Commit 45b96ac4 authored by TomKellyGenetics's avatar TomKellyGenetics
Browse files

correct indrops v1 and v2 barcodes to use reverse complement sequence

parent 35be04d3
Loading
Loading
Loading
Loading
+3 −2
Original line number Diff line number Diff line
@@ -1811,7 +1811,7 @@ else
            echo "  barcode adjusted to ${barcodelength} bp to match the length in the default whitelist for ${technology}"
        fi
        if [[ "$technology" == "indrop-v1" ]] || [[ "$technology" == "indrop-v2" ]]; then
            barcodefile=${whitelistdir}/inDrop-v2_barcodes.txt
            barcodefile=${whitelistdir}/inDrop-v1_barcodes.txt
        elif [[ "$technology" == "indrop-v3" ]]; then
            barcodefile=${whitelistdir}/inDrop-v3_barcodes.txt
            echo "***WARNING: combination of list1 and list2 from indrop-v2 (https://github.com/indrops/indrops/issues/32)***"  
@@ -1914,7 +1914,8 @@ else
            fi
        elif [[ "$technology" == "indrop-v"* ]]; then
            if [[ "$technology" == "indrop-v1" ]] || [[ $technology"" == "indrop-v2" ]]; then
                perl ${MAKEINDROPBARCODES} ${whitelistdir}/inDrop_gel_barcode1_list.txt ${whitelistdir}/inDrop_gel_barcode2_list.txt v2 ${whitelistdir}
                sed -E 's/.*(.{8})/\1/g' ${whitelistdir}/inDrop_gel_barcode1_list_revcomp.txt > ${whitelistdir}/inDrop_gel_barcode1_list_revcomp_tail.txt
                perl ${MAKEINDROPBARCODES} ${whitelistdir}/inDrop_gel_barcode1_list_revcomp_tail.txt ${whitelistdir}/inDrop_gel_barcode2_list_revcomp.txt v1 ${whitelistdir}
            elif [[ "$technology" == "indrop-v3" ]]; then
                #allow for barcodes in index (I1) and R1
                perl ${MAKEINDROPBARCODES} ${whitelistdir}/inDrop_gel_barcode1_list.txt ${whitelistdir}/inDrop_gel_barcode2_list.txt v3 ${whitelistdir}
+8 −1
Original line number Diff line number Diff line
@@ -33,7 +33,14 @@ my $length = scalar (@list1);


my @list12;
if ($version =~ m/v2/) {
if ($version =~ m/v1/) {
