Commit ddb32220 authored by TomKellyGenetics's avatar TomKellyGenetics
Browse files

metadata documenting how published data was prepared

parent aa068096
Loading
Loading
Loading
Loading
+2 −1
Original line number Diff line number Diff line
@@ -11,7 +11,8 @@ Study Accession: EGAS00001002320
https://ega-archive.org/studies/EGAS00001002320
Data Accession: EGAD00001003443
https://ega-archive.org/datasets/EGAD00001003443

File Accession: EGAF00001698000
Sample: 72618_KU812 (Human KU812 cells)

## Data preparations
Filtered for regions mapping to HUMAN_21:9825832-48085036 GRCh38 (hg38)
+0 −18
Original line number Diff line number Diff line
/sequencedata/Hiseq2000/190408_D00364_0405_BHWLL2BCX2/Unaligned_for_Lane1/Project_LS3492_RNhi10764_Lane1/Sample_RNhi10764_190408_D00364_0405_BHWLL2BCX2/

HiSeq2000 run on 2019/04/08 (1 lanes in rapid mode): Project_LS3492

Tissue: MCF10A (breast cell line)

Species: Homo sapiens (Human)

Sample Provider: Shiori Aki (Umeda Lab, NAIST)

Samples Prepared: Nicola Hetherington (RIKEN IMS)

Single-cell (iCELL8)

iCELL8 initiated: 
    2019/01/24 (iCELL8_01)

