Commit 1cd26baf authored by TomKellyGenetics's avatar TomKellyGenetics
Browse files

add Aligent Bravo B with KAPA dual indexes

parent 84b2e0e3

README.Rmd

+2 −0
Original line number Diff line number Diff line
@@ -164,6 +164,7 @@ default settings, see the [installation](#Uninstalling) or [troubleshooting](#De 
-  10x Genomics (version automatically detected): 10x, chromium

    -  10x Genomics version 2 (16 bp barcode, 10 bp UMI): 10x-v2, chromium-v2

    -  10x Genomics version 3 (16 bp barcode, 12 bp UMI): 10x-v3, chromium-v3

-  Aligent Bravo B (16 bp barcode, No UMI): aligent, bravo 

-  BD Rhapsody (27 bp barcode, 8 bp UMI): bd-rhapsody

-  CEL-Seq

    -  CEL-Seq  (8 bp barcode, 4 bp UMI): celseq
@@ -1101,6 +1102,7 @@ Mandatory arguments to long options are mandatory for short options too. 
                                  10x Genomics (version automatically detected): 10x, chromium

                                  10x Genomics version 2 (16 bp barcode, 10 bp UMI): 10x-v2, chromium-v2

                                  10x Genomics version 3 (16 bp barcode, 12 bp UMI): 10x-v3, chromium-v3

                                  Aligent Bravo B (16 bp barcode, No UMI): aligent, bravo

                                  BD Rhapsody (27 bp barcode, 8 bp UMI): bd-rhapsody

                                  CEL-Seq (8 bp barcode, 4 bp UMI): celseq

                                  CEL-Seq2 (6 bp UMI, 6 bp barcode): celseq2

README.html

+2 −0
Original line number Diff line number Diff line
@@ -46,6 +46,7 @@ 
<li>10x Genomics version 2 (16 bp barcode, 10 bp UMI): 10x-v2, chromium-v2</li>

<li>10x Genomics version 3 (16 bp barcode, 12 bp UMI): 10x-v3, chromium-v3</li>

</ul></li>

<li>Aligent Bravo B (16 bp barcode, No UMI): aligent, bravo</li>

<li>BD Rhapsody (27 bp barcode, 8 bp UMI): bd-rhapsody</li>

<li>CEL-Seq

<ul>
@@ -537,6 +538,7 @@ Mandatory arguments to long options are mandatory for short options too. 
                                  10x Genomics (version automatically detected): 10x, chromium

                                  10x Genomics version 2 (16 bp barcode, 10 bp UMI): 10x-v2, chromium-v2

                                  10x Genomics version 3 (16 bp barcode, 12 bp UMI): 10x-v3, chromium-v3

                                  Aligent Bravo B (16 bp barcode, No UMI): aligent, bravo

                                  BD Rhapsody (27 bp barcode, 8 bp UMI): bd-rhapsody

                                  CEL-Seq (8 bp barcode, 4 bp UMI): celseq

                                  CEL-Seq2 (6 bp UMI, 6 bp barcode): celseq2

README.md

+3 −1
Original line number Diff line number Diff line
@@ -6,7 +6,7 @@ affiliations: 
   index: 1

 - name: "RIKEN Center for Sustainable Resource Sciences, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Kanagawa 230-0045, Japan"

   index: 2

date: "Wednesday 12 May 2021"

date: "Friday 21 May 2021"

output:

  prettydoc::html_pretty:

       theme: cayman
@@ -164,6 +164,7 @@ default settings, see the [installation](#Uninstalling) or [troubleshooting](#De 
-  10x Genomics (version automatically detected): 10x, chromium

    -  10x Genomics version 2 (16 bp barcode, 10 bp UMI): 10x-v2, chromium-v2

    -  10x Genomics version 3 (16 bp barcode, 12 bp UMI): 10x-v3, chromium-v3

-  Aligent Bravo B (16 bp barcode, No UMI): aligent, bravo 

-  BD Rhapsody (27 bp barcode, 8 bp UMI): bd-rhapsody

-  CEL-Seq

    -  CEL-Seq  (8 bp barcode, 4 bp UMI): celseq
@@ -1101,6 +1102,7 @@ Mandatory arguments to long options are mandatory for short options too. 
                                  10x Genomics (version automatically detected): 10x, chromium