    for (my $i = 0; $i < $length; $i++) {
        my $element1 = substr ($list1[$i], 0, 8);
        my $element12 = $element1.$list2[$i];
        push (@list12, $element12);
    }
}
elsif ($version =~ m/v2/) {
    for (my $i = 0; $i < $length; $i++) {
        my $element1 = substr ($list1[$i], 0, 8);
        my $element12 = $element1.$list2[$i];
+384 −0
Original line number Diff line number Diff line
GTTTGTTT
ACCGTGTTT
GATAGTGTTT
TGAGGCGGTTT
GATCGTTT
ATCACGTTT
GATGTAGTTT
TGACACAGTTT
CTTTCTTT
AGCCTCTTT
GACGGGCTTT
TGAATGACTTT
TGCTATTT
ACGGAATTT
GACATTTGTT
TGAGTTCTGTT
CCGCTGTT
AAAATCGTT
GATTGGCGTT
TGACTACCGTT
GTAACGTT
AACTGAGTT
GAAGGCAGTT
TGACTGTTCTT
ACCTTCTT
AATACTCTT
GAGAAGGCTT
TGAAGGAGCTT
TCATCCTT
AAGCGCCTT
GAGGTCCCTT
TGACAATACTT
TTGGACTT
ACCCGACTT
GATCTCACTT
TGAGACAACTT
TCCTTATT
AGATGTATT
GAGTCATATT
TGAGCCGGATT
CTTCGATT
AGAACGATT
GAACGCCATT
TGACATACATT
ATCTTTGT
ACTACTTGT
GAAAGATTGT
TGACTTGGTGT
TTATCTGT
ATGGCCTGT
GACGAGATGT
TGAGTCCATGT
GGGTTGGT
ACCCTTGGT
GATCTGTGGT
TGAAAACTGGT
GCATGGGT
AAATCGGGT
GATTGAGGGT
TGATCGACGGT
CTTCAGGT
AGGGAAGGT
GAGAATTCGT
TGAGTCGTCGT
TTAAGCGT
ATGCTCCGT
GAACTGCCGT
TGATAACCCGT
CCAACCGT
AGTTTACGT
GACAATTAGT
TGACGGGTAGT
GCTCTAGT
AGTATGAGT
GATTCCGAGT
TGACCAGCAGT
TGACCAGT
AAGCGAAGT
GATGGTTTCT
TGACACTTTCT
AAGCTTCT
ATTGATTCT
GATGAGGTCT
TGACCTCGTCT
GTCTCTCT
AGCACCTCT
GAGCGTTGCT
TGATACGTGCT
GGCATGCT
AAGATGGCT
GAACCACGCT
TGAGTGGAGCT
TCGAAGCT
ATGTGTCCT
GACGACTCCT
TGATATTGCCT
TTCGGCCT
AAAACGCCT
GACAGTCCCT
TGATTTACCCT
GCTTACCT
AATATACCT
GAGGGAACCT
TGACCATTACT
TAACTACT
ATTGTGACT
GACACGGACT
TGAGAAGCACT
GTTCAACT
ACCGCAACT
GATACAAACT
TGACCTGTTAT
TAGCTTAT
AGGGTGTAT
GAGAGAGTAT
TGAACATCTAT
TTGCATAT
AACCCATAT
GACGATTGAT
TGATCCCTGAT
GGTGGGAT
AATGCGGAT
GAACTAGGAT
TGAAGCGCGAT
GTTACGAT
AGCCAAGAT
GAGTTGTCAT
TGACAAGTCAT
ATATGCAT
ACTCCGCAT
GAGAGCCCAT
TGACAGACCAT
CGGCACAT
AAAGGTAAT
GACGAATAAT
TGACTCAGAAT
ACTTCAAT
AGGGCCAAT
GAATGGAAAT
TGACAACAAAT
AATGTTTG
ACTGCGTTG
GAATTCCTTG
TGAAACCCTTG
GTACCTTG
ACTAGATTG
GAGAGAATTG
TGAAGGTTGTG
TACTTGTG
AGGTTAGTG
GAATCAAGTG
