Loading launch_universc.sh +49 −1 Original line number Diff line number Diff line Loading @@ -1611,6 +1611,10 @@ else fi elif [[ "$technology" == "smartseq3" ]]; then barcodefile=${whitelistdir}/SmartSeq3_barcode.txt elif [[ "$technology" == "strt-seq" ]]; then barcodefile=${whitelistdir}/STRTSeq_barcode.txt elif [[ "$technology" == "strt-seq-c1" ]]; then barcodefile=${whitelistdir}/STRTSeqC1_barcode.txt else echo "***WARNING: whitelist for ${technology} will be all possible combinations of ${minlength}bp. valid barcode will be 100% as a result***" barcodelength=${minlength} Loading Loading @@ -2550,6 +2554,50 @@ else done fi #STRT-Seq if [[ "$technology" == "strt-seq" ]]; then echo " ...processsing for ${technology}" if [[ $verbose ]]; then echo "Note: STRT-Seq does not contain UMIs" fi for convFile in "${convFiles[@]}"; do read=$convFile convR1=$read # add mock UMI (count reads instead of UMI) barcodelength=6, umi_default=10 echo " ...generate mock UMI for compatibility" perl sub/AddMockUMI.pl --fastq=${convR1} --out_dir $crIN --head_length=$barcodelength --umi_length=$umi_default umilength=$umi_default umiadjust=0 chemistry="SC5P-PE" #returns a combined R1 file with barcode and mock UMI ## 6 bp barcode, 10 bp UMI, GGG for TSO mv $crIN/mock_UMI.fastq ${convR1} #convert TSO to expected length for 10x 5' (TSS in R1 from base 39) echo " handling $convFile ..." tsoS="TTTCTTATATGGG" tsoQ="IIIIIIIIIIIII" #Add 10x TSO characters to the end of the sequence cmd=$(echo 'sed -E "2~4s/(.{'$barcodelength'})(.{'${umilength}'})(.{3})/\1\2'$tsoS'/" '$convFile' > '${crIN}'/.temp') if [[ $verbose ]]; then echo technology $technology echo barcode: $barcodelength echo umi: $umilength echo $cmd fi # run command with barcode and umi length, e.g.,: sed -E "2~4s/(.{16})(.{8})(.{3})(.*)/\1\2$tsoS\4/" $convFile > ${crIN}/.temp eval $cmd mv ${crIN}/.temp $convFile #Add n characters to the end of the quality cmd=$(echo 'sed -E "4~4s/(.{'$barcodelength'})(.{'${umilength}'})(.{3})/\1\2'$tsoQ'/" '$convFile' > '${crIN}'/.temp') # run command with barcode and umi length, e.g.,: sed -E "4~4s/(.{16})(.{8})(.{3})(.*)/\1\2$tsoQ\4/" $convFile > ${crIN}/.temp eval $cmd mv ${crIN}/.temp $convFile echo " ${convFile} adjusted" done fi #SureCell: remove adapter and correct phase blocks ## https://github.com/Hoohm/dropSeqPipe/issues/42 if [[ "$technology" == "surecell" ]]; then Loading sub/AddMockUMI.pl 0 → 100755 +127 −0 Original line number Diff line number Diff line #!/usr/bin/perl ######################################### # # # Written by Kai Battenberg # # Plant Symbiosis Research Team # # # ######################################### use strict; use warnings; use Getopt::Long; #####SCRIPT DESCRIPTION##### #Script "add_mock_UMI.pl" given a FASTQ file, starting position, and desired UMI length, generates a new FASTQ file with a mock UMI inserted. ########### ######Options##### my $fastq_in = ""; my $fastq_out = "mock_UMI.fastq"; my $head_length = ""; #number of characters to have before insertion of mock UMI. my $umi_length = ""; #length of desired UMI my $out_dir = "."; ########## #####Checking Options##### #making the options into external arguments. GetOptions ( 'fastq=s' => \$fastq_in, 'head_length=s' => \$head_length, 'umi_length=s' => \$umi_length, 'out_dir=s' => \$out_dir ); #checking for required options. if (!