Vartrix

data/.gitignore

@@ -0,0 +1,3 @@
+10k_PBMC_Multiome_nextgem_Chromium_X_atac_possorted_bam.bam
+10k_PBMC_Multiome_nextgem_Chromium_X_atac_possorted_bam.bam.bai
+.README.md.swp

data/README.md

@@ -0,0 +1,72 @@
+# nf-core/mitotags test files
+
+This is the minimal test files to test the nf-core/mitotags package.
+
+## input 
+
+ChrM_testData_R1_001.fastq.gz
+
+```
+bedtools bamtofastq -i ChrM_subset.bam -fq ChrM_testData_R1_001.fastq -fq2 ChrM_testData_R2_001.fastq
+gzip *.fastq
+```
+
+## bam 
+
+ChrM_subset.bam
+
+
+```
+wget https://s3-us-west-2.amazonaws.com/10x.files/samples/cell-arc/2.0.0/10k_PBMC_Multiome_nextgem_Chromium_X/10k_PBMC_Multiome_nextgem_Chromium_X_atac_possorted_bam.bam
+wget https://s3-us-west-2.amazonaws.com/10x.files/samples/cell-arc/2.0.0/10k_PBMC_Multiome_nextgem_Chromium_X/10k_PBMC_Multiome_nextgem_Chromium_X_atac_possorted_bam.bam.bai
+samtools view 10k_PBMC_Multiome_nextgem_Chromium_X_atac_possorted_bam.bam chrM:15000-22000 -b > Chrm_subset.bam
+## find the 300 highest chrM read count barcodes and split on them.
+gunzip barcodes.tsv
+samtools view -h Chrm_subset.bam | head -n 3000 | grep "^@" > ChrM_subset.sam
+samtools view Chrm_subset.bam | grep -f barcodes.tsv  >> ChrM_subset.sam
+samtools view ChrM_subset.sam -b > ChrM_subset.bam
+gzip barcodes.tsv
+rm Chrm_subset.bam 
+rm ChrM_subset.sam
+
+```
+
+## bai
+
+ChrM_subset.bam.bai
+
+```
+samtools index ChrM_subset.bam
+```
+
+## barcodes  
+
+barcodes.tsv.gz
+
+```
+samtools view Chrm_subset.bam | grep -o "CB:Z:[AGCT]*-1" > barcodes_total.txt
+```
+
+R script to get the top 300 barcodes:
+
+```
+dat = scan( 'barcodes_total.txt', what=character())
+write ( names( sort(table(dat), decreasing=TRUE)[1:300]), file="barcodes.tsv" )
+```
+
+Or on the command line (slow!):
+
+```
+sort barcodes_total.txt | uniq -c > barcodes_unique.txt
+sort -k 2n  barcodes_unique.txt| head -n 300 | cut -f1 > barcodes.tsv
