Commit c38e32ea authored by TomKellyGenetics's avatar TomKellyGenetics
Browse files

Merge branch 'dev' of github.com:kbattenb/universc into dev

parents 9dd7a4c0 ebc55103

.gitattributes

+5 −0
Original line number Diff line number Diff line
@@ -59,3 +59,8 @@ test/shared/smartseq3-test/Smartseq3_diySpike_R1.fastq.gz filter=lfs diff=lfs me 
test/shared/smartseq3-test/Smartseq3_diySpike_R2.fastq.gz filter=lfs diff=lfs merge=lfs -text

test/shared/sciseq-v3-test/SRR7827205_S1_R1.fastq.gz filter=lfs diff=lfs merge=lfs -text

test/shared/sciseq-v3-test/SRR7827205_S1_R2.fastq.gz filter=lfs diff=lfs merge=lfs -text

test/shared/icell8-test/72618_KU812_L002_R2_001.fastq.gz filter=lfs diff=lfs merge=lfs -text

test/shared/cellranger-tiny-fastq/1.2.0/read-RA_si-TTTCATGA_lane-008-chunk-001.fastq.gz filter=lfs diff=lfs merge=lfs -text

test/shared/icell8-test/72618_KU812_L001_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text

test/shared/icell8-test/72618_KU812_L001_R2_001.fastq.gz filter=lfs diff=lfs merge=lfs -text

test/shared/icell8-test/72618_KU812_L002_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text

launch_universc.sh

+70 −60
Original line number Diff line number Diff line
@@ -1003,13 +1003,14 @@ if [[ $setup == "false" ]]; then 
fi



if [[ $verbose ]]; then

    echo "  ${#read1[@]} read1s: ${read1[@]}"

    echo "  ${#read2[@]} read2s: ${read2[@]}"

    echo " Input files prost-curation 1"

    echo "  ${#read1[@]}files - read1s: ${read1[@]}"

    echo "  ${#read2[@]}files - read2s: ${read2[@]}"

    if [[ ${#index1[@]} -gt 0 ]]; then

        echo "  ${#index1[@]} I1s: ${index1[@]}"

        echo "  ${#index1[@]}files - I1s: ${index1[@]}"

    fi

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

        echo "  ${#index2[@]} I2s: ${index2[@]}"

        echo "  ${#index2[@]}files - I2s: ${index2[@]}"

    fi

    echo "  number of these files are as expected"

fi
@@ -1109,13 +1110,14 @@ for key in ${keys[@]}; do 
done



if [[ $verbose ]]; then

    echo "  ${#read1[@]} read1s: ${read1[@]}"

    echo "  ${#read2[@]} read2s: ${read2[@]}"

    echo " Input files post-curation 2"

    echo "  ${#read1[@]}files - read1s: ${read1[@]}"

    echo "  ${#read2[@]}files - read2s: ${read2[@]}"

    if [[ ${#index1[@]} -gt 0 ]]; then

        echo "  ${#index1[@]} I1s: ${index1[@]}"

        echo "  ${#index1[@]}files - I1s: ${index1[@]}"

    fi

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

        echo "  ${#index2[@]} I2s: ${index2[@]}"

        echo "  ${#index2[@]}files -  I2s: ${index2[@]}"

    fi

    echo "  files exist, with extentions compatible with launch_universc.sh"

fi
@@ -1296,13 +1298,14 @@ for key in ${keys[@]}; do 
done



if [[ $verbose ]]; then

    echo "  ${#read1[@]} read1s: ${read1[@]}"

    echo "  ${#read2[@]} read2s: ${read2[@]}"

    echo " Input files post-curation 3"

    echo "  ${#read1[@]}files - read1s: ${read1[@]}"

    echo "  ${#read2[@]}files - read2s: ${read2[@]}"

    if [[ ${#index1[@]} -gt 0 ]]; then

        echo "  ${#index1[@]} I1s: ${index1[@]}"

        echo "  ${#index1[@]}files - I1s: ${index1[@]}"

    fi

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

        echo "  ${#index2[@]} I2s: ${index2[@]}"

        echo "  ${#index2[@]}files - I2s: ${index2[@]}"