                                  10x Genomics version 2 (16 bp barcode, 10 bp UMI): 10x-v2, chromium-v2

                                  10x Genomics version 3 (16 bp barcode, 12 bp UMI): 10x-v3, chromium-v3

                                  Aligent Bravo B (16 bp barcode, No UMI): aligent, bravo

                                  BD Rhapsody (27 bp barcode, 8 bp UMI): bd-rhapsody

                                  CEL-Seq (8 bp barcode, 4 bp UMI): celseq

                                  CEL-Seq2 (6 bp UMI, 6 bp barcode): celseq2

launch_universc.sh

+35 −21
Original line number Diff line number Diff line
@@ -197,6 +197,7 @@ Mandatory arguments to long options are mandatory for short options too. 
                                  10x Genomics (version automatically detected): 10x, chromium

                                  10x Genomics version 2 (16 bp barcode, 10 bp UMI): 10x-v2, chromium-v2

                                  10x Genomics version 3 (16 bp barcode, 12 bp UMI): 10x-v3, chromium-v3

                                  Aligent Bravo B (16 bp barcode, No UMI): aligent, bravo

                                  BD Rhapsody (27 bp barcode, 8 bp UMI): bd-rhapsody

                                  C1 Fluidigm (16 bp barcode, No UMI): c1, fluidgm-c1

                                  C1 CAGE (16 bp, No UMI): c1-cage
@@ -619,6 +620,11 @@ elif [[ "$technology" == "10x-v2" ]] || [[ "$technology" == "chromium-v2" ]]; th 
    technology="10x-v2"

elif [[ "$technology" == "10x-v3" ]] || [[ "$technology" == "chromium-v3" ]]; then

    technology="10x-v3"

elif [[ "$technology" == "bd-rhapsody" ]] || [[ "$technology" == "bd" ]] || [[ "$technology" == "rhapsody" ]] || [[ "$technology" == "bdrhapsody" ]]; then

    technology="bd-rhapsody"

elif [[ "$technology" == "aligent" ]] || [[ "$technology" == "bravo" ]] || [[ "$technology" == "aligent-bravo" ]] || [[ "$technology" =="bravo-b" ]] || [[ "$technology" == "aligent-bravo-b" ]]; then

    techology="bravo"

    nonUMI=false

elif [[ "$technology" == "c1" ]] || [[ "$technology" == "c1-fluidigm" ]] || [[ "$technology" == "fluidigm" ]] || [[ "$technology" == "fluidigm-c1" ]]|| [[ "$technology" == "fluidigmc1" ]] ||  [[ "$technology" == "c1-rna-seq" ]]|| [[ "$technology" == "c1-mrna-seq" ]] ||  [[ "$technology" == "c1-rnaseq" ]]|| [[ "$technology" == "c1-scrna" ]]; then

    technology="fluidigm-c1"

    nonUMI=true
@@ -629,8 +635,6 @@ elif [[ "$technology" == "celseq" ]] || [[ "$technology" == "cel-seq" ]]; then 
    technology="celseq"

elif [[ "$technology" == "celseq2" ]] || [[ "$technology" == "cel-seq2" ]]; then

    technology="celseq2"

elif [[ "$technology" == "bd-rhapsody" ]] || [[ "$technology" == "bd" ]] || [[ "$technology" == "rhapsody" ]] || [[ "$technology" == "bdrhapsody" ]]; then

    technology="bd-rhapsody"

elif [[ "$technology" == "nadia" ]] || [[ "$technology" == "dropseq" ]] || [[ "$technology" == "drop-seq" ]]; then

    technology="nadia"

elif [[ "$technology" == "icell8" ]] || [[ "$technology" == "icell-8" ]] ||  [[ "$technology" == "icell8-v3" ]] ||  [[ "$technology" == "icell8v3" ]]; then
@@ -638,7 +642,7 @@ elif [[ "$technology" == "icell8" ]] || [[ "$technology" == "icell-8" ]] || [[ 
    #set as "icell8-5-prime" if called by chemistry

    if [[ "$chemistry" == "SC5P-"* ]] || [[ "$chemistry" == "fiveprime" ]]; then

        technology="icell8-icell8-5-prime"

        nonUMI=false

        nonUMI=true

    fi

elif [[ "$technology" == "icell8-non-umi" ]] || [[ "$technology" == "icell8-nonumi" ]] ||  [[ "$technology" == "icell8-v2" ]] ||  [[ "$technology" == "icell8v2" ]]; then