+```
+
+Clean up
+
+```
+gzip barcodes.tsv
+rm barcodes_total.txt
+```
+
+## genome 
+ChrM.fa.gz

data/barcodes.tsv

@@ -0,0 +1,300 @@
+CB:Z:TGTGTTAAGTAGCGGG-1
+CB:Z:TAGTTGTCAAACCCTA-1
+CB:Z:CGGCAATGTCAAAGGG-1
+CB:Z:GTCGAGGAGTGAACGA-1
+CB:Z:CGAGCGAAGTCATTAG-1
+CB:Z:GAAGGCTAGGCAAGTA-1
+CB:Z:ATTCAACCAATCGCAC-1
+CB:Z:TGTTGTTTCACGAATC-1
+CB:Z:GAACCAGCACCTCAGG-1
+CB:Z:GATTTGCAGTAGCGCC-1
+CB:Z:CCTAAATCATAAGGAC-1
+CB:Z:TCTGGCTTCTCGACCT-1
+CB:Z:TTAAGGACACCAGGTT-1
+CB:Z:TGGTTAATCAGCTAAC-1
+CB:Z:GATTGATGTGAGCACT-1
+CB:Z:GACGCAACACGGTACT-1
+CB:Z:GTTTGCTGTGCTCCGT-1
+CB:Z:GTAGTTTCATTGGGAG-1
+CB:Z:ACCTGGTCAATTAAGG-1
+CB:Z:CCAGTTTGTAACGAGG-1
+CB:Z:CGAGGAAGTGAGCACT-1
+CB:Z:CCATAAATCCGCAACA-1
+CB:Z:ATGTCAATCGCTAAAC-1
+CB:Z:CAGGTCCAGCTAATTG-1
+CB:Z:GTGCTCCGTACCAGGT-1
+CB:Z:TAAGTAGCAATTGAGA-1
+CB:Z:ACCCAGGGTGACATGC-1
+CB:Z:GCTTAACAGCTTATGA-1
+CB:Z:GGCCTAATCGCAGGCT-1
+CB:Z:CCGCAAATCACGAATC-1
+CB:Z:AGGTTAACAGCAATAA-1
+CB:Z:TCCGGAATCAGGTTTA-1
+CB:Z:CAGATTCAGCACAGCC-1
+CB:Z:ACAGCCGGTTAGGTTG-1
+CB:Z:CGGGCTTAGAGAGGAG-1
+CB:Z:TCAAGCTAGAAGGTGC-1
+CB:Z:GTGCAAGCAATTGACT-1
+CB:Z:CGGTAACGTGTGTGGT-1
+CB:Z:CAATATGTCCTGGCTT-1
+CB:Z:GTTCTTGTCGGTTCCT-1
+CB:Z:GGATACTTCTCCTCTT-1
+CB:Z:GCTTTGTGTTTGTCTA-1
+CB:Z:AACAAGCCATTCAGCA-1
+CB:Z:TGGATTCAGCCTAACG-1
+CB:Z:CTTTAGTTCCTGGTCT-1
+CB:Z:CCTATATTCGCAATCG-1
+CB:Z:GATTCGCCACTAAGCC-1
+CB:Z:GAGAGGCGTTGTCATC-1
+CB:Z:GCTGTACCAATCATGT-1
+CB:Z:TCACATAAGCCTTAAA-1
+CB:Z:ACGGTACGTCTCACTG-1
+CB:Z:ACAACAGAGGCCTTAG-1
+CB:Z:CTTAAGATCCGCATGA-1
+CB:Z:TAATTGCCAATATGGA-1
+CB:Z:ATATGCTCAGCAACAG-1
+CB:Z:CGCACCACACAGAACG-1
+CB:Z:TCGCTAACAAATTCGT-1
+CB:Z:GATTCATCATGTCAGC-1
+CB:Z:TTGGCTGAGATAACCC-1
+CB:Z:CTCGCTCCAGGCGATA-1
+CB:Z:ATTGTGATCTTGGATA-1
+CB:Z:ACACGGACAGGAACAT-1
+CB:Z:GATTGCGTCGCATTAA-1
+CB:Z:ATGATGGAGTTAACCA-1
+CB:Z:AAGTCTATCAGCTAAC-1
+CB:Z:CAATCGCCACACAATT-1
+CB:Z:GCATTGCCAGTTATCG-1
+CB:Z:CAAGACAAGGACACTT-1
+CB:Z:CGAGCGAAGCTCAATA-1
+CB:Z:TACGCACCATTAGGTT-1
+CB:Z:AACGCCCAGCAAACCT-1