$fastq_in) { die "USAGE: option --fastq <FASTQ FILE> is required.\n"; } elsif (!$head_length) { die "USAGE: option --head_length <INTEGER> is required.\n"; } elsif (!$umi_length) { die "USAGE: option --umi_length <INTEGER> is required.\n"; } elsif (!$out_dir) { die "USAGE: option --out_dir <OUTPUT_DIRECTORY> is required.\n"; } $fastq_out = $out_dir."/".$fastq_out; $fastq_out =~ s/\/\//\//; ########## #checking head length if ( $head_length !~ /^-?\d+\.?\d*$/ ) { die "Error: option --head_length needs to be numeric\n"; } elsif ( $head_length < 0 || $head_length !~ /^-?\d+$/ ) { die "Error: option --head_length needs to be an integer 0 or greater\n"; } #checking umi length if ( $umi_length !~ /^-?\d+\.?\d*$/ ) { die "Error: option --umi_length needs to be numeric\n"; } elsif ( $head_length < 1 || $head_length !~ /^-?\d+$/ ) { die "Error: option --umi_length needs to be an integer 0 or greater\n"; } ########## #####Main##### my %nucleotide = ( '00' => "A", '01' => "C", '10' => "G", '11' => "T" ); my $insert_q = "I" x $umi_length; my $read_count = -1; open (IN, "<", $fastq_in) or die "cannot open $fastq_in.\n"; open (OUT, ">", $fastq_out) or die "cannot open $fastq_out.\n"; while (my $line = <IN>) { $read_count++; #get binary read count my $binary = sprintf ("%b", $read_count); $binary = (0 x (2 * $umi_length)).$binary; $binary = reverse(substr (reverse ($binary), 0, 2 * $umi_length)); my @binary = ( $binary =~ m/../g ); #get mock UMI my $mock_umi = ""; foreach my $character (@binary) { $mock_umi = $mock_umi.$nucleotide{$character}; } #get data from FASTQ file my $header = $line; chomp $header; my $seq = <IN>; chomp $seq; my $plus = <IN>; my $q = <IN>; chomp $q; #insert my $seq_head = substr($seq, 0, $head_length); my $seq_tail = reverse(substr (reverse ($seq), 0, length($seq) - $head_length)); my $q_head = substr($q, 0, $head_length); my $q_tail = reverse(substr (reverse ($q), 0, length($q) - $head_length)); print OUT "$header\n"; print OUT "$seq_head$mock_umi$seq_tail\n"; print OUT "$plus"; print OUT "$q_head$insert_q$q_tail\n"; } close (IN); close (OUT); ########## __END__ whitelists/STRTSeq_barcode.txt 0 → 100644 +96 −0 Original line number Diff line number Diff line TTTAGG ATTCCA GCTCAA CATCCC TTGGAC CTGTGT GGACAT CAAAGT AAGCGG AATAAA GAGGAG GGTACA AGCGAG GTCGGT ATTTGC AGGACT GCCCTC TCGTAA CCAGAC TATGTA ACAATA ATGCTT AGTTTA CACAAG ATCAAC TAGTCG TAGAGA GTCCCG TACTTC AAAGTT TAAGGG GTTGCC AAGTAC GATCTT TTAACT GCGAAT CCGCTA TGAAGC ATACAG CTTCTG GAGATC CCGACG CTCCAT AAAACG TAGCAT TCGGGT GTGGTA CCTAGA GGGTTT ATGGCG TTCATA AACGCC GGCTGC GCTGTG AGATGG GTAATG AGGGTC ATCTCT GCCTAG TCAAAG CATGAT TGTGCG GCAGGA TCTACC AGTCGT CGTGGC GCGTCC GAACGC ACTTAT TGGATG TATTGT ACGTTG GAATTA CCATCT TGATCA CGTATT CGGCAG GACACT TTCCGC CTCGCA GTATAC TGTCAC TGCGGA ACGAGC ACACCC CGCTTG TGCAAT CAACAA CTGAAA AACCTA ACCTGA TCACTT GGGCGA CGCACC CGAGTA CCTTTC Loading
