shell:
    "mkdir -p ribotish; RiboReport/scripts/createRiboTISHannotation.py -a {input.annotation} --genome_sizes {input.sizes} --annotation_output {output}"

shell:
    "mkdir -p ribotish; gff3ToGenePred {input} {output}"

shell:
    "mkdir -p ribotish; genePredToBed {input} {output}"

shell:
    "mkdir -p qc/all; RiboReport/scripts/annotation_featurecount.py -a {input.annotation} -o {output};"

shell:
    "mkdir -p auxiliary; RiboReport/scripts/enrich_annotation.py -a {input.annotation} -o {output}"

shell:
    """
    mkdir -p auxiliary;
    awk -F'\\t' '/^[^#]/ {{printf "%s\\t%s\\t%s\\t%s\\t%s\\t%s\\t%s\\t%s\\tID=uid%s;\\n", $1, $2, $3, $4, $5, $6, $7, $8, NR-1}}' {input} > {output}
    """

run:
    shell("mkdir -p deepribo; mv {input} deepribo/DeepRibo_model_v1.pt")

shell:
    "mkdir -p coverage_deepribo; RiboReport/scripts/coverage_deepribo.py --alignment_file {input.bam} --output_file_prefix coverage_deepribo/{wildcards.condition}-{wildcards.replicate}"

shell:
    """
    mkdir -p deepribo/{wildcards.condition}-{wildcards.replicate}/0/;
    mkdir -p deepribo/{wildcards.condition}-{wildcards.replicate}/1/;
    DataParser.py {input.covS} {input.covAS} {input.asiteS} {input.asiteAS} {input.genome} deepribo/{wildcards.condition}-{wildcards.replicate} -g {input.annotation}
    """

shell:
    "mkdir -p deepribo; Rscript RiboReport/scripts/parameter_estimation.R -f {input} -o {output}"

shell:
    """
    mkdir -p deepribo;
    DeepRibo.py predict deepribo/ --pred_data {wildcards.condition}-{wildcards.replicate}/ -r {params.rpkm} -c {params.cov} --model {input.model} --dest {output} --num_workers {threads}
    """

shell:
    "mkdir -p tracks; RiboReport/scripts/deepriboGFF.py -c {wildcards.condition}  -i {input} -o {output}"

shell:
    "mkdir -p tracks; RiboReport/scripts/concatGFF.py {input} -o {output}"

shell:
    "mkdir -p genomes; cut -f1,2 {input[0]} > genomes/sizes.genome"

shell:
    "samtools index -@ {threads} maplink/{params.prefix}"

shell:
    "mkdir -p transcripts; RiboReport/scripts/transcriptsToBed.py -i {input} -o {output}"

shell:
    "mkdir -p transcripts; bedtools getfasta -fi {input.genome} -name -bed {input.transcripts} -fo {output}"

shell:
    """
    mkdir -p irsom/model/Escherichia_coli/
    mv forge.ibisc.univ-evry.fr/lplaton/IRSOM/raw/master/model/Escherichia_coli/SLSOM irsom/model/Escherichia_coli/
    mv forge.ibisc.univ-evry.fr/lplaton/IRSOM/raw/master/model/Escherichia_coli/SOM irsom/model/Escherichia_coli/
    """

shell:
    """
    mkdir -p irsom;
    predict.py --featurer={input.featurer} --file={input.transcripts} --model=irsom/model/Escherichia_coli/ --output=irsom/{wildcards.condition}-{wildcards.replicate}/
    """

shell:
    "mkdir -p tracks; RiboReport/scripts/irsomGFF.py -c {wildcards.condition}  -i {input} -o {output}"

shell:
    "mkdir -p tracks; RiboReport/scripts/concatGFF.py {input} -o {output}"

shell:
    "mkdir -p maplink; ln -s {params.inlink} {params.outlink}"

shell:
    "mkdir -p maplink/RIBO/; ln -s {params.inlink} {params.outlink}"

shell:
    "mkdir -p maplink/RIBO/; ln -s {params.inlink} {params.outlink}"

shell:
    "mkdir -p maplink/RNA/; ln -s {params.inlink} {params.outlink}"