+CB:Z:TTAGAAGCAATTTAGC-1
+CB:Z:TGTGTGAGTTAGGTTG-1
+CB:Z:TACCTGCTCATGCTAA-1
+CB:Z:ATGAAGCCAGGAACTG-1
+CB:Z:GTCATGAGTCACGGAT-1
+CB:Z:TAGTTTGAGCGCAATT-1
+CB:Z:GGTACCGGTGTCCAGG-1
+CB:Z:TCGTTTCCACTATGGC-1
+CB:Z:CCTAGTTGTACTTCAC-1
+CB:Z:GGATGTAAGGCGCACT-1
+CB:Z:GCTTAACAGTTATCTC-1
+CB:Z:GGTAAACCAGCGCTTG-1
+CB:Z:CTAATAGTCAGAAACG-1
+CB:Z:TCTAATCTCTAAGTGC-1
+CB:Z:TTCAGCACAAGCCACT-1
+CB:Z:TAGGTTATCCGGTTGA-1
+CB:Z:TAAGCCTAGGCGCTTA-1
+CB:Z:TACGGATTCCTTCTAG-1
+CB:Z:CAAGGCTGTTGAGGTC-1
+CB:Z:TAGTGAGAGTTGGGCC-1
+CB:Z:CGGTGAACATGTGGGA-1
+CB:Z:GGTAGGAGTGGAAACG-1
+CB:Z:GAACGAATCGCTATAA-1
+CB:Z:GGTGAGCCAATCCCTT-1
+CB:Z:AAGCCTGTCCTAATAG-1
+CB:Z:ATATGCTCAAGGTCCT-1
+CB:Z:AGCTTTAAGCTTAGTA-1
+CB:Z:TAACAAGCACTCAACA-1
+CB:Z:TCTTAGCGTGTGTCCC-1
+CB:Z:AACTGTTCAACCTGGT-1
+CB:Z:GTTCTCATCCAGGTTG-1
+CB:Z:GGCAGGATCCGCATGA-1
+CB:Z:AGTAATGCACGTAATT-1
+CB:Z:CGTCAATAGCGATAGA-1
+CB:Z:CGTCCTAGTAGGATTT-1
+CB:Z:TTATCCGTCTTAATGG-1
+CB:Z:AATTTGCCATGAATCT-1
+CB:Z:TCTCAAGCAATAGCAA-1
+CB:Z:AGGTGAGGTTACTTCA-1
+CB:Z:GCTCCTTAGATGGAGC-1
+CB:Z:AAAGGAGCATAATTGC-1
+CB:Z:GCAAGTCGTCAAGTAT-1
+CB:Z:TTAAGGACAGCATGTC-1
+CB:Z:TTAGGCGTCGGGACCT-1
+CB:Z:ATTCCGGAGCAAGATG-1
+CB:Z:ATGAAGTAGTGAGGTA-1
+CB:Z:TTTCGTCCAGCAAGAT-1
+CB:Z:GAGTGTTTCCCTCGCA-1
+CB:Z:CGAAGCGAGCTAAAGG-1
+CB:Z:TCGTGCTTCGGTTTGG-1
+CB:Z:ATGTTTGAGCGCCTTT-1
+CB:Z:GCTTTATTCCTAAGAC-1
+CB:Z:AGGCAATCAGGCGAGT-1
+CB:Z:CCTATTTAGCAGGTTT-1
+CB:Z:GTGCCTTTCTTGCAGG-1
+CB:Z:TTAGGAACAGAAATGC-1
+CB:Z:AGCACTTAGTAAGAAC-1
+CB:Z:GGCAATCGTCATAACG-1
+CB:Z:CCTAAGTAGGCGCTAC-1
+CB:Z:GCAAGTCGTTGGTGAC-1
+CB:Z:GTTGCCCGTTAGTTGG-1
+CB:Z:AACCCGCAGTCACCAG-1
+CB:Z:GGTCGGTTCCGCCAAA-1
+CB:Z:CTCCAAACAAGTAAGC-1
+CB:Z:AGGGTTGCAAAGCTCC-1
+CB:Z:AGGCAGGTCAGGATGA-1
+CB:Z:TTTGCGACAGTTTCTC-1
+CB:Z:GCTCTGTTCCTAGTTT-1
+CB:Z:TGAGCACGTGGTGAGA-1
+CB:Z:ATGAAGCCAGTAAAGC-1
+CB:Z:AATCATGTCTTAGCCC-1
+CB:Z:TGGTCAAGTTTGGCTT-1
+CB:Z:CTAGGACGTGCCGCAA-1
+CB:Z:GGCGGTAAGTTGGCCA-1
+CB:Z:CCAATATCACAAAGCG-1
+CB:Z:GGATTCAGTGATCAGC-1
