: 1.565%.
AUC: 99.77%.

Can't run classifier.
java.io.IOException: nominal value not declared in header, read Token[null], line 19
at weka.core.converters.ArffLoader$ArffReader.errorMessage(ArffLoader.java:240)
at weka.core.converters.ArffLoader$ArffReader.getInstanceFull(ArffLoader.java:578)
at weka.core.converters.ArffLoader$ArffReader.getInstance(ArffLoader.java:423)
at weka.core.converters.ArffLoader$ArffReader.readInstance(ArffLoader.java:391)
at weka.core.converters.ArffLoader$ArffReader.readInstance(ArffLoader.java:376)
at weka.core.converters.ArffLoader$ArffReader.(ArffLoader.java:138)
at weka.core.Instances.(Instances.java:126)
at main.Prediction.runClassifier(Prediction.java:233)
at main.runISOWN.main(runISOWN.java:90)

...
Total number of predicted somatic mutations 0
Final results are saved here: 181023001/181023001.isown.txt
...

Done

INTERESTINGLY, I got no error running both database_annotation.pl and run_isown.pl with the two vcf files provided in the test_data/ directory ...

I googled about the "nominal value not declared in header" and some said it is something to do with weka, so I checked:

java -jar /workplace/Software/ISOWN/bin/weka.jar

Exception in thread "main" java.lang.ExceptionInInitializerError
Caused by: java.awt.HeadlessException:
No X11 DISPLAY variable was set, but this program performed an operation which requires it.
at java.awt.GraphicsEnvironment.checkHeadless(GraphicsEnvironment.java:204)
at java.awt.Window.(Window.java:536)
at java.awt.Frame.(Frame.java:420)
at javax.swing.JFrame.(JFrame.java:233)
at weka.gui.LogWindow.(LogWindow.java:252)
at weka.gui.GUIChooser.(GUIChooser.java:215)

So did I miss anything? By the way, the weka.jar was already in the bin/ directory when I installed ISOWN, so I did not do any replacement of weka.jar since check_dependencies.pl said everything was installed.

Thank you very much!

Pang

Hi, Pang
Have you solve the problem? I just get the same error Can't run classifier.

thanks
yueyang

zjiang-lji · 2021-08-01T20:40:40Z

@Guofengyu, I got this error from the first command, reformatting to emaf, of the classifying step:

Exception in thread "main" java.lang.ArrayIndexOutOfBoundsException: -1
        at com.Processing.processVcf(Processing.java:119)
        at com.runReformating.main(runReformating.java:39)

The beginning of my input VCF is the annotated version of the sample VCF. It looks like this:

##fileformat=VCFv4.1																																				
##fileDate=20160129																																				
##pancancerversion=1.0																																				
##reference=<ID=hs37d5,Source=ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/phase2_reference_assembly_sequence/hs37d5.fa.gz>;																																				
##center="DKFZ"																																				
##workflowName=DKFZ_SNV_workflow																																				
##workflowVersion=1.0.0																																				
##INFO=<ID=SOMATIC,Number=0,Type=Flag,Description="Indicates if record is a somatic mutation">																																				
##INFO=<ID=GERMLINE,Number=0,Type=Flag,Description="Indicates if record is a germline mutation">																																				
##INFO=<ID=UNCLEAR,Number=0,Type=Flag,Description="Indicates if the somatic status of a mutation is unclear">																																				
##INFO=<ID=VT,Number=1,Type=String,Description="Variant type, can be SNP, INS or DEL">																																				
##INFO=<ID=AF,Number=.,Type=Float,Description="Allele Frequency in primary data, for each ALT allele, in the same order as listed">																																				
##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership">																																				
##INFO=<ID=MQ,Number=1,Type=Integer,Description="RMS Mapping Quality">																																				
##INFO=<ID=1000G,Number=0,Type=Flag,Description="Indicates membership in 1000Genomes">																																				
##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">																																				
##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read depth at this position in the sample">																																				
##FORMAT=<ID=DP4,Number=4,Type=Integer,Description="Number of high-quality ref-forward, ref-reverse, alt-forward and alt-reverse bases">																																				
##FILTER=<ID=RE,Description="variant in UCSC_27Sept2013_RepeatMasker.bed.gz region and/or SimpleTandemRepeats_chr.bed.gz region, downloaded from UCSC genome browser and/or variant in segmental duplication region, annotated by annovar">																																				
##FILTER=<ID=BL,Description="variant in DAC-Blacklist from ENCODE or in DUKE_EXCLUDED list, both downloaded from UCSC genome browser">																																				
##FILTER=<ID=DP,Description="<= 5 reads total at position in tumor">																																				
##FILTER=<ID=SB,Description="Strand bias of reads with mutant allele = zero reads on one strand">																																				
##FILTER=<ID=TAC,Description="less than 6 reads in Tumor at position">																																				
##FILTER=<ID=dbSNP,Description="variant in dbSNP135">																																				
##FILTER=<ID=DB,Description="variant in 1000Genomes, ALL.wgs.phase1_integrated_calls.20101123.snps_chr.vcf.gz or dbSNP">																																				
##FILTER=<ID=HSDEPTH,Description="variant in HiSeqDepthTop10Pct_chr.bed.gz region, downloaded from UCSC genome browser">																																				