TGACGAGTCTG
CCCATCTG
AGCAACCTG
GATTAAACTG
TGATCGTCATG
GCAGCATG
AAATGAATG
GACCCGAATG
TGATAGAAATG
AGAGGTGG
ACAACGTGG
GACTGTCTGG
TGATTCGCTGG
TCATATGG
AGTGGATGG
GAGACGATGG
TGAATGCATGG
CTTACGGG
AAGAACGGG
GACAAGAGGG
TGAAAACAGGG
TGCAAGGG
AAAAGTCGG
GAGATCTCGG
TGACGTATCGG
ATTTCCGG
AAGCTACGG
GATAAGACGG
TGAAGCGTAGG
TAAATAGG
ATCATGAGG
GATGTAAAGG
TGAGACAAAGG
GAGTTTCG
ATCGGTTCG
GACTTCTTCG
TGAAAATGTCG
TAGCCTCG
ATTGGATCG
GATGCCATCG
TGATTAGTCCG
TACAGCCG
AACTCACCG
GATCGGTACG
TGAATTCGACG
GTTGCACG
AATCCCACG
GATGTACACG
TGAAACACACG
AGGCAACG
AACGAAACG
GAGGCGTTAG
TGATCCCGTAG
TAGTCTAG
ACGTGCTAG
GACCTACTAG
TGATGTTTGAG
GATGTGAG
ATTTGGGAG
GATGGAGGAG
TGATCACCGAG
CTATAGAG
AACGCAGAG
GACCCTTCAG
TGAACGCTCAG
CATCGCAG
ATCTAGCAG
GATGTTCCAG
TGAATACCCAG
TGCGACAG
AGGTCACAG
GATTTAACAG
TGACACAACAG
GGAAACAG
AGGCCTAAG
GAACACTAAG
TGACGTAGAAG
GGATAAAG
AAGTGAAAG
GAGTCCAAAG
TGATGTCTTTC
CGTATTTC
AATATCTTC
GATGGGATTC
TGAGCGCATTC
TTTGTGTC
ACAGGTGTC
GACGCTAGTC
TGAGGTTTCTC
TTCCGCTC
ACACTCCTC
GATGACCCTC
TGAGTACACTC
TGCGTATC
ATCTGCATC
GATAACCATC
TGAGCCACATC
CTTTAATC
AAAGTAATC
GATCCCAATC
TGAGGGAAATC
CAGTTTGC
ACTGAGTGC
GAAGTGATGC
TGACTCGATGC
GCTTTGGC
AATGTTGGC
GATACCAGGC
TGACACAAGGC
ATCAGCGC
AGTTACCGC
GAGAATACGC
TGATTGCACGC
AACTTAGC
AACGGTAGC
GACCCATAGC
TGACTACGAGC
GGAGAAGC
ATTCGTTCC
GAGGACTTCC
TGATCCAGTCC
AGAAGTCC
AAAACCTCC
GACTTACTCC
TGAAACAATCC
ACCTTGCC
AGAAGTGCC
GAATTGGGCC
TGATTGTCGCC
TTATAGCC
AGCAAAGCC
GACATCTCCC
TGAGTAATCCC
TGATGCCC
AAATGACCC
GACTAGACCC
TGAGATTTACC
TGGCTACC
ATTAGGACC
GAGAAAGACC
TGATCGACACC
GTGTAACC
ACCCTAACC
GATCTCAACC
TGATTGTTTAC
CGGCTTAC
ACAGATTAC
GAAAGCGTAC
TGAGTCCGTAC
ACGTATAC
AGTCAATAC
GACTCTTGAC
TGAGGTCTGAC
AACCTGAC
ATAGTGGAC
GATGACGGAC
TGAGCAAGGAC
GATTAGAC
ATTCCAGAC
GAAGGAAGAC
TGAGAGTTCAC
TGCCTCAC
ATTTATCAC
GAATGGGCAC
TGACTTCGCAC
AGCACCAC
AGGTGACAC
GACCTGACAC
TGACTAGTAAC
AGCAGAAC
ACGGACAAC
GATCGGTTTA
TGAAGAAGTTA
GGCCCTTA
AATGGATTA
GACCACATTA
TGAGCAGGGTA
GAGCGGTA
ACTTAGGTA
GAGGGAGGTA
TGACTCGCGTA
CGAACGTA
AATTCAGTA
GATTGATCTA
TGATGTGGCTA
ATCCGCTA
AAAAGCCTA
GACGTACCTA
TGAGGCTACTA