Note that UMI iCELL8 runs are being sequenced for comparison
+1513 −0
Original line number Diff line number Diff line
GTTGGATAGCC
GTTGAGCTGCG
CCTCCGCCTGC
CCGTCCTCAGT
TGGTACTATAT
AAGAGAGACGC
GGCTCGTTAGC
ATTATATCTCA
ATGGCCGTATG
AAGAATTGCAT
ATTCCGAGCGG
AAGAATAACGA
TCAATTACGAC
CGGTTGGTAGA
CCGTCCGTCGA
CCAGACCAACC
TTGGAGAGTAG
CAATAGAATGG
GGTCATAATGG
TCAGAGCCTCG
GTTATCGGACC
GTTGGCGCGAC
GGTATAGACTA
AGAAGCCTTGG
TTGATTCAGAT
TGCGGTTCCTG
ATTGCGTTCAA
GCTTATGCTGC
TTGAGAGTTCC
CCTCCAACCGA
GCTGCAACCTT
ACGCAATCCTT
TGCCTCTTCTG
CGGTTGCCAGC
CGAATCTAATT
AACTCTAGTAT
GGTTCAAGCAG
CCATCTGAGAT
ACTTCAGCGAT
AGAACTATGGT
CCGGTCATCTA
GCAACCGCTCC
CCTCTCTCATT
TGGAGTATATT
AACCTACGCGC
ACGTACGGAAG
GTCTGGTCCTT
AACTTATTGCA
GGTTCGTCTTG
TGCTCTCTAGG
AGAACCGCTTC
CTATCAGCATC
TGGTCCGCATC
TAACCTCCGCG
GGCGTCCGTTG
TCGTATTCGCC
GCTTGCCTTCG
TTGGAACGTAA
CTGGTTGCTGG
CCTATCGTTGA
AGAACCATAGG
AAGAGAGAACG
AACTAACCTTG
TGGATGGCAGT
TGGCCGAGCTG
CCATAGCCTCA
CCTCCGAGGAC
AAGAACTAATC
GGTATCTCTCG
AGAATCAGTCT
GGTTCCGTTGC
AACGCTCCGGA
AAGAGCAGAGC
AGGTTAGTACG
TGGATATTGCC
TCGTTGCGTAC
GCCAGCCGAAC
TGCGGATGGTT
GGCGGCTGCGA
TAGCTAAGGCG
CCTCTTACCTT
GTTGGCAACGG
GTAGGACCGAG
CGTTAGATACC
GGTTAAGTCTG
AACTCATAGGA
AAGACCGCCAT
CAGCTTGGATT
GCTTATGGAGT
CGATGGTAATA
TTCCTCGCATA
GGTTACTCCTT
GCTGGAGTAGG
TAACCTTCCGG
GAAGAGCGGTC
AGAATCCGCAT
TGCGGCATATC
TTGATTAGCCA
AACGCTGGATT
AGGAACGATCA
GGTACGGTACC
GGTAACCTGAC
CCTCGTATTCG
CGCCAACTCGG
TTGCTCTCAAG
CCAATTGCTAG
CCTCAGAACCG
AACCAAGAACG
ACCAGAACTCT
CCAAGACTTCT
GAAGCGCTTCC
GTTCGGCGGAT
CCGCATCGAGT
TTGCTTACGGA
AACCGCAAGAA
CGTTGGCCTGA
AGTCTGGCGCT
GAACCTCGTCG
GATTCTAGGTT
TACGATCTACG
GGCGTTGACTG
TAGGTCGTCCT
TGAGTTGCTCA
AACTGAGAAGG
GTTCAATTATG
GAAGATTCCTT
GTAAGCGCGCG
ACCAGCTCTTG
CTTGGATAACT
ATTGATAGTCC
GAACGGAGAGT
TCAGGAACCTC
TTCGTATACGT
AGGTCGTACGC
AGAAGTCATAG
GTCTAACCTTA
ACCATCGGATG
GAATAAGTCAA
CCAGGCCAGTC
AACTGGTAGCA
GTCTATGGCAA
CCAGTTAGGTA
GGTAGCCTTGC
AGAACCGATAA
CTCCTCCGTAG
TGGTAACTGCT
GCGAGCTGAAT
AACCGCAACCT
CTTCTTGACGG
GTAACTTGGCA
CCAGAAGATAG
ACGAGACGGCT
GGTAGTCTCCA
TTCGGCTTGGA
CCATTCCTTAC
CGGCGCGGCGA
GAACCGTCAGG
CCGCCATGCCA
CCTATTCATAT
AACCTTGCAAG
TTCTTACTTGC
TCGGAGCAGAG
TCTATACGATG
GGTTGGTCATA
CGTCTCAATTA
TTGGTTGAATC
AACGAGACGTC
TGGCAGGATGC
CAACCAGTTGC
TGCGTAGGTAA
ACGACCTAGGC
CATCCGCTCAT
CTCTATCTCAG
AACGGATCAAT
AACTCGCATGG
GTCGCGAGTAA
GAAGACGTCCT
AAGAACGCCGG
CGGATTGCTGA
GTTCGTCGTTC
AACCATCGTTC
CGAACCGGATT
CCGTCTGCGAA
CGCCTCAGGAG
TTGCTAGACCT
CCTAAGTCCTC
TTGGATCAGAA
CCAACTCCGAT
TGGCTGAGGCC
CCTGGCCTTCA
GTTGACCTCGG
TCAATCAACCG
TTCGCGCGTCA
CGTTGCTGGAT
CCGAACTGGAG
AACGATAGCAT
TTGATATACTA
TGAGGTTGGCT
CCTAACTAATT
TGCTGGTTGGA
CCTCGGTCTAT
ATATGCGTTAG
GTCTGCAACGC
ACCAACTCTCA
GGTATCCGTCC
AACCTTATCGG
GAACGGACCTC
TGCCGGCGCGC
CCAGCATTCGC
CCAATGCCGCA
CCTCGCTCGTA
AAGACTAAGCT
CCTCAAGCTAG
CCGTAACTATT
TTGAGACGGAT
GTTGAGTCAAC
GGAGTTCGTCT
GTATGATCTAC
GGAGCGTTGGT
CCAATATATTA
GCAGAGCTCGA
GTTGCATTCCT
GGTAAGATCTC
TGAGGTATCTC
AACGTAATCGC
ACGAATAATCT
TTCAGGTAGGA
CCGCAACTAGG
TTGAATTAATA
GATGAGAGTAA
ATGCAGTAACG
GTATGCCTCTG
AACTACCGCGA
GCTATTGACTG
GGTTCTCAGCA
TTGGCAGTCGC
TTGATGGATCT
AGAACCTGGAA
CCAATGCTGGT
TGGACTATACC
GCGCCAGCCTG
TATCTGGCTGG
TCGTTCAATCC
GTAATTGCTCT