shell:
    "mkdir -p maplink/RNA/; ln -s {params.inlink} {params.outlink}"

shell:
    "mkdir -p maplink/TIS/; ln -s {params.inlink} {params.outlink}"

shell:
    "mkdir -p maplink/TIS/; ln -s {params.inlink} {params.outlink}"

shell:
    "mkdir -p maplink/RNATIS/; ln -s {params.inlink} {params.outlink}"

shell:
    "mkdir -p maplink/RNATIS/; ln -s {params.inlink} {params.outlink}"

shell:
    "mkdir -p genomeSegemehlIndex; echo \"Computing Segemehl index\"; segemehl.x --threads {threads} -x {output.index} -d {input.genome} 2> {log};"

shell:
    "mkdir -p sammulti; segemehl.x -e -d {input.genome} -i {input.genomeSegemehlIndex} -q {input.fastq} --threads {threads} -o {output.sammulti} 2> {log}"

shell:
    """
    set +e
    mkdir -p sam
    awk '$2 == "4"' {input.sammulti} > {input.sammulti}.unmapped
    gawk -i inplace '$2 != "4"' {input.sammulti}
    samtools view -H <(cat {input.sammulti}) | grep '@HD' > {output.sam}
    samtools view -H <(cat {input.sammulti}) | grep '@SQ' | sort -t$'\t' -k1,1 -k2,2V >> {output.sam}
    samtools view -H <(cat {input.sammulti}) | grep '@RG' >> {output.sam}
    samtools view -H <(cat {input.sammulti}) | grep '@PG' >> {output.sam}
    cat {input.sammulti} |grep -v '^@' | grep -w 'NH:i:1' >> {output.sam}
    exitcode=$?
    if [ $exitcode -eq 1 ]
    then
        exit 1
    else
        exit 0
    fi
    """

shell: "if [ \"{params.method}\" == \"NOTSET\" ]; then RiboReport/scripts/samstrandinverter.py --sam_in_filepath={input.sam} --sam_out_filepath={output.sam}; else cp {input.sam} {output.sam}; fi"

shell:
    "mkdir -p bammulti; samtools view -@ {threads} -bh {input.sam} | samtools sort -@ {threads} -o {output} -O bam"

shell:
    "mkdir -p rRNAbam; samtools view -@ {threads} -bh {input.sam} | samtools sort -@ {threads} -o {output} -O bam"

shell:
    """
    mkdir -p tracks;
    cat {input.spectre} > {output}.unsorted;
    cat {input.ribotish} >> {output}.unsorted;
    cat {input.reparation} >> {output}.unsorted;
    cat {input.deepribo} >> {output}.unsorted;
    cat {input.irsom} >> {output}.unsorted;
    cat {input.smorfer} >> {output}.unsorted;
    cat {input.ribotricer} >> {output}.unsorted;
    cat {input.price} >> {output}.unsorted;
    bedtools sort -i {output}.unsorted > {output};
    """

shell:
    "mkdir -p tracks; RiboReport/scripts/concatGFF.py {input.mergedGff} -o {output}"

shell:
    "mkdir -p tracks; RiboReport/scripts/allToUniqueGTF.py -i {input} -o {output}"

shell:
    "mkdir -p genomes; mv genome.fa genomes/"

shell:
    "mkdir -p annotation; mv annotation.gff annotation/"

shell:
    "mkdir -p annotation; RiboReport/scripts/gtf2gff3.py -a {input} -o {output}"

shell:
    "mkdir -p annotation; RiboReport/scripts/gff2gtf.py -i {input} -o {output}"

shell:
    """
    mkdir -p price;
    gedi -e IndexGenome -s {input.genome} -a {input.annotation} -nobowtie -nokallisto -nostar -f price/ -o {output} -n price_genome
    """

shell:
    """
    mkdir -p price;
    gedi -e Price -reads {input.bam} -genomic {input.genomic} -prefix price/{wildcards.condition}-{wildcards.replicate}/results
    """

shell:
    """
    mkdir -p price;
    gedi -e ViewCIT -m bed -name 'd.getType()' {input.cit} > {output.bed}
    """