##FILTER=<ID=MAP,Description="variant overlaps a region from wgEncodeCrgMapabilityAlign100mer.bedGraph.gz:::--breakPointMode --aEndOffset=1 with a value below 0.5, punishment increases with a decreasing mapability">																																				
##FILTER=<ID=SBAF,Description="Strand bias of reads with mutant allele = zero reads on one strand and variant allele frequency below 0.1">																																				
##FILTER=<ID=FRQ,Description="variant allele frequency below 0.05">																																				
##FILTER=<ID=TAR,Description="Only one alternative read in Tumor at position">																																				
##FILTER=<ID=UNCLEAR,Description="Classification is unclear">																																				
##FILTER=<ID=DPHIGH,Description="Too many reads mapped in control at this region">																																				
##FILTER=<ID=DPLOWC,Description="Only 5 or less reads in control">																																				
##FILTER=<ID=1PS,Description="Only two alternative reads, one on each strand">																																				
##FILTER=<ID=ALTC,Description="Alternative reads in control">																																				
##FILTER=<ID=ALTCFR,Description="Alternative reads in control and tumor allele frequency below 0.3">																																				
##FILTER=<ID=FRC,Description="Variant allele frequency below 0.3 in germline call">																																				
##FILTER=<ID=YALT,Description="Variant on Y chromosome with low allele frequency">																																				
##FILTER=<ID=VAF,Description="Variant allele frequency in tumor < 5 times allele frequency in control">																																				
##FILTER=<ID=BI,Description="Bias towards a PCR strand or sequencing strand">																																				
##SAMPLE=<ID=CONTROL,SampleName=control_NA,Individual=NA,Description="Control">																																				
##SAMPLE=<ID=TUMOR,SampleName=tumor_NA,Individual=NA,Description="Tumor">																																				
##TARGET_FILE:SureSelectHumanAllExonV4=file:///oicr/data/genomes/homo_sapiens_mc/Agilent/SureSelectHumanAllExonV4/S03723314_Regions.merged.sorted.bed.gz																																				
##VCF_FILE:dbSNP152_All_20180423=file:///oasis/tscc/scratch/z8jiang/ISOWN/bin/../external_databases/dbSNP152_All_20180423.vcf.gz.modified.vcf.gz																																				
##VCF_FILE:COSMIC_94=file:///oasis/tscc/scratch/z8jiang/ISOWN/bin/../external_databases/COSMIC_v94.vcf.gz																																				
##VCF_FILE:ExAC.r0.3.1=file:///oasis/tscc/scratch/z8jiang/ISOWN/bin/../external_databases/ExAC.r0.3.1.sites.vep.vcf.gz																																				
##VCF_FILE:2021_07_23_MA=file:///oasis/tscc/scratch/z8jiang/ISOWN/bin/../external_databases/2021_07_23_MA.vcf.gz																																				
#TAB_DELIMITED_HEADER=sample_name       chr     pos     reference       alternative     genotype        totalReadDepth  %readDepthAlt   in.dbSNP.or.not in.dbSNP.COMMON.or.not      in.COSMIC.or.not        MA_functional_impact    MA_score        is.SOMATIC      in.ExAC ExAC_NCC        FLANKING_STR    POLYPHEN   VARIANT_CLASS    LENGTH  CHROM   POS     ID      REF     ALT     QUAL    FILTER  INFO    FORMAT  TUMOR																																				