GTCGGTTCCAT
GCTCCGCTTCG
TGGCGTTATCT
CCAGCGCCAGT
CCTAGATAATA
CCGCGCTCTTC
GGTAAGTAATA
ACCAAGATATG
CAACTAACCGA
ATCTTGGACCT
CCAACTAGTCA
CGGAGGCTGCC
CCTGCCGATCG
AAGAGATAAGT
GCGGTATAAGC
AACTGCCTTGC
AGAAGTAACTG
GTTCGGTTCTT
CGCTTCTGCTC
CCGAACTCTAC
CGGAGTAACTA
CTGGATACTGC
CCATCAATTAG
GTTGATCATAG
AACGTCTCATA
GTACTGGCGCC
CCTCAGGAGAG
TAACCATCGAT
TGGTAGCTATA
AGGCTTAGATA
TCGTTGGTCCG
GTATATCGAAC
AACGGAACGTT
CGCGCCGGATA
TGAGGCCTTCA
CGGTAGAGGAC
CCGTTACCTCG
GCTCGCCTGAC
CGGTATCCTGC
AACTTCCATTC
GGTTGGTAACG
TTATACGTATC
GGAGGCGGAGA
GGTATTCCTGG
TATATCGGAGG
AACGGAGATAG
CGGCTGCGTCA
GCTTGGATAGT
GTAGCCGAGAA
AACGACGGCAA
GGATCTCTCAA
CTAGCTCCTAT
AACCTTGATGA
AACCTCGGCTT
AACGATCTCCA
GACTTGCATAA
CATGGTTGCTC
CGTAGCAGTTA
TGGATCGGTCT
GAGTTCTAGGA
ACCAAGCGAGA
GTTATAATTCT
GTATTGCCTGA
ATGGAGATGGC
GCGAACGCTGC
AACTTGCTCTT
CCAATTCGACC
TTCAGCGGCGA
TTGGCAGCTTG
AACTCCAGCAA
CGGTATCTTAA
GCGGTTGATAA
ACCTCTCTTGG
AACGCGCGGTT
AACGCAAGCGA
AACCTAACTCA
CCAAGCGCATG
CTACGCGAGCA
TGACTGAGGAA
TCGACCAAGAG
CTAGCTCAAGA
GGATGGATACG
GTTGATACGCG
GTATCCTAATC
AAGAGATCATG
AACCGCAGCTG
CCATAAGGATG
GCGTTGGCCGC
AACCTGAGGCA
GCTGGCGGCGC
CCGGTTGACGG
CTCCATCTGCG
CGATGATGAGC
AAGAATCGGTT
GTTATTCCATC
ACCAACCAGAG
TGGTTACTTCA
CAGCAACTCTT
CGAACCATCGA
TTATGACGCAG
GTATTATGCGT
CCAAGCTAGGA
AACTGGCTACT
GTTGAATAGTA
CCTCAGTTCAA
TATTGATCCAA
TGGATCTCCAG
GTTGACTATAC
CTCTAACTAGA
CCAACCTATTG
TGGTTCGGAAG
GTTAAGTTCGC
AAGAGAAGAAT
CTGGATTCCTT
AGAACTGACCA
GTTGGCTAGAA
CGTAGGTTGAC
GATTAGATTCT
CCTCTAAGGAG
GTAGTTCTGCC
CGTTGATTGGC
AACTGCCGGAT
TCATGGCGCGA
TTCTTAAGTAT
AACGCAGAAGC
AGAACTAGCAG
TTCGCCAGGCC
CCATATGGCGC
CAACCTAACGG
AACTTACGGAG
TTGCCTGATGA
CGAACCGAGAG
GGCTGGTAGGT
GAACTTGGTTG
CGACCATCGAA
CTCCAGCCTTC
ACGAATACGCA
AAGAACCGAAT
CTCCTAACTTC
AGAAGCGGAAC
TGAACCAATTG
TCAGTTCATAA
AACGCGCAACG
GCAGCCTCAAT
CCAAGCTTGCC
AACTAATTCAG
TAACGAGCTCT
CTAATCTTAAG
GGATTGCAGTT
TACGCTCTTCT
GGTTCGACCAA
GCGAACCGTCC
TAGGCTACCTG
AACTGGTCAGT
CCTCTCTACTA
CCATTCAATAG
AACCGATATGA
TTAGGACCAAC
CTGGAGCTCTT
CCATCTTACCT
AACCAGCGCTG
CAGCAATACTC
GGTTGAGCATC
TTATATCAGTT
TGCAGTTCGCC
ATTGACGCGCC
GCATGGATTGG
GCGGTCCATCC
CCAGCGATAGC
CCAGCTAATAG
AAGAGATACCA
ACGAGCTTCGC
CAACCGCATCC
TGCGATGATCA
GGTTGGTATAT
TGAGGCTGGAA
GTTGCGCTTAT
TCATCGCTTGA
CTCCAGATCAG
GATGGCTTAGA
TCAACTACTAG
AACGCCAGGCT
GGTTAAGATCA
TGATCTTCAGA
GTCAAGTTCCT
AACGAGTTGGA
GTTCTTACTCC
CTGCGAGCTGA
GCCATTGGCAT
TTGACTCCGTC
GTCCTTGGTAG
TGGATGAATTC
AAGGAACCGAC
CGGAGTCTTCA
ACGAATTCCGG
CTGGAGGTTAG
TTGATAAGTAC
TGGAGACTCTT
TTGGCGCGCGG
TCCTCCTTGCT
ACGACGGTATT
CGTTATATCAT
GGTCGGCGAAC
GCCAACCGTTG
TATGATTCGGT
CAAGAGATATG
GCTGGTTGGCC
CCAATCCATAA
AGAACGCTCGC
GTTAGAACCGT
TCCTCGCGACG
GAAGGAACTGG
TTGGCAGAAGA
CGACCTTCATC
GCTGCTGCAAC
TATACTTGCGA
AACTCAATGAG
GGTCTGAACCG
CTTGAGAAGGA
TTGGCATGCCT
TGGCGACCGAA
GAAGAGCCATT
AAGAACCTAGC
GGTCATATCCA
TCAAGAGCTGC
CCATCTGATGG
TGGATACGGAC
GGTCCGGACGA
TTAGGTCCTTC
GGATTGAGTCT
AACTGCATCCG
AATAACCAATT
CGATAGGTTAG
AAGAACTCGAG
TCGGCTGGCGG
TTGCCGCTGGA
GAGTCGCGGCC
TGAGTAGAAGA
AAGACGCGACT
TCCATGAAGGT
ACGATACGGTA
ATGATCGTTGG
AAGAAGATCTC
TCCTATAGTTC
TCATACCGGCG
TCAGCGTCGTC
AGAAGTTGCCG
GGTCGGCATTA
GAACTGGCAAT
ACTCAGTAACC
GTATGAGGAGA
CTTCCATTGGT
AAGATAACGAC
AACGGCTCGGT