shell:
    "mkdir -p tracks; RiboReport/scripts/priceGFF.py -c {wildcards.condition}  -i {input.filtered} -u {input.unfiltered} -o {output.unfiltered} -f {output.filtered}"

shell:
    """
    mkdir -p tracks;
    RiboReport/scripts/concatGFF.py {input.unfiltered} -o {output.unfiltered}
    RiboReport/scripts/concatGFF.py {input.filtered} -o {output.filtered}
    """

shell:
    "mkdir -p qc/3mapped; fastqc -o qc/3mapped -t {threads} -f sam_mapped {input.sam}; mv qc/3mapped/{params.prefix}_fastqc.html {output.html}; mv qc/3mapped/{params.prefix}_fastqc.zip {output.zip}"

shell:
    "mkdir -p qc/1raw; fastqc -o qc/1raw -t {threads} {input.fastq}; mv qc/1raw/{params.prefix}_fastqc.html {output.html}; mv qc/1raw/{params.prefix}_fastqc.zip {output.zip}"

shell:
    "mkdir -p qc/2trimmed; fastqc -o qc/2trimmed -t {threads} {input}; mv qc/2trimmed/{params.prefix}_fastqc.html {output.html}; mv qc/2trimmed/{params.prefix}_fastqc.zip {output.zip}"

shell:
    "mkdir -p qc/5removedrRNA; fastqc -o qc/5removedrRNA -t {threads} {input}; mv qc/5removedrRNA/{params.prefix}_fastqc.html {output.html}; mv qc/5removedrRNA/{params.prefix}_fastqc.zip {output.zip}"

shell:
    """
    mkdir -p qc/trnainall;
    column3=$(cut -f3 auxiliary/unambigous_annotation.gff | sort | uniq)
    if [[ " ${{column3[@]}} " =~ "tRNA" ]];
    then
        featureCounts -T {threads} -t tRNA -g ID -a {input.annotation} -o {output.txt} {input.bam};
    else
        touch {output.txt};
    fi
    """

shell:
    """
    mkdir -p qc/rrnainall;
    column3=$(cut -f3 auxiliary/unambigous_annotation.gff | sort | uniq)
    if [[ " ${{column3[@]}} " =~ "rRNA" ]];
    then
        featureCounts -T {threads} -t rRNA -g ID -a {input.annotation} -o {output.txt} {input.bam};
    else
        touch {output.txt};
    fi
    """

shell:
    """
    mkdir -p qc/rrnainallaligned;
    column3=$(cut -f3 auxiliary/unambigous_annotation.gff | sort | uniq)
    if [[ " ${{column3[@]}} " =~ "rRNA" ]];
    then
        featureCounts -T {threads} -t rRNA -g ID -a {input.annotation} -o {output.txt} {input.bam};
    else
        touch {output.txt};
    fi
    """

shell:
    """
    mkdir -p qc/rrnainuniquelyaligned;
    column3=$(cut -f3 auxiliary/unambigous_annotation.gff | sort | uniq)
    if [[ " ${{column3[@]}} " =~ "rRNA" ]];
    then
        featureCounts -T {threads} -t rRNA -g ID -a {input.annotation} -o {output.txt} {input.bam};
    else
        touch {output.txt};
    fi
    """

shell:
    "mkdir -p coverage; bedtools genomecov -ibam {input} -bg > {output}"

shell:
    """
    mkdir -p auxiliary
    UNIQUE="$(cut -f3 {input.annotation} | sort | uniq)"
    IDENTIFIER="ID"
    LINE="$(sed '3q;d' {input.annotation})"
    if [[ $LINE == *"gene_id="* ]]; then IDENTIFIER="gene_id"; fi;
    for f in ${{UNIQUE}}
    do
        featureCounts -F GTF -s 1 -g $IDENTIFIER -O -t $f -M --fraction -a {input.annotation} {input.bam} -T {threads} -o auxiliary/annotation_total_reads.raw.tmp
        cat auxiliary/annotation_total_reads.raw.tmp | sed 1,2d | awk -v var=$f -FS'\\t' '{{print $0"\\t"var}}' >> {output}
        rm auxiliary/annotation_total_reads.raw.tmp
    done
    """