launch_universc.sh +49 −1 Original line number Diff line number Diff line Loading @@ -1611,6 +1611,10 @@ else fi elif [[ "$technology" == "smartseq3" ]]; then barcodefile=${whitelistdir}/SmartSeq3_barcode.txt elif [[ "$technology" == "strt-seq" ]]; then barcodefile=${whitelistdir}/STRTSeq_barcode.txt elif [[ "$technology" == "strt-seq-c1" ]]; then barcodefile=${whitelistdir}/STRTSeqC1_barcode.txt else echo "***WARNING: whitelist for ${technology} will be all possible combinations of ${minlength}bp. valid barcode will be 100% as a result***" barcodelength=${minlength} Loading Loading @@ -2550,6 +2554,50 @@ else done fi #STRT-Seq if [[ "$technology" == "strt-seq" ]]; then echo " ...processsing for ${technology}" if [[ $verbose ]]; then echo "Note: STRT-Seq does not contain UMIs" fi for convFile in "${convFiles[@]}"; do read=$convFile convR1=$read # add mock UMI (count reads instead of UMI) barcodelength=6, umi_default=10 echo " ...generate mock UMI for compatibility" perl sub/AddMockUMI.pl --fastq=${convR1} --out_dir $crIN --head_length=$barcodelength --umi_length=$umi_default umilength=$umi_default umiadjust=0 chemistry="SC5P-PE" #returns a combined R1 file with barcode and mock UMI ## 6 bp barcode, 10 bp UMI, GGG for TSO mv $crIN/mock_UMI.fastq ${convR1} #convert TSO to expected length for 10x 5' (TSS in R1 from base 39) echo " handling $convFile ..." tsoS="TTTCTTATATGGG" tsoQ="IIIIIIIIIIIII" #Add 10x TSO characters to the end of the sequence cmd=$(echo 'sed -E "2~4s/(.{'$barcodelength'})(.{'${umilength}'})(.{3})/\1\2'$tsoS'/" '$convFile' > '${crIN}'/.temp') if [[ $verbose ]]; then echo technology $technology echo barcode: $barcodelength echo umi: $umilength echo $cmd fi # run command with barcode and umi length, e.g.,: sed -E "2~4s/(.{16})(.{8})(.{3})(.*)/\1\2$tsoS\4/" $convFile > ${crIN}/.temp eval $cmd mv ${crIN}/.temp $convFile #Add n characters to the end of the quality cmd=$(echo 'sed -E "4~4s/(.{'$barcodelength'})(.{'${umilength}'})(.{3})/\1\2'$tsoQ'/" '$convFile' > '${crIN}'/.temp') # run command with barcode and umi length, e.g.,: sed -E "4~4s/(.{16})(.{8})(.{3})(.*)/\1\2$tsoQ\4/" $convFile > ${crIN}/.temp eval $cmd mv ${crIN}/.temp $convFile echo " ${convFile} adjusted" done fi #SureCell: remove adapter and correct phase blocks ## https://github.com/Hoohm/dropSeqPipe/issues/42 if [[ "$technology" == "surecell" ]]; then Loading
sub/AddMockUMI.pl 0 → 100755 +127 −0 Original line number Diff line number Diff line #!/usr/bin/perl ######################################### # # # Written by Kai Battenberg # # Plant Symbiosis Research Team # # # ######################################### use strict; use warnings; use Getopt::Long; #####SCRIPT DESCRIPTION##### #Script "add_mock_UMI.pl" given a FASTQ file, starting position, and desired UMI length, generates a new FASTQ file with a mock UMI inserted. ########### ######Options##### my $fastq_in = ""; my $fastq_out = "mock_UMI.fastq"; my $head_length = ""; #number of characters to have before insertion of mock UMI. my $umi_length = ""; #length of desired UMI my $out_dir = "."; ########## #####Checking Options##### #making the options into external arguments. GetOptions ( 'fastq=s' => \$fastq_in, 'head_length=s' => \$head_length, 'umi_length=s' => \$umi_length, 'out_dir=s' => \$out_dir ); #checking for required options. if (!