AACTCAGCCAA
ATTCTCTCCTG
TGGTAGATGGT
GTCCTCGCCTG
TGGTCTAGCGG
TGAGTCTATAT
TGACGATAGCT
CGCGAGAGATA
AGAAGACGGTT
CGGAGGCTTGG
TTATCGAAGAA
ACCAGCCAGTT
GTTCTCGCTGC
CCGACTTCTAT
CCTACGAGGCA
TTCTCGGCTAA
AGAAGATAATC
CGTATTCGAGA
AGAACGGCTAT
TCAAGATTAAC
AACTACGCTTA
TTACCTTCTAA
GGTTGAGAGAC
ACCAAGAGCTC
GTAGCTTGCTC
GAAGCCGCAGT
TGCTGCTATCC
AAGAGAAGCGA
ATTAGGCGGAG
AGAACGCAAGG
AGAATATCTAT
GTTCCATATTC
GTTATGAGCGT
GGCTACGTAAG
AACGCTTGCCA
ACGACGAAGCG
GTTCAACGGTT
GCAACCATAGC
AGAACTGCCTT
GGTTATGGCGG
CTGATCCAACG
GTTACGTATCG
TCGGAGGTACT
TGGAAGGTTGG
GGTTGGAATCA
TGATTCGGCCT
GAACGATCCGT
GTATCTACTAC
GAACCATCGCG
TTGCCAGCGGA
TTAGTACGTAC
GATTCTCGCCA
GGTAACTGGTT
TCGTTATTACC
CAGTTGGTAAT
TGGAGCGGACG
CGTTGGAACGT
CTCCGGCAGGA
AGAACCAGCGC
TTGCTCGAGAG
AACTCTAGCGC
TTATCAGCTCG
TGACGTTCAGG
CGACCGACTAG
AAGACGTTAAT
GCTTGGAGAAC
GCGGCTTATGC
GTTCCTCAGGT
CGATTGCTGGC
GGTACCAACCT
CTGCCTTCCGA
AACGAAGCTCG
GTTATCATCAA
AACTGCCGCTC
ACCATATTGAA
TCCGTCTGGAG
AACGCTCGCGT
AGTTAAGTCGA
AACTCGGAACT
AAGAGAACCAG
TCAACGCTCTT
CGGCTGGCGCG
CCAATGCTTAG
GTTAGTCTCGT
GTACTTGGATC
AAGAATCCATC
AACCATAACGT
GTTCCGGCGAA
TCGGCTGCTGA
ATATAGTACCT
GGAGTTGGCGA
AACCTAAGCCG
AACGCATCCGT
CTCCGCGTCGT
GGTTGCGTCTA
AACTCATTCGC
CTTATATGCGC
GGTTATCTCGA
TCGAGCGCTTG
AACGTCATCAA
CCAATCATCAA
GGTAGAGAACC
TGATAGCTCTG
CCGGTCTACGA
AAGAGCGTAAT
TGGACTTACGC
GAGTTGCCGTA
CTGAGGCGTAA
AACCGGAAGTT
GCTGCTGAGGA
TAACCTAATGC
CGTCTCGTAGG
AGAACTGAGAT
CCAGGAACGTT
TTGAAGCCGGA
AAGAGCCGCGT
CCGGCTCGACC
GTAGTCAACTT
TCGTTACGGAA
TGATTGGACCG
CAGCAGAATTA
GACCAGGCCGA
CGTCTTAAGCG
AACTGCAGGCA
AACTACCTTAA
CCAGTCATTCT
AACCGCTCATT
CGGTCTGGAGC
TGGAAGGCCAG
AACGTCGCTAG
TGGCAGTAGAC
TGGAGACGATG
AGAAGAAGACT
AAGAACGATAG
AAGAACCTCAG
TTGAACCAGTC
GGTTATCGTAG
TTGGTAAGGAG
AACTAGGACCG
CGTCTATACCG
TGGAATTCTTA
AAGAAGAAGAT
TCGGTCGAGCC
GGATCGCGCCA
ACTTCTCAAGA
CGCAGAGAGCA
AACCAACGCAA
AACTCAGACTT
TGGAAGATATC
GAATAACTACC
GAACGATGGCC
TGCCTGACTTA
AGAAGCCTCCA
GCGTTAGACTC
ATTGATATCTA
ATTAAGATGAA
ACCAACGAGCC
CCTGAAGTCAA
TGGCGGCGGAC
AACGTAATATA
TATTGGCCAGC
GCGGACGTTGA
CTTGCCTCTAC
GGTACCGGTAA
TGCAGTTCAGA
GAGAAGGCTCT
GTTGAATAAGG
CAAGAACCTGA
CTTCGCGTATA
AAGAGCGGCCG
GAACCTCAGGA
TTCGGTCATAT
CCAGCTAGCGG
TGGATTCTATA
TGAATATGGTA
TGACTGCTTCA
GTTAGGAGGCC
TGGCATTGCAT
GTTCAGCGCCT
AAGAGATTGGA
AAGCAACGAGT
GTACGCAGCTC
GTCCAATGCGC
AACGTCCGGAC
AACCATCTATT
TGGCCTGGCCA
AACCTATCTTG
CCGGCTGGATT
AACGCAACTGC
AGAATAGGATT
TCGAGAGAATG
TTGAGGTTCTA
CCAACGAAGTT
GTAGAGATATC
CTCCGACCTAG
CTGGTTGGAAT
CCAGAACCATT
AACCGTCTCTA
TCTATGATTCC
GGTCCGCGCTG
TGCTGGTCTTC
AACCGAAGAAG
AAGAATGCGAT
CGTTAGATCGG
GTCGTCATGCC
GCGTTAAGTAA
GTCGATAATTA
GCTGCTATGAT
TGAGGTCGATC
TGGTACGCGAC
AGAAGGTACCT
AACGAATCGAG
GTCGGTATGCA
CCGTAATAAGC
GCTTGCGAGCC
GGATTGCTAGA
ATCTTCAGCTA
CCGGTATGATT
AAGAATAGACG
GTCTGAATCTC
CAGTTATACGA
GCGTTGCAGCC
AGACCAAGCGT
TCCGCAGCGAA
GTTACCTGGAT
GTTCGCTTAGG
CAGGTAAGAGG
CTAACCATTCA
GCCTCTTACCA
TTACGTCCAGC
GGTATGAGCTG
CCAGCAAGGTC
TTGATCGCGCA
TATTGGTACTC
TCCTTCCATGC
AACGACTGGAT
GCGTTCTGCTA
AGGTTCTATAA
TCAACCTGCGC
CGGAGAGGACC
CCAACCGATAC
GGTTGCCGGCC
TGAGCTACGAG
GGTCTAACTTA
GAACCTGACCG
TGGCCTATGCG
AACTTATACGG
CCTCCGAAGGA
CAACCGAGTCT
TGAGCTCATAC
TCCAATCGAGT
CTGCGATCTTG
AACGGAGTATC
ATTGGAGAGAT