+CB:Z:AACTAGTGTAATCCCT-1
+CB:Z:GCTGCACAGTCACCAG-1
+CB:Z:GCTTTCATCCGGTTAG-1
+CB:Z:TTTGTGAAGGCTAAGA-1
+CB:Z:TCAAGACTCTGCAAAC-1
+CB:Z:AGTTTGCAGGCTACAT-1
+CB:Z:TCTAGCCTCGTGCTTC-1
+CB:Z:CTAGGACGTTAGCTGA-1
+CB:Z:CACAAGCGTTCGGTAA-1
+CB:Z:CGTGCTGCAAGGTATA-1
+CB:Z:CCTTCGTAGCATGTTA-1
+CB:Z:CGTTATCGTAAGCTCA-1
+CB:Z:GAGTATCTCCAGCACA-1
+CB:Z:TTCCTTCTCTCACACC-1
+CB:Z:AGTAACGAGTTGGCCA-1
+CB:Z:GAAACTGAGAAGGTGC-1
+CB:Z:GCATATATCCTCGATC-1
+CB:Z:AGTTTGATCAGGGCCT-1
+CB:Z:GAGGCTACAGTTATCG-1
+CB:Z:AATTGGACACCGGCTA-1
+CB:Z:GAGCTAGCAGCATGGA-1
+CB:Z:ACATCAATCCAGGGAG-1
+CB:Z:TTGTTGTTCTAGCTTT-1
+CB:Z:GGCATGGAGAATGACG-1
+CB:Z:CCGTTATGTAGGTGTC-1
+CB:Z:CTTAGTTTCCTAATTC-1
+CB:Z:GACTTGGTCGTAATCA-1
+CB:Z:ATGTCATCACGAATTT-1
+CB:Z:TGCTTAAAGGGCTTAT-1
+CB:Z:ACTGAAACAGCACCAT-1
+CB:Z:GTCCTAGAGGCATTGT-1
+CB:Z:ATCAGGTTCTGTGAGT-1
+CB:Z:TATAGGTGTAATCGCA-1
+CB:Z:GGGCATTGTCCTTCAG-1
+CB:Z:TTTGTGTTCTAGCGTG-1
+CB:Z:TTGAGCTAGACAACAG-1
+CB:Z:GAGAGGCGTGTTTGTC-1
+CB:Z:TCGACAAGTTCCGGCT-1
+CB:Z:TTGTCCGGTTGGTGAC-1
+CB:Z:CTCAATAAGGAACCAA-1
+CB:Z:GTAAGCGCAGTTATCG-1
+CB:Z:CATCCTGGTGGAGCAA-1
+CB:Z:ATTAGTCCAGTTATGT-1
+CB:Z:TGTGGAGCAAACCTTG-1
+CB:Z:AGTGTGGCAGTTGCGT-1
+CB:Z:CGTTTGGAGTTCCTCA-1
+CB:Z:GTCCAAGTCCTTCGTA-1
+CB:Z:GGAACTAAGGCAATAG-1
+CB:Z:GCGCGATTCAATCTCT-1
+CB:Z:CGTTATCGTCATCAAG-1
+CB:Z:GCTAAGTTCGCCTGTT-1
+CB:Z:TCTCGCCCACAACCTA-1
+CB:Z:GGTAACCGTGTGTGGT-1
+CB:Z:CGTTGCGCACGGTTTA-1
+CB:Z:ACAAAGGTCGGCCAGT-1
+CB:Z:AAAGCACCAAGATTCT-1
+CB:Z:GGTACCGGTCATAGAT-1
+CB:Z:CTAACCTGTAATAGCT-1
+CB:Z:TTGGGCGGTACGGGTT-1
+CB:Z:GCGCCTTGTGCTGGTG-1
+CB:Z:AATCATGTCGGTACGC-1
+CB:Z:GAGTGATCAGTTTGGC-1
+CB:Z:GCGCAAACATCTAGCA-1
+CB:Z:AATCGCCCAGGCGAGT-1
+CB:Z:GGTGAGGTCCGGCTAA-1
+CB:Z:CCAGCCTGTTAGAGCC-1
+CB:Z:ACACTAGGTCACAAAT-1
+CB:Z:TTTGTCTAGAACAAGT-1
+CB:Z:GCAAGTCGTTTCCGGC-1
+CB:Z:GCTAACCCATGGCCCA-1
+CB:Z:CCCGTAAAGGTCCGTA-1
+CB:Z:TTGGAGGCATATAACC-1
+CB:Z:CCTGATGAGAAGCTAG-1
+CB:Z:CGATTTGCACCGGTAT-1
+CB:Z:CTCACACTCGACAAAG-1
+CB:Z:TGGCCTGCATAAGTCT-1
+CB:Z:TGTTATGAGCACAGCC-1