shell:
    """
    mkdir -p auxiliary; RiboReport/scripts/map_reads_to_annotation.py -i {input.reads} -a {input.annotation} -o {output}
    """

shell:
    "mkdir -p auxiliary; RiboReport/scripts/total_mapped_reads.py -b {input.bam} -m {output.mapped} -l {output.length}"

shell:
    "mkdir -p auxiliary; RiboReport/scripts/generate_output_annotation.py -t {input.total} -r {input.reads} -g {input.genome} -o {output.xlsx} --simple {output.annotation} --complete {output.complete}"

run:
    outputName = os.path.basename(input[0])
    shell("mkdir -p uniprotDB; mv {input} uniprotDB/{outputName}; gunzip uniprotDB/{outputName}")

shell:
    "mkdir -p reparation; if [ uniprotDB/uniprot_sprot.fasta.bak does not exist ]; then cp -p uniprotDB/uniprot_sprot.fasta uniprotDB/uniprot_sprot.fasta.bak; fi; mkdir -p {params.prefix}/tmp; reparation.pl -bam {input.bam} -g {input.genome} -gtf {input.gtf} -db {input.db} -out {params.prefix} -threads {threads}; if [ uniprotDB/uniprot_sprot.fasta does not exist ]; then cp -p uniprotDB/uniprot_sprot.fasta.bak uniprotDB/uniprot_sprot.fasta; fi;"

shell:
    "mkdir -p tracks; RiboReport/scripts/reparationGFF.py -c {wildcards.condition}  -r {wildcards.replicate} -i {input} -o {output}"

shell:
    "mkdir -p tracks; RiboReport/scripts/concatGFF.py {input} -o {output}"

shell:
    "mkdir -p ribotish; ribotish quality -v -p {threads} -b {input.fp} -g {input.annotation} -o {params.reporttxt} -f {params.reportpdf} 2> {log} || true; if grep -q \"offdict = {{'m0': {{}}}}\" {params.offsetparameters}; then mv {params.offsetparameters} {params.offsetparameters}.unused; fi; touch {output.offsetdone}"

shell:
    "mkdir -p ribotish; ribotish predict -v {params.codons} -p {threads} -b {params.fplist} -g {input.annotation} -f {input.genome} -o {output.filtered} 2> {log}"

shell:
    "mkdir -p tracks; RiboReport/scripts/ribotishGFF.py -c {wildcards.condition} -i {input} -o {output}"

shell:
    """
    mkdir -p ribotricer;
    ribotricer prepare-orfs --gtf {input.annotation} --fasta {input.genome} --prefix ribotricer/ribotricer --min_orf_length 6 --start_codons ATG,GTG,TTG
    """

shell:
    """
    mkdir -p ribotricer/{wildcards.condition}-{wildcards.replicate};
    ribotricer learn-cutoff --ribo_bams {input.bam_ribo} --rna_bams {input.bam_rna}  --prefix ribotricer/ribotricer --ribotricer_index {input.index} | tail -n 1 | grep -Eo '[+-]?[0-9]+([.][0-9]+)?'> {output}
    """

shell:
    """
    mkdir -p ribotricer/{wildcards.condition}-{wildcards.replicate}
    ribotricer detect-orfs --bam {input.bam_ribo} --ribotricer_index {input.index} --prefix ribotricer/{wildcards.condition}-{wildcards.replicate}/ribotricer --phase_score_cutoff {params.cutoff}
    """

shell:
    "mkdir -p tracks; RiboReport/scripts/ribotricerGFF.py -c {wildcards.condition}  -i {input} -o {output}"

shell:
    "mkdir -p tracks; RiboReport/scripts/concatGFF.py {input} -o {output}"

shell:
    """
    mkdir -p annotation; awk -F'\\t' '$3 == "rRNA" || $3 == "tRNA"' {input.annotation} | awk -F'\\t' '{{print $1 FS $4 FS $5 FS "." FS "." FS $7}}' > {output.annotation}
    """