TAACGCATTAT
GCAGATACCTC
TTGCTGAGACT
AAGAGATAGTC
AAGAGCATGAC
AACCAGGTCTA
TAACGAAGGTC
TCATCGTCCAA
AACGAGCGGCC
CGTTATGAACT
CCTGCATCGTA
AAGCAAGATCA
TTGCATTGAAC
TTCAAGAGGTT
AACCTATAGTA
AATATACTCTG
TTAGTCGTATG
GTAGTAAGGCC
CCAGCCGGAGC
GTTCTGCTCCA
GTAAGGATATA
TCGTTACCAAG
AACCGCGCAGG
TATATCTGCCG
CGACTTAATAG
AGAACCGAACC
CGTTGCATGCA
CTCCGAACGTA
CCTCTCGTCTT
TTCTACGCAGC
CCGACGAACTA
GCTCTCATTCT
AACGGAATAGG
TTCGCTGATTA
CGGCGTCCTGA
AACGTTAGGCC
AACGTTACTCG
GGTATAGATAC
TTCATCTCTCG
AACGACTACGG
AGGTCCGTTGA
AACCGCCATAT
TTGGAGGCGCG
GTTACTCTACT
AACTAGCGGTA
TGGTCGATCTC
CCGTCCATCCT
ACGCGCTGGAG
TGGCGTCAATT
CTAATTCCTTA
TCTATCGCGCG
CGGTAGAACCG
GCCTCGCCGGT
CGCCATAGGAT
CTGGAGACGTC
AACGGCCTTCG
ATAACCAGACC
AACGCGCCAGT
CTGGCGGCATA
CTTCGGAATAA
GAAGCTGGCTG
ACCATACTGGT
CTTGGCCTGGT
AACGTATAGGT
CTCTTGGTAGC
TAGTTACGATG
TAGTTGCTAGC
GTTGCAGTATT
CCAGACCGAAG
GAACGAGAATG
AGGTTAATATT
CCAACCAGGCC
CGTCGCTGCTG
GTTGGCAATTA
CGTTCGGCCGC
GTTAATGCAAC
AGAAGTCAGGC
CCATTATTCGG
CCAATTGATGC
CAGCGCAATCG
CCATCGACTAT
GTTACGACGAT
GCCTATTATCG
CCATGACTCTA
GAACCTCGCTT
CCTATCATGCG
CTCCTCCGCCA
ATTCCGGAGGT
CGTAGGTAGTT
CCGCTTGCGCT
CCAGCTCTCCA
AGAACGTTGAT
CTTGCTAACCG
TTAGGTACCTG
GCATTCTAACC
GCTTAGGTAAC
GGATGGAGAGA
GCTTGGACGTA
GTTGGTAGCCT
AACTTACCGTT
ACCAGATGCAA
CAGAACGAGCT
CATTCTTCCAA
TGCCTATTAGC
GTTATATTGCG
GTTCGAGAGCG
ACTCCATCAAT
AACGTAGATCT
GTTCTACTTCC
AAGAGAATTAA
GGATAATCCGT
GTTCTCTAGCA
GAAGAGACTTG
GGATATGGTTC
TCCTCCATGGC
CCAAGCGGTCC
GCTGATGCCTG
TTAGTCATACC
AACGGATCCTG
GGTATGGTCTT
GGTTACTCTAG
AACTTGACTCT
AGCGTTCTCGA
CGATATACGGT
GAAGATAGGCT
CTTGAGTAGAT
AAGACTACTGA
AACCGAGGTTG
TTGGCCAGCTA
TTGCAAGACTA
CGACTCCTTGG
GACTCGCTCAT
ATTGCCGAAGA
AGTAGGCGCTC
TTGGTCGTTCC
CTGGTAGTATA
AGAACGCCGAG
CCAGACTAAGG
GTCGTTACTAG
TGAATTAATCC
TCAGATTAAGT
CGGTCTTCTTC
GGTCAGCCGCT
TGGAGTTATAA
AACGCCTGCTT
AACGCCGCGCC
CGGTTCAACTT
AACGATCTTGG
AACTGGAGAGA
AGAGAACGACG
CTTAGTATGGT
AACGACCTGGC
CCATCTAACTA
CTTGGATCGAA
GCAAGTATCCG
ACCTCCGCCGG
CGGATGCGTAC
CCGCAAGCGCA
TGGTATGCAGC
CCGAATTAGCG
GCTCCAGCTTC
GTTACTTACCT
GATTCTTCTGG
CTCCAGGCAAG
TTCCTCAATAT
TGATATTGCTC
AGGTTCCTTGG
TGAGGACGCTA
GCCAGTAGGCG
TCAGATCCGTA
GGTTGCCGTTG
GGTAGACGCAT
CCTTCTATTCT
CAACCAATCCT
CTCGACTGATA
TTACGTTCCGT
TCAACCTCGGT
GAGTCGCTCTG
ATTGCTGCTAC
GCGCTTAGCTT
GTAGTTGATGA
CGTCCGGTTGC
CCAACCAAGAA
TGCTATCGATA
GTAGAATAGAG
GAAGCGAAGAA
ATTGGTATTCG
TGAGTACGAGC
GCTCATCAAGT
CCTCGCTGCAA
AGAGAACCGCT
CGTTACGCATG
AGAAGGCTAGA
CGGTATATCGA
GTCTGGTATTC
TCCTTCATAAT
TTATTCTGGCT
AGAAGCCAACG
TCCTAACTCAT
GCTGCTTGATT
GTTGGCGAAGC
AGAAGAAGCTC
TGAGTCTAAGC
CTAGGTTCTCA
CGGCAGTTGCG
GTAGAGTATAT
CGATTGAGGTA
GCTGCAGTCGA
TTATCATATAA
ATTGATGATTC
CTTGCGTCCTT
CTCCAGTTCTC
TCAACTCAGGC
CCATACGAGAA
CAACCAATAGA
GATTGACGTCC
TTACTTAGATT
TCCTGGCTGGT
GAAGCAGACGC
GAACCTGCGCT
CCGCATTCCTG
TGCGAGCATAA
TTGGACTGGTC
TATATAGTCTT
CCATGGTACCG
CGGCGGTAAGT
TCAAGGCGGCA
AACGCGCGCAA
CTGGCCAGGTC
TGGTAATAGAA
TGGTCCGAGAG
GGCCTCGACCA
CGGTAGTTATG
AACCATCCGAT
AGAACTTCATA
AACCAGAACCA
GGCGGTCTACT
TGATGGAGACC
CTCCAACGCCG
CGGATATCGAA
AGAACCAACCG
AAGACTCAGGA
GATGAATTGAG
GTTGGATTATA
GAACCTGGACC
AACTCAAGAGG
AACTAGAGCCT
CGTCTGCTGAC
AACGCGACTTG
GTTCGTCATGG
GGACGGCGACG
CCGCTTAGACG
AGAAGACTCGT
ATATTGCTCGA