#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	TUMOR																											
TUMOR	chr1	876499	A	G	GENOTYPE_BB	48	100	IN.dbSNP	not.in.dbSNP.COMMON	IN.COSMIC_CNT=0	.	0	0	1	NCC=	V1=[.;.;.;.;.];X=[chr1;876499;0.0000;0.0000;0.0000];V2=[.;.;.;.;.];Distance_Between_V1_and_X=-1;Distance_Between_V2_and_X=-1;V1overlappedX=0;V2overlappedX=0;V1overlappedV2=0	NO_POLYPHEN_DATA	VARIANT_CLASS_SINGLE_NUCLEOTIDE_VARIANT	1	chr1	876499	rs4372192_876499	A	G	.	PASS	GERMLINE;SNP;AF=1.00,1.00;MQ=60;DB;1000G;[SureSelectHumanAllExonV4=1,1,[chr1,876429,876641]];ANNOVAR=intronic,SAMD11;ANNOTATIONS={dbSNP152_All_20180423=0;0;.;.;.},{COSMIC_94=0;0;.;.;.},{ExAC.r0.3.1=0;0;.;.;.},{2021_07_23_MA=0;0;.;.;.};POLYPHEN=[polyphenWHESS_20150403=0,NO_POLYPHEN_DATA];SEQUENCE_CONTEXT=GAT;OICR_FLANKING={V1=[.;.;.;.;.];X=[chr1;876499;0.0000;0.0000;0.0000];V2=[.;.;.;.;.];Distance_Between_V1_and_X=-1;Distance_Between_V2_and_X=-1;V1overlappedX=0;V2overlappedX=0;V1overlappedV2=0}	AD:GT:DP:DP4	0,48:1/1:48:0,0,32,16							
TUMOR	chr1	877715	C	G	GENOTYPE_BB	34	100	IN.dbSNP	not.in.dbSNP.COMMON	IN.COSMIC_CNT=0	.	0	0	1	NCC=	V1=[.;.;.;.;.];X=[chr1;877715;0.0000;0.0000;0.0000];V2=[.;.;.;.;.];Distance_Between_V1_and_X=-1;Distance_Between_V2_and_X=-1;V1overlappedX=0;V2overlappedX=0;V1overlappedV2=0	NO_POLYPHEN_DATA	VARIANT_CLASS_SINGLE_NUCLEOTIDE_VARIANT	1	chr1	877715	rs6605066_877715	C	G	.	PASS	GERMLINE;SNP;AF=1.00,1.00;MQ=60;DB;1000G;[SureSelectHumanAllExonV4=1,1,[chr1,877537,878481]];ANNOVAR=intronic,SAMD11;ANNOTATIONS={dbSNP152_All_20180423=0;0;.;.;.},{COSMIC_94=0;0;.;.;.},{ExAC.r0.3.1=0;0;.;.;.},{2021_07_23_MA=0;0;.;.;.};POLYPHEN=[polyphenWHESS_20150403=0,NO_POLYPHEN_DATA];SEQUENCE_CONTEXT=CCG;OICR_FLANKING={V1=[.;.;.;.;.];X=[chr1;877715;0.0000;0.0000;0.0000];V2=[.;.;.;.;.];Distance_Between_V1_and_X=-1;Distance_Between_V2_and_X=-1;V1overlappedX=0;V2overlappedX=0;V1overlappedV2=0}	AD:GT:DP:DP4	0,34:1/1:34:0,0,13,21							
TUMOR	chr1	877831	T	C	GENOTYPE_BB	33	100	IN.dbSNP	not.in.dbSNP.COMMON	IN.COSMIC_CNT=0	.	0	0	1	NCC=	V1=[.;.;.;.;.];X=[chr1;877831;0.0000;0.0000;0.0000];V2=[.;.;.;.;.];Distance_Between_V1_and_X=-1;Distance_Between_V2_and_X=-1;V1overlappedX=0;V2overlappedX=0;V1overlappedV2=0	transcript:uc001abw.1,uc001abx.1;hdiv_prediction:benign,benign;hdiv_class:neutral,neutral;hvar_prediction:benign,benign;hvar_class:neutral,neutral	VARIANT_CLASS_SINGLE_NUCLEOTIDE_VARIANT	1	chr1	877831	rs6672356_877831	T	C	.	PASS	GERMLINE;SNP;AF=1.00,1.00;MQ=60;DB;1000G;[SureSelectHumanAllExonV4=1,1,[chr1,877537,878481]];ANNOVAR=exonic,SAMD11;ANNOVAR_EXONIC=nonsynonymous	SNV,SAMD11:NM_152486:exon10:c.T1027C:p.W343R,;ANNOTATIONS={dbSNP152_All_20180423=0;0;.;.;.},{COSMIC_94=0;0;.;.;.},{ExAC.r0.3.1=0;0;.;.;.},{2021_07_23_MA=1;1;VARIANT_MATCHED;.;[chr1|877831|.|T|C|.|.|RefGenome	variant=W>R;Gene=SAMD11;Uniprot=SAM11_HUMAN;Info=;Uniprot	variant=W343R;Func.	Impact=neutral;FI	score=-2.1]};POLYPHEN=[polyphenWHESS_20150403=1,transcript:uc001abw.1,uc001abx.1;hdiv_prediction:benign,benign;hdiv_class:neutral,neutral;hvar_prediction:benign,benign;hvar_class:neutral,neutral];SEQUENCE_CONTEXT=CTG;OICR_FLANKING={V1=[.;.;.;.;.];X=[chr1;877831;0.0000;0.0000;0.0000];V2=[.;.;.;.;.];Distance_Between_V1_and_X=-1;Distance_Between_V2_and_X=-1;V1overlappedX=0;V2overlappedX=0;V1overlappedV2=0}	AD:GT:DP:DP4	0,33:1/1:33:0,0,15,18		
