Commit 314f9c6b authored by TomKellyGenetics's avatar TomKellyGenetics
Browse files

add whitelist for inDrop-v3 https://github.com/indrops/indrops/issues/32

parent 851a0751
Loading
Loading
Loading
Loading
+384 −0
Original line number Diff line number Diff line
AAACAAAC
AAACACGGT
AAACACTATC
AAACCGCCTCA
AAACGATC
AAACGTGAT
AAACTACATC
AAACTGTGTCA
AAAGAAAG
AAAGAGGCT
AAAGCCCGTC
AAAGTCATTCA
AAATAGCA
AAATTCCGT
AACAAATGTC
AACAGAACTCA
AACAGCGG
AACGATTTT
AACGCCAATC
AACGGTAGTCA
AACGTTAC
AACTCAGTT
AACTGCCTTC
AAGAACAGTCA
AAGAAGGT
AAGAGTATT
AAGCCTTCTC
AAGCTCCTTCA
AAGGATGA
AAGGCGCTT
AAGGGACCTC
AAGTATTGTCA
AAGTCCAA
AAGTCGGGT
AAGTGAGATC
AAGTTGTCTCA
AATAAGGA
AATACATCT
AATATGACTC
AATCCGGCTCA
AATCGAAG
AATCGTTCT
AATGGCGTTC
AATGTATGTCA
ACAAAGAT
ACAAGTAGT
ACAATCTTTC
ACACCAAGTCA
ACAGATAA
ACAGGCCAT
ACATCTCGTC
ACATGGACTCA
ACCAACCC
ACCAAGGGT
ACCACAGATC
ACCAGTTTTCA
ACCCATGC
ACCCGATTT
ACCCTCAATC
ACCGTCGATCA
ACCTGAAG
ACCTTCCCT
ACGAATTCTC
ACGACGACTCA
ACGCTTAA
ACGGAGCAT
ACGGCAGTTC
ACGGGTTATCA
ACGGTTGG
ACGTAAACT
ACTAATTGTC
ACTACCCGTCA
ACTAGAGC
ACTCATACT
ACTCGGAATC
ACTGCTGGTCA
ACTGGTCA
ACTTCGCTT
AGAAACCATC
AGAAAGTGTCA
AGAAGCTT
AGAATCAAT
AGACCTCATC
AGACGAGGTCA
AGAGAGAC
AGAGGTGCT
AGCAACGCTC
AGCACGTATCA
AGCATGCC
AGCCATCTT
AGCGTGGTTC
AGCTCCACTCA
AGCTTCGA
AGGACACAT
AGGAGTCGTC
AGGCAATATCA
AGGCCGAA
AGGCGTTTT
AGGGACTGTC
AGGGTAAATCA
AGGTAAGC
AGGTATATT
AGGTTCCCTC
AGTAATGGTCA
AGTAGTTA
AGTCACAAT
AGTCCGTGTC
AGTGCTTCTCA
AGTTGAAC
AGTTGCGGT
AGTTTGTATC
ATAACAGGTCA
ATAAGCTA
ATACACCCT
ATACTCTCTC
ATAGATGTTCA
ATATGCAA
ATATGGGTT
ATCAATCGTC
ATCAGGGATCA
ATCCCACC
ATCCGCATT
ATCCTAGTTC
ATCGCGCTTCA
ATCGTAAC
ATCTTGGCT
ATGACAACTC
ATGACTTGTCA
ATGCATAT
ATGCGGAGT
ATGGGCTCTC
ATGGTCTGTCA
ATGTGCCG
ATTACCTTT
ATTATTCGTC
ATTCTGAGTCA
ATTGAAGT
ATTGGCCCT
ATTTCCATTC
ATTTGTTGTCA
CAAACATT
CAACGCAGT
CAAGGAATTC
CAAGGGTTTCA
CAAGGTAC
CAATCTAGT
CAATTCTCTC
CACAACCTTCA
CACAAGTA
CACTAACCT
CACTTGATTC
CAGACTCGTCA
CAGATGGG
CAGGTTGCT
CAGTTTAATC
CATGACGATCA
CATGCTGC
CATTCATTT
CATTCGGGTC
CATTTCTATCA
CCACCTCT
CCACGTTGT
CCAGACAGTC
CCAGCGAATCA
CCATATGA
CCATCCACT
CCATCGTCTC
CCATGCATTCA
CCCGTAAG
CCCGTTCTT
CCCTCTTGTC
CCCTGTTTTCA
CCCTTGCA
CCGACTTTT
CCGAGATCTC
CCGATACGTCA
CCGGAAAT
CCGTAGCTT
CCGTCTTATC
CCTACGCTTCA
CCTATTTA
CCTCATGAT
CCTTTACATC
CCTTTGTCTCA
CGAAACTC