shell:
    "bedtools intersect -v -a {input.mapuniq} -b {input.annotation} > {output.bam}"

shell:
    """
    mkdir -p smorfer;
    smorfer.sh -s putative_orfs.sh -g {input.genome} -c {params.genome_name} -n smorfer_pORFs -i 9-150 -o smorfer/
    """

shell:
    """
    mkdir -p smorfer;
    smorfer.sh -s FT_GCcontent.sh -g {input.genome} -o smorfer/ -b {input.bed}
    """

shell:
    """
    mkdir -p smorfer/{wildcards.condition}-{wildcards.replicate};
    smorfer.sh -s count_RPF.sh -b {input.bed} -a {input.bam} -o smorfer/{wildcards.condition}-{wildcards.replicate}/
    """

shell:
    """
    mkdir -p smorfer/{wildcards.condition}-{wildcards.replicate};
    smorfer.sh -s FT_RPF.sh high_expressed_ORFs.bed calibrated_RiboSeq.bam -b {input.bed} -a {input.bam} -o smorfer/{wildcards.condition}-{wildcards.replicate}/
    """

shell:
    """
    mkdir -p smorfer/{wildcards.condition}-{wildcards.replicate};
    smorfer.sh -s find_best_start.sh -b {input.bed} -a {input.bam} -o smorfer/{wildcards.condition}-{wildcards.replicate}/
    """

shell:
    """
    mkdir -p smorfer/{wildcards.condition}-{wildcards.replicate}_noFT;
    smorfer.sh -s count_RPF.sh -b {input.bed} -a {input.bam} -o smorfer/{wildcards.condition}-{wildcards.replicate}_noFT/
    """

shell:
    "mkdir -p tracks; RiboReport/scripts/smorferGFF.py -c {wildcards.condition}  -i {input} -o {output}"

shell:
    "mkdir -p tracks; RiboReport/scripts/concatGFF.py {input} -o {output}"

shell:
    """
    mkdir -p spectre;
    SPECtre.py --input {input.bam} --output {output.results} --log {output.log} --fpkm {input.fpkm} --gtf {input.gtf} --nt {threads}
    """

shell:
    "mkdir -p tracks; RiboReport/scripts/spectreGFF.py -c {wildcards.condition}  -i {input} -o {output}"

shell:
    "mkdir -p tracks; RiboReport/scripts/concatGFF.py {input} -o {output}"

shell:
    "mkdir -p trimlink; ln -s {params.inlink} {params.outlink};"

shell:
    "mkdir -p genomes; RiboReport/scripts/reverseComplement.py --input_fasta_filepath genomes/genome.fa --output_fasta_filepath genomes/genome.rev.fa"

shell:
    "mkdir -p tracks; RiboReport/scripts/motif2GFF3.py --input_genome_fasta_filepath {input.fwd} --input_reverse_genome_fasta_filepath {input.rev} --motif_string ATG --output_gff3_filepath {output}"

shell:
    "mkdir -p tracks; RiboReport/scripts/motif2GFF3.py --input_genome_fasta_filepath {input.fwd} --input_reverse_genome_fasta_filepath {input.rev} --motif_string GTG,TTG,CTG --output_gff3_filepath {output}"

shell:
    "mkdir -p tracks; RiboReport/scripts/motif2GFF3.py --input_genome_fasta_filepath {input.fwd} --input_reverse_genome_fasta_filepath {input.rev} --motif_string TAG,TGA,TAA --output_gff3_filepath {output}"

shell:
    "mkdir -p tracks; RiboReport/scripts/motif2GFF3.py --input_genome_fasta_filepath {input.fwd} --input_reverse_genome_fasta_filepath {input.rev} --motif_string AAGG --output_gff3_filepath {output}"

shell:
   "mkdir -p globaltracks; mkdir -p globaltracks/raw; mkdir -p globaltracks/mil; mkdir -p globaltracks/min; RiboReport/scripts/mapping.py --mapping_style global --bam_path {input.bam} --wiggle_file_path globaltracks/ --no_of_aligned_reads_file_path {input.stats} --library_name {params.prefix};"

shell:
    "wigToBigWig {input.rev} {input.genomeSize} {output.rev}"