AGAGACTA
ACGTGGATA
GAGACAGATA
TGATTCACATA
CGCTAATA
ACCATTTGA
GACGCCTTGA
TGAGAGGCTGA
TGGTATGA
AAGCTATGA
GATGAAATGA
TGACTTCTGGA
TCCAGGGA
AGTGTCGGA
GAACAGCGGA
TGAATATAGGA
GCAGTCGA
AAAACTCGA
GAGATTGCGA
TGAATGACCGA
ACCCACGA
AGGGAACGA
GAAGTTTAGA
TGAGGAATAGA
AAATCAGA
AGTCAAAGA
GACCTATTCA
TGAAGGATTCA
CGACGTCA
ACGCTCTCA
GATGTGCTCA
TGACTGGTGCA
TACCGGCA
ATAGTCGCA
GACGTCAGCA
TGAATGAAGCA
CCCAAGCA
AGCTTTCCA
GATCCGTCCA
TGAACTAGCCA
AATTCCCA
AAGACACCA
GAGTTAACCA
TGATGATAACA
+384 −0
Original line number Diff line number Diff line
GTTTGTTT
CCGTGTTT
TAGTGTTT
GGCGGTTT
GATCGTTT
TCACGTTT
TGTAGTTT
CACAGTTT
CTTTCTTT
GCCTCTTT
CGGGCTTT
ATGACTTT
TGCTATTT
CGGAATTT
CATTTGTT
GTTCTGTT
CCGCTGTT
AAATCGTT
TTGGCGTT
CTACCGTT
GTAACGTT
ACTGAGTT
AGGCAGTT
CTGTTCTT
ACCTTCTT
ATACTCTT
GAAGGCTT
AGGAGCTT
TCATCCTT
AGCGCCTT
GGTCCCTT
CAATACTT
TTGGACTT
CCCGACTT
TCTCACTT
GACAACTT
TCCTTATT
GATGTATT
GTCATATT
GCCGGATT
CTTCGATT
GAACGATT
ACGCCATT
CATACATT
ATCTTTGT
CTACTTGT
AAGATTGT
CTTGGTGT
TTATCTGT
TGGCCTGT
CGAGATGT
GTCCATGT
GGGTTGGT
CCCTTGGT
TCTGTGGT
AAACTGGT
GCATGGGT
AATCGGGT
TTGAGGGT
TCGACGGT
CTTCAGGT
GGGAAGGT
GAATTCGT
GTCGTCGT
TTAAGCGT
TGCTCCGT
ACTGCCGT
TAACCCGT
CCAACCGT
GTTTACGT
CAATTAGT
CGGGTAGT
GCTCTAGT
GTATGAGT
TTCCGAGT
CCAGCAGT
TGACCAGT
AGCGAAGT
TGGTTTCT
CACTTTCT
AAGCTTCT
TTGATTCT
TGAGGTCT
CCTCGTCT
GTCTCTCT
GCACCTCT
GCGTTGCT
TACGTGCT
GGCATGCT
AGATGGCT
ACCACGCT
GTGGAGCT
TCGAAGCT
TGTGTCCT
CGACTCCT
TATTGCCT
TTCGGCCT
AAACGCCT
CAGTCCCT
TTTACCCT
GCTTACCT
ATATACCT
GGGAACCT
CCATTACT
TAACTACT
TTGTGACT
CACGGACT
GAAGCACT
GTTCAACT
CCGCAACT
TACAAACT
CCTGTTAT
TAGCTTAT
GGGTGTAT
GAGAGTAT
ACATCTAT
TTGCATAT
ACCCATAT
CGATTGAT
TCCCTGAT
GGTGGGAT
ATGCGGAT
ACTAGGAT
AGCGCGAT
GTTACGAT
GCCAAGAT
GTTGTCAT
CAAGTCAT
ATATGCAT
CTCCGCAT
GAGCCCAT
CAGACCAT
CGGCACAT
AAGGTAAT
CGAATAAT
CTCAGAAT
ACTTCAAT
GGGCCAAT
ATGGAAAT
CAACAAAT
AATGTTTG
CTGCGTTG
ATTCCTTG
AACCCTTG
GTACCTTG
CTAGATTG
GAGAATTG
AGGTTGTG
TACTTGTG
GGTTAGTG
ATCAAGTG
CGAGTCTG
CCCATCTG
GCAACCTG
TTAAACTG
TCGTCATG
GCAGCATG
AATGAATG
CCCGAATG
TAGAAATG
AGAGGTGG
CAACGTGG
CTGTCTGG