    fi

    echo "  names of these files are compatible with launch_universc.sh"

fi
@@ -1383,13 +1386,14 @@ if [[ "$technology" == "indrop-v2" ]] || [[ "$technology" == "indrop-v3" ]] || [ 
fi



if [[ $verbose ]]; then

    echo "  ${#read1[@]} read1s: ${read1[@]}"

    echo "  ${#read2[@]} read2s: ${read2[@]}"

    echo " Input files post-curation 4"

    echo "  ${#read1[@]}files - read1s: ${read1[@]}"

    echo "  ${#read2[@]}files - read2s: ${read2[@]}"

    if [[ ${#index1[@]} -gt 0 ]]; then

        echo "  ${#index1[@]} I1s: ${index1[@]}"

        echo "  ${#index1[@]}files - I1s: ${index1[@]}"

    fi

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

        echo "  ${#index2[@]} I2s: ${index2[@]}"

        echo "  ${#index2[@]}files -  I2s: ${index2[@]}"

    fi

    echo "  input files adjusted for technology-specific conditions"

fi
@@ -1407,12 +1411,12 @@ elif [[ ${#index1[@]} -gt 0 ]]; then 
fi



if [[ $verbose ]]; then

    echo "reads:" ${read12[@]}

    echo "files to be curated:" ${read12[@]}

fi



for fq in "${read12[@]}"; do

    if [[ $verbose ]]; then

        echo "read: $fq"

        echo " read file: $fq"

    fi

    name=`basename $fq`

    name=${name%.*}
@@ -1437,13 +1441,16 @@ for fq in "${read12[@]}"; do 
        exit 1

    fi

    

    if [[ $verbose == true ]]; then

       echo "SAMPLE: $SAMPLE"

       echo "sample (field): $sn"

    if [[ $verbose ]]; then

        echo "  $sn(extracted from file) <- $fq"

        echo "  SAMPLE NAME: $SAMPLE"

    fi



    if [[ ${sn} != $SAMPLE ]]; then

        if [[ -z $SAMPLE ]]; then

            if [[ $verbose ]]; then

                echo "  setting SAMPLE NAME to ${sn}"

            fi

            SAMPLE=${sn}

        else

            echo "Error: some samples are labeled $SAMPLE while others are labeled $sn. cellranger can only handle files from one sample at a time."
@@ -1592,7 +1599,7 @@ fi 






#####check if reference is present#####

####check if reference is present#####

if [[ -z $reference ]]; then

    if [[ $setup == "false" ]] || [[ ${#read1[@]} -ne 0 ]] || [[ ${#read2[@]} -ne 0 ]]; then

        echo "Error: option --reference is required";
@@ -1695,6 +1702,7 @@ crIN=${crIN}_${id} 
##########







#####checking if crIN exists#####

if [[ ! -d $crIN ]]; then

    convert=true
@@ -1867,6 +1875,7 @@ if [[ $lock -eq 0 ]]; then 
            sed -i "s/assert np.array_equal(in_mc.get_barcodes(), barcodes)/#assert np.array_equal(in_mc.get_barcodes(), barcodes)/g" ${cellrangerpath}-cs/${cellrangerversion}/lib/python/cellranger/molecule_counter.py

        fi

    fi

    

    #backup 10x navbar

    if [[ ! -f ${cellrangerpath}-cs/${cellrangerversion}/lib/python/cellranger/webshim/template/navbar.backup.html ]];then

        cp ${cellrangerpath}-cs/${cellrangerversion}/lib/python/cellranger/webshim/template/navbar.html ${cellrangerpath}-cs/${cellrangerversion}/lib/python/cellranger/webshim/template/navbar.backup.html
@@ -1880,6 +1889,7 @@ if [[ $lock -eq 0 ]]; then 
        if [[ -f ${cellrangerpath}-cs/${cellrangerversion}/lib/python/cellranger/webshim/template/navbar.backup.html ]];then

            cp ${cellrangerpath}-cs/${cellrangerversion}/lib/python/cellranger/webshim/template/navbar.backup.html ${cellrangerpath}-cs/${cellrangerversion}/lib/python/cellranger/webshim/template/navbar.html

        fi

        