shell:
    "wigToBigWig {input.fwd} {input.genomeSize} {output.fwd}"

shell:
    "wigToBigWig {input.rev} {input.genomeSize} {output.rev}"

shell:
    "wigToBigWig {input.fwd} {input.genomeSize} {output.fwd}"

shell:
    "wigToBigWig {input.rev} {input.genomeSize} {output.rev}"

shell:
     "mkdir -p centeredtracks; mkdir -p centeredtracks/raw; mkdir -p centeredtracks/mil; mkdir -p centeredtracks/min; RiboReport/scripts/mapping.py --mapping_style centered --bam_path {input.bam} --wiggle_file_path centeredtracks/ --no_of_aligned_reads_file_path {input.stats} --library_name {params.prefix};"

shell:
    "wigToBigWig {input.fwd} {input.genomeSize} {output.fwd}"

shell:
    "wigToBigWig {input.rev} {input.genomeSize} {output.rev}"

shell:
    "wigToBigWig {input.fwd} {input.genomeSize} {output.fwd}"

shell:
    "wigToBigWig {input.rev} {input.genomeSize} {output.rev}"

shell:
    "wigToBigWig {input.fwd} {input.genomeSize} {output.fwd}"

shell:
    "wigToBigWig {input.rev} {input.genomeSize} {output.rev}"

shell:
    "mkdir -p fiveprimetracks; mkdir -p fiveprimetracks/raw; mkdir -p fiveprimetracks/mil; mkdir -p fiveprimetracks/min; RiboReport/scripts/mapping.py --mapping_style first_base_only --bam_path {input.bam} --wiggle_file_path fiveprimetracks/ --no_of_aligned_reads_file_path {input.stats} --library_name {params.prefix};"

shell:
    "wigToBigWig {input.fwd} {input.genomeSize} {output.fwd}"

shell:
    "wigToBigWig {input.rev} {input.genomeSize} {output.rev}"

shell:
    "wigToBigWig {input.fwd} {input.genomeSize} {output.fwd}"

shell:
    "wigToBigWig {input.rev} {input.genomeSize} {output.rev}"

shell:
    "wigToBigWig {input.fwd} {input.genomeSize} {output.fwd}"

shell:
    "wigToBigWig {input.rev} {input.genomeSize} {output.rev}"

shell:
    "mkdir -p threeprimetracks; mkdir -p threeprimetracks/raw; mkdir -p threeprimetracks/mil; mkdir -p threeprimetracks/min; RiboReport/scripts/mapping.py --mapping_style last_base_only --bam_path {input.bam} --wiggle_file_path threeprimetracks/ --no_of_aligned_reads_file_path {input.stats} --library_name {params.prefix};"

shell:
    "wigToBigWig {input.fwd} {input.genomeSize} {output.fwd}"

shell:
    "wigToBigWig {input.rev} {input.genomeSize} {output.rev}"

shell:
    "wigToBigWig {input.fwd} {input.genomeSize} {output.fwd}"

shell:
    "wigToBigWig {input.rev} {input.genomeSize} {output.rev}"

shell:
    "wigToBigWig {input.fwd} {input.genomeSize} {output.fwd}"

shell:
    "wigToBigWig {input.rev} {input.genomeSize} {output.rev}"

shell:
    "mkdir -p tracks; multiBamSummary bins --smartLabels --bamfiles maplink/*.bam -o {output} -p {threads};"

shell:
    "mkdir -p figures; plotCorrelation -in {input.npz} --corMethod spearman --skipZeros --plotTitle \"Spearman Correlation of Read Counts\" --whatToPlot heatmap --colorMap RdYlBu --plotNumbers -o {output.correlation} --outFileCorMatrix SpearmanCorr_readCounts.tab"

shell:
    "mkdir -p tracks; cut -f1-6 {input[0]} > tracks/annotationNScore.bed6;  awk '{{$5=1 ; print ;}}' tracks/annotation.bed6 > tracks/annotation.bed6; bedToBigBed -type=bed6 -tab tracks/annotation.bed6 {input[1]} tracks/annotation.bb"