TTCGCTGG
TCATATGG
GTGGATGG
GACGATGG
ATGCATGG
CTTACGGG
AGAACGGG
CAAGAGGG
AAACAGGG
TGCAAGGG
AAAGTCGG
GATCTCGG
CGTATCGG
ATTTCCGG
AGCTACGG
TAAGACGG
AGCGTAGG
TAAATAGG
TCATGAGG
TGTAAAGG
GACAAAGG
GAGTTTCG
TCGGTTCG
CTTCTTCG
AAATGTCG
TAGCCTCG
TTGGATCG
TGCCATCG
TTAGTCCG
TACAGCCG
ACTCACCG
TCGGTACG
ATTCGACG
GTTGCACG
ATCCCACG
TGTACACG
AACACACG
AGGCAACG
ACGAAACG
GGCGTTAG
TCCCGTAG
TAGTCTAG
CGTGCTAG
CCTACTAG
TGTTTGAG
GATGTGAG
TTTGGGAG
TGGAGGAG
TCACCGAG
CTATAGAG
ACGCAGAG
CCCTTCAG
ACGCTCAG
CATCGCAG
TCTAGCAG
TGTTCCAG
ATACCCAG
TGCGACAG
GGTCACAG
TTTAACAG
CACAACAG
GGAAACAG
GGCCTAAG
ACACTAAG
CGTAGAAG
GGATAAAG
AGTGAAAG
GTCCAAAG
TGTCTTTC
CGTATTTC
ATATCTTC
TGGGATTC
GCGCATTC
TTTGTGTC
CAGGTGTC
CGCTAGTC
GGTTTCTC
TTCCGCTC
CACTCCTC
TGACCCTC
GTACACTC
TGCGTATC
TCTGCATC
TAACCATC
GCCACATC
CTTTAATC
AAGTAATC
TCCCAATC
GGGAAATC
CAGTTTGC
CTGAGTGC
AGTGATGC
CTCGATGC
GCTTTGGC
ATGTTGGC
TACCAGGC
CACAAGGC
ATCAGCGC
GTTACCGC
GAATACGC
TTGCACGC
AACTTAGC
ACGGTAGC
CCCATAGC
CTACGAGC
GGAGAAGC
TTCGTTCC
GGACTTCC
TCCAGTCC
AGAAGTCC
AAACCTCC
CTTACTCC
AACAATCC
ACCTTGCC
GAAGTGCC
ATTGGGCC
TTGTCGCC
TTATAGCC
GCAAAGCC
CATCTCCC
GTAATCCC
TGATGCCC
AATGACCC
CTAGACCC
GATTTACC
TGGCTACC
TTAGGACC
GAAAGACC
TCGACACC
GTGTAACC
CCCTAACC
TCTCAACC
TTGTTTAC
CGGCTTAC
CAGATTAC
AAGCGTAC
GTCCGTAC
ACGTATAC
GTCAATAC
CTCTTGAC
GGTCTGAC
AACCTGAC
TAGTGGAC
TGACGGAC
GCAAGGAC
GATTAGAC
TTCCAGAC
AGGAAGAC
GAGTTCAC
TGCCTCAC
TTTATCAC
ATGGGCAC
CTTCGCAC
AGCACCAC
GGTGACAC
CCTGACAC
CTAGTAAC
AGCAGAAC
CGGACAAC
TCGGTTTA
AGAAGTTA
GGCCCTTA
ATGGATTA
CCACATTA
GCAGGGTA
GAGCGGTA
CTTAGGTA
GGGAGGTA
CTCGCGTA
CGAACGTA
ATTCAGTA
TTGATCTA
TGTGGCTA
ATCCGCTA
AAAGCCTA
CGTACCTA
GGCTACTA
AGAGACTA
CGTGGATA
GACAGATA
TTCACATA
CGCTAATA
CCATTTGA
CGCCTTGA
GAGGCTGA
TGGTATGA
AGCTATGA
TGAAATGA
CTTCTGGA
TCCAGGGA
GTGTCGGA
ACAGCGGA
ATATAGGA
GCAGTCGA
AAACTCGA
GATTGCGA
ATGACCGA
ACCCACGA
GGGAACGA
AGTTTAGA
GGAATAGA
AAATCAGA
GTCAAAGA
CCTATTCA
AGGATTCA
CGACGTCA
CGCTCTCA
TGTGCTCA
CTGGTGCA
TACCGGCA
TAGTCGCA
CGTCAGCA
ATGAAGCA
CCCAAGCA
GCTTTCCA
TCCGTCCA
ACTAGCCA
AATTCCCA
AGACACCA
GTTAACCA
TGATAACA