$fastq_in) { die "USAGE: option --fastq <FASTQ FILE> is required.\n"; } elsif (!$head_length) { die "USAGE: option --head_length <INTEGER> is required.\n"; } elsif (!$umi_length) { die "USAGE: option --umi_length <INTEGER> is required.\n"; } elsif (!$out_dir) { die "USAGE: option --out_dir <OUTPUT_DIRECTORY> is required.\n"; } $fastq_out = $out_dir."/".$fastq_out; $fastq_out =~ s/\/\//\//; ########## #checking head length if ( $head_length !~ /^-?\d+\.?\d*$/ ) { die "Error: option --head_length needs to be numeric\n"; } elsif ( $head_length < 0 || $head_length !~ /^-?\d+$/ ) { die "Error: option --head_length needs to be an integer 0 or greater\n"; } #checking umi length if ( $umi_length !~ /^-?\d+\.?\d*$/ ) { die "Error: option --umi_length needs to be numeric\n"; } elsif ( $head_length < 1 || $head_length !~ /^-?\d+$/ ) { die "Error: option --umi_length needs to be an integer 0 or greater\n"; } ########## #####Main##### my %nucleotide = ( '00' => "A", '01' => "C", '10' => "G", '11' => "T" ); my $insert_q = "I" x $umi_length; my $read_count = -1; open (IN, "<", $fastq_in) or die "cannot open $fastq_in.\n"; open (OUT, ">", $fastq_out) or die "cannot open $fastq_out.\n"; while (my $line = <IN>) { $read_count++; #get binary read count my $binary = sprintf ("%b", $read_count); $binary = (0 x (2 * $umi_length)).$binary; $binary = reverse(substr (reverse ($binary), 0, 2 * $umi_length)); my @binary = ( $binary =~ m/../g ); #get mock UMI my $mock_umi = ""; foreach my $character (@binary) { $mock_umi = $mock_umi.$nucleotide{$character}; } #get data from FASTQ file my $header = $line; chomp $header; my $seq = <IN>; chomp $seq; my $plus = <IN>; my $q = <IN>; chomp $q; #insert my $seq_head = substr($seq, 0, $head_length); my $seq_tail = reverse(substr (reverse ($seq), 0, length($seq) - $head_length)); my $q_head = substr($q, 0, $head_length); my $q_tail = reverse(substr (reverse ($q), 0, length($q) - $head_length)); print OUT "$header\n"; print OUT "$seq_head$mock_umi$seq_tail\n"; print OUT "$plus"; print OUT "$q_head$insert_q$q_tail\n"; } close (IN); close (OUT); ########## __END__
whitelists/STRTSeq_barcode.txt 0 → 100644 +96 −0 Original line number Diff line number Diff line TTTAGG ATTCCA GCTCAA CATCCC TTGGAC CTGTGT GGACAT CAAAGT AAGCGG AATAAA GAGGAG GGTACA AGCGAG GTCGGT ATTTGC AGGACT GCCCTC TCGTAA CCAGAC TATGTA ACAATA ATGCTT AGTTTA CACAAG ATCAAC TAGTCG TAGAGA GTCCCG TACTTC AAAGTT TAAGGG GTTGCC AAGTAC GATCTT TTAACT GCGAAT CCGCTA TGAAGC ATACAG CTTCTG GAGATC CCGACG CTCCAT AAAACG TAGCAT TCGGGT GTGGTA CCTAGA GGGTTT ATGGCG TTCATA AACGCC GGCTGC GCTGTG AGATGG GTAATG AGGGTC ATCTCT GCCTAG TCAAAG CATGAT TGTGCG GCAGGA TCTACC AGTCGT CGTGGC GCGTCC GAACGC ACTTAT TGGATG TATTGT ACGTTG GAATTA CCATCT TGATCA CGTATT CGGCAG GACACT TTCCGC CTCGCA GTATAC TGTCAC TGCGGA ACGAGC ACACCC CGCTTG TGCAAT CAACAA CTGAAA AACCTA ACCTGA TCACTT GGGCGA CGCACC CGAGTA CCTTTC