GAACCTACCGT
TGGCGTACTGC
AGTTACGGCAA
CGGATGGTACC
CTGGCTTGGAC
CTGGTCGTCAT
AGAAGGCAGAT
TTCTCTTGCCG
AACTCCAACGG
GAGCAGAGTTG
CAACCAGGCAG
AACTTAATCTG
CGTTGCATTGC
CGGCTTATGGC
CGAACTAACGT
TGCGGTCGCGT
AACTCGATGGC
GAACCTAATCT
AACTTAAGTAA
ACGAACTGACG
AACGACGCCGC
TGCTCAGGCTG
CTCCAGACTGA
CCAATATGCAA
TTGCTAATGAA
TGGATTCGCTG
GTCGTCTACGC
GTAGTCTATTA
ATTGGTTAATG
AACGATGCGAC
AGGTCGTTGAA
CAGAATCTCGT
GAACCGCAGCG
TTAGGAGTATA
GCTGCGGCTTG
ATTAACTGGTC
TGATTGCCTTC
AACCTTGCCGT
CTCTACGATTA
AGAGAACCTTA
AACGCATAACT
TTGGTCGCCTC
GGTACGTTCTA
TTCCATGGTAA
GAAGAGATGAG
GCGTATGCGGA
CTTCATATTAC
CGCCAATTATA
GTTCATTGGTC
GCTCTTCCGTT
CCTGACTTACT
GAAGCGGACCT
CGCCTATAATC
CGACTAGATTG
GGTTGGCTACC
GAACGCTAAGG
CAGAACGTAGA
CCATCTGCAGC
AACTGCAATTA
AACTATAAGAG
AACGGTCGTAA
GGTTAGGACCG
AGTTGCGCTAA
GGTCTCGATCG
CTCCGATCGGT
TTGGTCCTACT
CTTCATCGGCC
CTTGCCTTCAT
TGGTTGACCAT
GATCTGCTAAC
TTATATTAGCC
CGTTCGATAGA
CTTGATATGAA
AGAATCTATGA
CGCCAACCTCG
ACCGAACCGAT
AACCAGTCAGG
CGAAGCCATCC
GAACGGTACGC
GAACCGCGAAC
CCATGCAACGT
AGAAGCCGTAA
CGAAGGTAAGG
CCAGTACGATA
GTTGCGCAAGT
CCGTCATTGCG
GGTCTCAAGGT
GCTTGGTCCAA
TTACGCTCGTA
CGTTATCTAGG
TTGGAATATAG
AACGCATGATG
GGCTGGATGAT
GCGTCTGAGTA
GTAGGCGTATC
AGAATAGCTCC
TGGATCGGAGA
AGAAGAGATTA
ATTGATTGAAT
GTAGTTAATCT
GAACGGTTATT
CCTCGAGAGGA
CCGTTCGAAGC
CTCGTTATACT
TTCTCTATCCA
CTGGCTGCGAG
ACGTACGTCCG
AAGAGAGCAGA
AACGACGAAGA
GTATCTGCTTA
TTAGGTAGAAC
CGATTCTAGAT
TGCCTTCATCA
GCCGATACTGC
TGCGTAGTCGG
AGAACGGAGGC
GTTATTACTTG
GGCTGAACGTA
CGTTGATAATC
AACGAATCTTA
CTTCCGCTCGC
TCCTGAGCTCG
GTTGCCTCAGG
GCTCGGTTCCA
TCGCGAAGGTT
AGTCGGTCATG
CCTCTCCATGA
GGTAGGAGGTA
GAGTTGACCAA
GTTACGATTGC
CCTTCGATTGC
ACTTCGCAGGT
TATGATATTGC
CCGCCAAGTTC
AACGAGAGATT
TGGAGGTTGCG
GCATCAAGATC
AGTTGCGCGCG
AAGACTATCAT
AAGAGAATATC
AAGGAACCTGG
CTTGCGGATCT
AACGGTCAAGT
GTCTTCAGTCA
TTGGCCATTCG
CTGGCGCATTA
AACGATTAGGC
AGACCAACGGC
GGCTCATGCGC
GTTCCGATCAA
AACGGAATCCA
CCAAGCATAAC
CTCTTGCTACT
TGGTCGAGGCA
CAACCATACGA
GGTAGCAACGC
GGTTCTTATAC
TAGCGTTCTTC
GCTCCTCCTGG
ACGCATGAGGC
CCAACGTCTCT
AACCTAAGTTC
AACTCCGGCCT
CTCTAAGGTCG
ATAACCAGTAG
TTCATGGAACG
CCATTAGACTG
CCTCTGATTAG
CTACGTCTGCA
AACTTATATAT
TGGCGCCTAAT
GTTCCGAGCTC
TTCTGGATCGC
AGAACCATTCC
TCAATTAGTAT
ACGACTCTGAT
CGTCCGAAGAG
GGTTATAAGCT
GGTTGGCTTGG
AACGCCTAGCG
TCGTTCTTGGT
CCGAGGATAGC
GGTTCTGAATA
CCGCGCATCAA
TCTAGCATGGC
TCCGGCTCTGA
TCCAACTGACT
CCATGAAGGAC
AGAACGAATAG
AGAATACTCTA
CAAGCAGTACT
CAACGCAGAAC
CTCTCGCTGCC
TTACGACCGCA
TATTGCTAGGT
GCATCCTGCCT
AACCGCTCGAG
CCTCGGAGCTA
TTGAGCGCGTC
AACGTTGCAGA
TCCTTGGACGG
CCTCGATACTG
CGTAACCTCTT
ACCAACGAAGG
CTCCGAGGATC
CCAACTGCTTA
CCGCAGGCCGG
GGCGTATAGAA
GTATAATATCT
GCTTCGTTCTT
CAGGACGTCTG
CTTCGGTTGCG
GCAAGATAGGT
AACTTCAGATG
AGAAGCATTAT
CTGGTTCATTC
CCGAACGGAAC
GCTATGGCAAC
CCTTCCTGCGC
GTTGAAGTTCG
GTCTGCGTTCC
TCGGTTGGAGT
TCGTTAAGTTC
GGATGGTACGG
GCCGGTTGAAG
TGGAAGACTCC
AAGAGAACGCA
GGTAGGCATCC
CCAGATCCTAA
AACCATATCAA
ATTATTCAGGT
CCGCGTCGGCG
CCAAGCAACTG
GAACCGGTCTA
CTGGAAGCTCT
TGGTTCGCTCG
TTCCTATTCAA
CCAATTCTTGA
CCGTATGGAAT
GGTCAACCATG
TTGGTCATAGG
GTTGAGACCGC
CAGGCAATGAT
TGCGTCGATGG
CGTTGCGCCGT
GACCAACTGCT
CCATATTACTC
GCAGTTGCCAG
CTCTCCGACGG
AACGCCATATG
TATTCTAGGAA
TGCGTAATAGA
TGGTTAGATTG
GAAGCGTCCTG