    technology="icell8"
@@ -868,7 +872,7 @@ elif [[ "$technology" == "seqwell" ]]; then 
    barcodelength=8

    umilength=12

    minlength=8

elif [[ "$technology" == "smartseq2" ]] || [[ "$technology" == "smartseq3" ]] || [[ "$technology" == "icell8-full-length" ]] || [[ "$technology" == "fluidigm-c1" ]] || [[ "$technology" == "c1-cage" ]] || [[ "$technology" == "quartz-seq" ]] || [[ "$technology" == "ramda-seq" ]] || [[ "$technology" == "c1-ramda-seq" ]]; then

elif [[ "$technology" == "smartseq2" ]] || [[ "$technology" == "smartseq3" ]] || [[ "$technology" == "icell8-full-length" ]] || [[ "$technology" == "fluidigm-c1" ]] || [[ "$technology" == "c1-cage" ]] || [[ "$technology" == "quartz-seq" ]] || [[ "$technology" == "ramda-seq" ]] || [[ "$technology" == "c1-ramda-seq" ]] || [[ "$technology" == "bravo" ]]; then

    barcodelength=16

    if [[ $nonUMI == "true" ]]; then

       umilength=0
@@ -1510,7 +1514,7 @@ fi 




#generate missing indexes if required (generating I1 and I2)

if [[ "$technology" == "indrop-v3" ]] ||  [[ "$technology" == "icell8-full-length" ]] || [[ "$technology" == "sciseq2" ]] || [[ "$technology" == "sciseq3" ]] || [[ "$technology" == "scifiseq" ]] || [[ "$technology" == "smartseq2" ]] ||[[ "$technology" == "smartseq3" ]] || [[ "$technology" == "strt-seq-2i" ]] ; then

if [[ "$technology" == "indrop-v3" ]] ||  [[ "$technology" == "icell8-full-length" ]] || [[ "$technology" == "sciseq2" ]] || [[ "$technology" == "sciseq3" ]] || [[ "$technology" == "scifiseq" ]] || [[ "$technology" == "smartseq2" ]] ||[[ "$technology" == "smartseq3" ]] || [[ "$technology" == "strt-seq-2i" ]] || [[ "$technology" == "bravo" ]]; then

     echo "dual indexes I1 and I2 required for $technology"

     if [[ ${#index2[@]} -le 0 ]]; then

         echo " automatically generating I1 and I2 index files from file headers"
@@ -1707,7 +1711,7 @@ if [[ -n "$barcodefile" ]]; then 
        barcodefile=$(readlink -f $barcodefile)

        custombarcodes=true

        #allowing WellList from ICELL8 and other well-based techniques

        if [[ "$technology" == "bd-rhapsody" ]] || [[ "$technology" == "fluidigm-c1" ]] || [[ "$technology" == "c1-cage" ]] || [[ "$technology" == "icell8" ]] || [[ "$technology" == "quartz-seq" ]] || [[ "$technology" == "ramda-seq" ]] || [[ "$technology" == "c1-ramda-seq" ]] || [[ "$technology" == "quartz-seq2*" ]] || [[ "$technology" == "microwellseq" ]] || [[ "$technology" == "smartseq*" ]] || [[ "$technology" == "seqwell" ]] || [[ "$technology" == "sciseq2" ]] || [[ "$technology" == "sciseq3" ]] || [[ "$technology" == "scifiseq" ]] || [[ "$technology" == "splitseq" ]] || [[ "$technology" == "splitseq2" ]] || [[ "$technology" == "custom" ]]; then

        if [[ "$technology" == "bd-rhapsody" ]] || [[ "$technology" == "bravo" ]] || [[ "$technology" == "fluidigm-c1" ]] || [[ "$technology" == "c1-cage" ]] || [[ "$technology" == "icell8" ]] || [[ "$technology" == "quartz-seq" ]] || [[ "$technology" == "ramda-seq" ]] || [[ "$technology" == "c1-ramda-seq" ]] || [[ "$technology" == "quartz-seq2*" ]] || [[ "$technology" == "microwellseq" ]] || [[ "$technology" == "smartseq*" ]] || [[ "$technology" == "seqwell" ]] || [[ "$technology" == "sciseq2" ]] || [[ "$technology" == "sciseq3" ]] || [[ "$technology" == "scifiseq" ]] || [[ "$technology" == "splitseq" ]] || [[ "$technology" == "splitseq2" ]] || [[ "$technology" == "custom" ]]; then

