########################################################################################################## #SequenceVariantAnalyzer project file. #Authors: Dongliang Ge & David B. Goldstein #Duke Institute for Genome Sciences & Policy, Center for Human Genome Variation #Note: lines after the commenting symbol (#) will be ignored in the analysis. ########################################################################################################## ########################################################################################################## #The following section lists the inputs and outputs used in the annotation. You need to specify your files. ########################################################################################################## [INPUT]=cacosnv,/project/erasys1/ngs/sva/svacaco/casnv.samtools #[INPUT_CONTROL]=, [INDELINPUT]=cacoind,/project/erasys1/ngs/sva/svacaco/caindel.samtools #[INDELINPUT]=, #[HMMSVINPUT]=, [COVERAGE]=1,cabco1,/project/erasys1/ngs/sva/svacaco/cabco_.1.bco [COVERAGE]=2,cabco2,/project/erasys1/ngs/sva/svacaco/cabco_.2.bco [COVERAGE]=3,cabco3,/project/erasys1/ngs/sva/svacaco/cabco_.3.bco [COVERAGE]=4,cabco4,/project/erasys1/ngs/sva/svacaco/cabco_.4.bco [COVERAGE]=5,cabco5,/project/erasys1/ngs/sva/svacaco/cabco_.5.bco [COVERAGE]=6,cabco6,/project/erasys1/ngs/sva/svacaco/cabco_.6.bco [COVERAGE]=7,cabco7,/project/erasys1/ngs/sva/svacaco/cabco_.7.bco [COVERAGE]=8,cabco8,/project/erasys1/ngs/sva/svacaco/cabco_.8.bco [COVERAGE]=9,cabco9,/project/erasys1/ngs/sva/svacaco/cabco_.9.bco [COVERAGE]=10,cabco10,/project/erasys1/ngs/sva/svacaco/cabco_.10.bco [COVERAGE]=11,cabco11,/project/erasys1/ngs/sva/svacaco/cabco_.11.bco [COVERAGE]=12,cabco12,/project/erasys1/ngs/sva/svacaco/cabco_.12.bco [COVERAGE]=13,cabco13,/project/erasys1/ngs/sva/svacaco/cabco_.13.bco [COVERAGE]=14,cabco14,/project/erasys1/ngs/sva/svacaco/cabco_.14.bco [COVERAGE]=15,cabco15,/project/erasys1/ngs/sva/svacaco/cabco_.15.bco [COVERAGE]=16,cabco16,/project/erasys1/ngs/sva/svacaco/cabco_.16.bco [COVERAGE]=17,cabco17,/project/erasys1/ngs/sva/svacaco/cabco_.17.bco [COVERAGE]=18,cabco18,/project/erasys1/ngs/sva/svacaco/cabco_.18.bco [COVERAGE]=19,cabco19,/project/erasys1/ngs/sva/svacaco/cabco_.19.bco [COVERAGE]=20,cabco20,/project/erasys1/ngs/sva/svacaco/cabco_.20.bco [COVERAGE]=21,cabco21,/project/erasys1/ngs/sva/svacaco/cabco_.21.bco [COVERAGE]=22,cabco22,/project/erasys1/ngs/sva/svacaco/cabco_.22.bco [COVERAGE]=X,cabcoX,/project/erasys1/ngs/sva/svacaco/cabco_.X.bco [COVERAGE]=Y,cabcoY,/project/erasys1/ngs/sva/svacaco/cabco_.Y.bco [COVERAGE]=M,cabcoM,/project/erasys1/ngs/sva/svacaco/cabco_.M.bco #[PEDINFO]= [HMMSVMINLOD]=0 #Output file #[OUTPUT]=cacoout,/project/erasys1/ngs/sva/svacaco/caco.out #Automatically changed to: [OUTPUT]=/project/erasys1/ngs/sva/svacaco/caco.sva ########################################################################################################## #The following section lists an genome buffering option. Enabling this option will speedup the loading an integrated genome browser in this #software. You will need to specify a file to store the buffered information. ########################################################################################################## [GenomeBrowserBufferSwitch]=off #[GenomeBrowserBuffer]= ########################################################################################################## #The following section lists the annotation options. ########################################################################################################## #If specified as "on", this option tells SequenceVariantAnalyzer to skip the annotation procedures and directly load the binary output instead. [SKIPANNOTATION]=on #Define upstream/downstream span [UPSTREAM]=1000 [DOWNSTREAM]=1000 #Define intronic exon boundary. [INTRON_EXON_BOUNDARY_INTO_INTRON]=8 [INTRON_EXON_BOUNDARY_INTO_EXON]=3 #Define threshold to group structural variations with recorded DGV CNVs - defualt is 50%. [DGVCNVOVERLAP]=0.50 #Specify comprehensive or abbreviated annotation output. Note: comprehensive annotations include functionality for all relevant transcripts, #while abbreviated output only includes the potentially most important one, but at a risk of losing information. [DETAILED_OUTPUT]=on ########################################################################################################## #The following section lists the databases used in the annotation. You do not need to change them unless you need to use