GTTATCTTCCT
CTCCTTCTCGC
AACCGAAGGTA
AGTCTCGGAAC
TGCGATCGGAA
CTGGATGGCAA
GGTAAGGCATG
TCGCCAGTTCC
AGAACCTTGCG
ATGGTTGAGAG
GCGCTGATTCA
GGTCGGAGCGG
GTAGAGGTTGG
TGGTCATCCGG
TTACTCGGCGC
TTCGAATACTA
AAGACCATACC
TTGCATAACGT
GTCGGCTGGAT
TTGCCGAAGCG
GTACGTTAAGT
CCAAGATGCCG
AACGCTCGACC
CCTAATGCATG
GGTTCGGATAA
GTCTGGCGCGG
GAACCGGCTCC
AGAAGGATCGG
CCATATAAGCG
GAAGAGGCTGC
AACTCATTATT
TCGTTGCCGGA
TTGCTCAACGC
TGAGGCTTCGC
GAACGGACTCG
GTCGGTCAACG
AACTATAATGA
CGCAGCTTAGA
GTTCGCGGTCC
TGAGTACTTAA
TTGATGCGGAA
AAGAGATATAG
CGACTTATCTT
AAGAGCAGTTA
ACCAACCATGC
AGAAGAGCATG
GGTAGCTAATT
CCGAATATACG
AGAATCCAGAG
CTGGTACGTCT
TAGTAGGATTA
GGTTAGATGGC
AACCGCATTAG
GTCTTATGGTA
GAACCTTATAG
GGTAATTGATC
CCTCTCAGCTG
GGTAGTCAGAC
AAGAGGCTAGT
GGCTTGGCGAT
CCAGCTCTGGC
CCATCGCATAC
TGGATCCTCAT
AAGACTCCAGG
GGTTCATCAAG
AGTATTATAGA
CCATAAGAGTT
GAGTTATTAGT
AATAACCATCC
GGTAGCTGACC
AACGCAGTAAG
CCATCGTTAAC
AACGGCATGCC
GTCTTGGCATG
CTGGCATGATA
CCAATGGACTC
ACCAATAGCAA
AACTATACGCA
TTCGGATAATG
TTGAGATGAAC
AACTCGTAGTC
CCTCATCAGCG
TATGGCTCTTA
GCCGCCTACGG
CTATGACCTAA
GCTGCGTCCTC
CAAGCGCGCAG
GTCCGCGACGG
TTGGAACGGTT
AGAATCATCAG
TTACTGCTTAC
ATTCGCGCGAA
GGTAGCTTCGT
GTTAGCTATGA
TGATCCTCAAT
GTTCATTATAA
CGTCAAGTCCA
TGGAATATTAA
CCTCCTGGACT
GCCTGAACCAA
AACCTTAGTAG
CTGCGTACGGT
CGCATCTGCAT
AACCTGGCTCC
TGATTATGAGA
TTCTTAGCGAG
AACCTCATACG
CGAACCAGTCG
GAACCAATATC
CGCGCGCAGCC
CCAAGCATTCG
GAAGCCTTCCG
TTAATCTCGAG
CCATACCGCCT
CTGGAGCAACC
GCCGCTTGCTG
TCAGGTTATCG
GGTCGCCGCAA
CGGTTCATGGT
TCCTTAGAATT
TTCTTATCCGC
GCTGGCTCTAA
CGACTGCCAAG
GAACTACTAGT
CCGCCTCAGTC
GAACCTCCGAC
CCAACTCTCTC
AACCAGACTTA
AACTTGAACGT
CCTTATCCTCG
CCAGCCTCCGG
TTGAAGGTCTC
ATTCCGAGTCC
GGAACCGCCTA
AACCGGACGGA
CAACCAGAGAA
AACCAGGCGGC
AAGACGATATG
CCAACGATCCT
GATTCGTTAGA
GACTCAAGCCT
CCTATCTCGAA
TTCCATTAAGG
CCAACGCAAGC
AACGAAGCGGA
AAGAATAGGAA
TGGCAGACTAA
AACCATACCTC
GTTGCGTTATC
CCAGCTCCATA
TTGCGTATGCA
GGAGGCATTGA
AACCTCGAACT
CCATGGACGTC
AAGACTTCCAA
TTGCGTATCTG
TTATTGGAGAT
CTCTACCGTTC
GCTGATGCGCC
AACGAGGAGAG
TTATACGAGGC
TGAGTCCGTTA
CCAATCTCCGC
TTGAAGCTAGG
GCGTCGGTTCT
CTTAGGACGCA
GAACGACTGCG
TGCTTGATAGC
GTTAGACGCCA
GCTGCTCATAT
AACGATCAGTT
CCAATAGATCG
TGAGGATAGTA
CCAACTGAGCC
CCTCCTCTGCA
AACTACGGTCC
CTTGATGACCA
TGGCGGAGCAT
CTCCGCTTAAG
CTTGCGCTGCT
AGAACTGCAGC
CAACCGTACCG
CCAGCATGAAG
TAGTATCTTGA
CAACGAATTAA
GTATATACCGT
TCGATCTCTGG
CTCGGTAGAGA
ACCAATTACTA
TAGTCAGCCTC
GTTGCCAGTAG
CTTGACTCGGT
TTCTCCTGGTA
TGGTTCCTAAC
AGAATATACGT
CCAACCTCAAG
CAACCAGATCG
GCATTCATCAG
GCCGTCGCGCT
CTCTGGTTCCT
CCTTAATACTT
AACGACGATAC
AAGAATCATTG
GCTGGTCTACC
CGGTTATAGCA
GGTCATCATCT
GATTCCGTCCT
GTCCTTGATCA
GAACTACCGTT
TCAATCCATTC
CTATGGTCGTA
CCGTTCCATGG
GTATACCAGAT
CGTTAGTTCTA
GGTTGAAGATA
TCCTTCGAGAT
AAGAACGCAAC
CCGACCTTAAT
AACTCGCTCGA
TTGGCTACCAA
CTTGATCAGGC
TGGCTCCGCGA
GGCGTCGTCAT
GTAGTCGTCCA
CAATCCATAGT
GTTAGTTCCTG
AACCGAATACT
GTCCATCGCTC
CCATCTCAATC
CTGGCTGGTTG
TGGATAGACGG
GGTCTGCTCGC
GAGGTTAGTTG
GAACTCGAATT
GTTGCGATCGT
TGGCTATGCCG
AACGGAGACGT
CCAAGTAACCT
CCAGAATCAGC
GGTATTCAGCG
GCAATACCGCT
CCTCTTGCTCG
CGAAGACCGGT
GTATTCGCGAC
AACTTCTAACG
ACCAATGCGAG
AACTATAGGTC
GAGAACTGCCG
CCTACTATGAC
CCATCAACTGC
TTGATACCAGC
ATATTGGCTAA
CCAAGAAGACC
+176 −73