+CB:Z:GATAACGAGCGTGCGT-1
+CB:Z:TCTAGCCTCTTGCAGG-1
+CB:Z:TTTAAGGTCGATAACC-1
+CB:Z:CAGCTCAAGTACCGCA-1
+CB:Z:CCAGGAACAGGCTAGA-1
+CB:Z:TTTAGGATCATAGCCG-1
+CB:Z:GCGGTTATCGGTTTCC-1
+CB:Z:TGGTGCATCCGCAAGC-1
+CB:Z:GACGCCTAGCTCCTTA-1
+CB:Z:CGCATGATCCTGGTCT-1
+CB:Z:GAGTGAGGTACGCGCA-1
+CB:Z:GTAGGATCAAGGACCA-1
+CB:Z:TCGACAAGTGGATTCA-1
+CB:Z:GTGCTGGGTCGACTAA-1
+CB:Z:ATCAATCCAGCTTAAT-1
+CB:Z:AATTGGGAGTCCTGAG-1
+CB:Z:GGACTAAAGGCTATGT-1
+CB:Z:GGCTTCAAGACAACAG-1
+CB:Z:TGCTCTCAGCTTTGTT-1
+CB:Z:ATCCTGACAGTAGCCT-1
+CB:Z:AGTAACCTCCGCATGA-1
+CB:Z:GCTGTGCAGGATGATG-1
+CB:Z:CAAGTATGTTGAGCCG-1
+CB:Z:ATCCATAAGATAGACG-1
+CB:Z:GAGTATCTCATTGCAA-1
+CB:Z:CCTCAATGTGGACCTG-1
+CB:Z:ACAGTATGTTGTTGGA-1
+CB:Z:CTTTGGTGTTGTTGGA-1
+CB:Z:CTCTAAGCAAGGACCA-1
+CB:Z:CATTGTGCACTTACAG-1
+CB:Z:ACTGAAACAACAGCCT-1
+CB:Z:CCAGTTTGTAACCTAG-1
+CB:Z:GTATTGATCCTAGTAA-1
+CB:Z:ATGGACAAGGGACCTC-1
+CB:Z:TGCCGGTAGGACCGCT-1
+CB:Z:TGAGGGAGTGACCTGG-1
+CB:Z:TTTAAGGTCGCTCCAT-1
+CB:Z:CCGTTATGTAATCGTG-1
+CB:Z:ACTTACTTCCAAGTGT-1
+CB:Z:AAAGGAGCATAAACCT-1
+CB:Z:GTACACCCACACAATT-1
+CB:Z:CGCTAACCACTTACAG-1
+CB:Z:TCTAGCACAACAGCCT-1
+CB:Z:GGGCGAATCATGCATA-1
+CB:Z:ACGTCCAAGTACTGGT-1
+CB:Z:TCTTCAAGTACGTTTC-1
+CB:Z:GCACCTAAGCACAGGG-1
+CB:Z:CCATAGCCAGCCTGCA-1
+CB:Z:ATTATCCTCATAATCG-1
+CB:Z:GTTGCCCGTCCTTTAA-1
+CB:Z:CGTTAACAGCCTGATG-1
+CB:Z:TTGCACACAACTGGGA-1
+CB:Z:TCGACAAGTTAACGGC-1
+CB:Z:TCTTCAAGTGTTCCCA-1
+CB:Z:AAGCTCCCAGGACCAA-1
+CB:Z:CCGTTGCGTAAGCTTG-1
+CB:Z:CGTGTGTCATTAGCGC-1
+CB:Z:GCACTAAGTACTGAAT-1
+CB:Z:GTCCGTAAGCTACTGG-1
+CB:Z:GGGCATTGTGACATAT-1
+CB:Z:CTCTTGATCGAGCAAA-1
+CB:Z:CTGTTCATCGGGACTC-1
+CB:Z:GGTCAATTCCGTTATT-1
+CB:Z:GGTCTTTGTGTGTGGT-1
+CB:Z:ATCCCGCGTTTAGTCC-1
+CB:Z:TTAGGCGTCGATTTAG-1
+CB:Z:ATCCTTAGTGACCTGG-1
+CB:Z:ATCTATGAGTTATTCC-1
+CB:Z:TTTCTTGCAGACAAAC-1
+CB:Z:CAAACACTCCTACCTA-1
+CB:Z:TGCTCTCAGGCTACAT-1
+CB:Z:AGCTACTAGGTGCGGA-1
+CB:Z:GCTGACCAGGCGCTAC-1
+CB:Z:CGAAGTAAGCAGGTGG-1
+CB:Z:TGATCGAGTCCGCTGT-1
+CB:Z:ACGTCCTTCGTTACTT-1