CGAACCGAT
CGAAGAAGTC
CGACATTTTCA
CGAGGCTA
CGATCCAAT
CGATGGCATC
CGGACTAATCA
CGGCTGTA
CGGTGAGTT
CGTACCGATC
CGTCGAATTCA
CGTGCAAC
CGTGGGATT
CGTGTACATC
CGTGTGTTTCA
CGTTGCCT
CGTTTCGTT
CTAACGCCTC
CTACGGGATCA
CTAGACTA
CTAGCACGT
CTAGTAGGTC
CTCAAACATCA
CTCACATC
CTCCCAAAT
CTCCTCCATC
CTCGGTGATCA
CTCTATAG
CTCTGCGTT
CTGAAGGGTC
CTGAGCGTTCA
CTGCGATG
CTGCTAGAT
CTGGAACATC
CTGGGTATTCA
CTGTCGCA
CTGTGACCT
CTGTTAAATC
CTGTTGTGTCA
CTGTTTCC
CTTAGGCCT
CTTAGTGTTC
CTTCTACGTCA
CTTTATCC
CTTTCACTT
CTTTGGACTC
GAAAGACATCA
GAAATACG
GAAGATATT
GAATCCCATC
GAATGCGCTCA
GACACAAA
GACACCTGT
GACTAGCGTC
GAGAAACCTCA
GAGCGGAA
GAGGAGTGT
GAGGGTCATC
GAGTGTACTCA
GATACGCA
GATGCAGAT
GATGGTTATC
GATGTGGCTCA
GATTAAAG
GATTACTTT
GATTGGGATC
GATTTCCCTCA
GCAAACTG
GCACTCAGT
GCATCACTTC
GCATCGAGTCA
GCCAAAGC
GCCAACATT
GCCTGGTATC
GCCTTGTGTCA
GCGCTGAT
GCGGTAACT
GCGTATTCTC
GCGTGCAATCA
GCTAAGTT
GCTACCGTT
GCTATGGGTC
GCTCGTAGTCA
GCTTCTCC
GGAACGAAT
GGAAGTCCTC
GGACTGGATCA
GGACTTCT
GGAGGTTTT
GGAGTAAGTC
GGATTGTTTCA
GGCAAGGT
GGCACTTCT
GGCCCAATTC
GGCGACAATCA
GGCTATAA
GGCTTTGCT
GGGAGATGTC
GGGATTACTCA
GGGCATCA
GGGTCATTT
GGGTCTAGTC
GGTAAATCTCA
GGTAGCCA
GGTCCTAAT
GGTCTTTCTC
GGTGTCGATCA
GGTTACAC
GGTTAGGGT
GGTTGAGATC
GTAAACAATCA
GTAAGCCG
GTAATCTGT
GTACGCTTTC
GTACGGACTCA
GTATACGT
GTATTGACT
GTCAAGAGTC
GTCAGACCTCA
GTCAGGTT
GTCCACTAT
GTCCGTCATC
GTCCTTGCTCA
GTCTAATC
GTCTGGAAT
GTCTTCCTTC
GTGAACTCTCA
GTGAGGCA
GTGATAAAT
GTGCCCATTC
GTGCGAAGTCA
GTGGTGCT
GTGTCACCT
GTGTCAGGTC
GTTACTAGTCA
GTTCTGCT
GTTGTCCGT
TAAACCGATC
TAACTTCTTCA
TAAGGGCC
TAATCCATT
TAATGTGGTC
TACCCTGCTCA
TACCGCTC
TACCTAAGT
TACCTCCCTC
TACGCGAGTCA
TACGTTCG
TACTGAATT
TAGATCAATC
TAGCCACATCA
TAGCGGAT
TAGGCTTTT
TAGGTACGTC
TAGTAGCCTCA
TAGTCTCT
TATCCACGT
TATCTGTCTC
TATGTGAATCA
TATTAGCG
TCAAATGGT
TCAAGGCGTC
TCAGCCTCTCA
TCATACCA
TCATAGCTT
TCATTTCATC
TCCAGAAGTCA
TCCCTGGA
TCCGACACT
TCCGCTGTTC
TCCTATATTCA
TCGACTGC
TCGAGTTTT
TCGCAATCTC
TCGGTCATTCA
TCGTGGGT
TCGTTCCCT
TCTAAACTTC
TCTATTCCTCA
TCTGATTT
TCTTTGACT
TGAATAGGTC
TGAATCCTTCA
TGACGTCG
TGAGAGCGT
TGAGCACATC
TGCACCAGTCA
TGCCGGTA
TGCGACTAT
TGCTGACGTC
TGCTTCATTCA
TGCTTGGG
TGGAAAGCT
TGGACGGATC
TGGCTAGTTCA
TGGGAATT
TGGTGTCTT
TGGTTAACTC
TGTTATCATCA
+384 −0
Original line number Diff line number Diff line
AAACAAAC
AAACACGG
AAACACTA
AAACCGCC
AAACGATC
AAACGTGA
AAACTACA