            seg=$'\t'

            n_col=$(awk -F'\t' '{print NF}' $barcodefile | sort -nu | tail -n 1)

            if [[ $n_col -eq 1 ]]; then
@@ -1746,6 +1750,11 @@ else 
        if [[ ! -f ${whitelistdir}/bd_rhapsody_barcode.txt ]]; then

            echo "  ...generating combination of I1, I2, and RT barcodes..."

        fi

    elif [[ "$technology" == "bravo" ]]; then

        barcodefile=${whitelistdir}/KAPA_UDI_dual_barcodes.txt

        if [[ ! -f ${whitelistdir}/KAPA_UDI_dual_barcodes.txt

            echo "  ...generating combination of I1, I2, and RT barcodes..."

        fi

    elif [[ "$technology" == "fluidigm-c1" ]] || [[ "$technology" == "c1-cage" ]] || [[ "$technology" == "ramda-seq" ]] || [[ "$technology" == "c1-ramda-seq" ]]; then

        barcodefile=${whitelistdir}/Illumina_Nextera_dual_barcodes.txt

        if [[ ! -f ${whitelistdir}/Illumina_Nextera_dual_barcodes.txt ]]; then
@@ -1882,6 +1891,11 @@ else 
                 join -j 9999 ${whitelistdir}/bd_rhapsody_cell_label_section1.txt ${whitelistdir}/bd_rhapsody_cell_label_section2.txt | sed "s/ //g" | \

                 join -j 9999 - ${whitelistdir}/bd_rhapsody_cell_label_section3.txt | sed "s/ //g"  > ${whitelistdir}/bd_rhapsody_barcode.txt

             fi

        elif [[ "$technology" == "bravo" ]]; then

            if [[ ! -f barcodefile=${whitelistdir}/KAPA_UDI_dual_barcodes.txt ]]; then

                  #generates all combinations of I1-I2-R1 barcodes

                  join -j 9999 ${whitelistdir}/KAPA_UDI_Index1_i7.txt ${whitelistdir}/KAPA_UDI_Index5_i5.txt | sed "s/ //g" > ${whitelistdir}/KAPA_UDI_dual_barcodes.txt

            fi

        elif [[ "$technology" == "fluidigm-c1" ]] || [[ "$technology" == "c1-cage" ]] || [[ "$technology" == "ramda-seq" ]] || [[ "$technology" == "c1-ramda-seq" ]] ||  [[ "$technology" == "smartseq2" ]] || [[ "$technology" == "smartseq3" ]]; then

            if [[ ! -f ${whitelistdir}/Illumina_Nextera_dual_barcodes.txt ]];then

                #generates all combinations of I1-I2 barcodes
@@ -2687,7 +2701,7 @@ else 
    fi

    

    #C1, Quartz-Seq and RamDA-Seq: add mock UMI for non-UMI techniques

    if [[ "$technology" == "fluidigm-c1" ]] || [[ "$technology" == "icell8-full-length" ]] || [[ "$technology" == "c1-cage" ]] || [[ "$technology" == "ramda-seq" ]] || [[ "$technology" == "c1-ramda-seq" ]] || [[ "$technology" == "quartz-seq" ]]; then

    if [[ "$technology" == "fluidigm-c1" ]] || [[ "$technology" == "icell8-full-length" ]] || [[ "$technology" == "bravo" ]] || [[ "$technology" == "c1-cage" ]] || [[ "$technology" == "ramda-seq" ]] || [[ "$technology" == "c1-ramda-seq" ]] || [[ "$technology" == "quartz-seq" ]]; then

        echo "  ...processsing for ${technology}"

        if [[ $verbose ]]; then

            echo "Note: ${technology} does not contain UMIs"

whitelists/KAPA_UDI_Index1_i7.txt

0 → 100644LFS
+3 −0
Original line number Diff line number Diff line 
version https://git-lfs.github.com/spec/v1

oid sha256:b6155fd1c06b221811ef357ade50425aaf1fc502c5102f7ac70d61f1f3c9a544

size 864

CRA Git | Maintained and supported by SUSTech CRA and CCSE