TUMOR	chr1	880238	A	G	GENOTYPE_BB	73	100	IN.dbSNP	not.in.dbSNP.COMMON	IN.COSMIC_CNT=0	.	0	0	1	NCC=	V1=[.;.;.;.;.];X=[chr1;880238;0.0000;0.0000;0.0000];V2=[.;.;.;.;.];Distance_Between_V1_and_X=-1;Distance_Between_V2_and_X=-1;V1overlappedX=0;V2overlappedX=0;V1overlappedV2=0	NO_POLYPHEN_DATA	VARIANT_CLASS_SINGLE_NUCLEOTIDE_VARIANT	1	chr1	880238	rs3748592_880238	A	G	.	PASS	GERMLINE;SNP;AF=1.00,1.00;MQ=60;DB;1000G;[SureSelectHumanAllExonV4=1,1,[chr1,880160,880280]];ANNOVAR=intronic,NOC2L;ANNOTATIONS={dbSNP152_All_20180423=0;0;.;.;.},{COSMIC_94=0;0;.;.;.},{ExAC.r0.3.1=0;0;.;.;.},{2021_07_23_MA=0;0;.;.;.};POLYPHEN=[polyphenWHESS_20150403=0,NO_POLYPHEN_DATA];SEQUENCE_CONTEXT=TAG;OICR_FLANKING={V1=[.;.;.;.;.];X=[chr1;880238;0.0000;0.0000;0.0000];V2=[.;.;.;.;.];Distance_Between_V1_and_X=-1;Distance_Between_V2_and_X=-1;V1overlappedX=0;V2overlappedX=0;V1overlappedV2=0}	AD:GT:DP:DP4	0,73:1/1:73:0,0,36,37							
TUMOR	chr1	880466	T	C	GENOTYPE_AB	65	35.38	IN.dbSNP	not.in.dbSNP.COMMON	IN.COSMIC_CNT=0	.	0	0	1	NCC=	V1=[.;.;.;.;.];X=[chr1;880466;25.5987;35.3846;45.1706];V2=[.;.;.;.;.];Distance_Between_V1_and_X=-1;Distance_Between_V2_and_X=-1;V1overlappedX=0;V2overlappedX=0;V1overlappedV2=0	NO_POLYPHEN_DATA	VARIANT_CLASS_SINGLE_NUCLEOTIDE_VARIANT	1	chr1	880466	rs138652036_880466	T	C	.	PASS	GERMLINE;SNP;AF=0.51,0.35;MQ=60;DB;[SureSelectHumanAllExonV4=1,1,[chr1,880449,880637]];ANNOVAR=exonic,NOC2L;ANNOVAR_EXONIC=nonsynonymous	SNV,NOC2L:NM_015658:exon18:c.A2114G:p.E705G,;ANNOTATIONS={dbSNP152_All_20180423=0;0;.;.;.},{COSMIC_94=0;0;.;.;.},{ExAC.r0.3.1=0;0;.;.;.},{2021_07_23_MA=1;1;VARIANT_MATCHED;.;[chr1|880466|.|T|C|.|.|RefGenome	variant=E>G;Gene=NOC2L;Uniprot=NOC2L_HUMAN;Info=;Uniprot	variant=E705G;Func.	Impact=neutral;FI	score=0.77]};POLYPHEN=[polyphenWHESS_20150403=0,NO_POLYPHEN_DATA];SEQUENCE_CONTEXT=CTC;OICR_FLANKING={V1=[.;.;.;.;.];X=[chr1;880466;25.5987;35.3846;45.1706];V2=[.;.;.;.;.];Distance_Between_V1_and_X=-1;Distance_Between_V2_and_X=-1;V1overlappedX=0;V2overlappedX=0;V1overlappedV2=0}	AD:GT:DP:DP4	42,23:0/1:65:19,23,10,13		
TUMOR	chr1	881627	G	A	GENOTYPE_BB	44	100	IN.dbSNP	not.in.dbSNP.COMMON	IN.COSMIC_CNT=0	.	0	0	1	NCC=	V1=[.;.;.;.;.];X=[chr1;881627;0.0000;0.0000;0.0000];V2=[.;.;.;.;.];Distance_Between_V1_and_X=-1;Distance_Between_V2_and_X=-1;V1overlappedX=0;V2overlappedX=0;V1overlappedV2=0	NO_POLYPHEN_DATA	VARIANT_CLASS_SINGLE_NUCLEOTIDE_VARIANT	1	chr1	881627	rs2272757_881627	G	A	.	PASS	GERMLINE;SNP;AF=1.00,1.00;MQ=60;DB;1000G;[SureSelectHumanAllExonV4=1,1,[chr1,881618,881803]];ANNOVAR=exonic,NOC2L;ANNOVAR_EXONIC=synonymous	SNV,NOC2L:NM_015658:exon16:c.C1843T:p.L615L,;ANNOTATIONS={dbSNP152_All_20180423=0;0;.;.;.},{COSMIC_94=0;0;.;.;.},{ExAC.r0.3.1=0;0;.;.;.},{2021_07_23_MA=1;1;VARIANT_MATCHED;.;[chr1|881627|.|G|A|.|.|RefGenome	variant=L>L;Gene=NOC2L;Uniprot=NOC2L_HUMAN;Info=synonymous	in	Uniprot;Uniprot	variant=L615L;Func.	Impact=;FI	score=]};POLYPHEN=[polyphenWHESS_20150403=0,NO_POLYPHEN_DATA];SEQUENCE_CONTEXT=AGG;OICR_FLANKING={V1=[.;.;.;.;.];X=[chr1;881627;0.0000;0.0000;0.0000];V2=[.;.;.;.;.];Distance_Between_V1_and_X=-1;Distance_Between_V2_and_X=-1;V1overlappedX=0;V2overlappedX=0;V1overlappedV2=0}	AD:GT:DP:DP4	0,44:1/1:44:0,0,30,14