File changed.

Preview size limit exceeded, changes collapsed.

+90 −0
Original line number Diff line number Diff line
args = commandArgs(trailingOnly=TRUE)
print(args)
sam_file <- data.table::fread(as.character(args[1]), data.table = F, skip = 3, header = F, fill=TRUE)
vcf_file <- data.table::fread(as.character(args[2]), data.table = F, skip = 28, fill = TRUE)

head(sam_file)
head(vcf_file)

sam_temp <- sam_file[,12:19]

if(nrow(vcf_file) > 0 ){
# reverse order by position to avoid upstream indesl affecting target position
for(ii in c(nrow(vcf_file)):1){
   print(paste("replace", vcf_file[ii,5], "with", vcf_file[ii,4], "at chr", vcf_file[ii,1], "pos", vcf_file[ii,2]))
   vcf_pos <- vcf_file[ii,2]
   vcf_chr <- vcf_file[ii,1]
   vcf_ref <- vcf_file[ii,4] 
   vcf_alt <- vcf_file[ii,5]
   ref_len <- nchar(vcf_file[ii,4])
   alt_len <- nchar(vcf_file[ii,5])
   sam_pos <- sam_file[,4]
   sam_chr <- sam_file[,3]
   sam_seq <- sam_file[,10]
   sam_qual <- sam_file[,11]
   #print(head(sam_file[,10]))
   read_length <- sapply(sam_file[,10], nchar)
   #print(head(read_length))
   #print(head((sam_chr ==  vcf_chr)))
   #loci <- apply(sam_file, 1, function(read) c(as.numeric(read[4]):as.numeric(read[4])+nchar(read[10])))
#   print(head( sam_pos ))
#   print(head( sam_pos+read_length ))
#   print(head( vcf_pos ))
#   print(head(  (vcf_pos <= sam_pos) & (vcf_pos >= sam_pos+read_length)  ))
#   print(table( (vcf_pos >= sam_pos) & (vcf_pos <= sam_pos+read_length)  ))
   matched_reads <- ((sam_chr ==  vcf_chr) & (vcf_pos >= sam_pos) & (vcf_pos <= sam_pos+read_length))

#   print(which(matched_reads))
#   print(table(matched_reads))
#   print(sam_seq[matched_reads])
#   print(sam_qual[matched_reads])



   print(vcf_pos)
   print(alt_len)
   print(ref_len)
 #  print(sam_pos[matched_reads])
 #  print(sam_pos[matched_reads] + read_length[matched_reads])
 #  print(vcf_pos - sam_pos[matched_reads] + 1)
 #  print( substr(sam_seq[matched_reads], vcf_pos - sam_pos[matched_reads] + 1, vcf_pos - sam_pos[matched_reads] + alt_len) )
 #   print(sam_seq[matched_reads][vcf_pos - sam_pos[matched_reads] + 1])
    print(     substr(sam_seq[matched_reads], vcf_pos - sam_pos[matched_reads] + 1 -1, vcf_pos - sam_pos[matched_reads] + alt_len + 1)   )
 print ( vcf_ref )
   #substr(sam_seq[matched_reads], vcf_pos - sam_pos[matched_reads] + 1, vcf_pos - sam_pos[matched_reads] + alt_len)  <- vcf_ref
   for(jj in c(1:length(sam_seq))[matched_reads]){
         sam_seq[jj] <- paste(c(substr(sam_seq[jj], 0, vcf_pos - sam_pos[jj]),
                        vcf_ref,
                        substr(sam_seq[jj], vcf_pos - sam_pos[jj] + alt_len + 1, nchar(sam_seq[jj]))),
                        collapse = "")
          sam_qual[jj] <- paste(c(substr(sam_qual[jj], 0, vcf_pos - sam_pos[jj]),
                        vcf_ref,
                        substr(sam_qual[jj], vcf_pos - sam_pos[jj] + alt_len + 1, nchar(sam_qual[jj]))),
                        collapse = "")
                 }
     print(     substr(sam_seq[matched_reads], vcf_pos - sam_pos[matched_reads] + 1 -1, vcf_pos - sam_pos[matched_reads] + ref_len + 1)   )
#   print(sam_seq[matched_reads][vcf_pos - sam_pos[matched_reads] + 1])
   #substr(sam_qual[matched_reads], vcf_pos - sam_pos[matched_reads] + 1, vcf_pos - sam_pos[matched_reads] + alt_len) <- paste0(rep("I", ref_len), collapse = "")
 #  print( substr(sam_seq[matched_reads], vcf_pos - sam_pos[matched_reads] + ref_len, vcf_pos - sam_pos[matched_reads] + ref_len ) )
 sam_file[,10] <- sam_seq
 sam_file[,11] <- sam_qual
}

#update CIGAR
read_length <- sapply(sam_file[,10], nchar)
sam_file[,6] <- paste0(read_length, "M")

sam_file[,10] <- sam_seq
sam_file[,11] <- sam_qual

sam_file[sam_file == ""] <- NA
}
#print(sam_file[23,])
#print(sam_file[24,])
sam_file <- sam_file[,1:19]
sam_file[,12:19] <- sam_temp

out_name <- paste0(c(as.character(args[1]), ".converted.sam"), collapse = "")
out_name <- gsub(".sam.converted" ,".converted", out_name)
print(out_name)
write.table(sam_file, file = out_name, col.names = FALSE, quote = FALSE, row.names = FALSE, sep = "\t", na = "NA")
Loading