AAACTGTG
AAAGAAAG
AAAGAGGC
AAAGCCCG
AAAGTCAT
AAATAGCA
AAATTCCG
AACAAATG
AACAGAAC
AACAGCGG
AACGATTT
AACGCCAA
AACGGTAG
AACGTTAC
AACTCAGT
AACTGCCT
AAGAACAG
AAGAAGGT
AAGAGTAT
AAGCCTTC
AAGCTCCT
AAGGATGA
AAGGCGCT
AAGGGACC
AAGTATTG
AAGTCCAA
AAGTCGGG
AAGTGAGA
AAGTTGTC
AATAAGGA
AATACATC
AATATGAC
AATCCGGC
AATCGAAG
AATCGTTC
AATGGCGT
AATGTATG
ACAAAGAT
ACAAGTAG
ACAATCTT
ACACCAAG
ACAGATAA
ACAGGCCA
ACATCTCG
ACATGGAC
ACCAACCC
ACCAAGGG
ACCACAGA
ACCAGTTT
ACCCATGC
ACCCGATT
ACCCTCAA
ACCGTCGA
ACCTGAAG
ACCTTCCC
ACGAATTC
ACGACGAC
ACGCTTAA
ACGGAGCA
ACGGCAGT
ACGGGTTA
ACGGTTGG
ACGTAAAC
ACTAATTG
ACTACCCG
ACTAGAGC
ACTCATAC
ACTCGGAA
ACTGCTGG
ACTGGTCA
ACTTCGCT
AGAAACCA
AGAAAGTG
AGAAGCTT
AGAATCAA
AGACCTCA
AGACGAGG
AGAGAGAC
AGAGGTGC
AGCAACGC
AGCACGTA
AGCATGCC
AGCCATCT
AGCGTGGT
AGCTCCAC
AGCTTCGA
AGGACACA
AGGAGTCG
AGGCAATA
AGGCCGAA
AGGCGTTT
AGGGACTG
AGGGTAAA
AGGTAAGC
AGGTATAT
AGGTTCCC
AGTAATGG
AGTAGTTA
AGTCACAA
AGTCCGTG
AGTGCTTC
AGTTGAAC
AGTTGCGG
AGTTTGTA
ATAACAGG
ATAAGCTA
ATACACCC
ATACTCTC
ATAGATGT
ATATGCAA
ATATGGGT
ATCAATCG
ATCAGGGA
ATCCCACC
ATCCGCAT
ATCCTAGT
ATCGCGCT
ATCGTAAC
ATCTTGGC
ATGACAAC
ATGACTTG
ATGCATAT
ATGCGGAG
ATGGGCTC
ATGGTCTG
ATGTGCCG
ATTACCTT
ATTATTCG
ATTCTGAG
ATTGAAGT
ATTGGCCC
ATTTCCAT
ATTTGTTG
CAAACATT
CAACGCAG
CAAGGAAT
CAAGGGTT
CAAGGTAC
CAATCTAG
CAATTCTC
CACAACCT
CACAAGTA
CACTAACC
CACTTGAT
CAGACTCG
CAGATGGG
CAGGTTGC
CAGTTTAA
CATGACGA
CATGCTGC
CATTCATT
CATTCGGG
CATTTCTA
CCACCTCT
CCACGTTG
CCAGACAG
CCAGCGAA
CCATATGA
CCATCCAC
CCATCGTC
CCATGCAT
CCCGTAAG
CCCGTTCT
CCCTCTTG
CCCTGTTT
CCCTTGCA
CCGACTTT
CCGAGATC
CCGATACG
CCGGAAAT
CCGTAGCT
CCGTCTTA
CCTACGCT
CCTATTTA
CCTCATGA
CCTTTACA
CCTTTGTC
CGAAACTC
CGAACCGA
CGAAGAAG
CGACATTT
CGAGGCTA
CGATCCAA
CGATGGCA
CGGACTAA
CGGCTGTA
CGGTGAGT
CGTACCGA
CGTCGAAT
CGTGCAAC
CGTGGGAT
CGTGTACA
CGTGTGTT
CGTTGCCT
CGTTTCGT
CTAACGCC
CTACGGGA
CTAGACTA
CTAGCACG
CTAGTAGG
CTCAAACA
CTCACATC
CTCCCAAA
CTCCTCCA
CTCGGTGA
CTCTATAG
CTCTGCGT
CTGAAGGG
CTGAGCGT
CTGCGATG
CTGCTAGA
CTGGAACA
CTGGGTAT
CTGTCGCA
CTGTGACC
CTGTTAAA
CTGTTGTG
CTGTTTCC
CTTAGGCC
CTTAGTGT
CTTCTACG
CTTTATCC
CTTTCACT
CTTTGGAC
GAAAGACA
GAAATACG
GAAGATAT
GAATCCCA
GAATGCGC
GACACAAA
GACACCTG
GACTAGCG
GAGAAACC
GAGCGGAA
GAGGAGTG
GAGGGTCA
GAGTGTAC
GATACGCA
GATGCAGA
GATGGTTA
GATGTGGC
GATTAAAG
GATTACTT
GATTGGGA
GATTTCCC