zjiang-lji · 2021-08-16T03:56:12Z

Can someone help me with this "Can't run classifier...nominal value not declared in header" error?

...
Your working directory is /oasis/tscc/scratch/z8jiang/ISOWN/run_isown_trial6
...
This file was chosen for classifier training: /oasis/tscc/scratch/z8jiang/ISOWN/training_data/COAD_100_TrainSet.arff
...
Total number of samples in your set is 2
...
Number of loaded nonsilent coding variants in test set is 6330
...
*************
Naive Bayes Classifier: 
Option: supervised discretization (SD) is true
10-fold cross-validation
*************
F1-measure: 96.163%.
Recall: 95.235%.
Precision: 97.11%.
False positive rate: 2.834%.
AUC: 99.39%.
*************
Can't run classifier.
java.io.IOException: nominal value not declared in header, read Token[null], line 59
	at weka.core.converters.ArffLoader$ArffReader.errorMessage(ArffLoader.java:240)
	at weka.core.converters.ArffLoader$ArffReader.getInstanceFull(ArffLoader.java:578)
	at weka.core.converters.ArffLoader$ArffReader.getInstance(ArffLoader.java:423)
	at weka.core.converters.ArffLoader$ArffReader.readInstance(ArffLoader.java:391)
	at weka.core.converters.ArffLoader$ArffReader.readInstance(ArffLoader.java:376)
	at weka.core.converters.ArffLoader$ArffReader.<init>(ArffLoader.java:138)
	at weka.core.Instances.<init>(Instances.java:126)
	at main.Prediction.runClassifier(Prediction.java:233)
	at main.runISOWN.main(runISOWN.java:90)

...
Total number of predicted somatic mutations 0
Final results are saved here: test.txt
...

The first few lines of my .emaf file looks like the following:

Variant	chr	pos	reference	alternative	sample_name	type	subtype	gene_name	amino_acid_change	MA_functional_impact	MA_score	isFlanking	is_in_COSMIC	CNT	is_in_dbSNP	is_in_dbSNP_common	readDepthAlt	totalReadDepth	SEQUENCING_CONTEXT	POLYPHEN_hdiv	POLYPHEN_hvar	is_in_ExAct	isSOMATIC
chr1,942665C>A	chr1	942665	C	A	SP10_filtered	exonic	nonsynonymous	SAMD11	L554M	.	.	NA	T	0	T	F	20.00	5	GCT	.	.	T	false
chr1,942668C>G	chr1	942668	C	G	SP10_filtered	exonic	nonsynonymous	SAMD11	Q555E	.	.	NA	T	0	T	F	20.00	5	GCA	.	.	T	false
chr1,942681CC>GG	chr1	942681	CC	GG	SP10_filtered	exonic	nonframeshift substitution	SAMD11	.	.	.	NA	T	0	T	F	20.00	5		.	.	T	false

HengqiLiu · 2022-08-19T11:53:14Z

nominal value not declared in header

Hi, zjiang-lji

Have you solve the problem? I just get the same error Can't run classifier.

Thanks,
Hengqi Liu

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Can't run classifier. #26

Can't run classifier. #26

LuoPangpang commented Jul 5, 2019

amit21AIT commented Jul 6, 2019 •

edited

Loading

LuoPangpang commented Jul 8, 2019 •

edited

Loading

Guofengyu commented Jul 18, 2019

Guofengyu commented Jul 24, 2019

yueyangtime commented Dec 30, 2019 •

edited

Loading

Done

zjiang-lji commented Aug 1, 2021

zjiang-lji commented Aug 16, 2021

HengqiLiu commented Aug 19, 2022

Can't run classifier. #26

Can't run classifier. #26

Comments

LuoPangpang commented Jul 5, 2019

Done

amit21AIT commented Jul 6, 2019 • edited Loading

LuoPangpang commented Jul 8, 2019 • edited Loading

Guofengyu commented Jul 18, 2019

Guofengyu commented Jul 24, 2019

yueyangtime commented Dec 30, 2019 • edited Loading

Done

zjiang-lji commented Aug 1, 2021

zjiang-lji commented Aug 16, 2021

HengqiLiu commented Aug 19, 2022

amit21AIT commented Jul 6, 2019 •

edited

Loading

LuoPangpang commented Jul 8, 2019 •

edited

Loading

yueyangtime commented Dec 30, 2019 •

edited

Loading