        #restore cloupe generation

        if [[ $verbose ]]; then

            echo "restore cloupe"
@@ -1894,6 +1904,7 @@ if [[ $lock -eq 0 ]]; then 
            echo "sed -i '/out cloupe *cloupe/ {s/^#*#//g}' ${cellrangerpath}-cs/${cellrangerversion}/mro/*mro"

        fi

        sed -i '/out cloupe *cloupe/ {s/^#*#//g}' ${cellrangerpath}-cs/${cellrangerversion}/mro/*mro

        

        #restore 11 lines for cloupe preprocess call (all following steps are needed to be called together or the call will break)

        ##restore defining CLOUPE_PREPROCESS

        if [[ $verbose ]]; then
@@ -1904,8 +1915,7 @@ if [[ $lock -eq 0 ]]; then 
        sed -i '/output_for_cloupe/s/^#*#//g' ${cellrangerpath}-cs/${cellrangerversion}/mro/*mro 

        ##remove calling CLOUPE_PREPROCESS

        ### iterate over all files calling CLOUPE_PREPROCESS

        for file in $(grep -l  "call CLOUPE_PREPROCESS"  ${cellrangerpath}-cs/${cellrangerversion}/mro/*.mro )

        do

        for file in $(grep -l  "call CLOUPE_PREPROCESS"  ${cellrangerpath}-cs/${cellrangerversion}/mro/*.mro ); do

            #find  start of CLOUPE_PREPROCESS call

            num=$(grep -n "call CLOUPE_PREPROCESS" $file |  head -n 1 | cut -d":" -f1)

            #find end of CLOUPE_PREPROCESS call
@@ -1921,6 +1931,7 @@ if [[ $lock -eq 0 ]]; then 
            #line of HTML in header is removed

            sed '/class="logo"/d' ${cellrangerpath}-cs/${cellrangerversion}/lib/python/cellranger/webshim/template/navbar.backup.html > ${cellrangerpath}-cs/${cellrangerversion}/lib/python/cellranger/webshim/template/navbar.html

        fi

        

        #disable cloupe generation

        if [[ $verbose ]]; then

            echo "disable cloupe"
@@ -2333,7 +2344,6 @@ else 
            

            #returns a combined R1 file with I1-I2-R1 concatenated (I1 and I2 are R1 barcode)

            mv $crIN/Concatenated_File.fastq ${convR1}



        done

    fi
@@ -2491,7 +2501,7 @@ else 
            

            echo "  ...remove internal for ${technology} by matching tag sequence for UMI reads"

            # filter UMI reads by matching tag sequence ATTGCGCAATG (bases 1-11 of R1) and remove as an adapters 

            perl sub/FilterSmartSeqReadUMI.pl --r1=${convR1} --r2=${convR2} --i1=${convI1} --i2=${convI2} --out_dir=$crIN --tag=

            perl sub/FilterSmartSeqReadUMI.pl --r1=${convR1} --r2=${convR2} --i1=${convI1} --i2=${convI2} --tag="ATTGCGCAATG" --out_dir=$crIN

            echo "  ...trim tag sequence from R1"

            

            # returns R1 with tag sequence removed (left trim) starting with 8pbp UMI and corresponding reads for I1, I2, and R2
@@ -2502,7 +2512,7 @@ else 


            echo "  ...concatencate barcodes to R1 from I1 and I2 index files"

            # concatenate barcocdes from dual indexes to R1 as barcode (bases 1-16)

            perl sub/ConcatenateDualIndexBarcodes.pl --additive=${convI1} --additive=${convI2} --ref_fastq=${convR1} --tag="ATTGCGCAATG" --out_dir=$crIN

            perl sub/ConcatenateDualIndexBarcodes.pl --additive=${convI1} --additive=${convI2} --ref_fastq=${convR1} --out_dir=$crIN



            #returns a combined R1 file with I1-I2-R1 concatenated (I1 and I2 are R1 barcode)

            mv $crIN/Concatenated_File.fastq ${convR1}

CRA Git | Maintained and supported by SUSTech CRA and CCSE