GCAAACTG
GCACTCAG
GCATCACT
GCATCGAG
GCCAAAGC
GCCAACAT
GCCTGGTA
GCCTTGTG
GCGCTGAT
GCGGTAAC
GCGTATTC
GCGTGCAA
GCTAAGTT
GCTACCGT
GCTATGGG
GCTCGTAG
GCTTCTCC
GGAACGAA
GGAAGTCC
GGACTGGA
GGACTTCT
GGAGGTTT
GGAGTAAG
GGATTGTT
GGCAAGGT
GGCACTTC
GGCCCAAT
GGCGACAA
GGCTATAA
GGCTTTGC
GGGAGATG
GGGATTAC
GGGCATCA
GGGTCATT
GGGTCTAG
GGTAAATC
GGTAGCCA
GGTCCTAA
GGTCTTTC
GGTGTCGA
GGTTACAC
GGTTAGGG
GGTTGAGA
GTAAACAA
GTAAGCCG
GTAATCTG
GTACGCTT
GTACGGAC
GTATACGT
GTATTGAC
GTCAAGAG
GTCAGACC
GTCAGGTT
GTCCACTA
GTCCGTCA
GTCCTTGC
GTCTAATC
GTCTGGAA
GTCTTCCT
GTGAACTC
GTGAGGCA
GTGATAAA
GTGCCCAT
GTGCGAAG
GTGGTGCT
GTGTCACC
GTGTCAGG
GTTACTAG
GTTCTGCT
GTTGTCCG
TAAACCGA
TAACTTCT
TAAGGGCC
TAATCCAT
TAATGTGG
TACCCTGC
TACCGCTC
TACCTAAG
TACCTCCC
TACGCGAG
TACGTTCG
TACTGAAT
TAGATCAA
TAGCCACA
TAGCGGAT
TAGGCTTT
TAGGTACG
TAGTAGCC
TAGTCTCT
TATCCACG
TATCTGTC
TATGTGAA
TATTAGCG
TCAAATGG
TCAAGGCG
TCAGCCTC
TCATACCA
TCATAGCT
TCATTTCA
TCCAGAAG
TCCCTGGA
TCCGACAC
TCCGCTGT
TCCTATAT
TCGACTGC
TCGAGTTT
TCGCAATC
TCGGTCAT
TCGTGGGT
TCGTTCCC
TCTAAACT
TCTATTCC
TCTGATTT
TCTTTGAC
TGAATAGG
TGAATCCT
TGACGTCG
TGAGAGCG
TGAGCACA
TGCACCAG
TGCCGGTA
TGCGACTA
TGCTGACG
TGCTTCAT
TGCTTGGG
TGGAAAGC
TGGACGGA
TGGCTAGT
TGGGAATT
TGGTGTCT
TGGTTAAC
TGTTATCA
+147072 −0

File added.

Preview size limit exceeded, changes collapsed.

+5 −0
Original line number Diff line number Diff line
@@ -778,7 +778,12 @@ else
    elif [[ "$technology" == "icell8" ]]; then
        barcodefile=${SDIR}/iCell8_barcode.txt
    elif [[ "$technology" == "indrop-v1" ]] || [[ "$technology" == "indrop-v2" ]]; then
        # use bustools whitelist for inDrops-v2 with adapters removed https://github.com/BUStools/bustools/issues/4 
        barcodefile=${SDIR}/inDrops_barcodes.txt
    elif [[ "$technology" == "indrop-v3" ]];
        # inDrops-v3 whitelist is a combination of v2 whitelists https://github.com/indrops/indrops/issues/32
        ## version 2 whitelist will be used until dual indexing (i7) is supported for read I2: https://github.com/alexdobin/STAR/issues/825
        barcodefile=${SDIR}/inDrops-v2_barcodes.txt 
    elif [[ "$technology" == "quartz-seq2-384" ]]; then
        barcodefile=${SDIR}/Quartz-Seq2-384_barcode.txt
    elif [[ "$technology" == "quartz-seq2-1536" ]]; then