other versions of #the databases. ########################################################################################################## #Reference database version [COREVERSION]=61_37f #Reference sequence, could be multiple lines, binary [REFBIN]=1,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.1.fa.bin [REFBIN]=2,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.2.fa.bin [REFBIN]=3,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.3.fa.bin [REFBIN]=4,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.4.fa.bin [REFBIN]=5,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.5.fa.bin [REFBIN]=6,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.6.fa.bin [REFBIN]=7,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.7.fa.bin [REFBIN]=8,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.8.fa.bin [REFBIN]=9,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.9.fa.bin [REFBIN]=10,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.10.fa.bin [REFBIN]=11,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.11.fa.bin [REFBIN]=12,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.12.fa.bin [REFBIN]=13,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.13.fa.bin [REFBIN]=14,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.14.fa.bin [REFBIN]=15,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.15.fa.bin [REFBIN]=16,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.16.fa.bin [REFBIN]=17,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.17.fa.bin [REFBIN]=18,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.18.fa.bin [REFBIN]=19,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.19.fa.bin [REFBIN]=20,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.20.fa.bin [REFBIN]=21,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.21.fa.bin [REFBIN]=22,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.22.fa.bin [REFBIN]=X,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.X.fa.bin [REFBIN]=Y,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.Y.fa.bin [REFBIN]=M,./datasource/ensembl/61_37f/Homo_sapiens.GRCh37.61.dna.chromosome.MT.fa.bin #RepeatMasker result folder [REPEATMASKERFOLDER]=./datasource/repeatMasker #A switch to turn on/off function for generating 'N' bases in reference sequence [REGENERATEREFNCALLS]=OFF #The following are the annotation databases #Core [GENEID]=./datasource/ensembl/61_37f/gene_stable_id.txt [TRANSCRIPT]=./datasource/ensembl/61_37f/transcript.txt [TRANSCRIPTID]=./datasource/ensembl/61_37f/transcript_stable_id.txt [TRANSLATION]=./datasource/ensembl/61_37f/translation.txt [EXON]=./datasource/ensembl/61_37f/exon.txt [EXONTRANSCRIPT]=./datasource/ensembl/61_37f/exon_transcript.txt [XREF]=./datasource/ensembl/61_37f/xref.txt [OBJECTXREF]=./datasource/ensembl/61_37f/object_xref.txt [GENE]=./datasource/ensembl/61_37f/gene.txt [SEQREGION]=./datasource/ensembl/61_37f/seq_region.txt #GO [GO]=./datasource/ensembl/61_37f/term.txt #Existing variations [VARIATION]=./datasource/ensembl/61_37f/variation.txt [VARIATIONFEATURE1]=./datasource/ensembl/61_37f/variation_feature.txt [VARIATIONFEATURE2]=./datasource/ensembl/61_37f/variation_feature2.txt [VARIATIONALLELE1]=./datasource/ensembl/61_37f/allele.txt [VARIATIONALLELE2]=./datasource/ensembl/61_37f/allele2.txt [VARIATIONSAMPLE]=./datasource/ensembl/61_37f/sample.txt #Protein sequence variation annotation (pre-calculated) [PROTEINVAR]=./datasource/proteinpoly/mapp.out #Hapmap [HAPMAP]=./datasource/hapmap/hapmap_r23a.bim #Illumina 1M chip [ILLUMINA1M]=./datasource/illumina/Human1Mv1_snptable.txt #CNV [DGVCNV]=./datasource/CNV/DGV/variation.hg19.v10.nov.2010.txt #[CNVTAGGING]=./datasource/CNV/DGV/variation.hg19.v10.nov.2010.txt #KEGG pathway files [KEGGMAPTITLE]=./datasource/kegg/Mar92011/map_title.tab [KEGGGENEPATHWAY]=./datasource/kegg/Mar92011/genes_pathway.list #Venter's variants #[VENTERSNPS]=./datasource/venter/HuRef.InternalHuRef-NCBI.snp.bin #[VENTERINDELS]=./datasource/venter/HuRef.InternalHuRef-NCBI.indel.bin #1000 Human Genome SNP #[1000HUMANGENOMESNP]=./datasource/1kgenome/CEU.frequency.filter #OMIM Gene map [OMIMGENEMAP]=./datasource/omim/Mar92011/genemap #An *optional* protein sequence output [PROTEINFASTAOUTPUTFOLDER]=./datasource/ensembl/61_37f/proteinfasta ########################################################################################################## #End of the SequenceVariantAnalyzer project script file. ##########################################################################################################