Util.rules

# output directory and log
U_OUT, U_LOG = prepare_environment('Util')

rule _DOWNLOAD_HUMAN_DB:
    output:
        expand("{path}/{filter}.{ext}", path=DBPATH + "/human", filter=config["human_filtering"]["filter"], ext=['fa'])
    params:
        filter = config["human_filtering"]["filter"], outdir = DBPATH + "/human"
    shell:
        """
        TMPD=$(mktemp -d -t --tmpdir={TMPDIR} "XXXXXX")
        wget {config[human_filtering][url]} -O $TMPD/{params.filter}.fa.gz
        gunzip $TMPD/{params.filter}.fa.gz
        mkdir -p {params.outdir}
        mv $TMPD/{params.filter}.fa {params.outdir}
        rm -rf $TMPD
        """


rule _DOWNLOAD_SORTMERNA_DATABASES:
    output:
        expand("{path}/{files}.fasta", files=config["sortmerna"]["files"], path=DBPATH + "/sortmerna")
    shell:
        """
        TMPD=$(mktemp -d -t --tmpdir={tmp} "XXXXXX")
        wget {pkg_url} -O $TMPD/sortmerna.tgz
        tar -xzf  $TMPD/sortmerna.tgz --strip-components=1 -C $TMPD
        mkdir -p {path}
        mv $TMPD/rRNA_databases/*.fasta {path}/.
        rm -rf $TMPD
        """.format(pkg_url=config["sortmerna"]["pkg_url"], path=DBPATH + "/sortmerna", tmp=TMPDIR)

rule _DOWNLOAD_PROKKA_DATABASES:
    output:
        expand("{path}/{db}", path=DBPATH, db=config["prokka"]["databases"])
    shell:
        """
        TMPDIR=$(mktemp -d -t "XXXXXX")
        wget {pkg_url} -O $TMPDIR/prokka.tgz
        tar -xzf $TMPDIR/prokka.tgz --strip-components=1 -C $TMPDIR
        mkdir -p {path}
        cp -r $TMPDIR/db/* {path}/.
        rm -rf $TMPDIR
        prokka --setupdb
        """.format(pkg_url=config["prokka"]["pkg_url"], path=DBPATH)


rule _DOWNLOAD_TRIMMOMATIC_ADAPTERS:
    output:
        "{DBPATH}/adapters/adapters.done"
    shell:
        """
        wget http://www.usadellab.org/cms/uploads/supplementary/Trimmomatic/Trimmomatic-Src-0.32.zip
        unzip Trimmomatic-Src-0.32.zip
        cp -r trimmomatic-0.32/adapters {DBPATH}
        rm Trimmomatic-Src-0.32.zip && rm -rf trimmomatic-0.32
        touch {output}
        """


rule _DOWNLOAD_LIBRARY_FILES:
    output:
        "lib/d3.min.js", "lib/d3pie.min.js", "lib/jquery-2.1.1.min.js"
    shell:
        """
        wget https://raw.githubusercontent.com/mbostock/d3/master/d3.min.js -O lib/d3.min.js
        wget https://raw.githubusercontent.com/benkeen/d3pie/0.1.3/d3pie/d3pie.min.js -O lib/d3pie.min.js
        wget http://code.jquery.com/jquery-2.1.1.min.js -O lib/jquery-2.1.1.min.js
        """

rule INDEX_SORTMERNA_DB:
    log:
        U_LOG
    benchmark:
        "%s/benchmarks/INDEX_SORTMERNA_DB.json" % U_OUT
    input:
        expand("{path}/{files}.fasta", files=config["sortmerna"]["files"], path=DBPATH + "/sortmerna")
    output:
        expand(
            "{path}/idx/{files}.{ext}",
            files=config["sortmerna"]["files"],
            path=DBPATH + "/sortmerna",
            ext=['bursttrie_0.dat', 'kmer_0.dat', 'pos_0.dat', 'stats'])
    run:
        fastaindexed = expand(
            "{path}/idx/{files}",
            files=config["sortmerna"]["files"],
            path=DBPATH + "/sortmerna")
        ref = ':'.join('%s,%s' % (a, b) for a, b in zip(input, fastaindexed))
        shell("mkdir -p {DBPATH}/sortmerna")
        shell("indexdb_rna --ref {ref} > {log}  2>&1")


rule DIAGRAMMS:
    message:
        "Creating diagramms."
    output:
        expand(["{dir}/workflow.png", "{dir}/workflow.pdf"], dir=OUTPUTDIR)
    params:
        outdir = "%s" % OUTPUTDIR
    shell:
        """
        snakemake ALL --forceall --dag | dot -Tpng > {params.outdir}/workflow.png
        snakemake ALL --forceall --dag | dot -Tpdf > {params.outdir}/workflow.pdf
        """

rule REPORT:
    input:
        ["lib/imp.html", "lib/d3.min.js", "lib/jquery-2.1.1.min.js", "lib/imp.js"] + expand(["{dir}/workflow.png", "{dir}/workflow.pdf"], dir=OUTPUTDIR)
    params:
        outdir = "%s" % OUTPUTDIR
    message:
        'Create report'
    run:
        with open('%s/data.js' % OUTPUTDIR, 'w') as whandle:
            towrite = json.dumps(config)
            whandle.write("IMP_CONFIG = %s;" % towrite)
            if os.path.exists('stats.json'):
                with open('stats.json', 'r') as rhandle:
                    towrite = json.load(rhandle)
                    whandle.write("\nIMP_STATS = %s;" % towrite )
        shell("cp {input[0]} {params.outdir}/IMP.html")
        shell("cp {input[1]} {params.outdir}")
        shell("cp {input[2]} {params.outdir}")
        shell("cp {input[3]} {params.outdir}")
        if os.path.exists('imp.log'):
            shell("mv imp.log {params.outdir}")


rule REPORT2:
        input:
            ["lib/imp.html", "lib/d3.min.js", "lib/jquery-2.1.1.min.js", "lib/imp.js"]
        params:
            outdir = "%s" % OUTPUTDIR
        message:
            'Create report'
        run:
          with open('%s/data.js' % OUTPUTDIR, 'w') as whandle:
                  towrite = json.dumps(config)
                  whandle.write("IMP_CONFIG = %s;" % towrite)
                  if os.path.exists('stats.json'):
                          with open('stats.json', 'r') as rhandle:
                                  towrite = json.load(rhandle)
                                  whandle.write("\nIMP_STATS = %s;" % towrite)
          shell("cp {input[0]} {params.outdir}/IMP.html")
          shell("cp {input[1]} {params.outdir}")
          shell("cp {input[2]} {params.outdir}")
          shell("cp {input[3]} {params.outdir}")
          if os.path.exists('imp.log'):
            shell("mv imp.log {params.outdir}")


rule INDEX_FASTA_FILE:
    log:
        U_LOG
    benchmark:
        "%s/benchmarks/INDEX_FASTA_FILE.json" % U_OUT
    input:
        "{fasta}"
    output:
        "{fasta}.amb",
        "{fasta}.bwt",
        "{fasta}.pac",
        "{fasta}.sa",
        "{fasta}.ann"
    shell:
        """
        bwa index {wildcards.fasta} > {log} 2>&1
        """

rule CHECK_TOOL_VERSION:
    log:
        U_LOG
    benchmark:
        "%s/benchmarks/CHECK_TOOL_VERSION.json" % U_OUT
    output:
        "%s/tools.versions" % U_OUT
    shell:
        """
        echo "# ht2-stat" > {output}
        ht2-stat --version >> {output}
        echo "# ht2-stat-draw.pl" >> {output}
        which ht2-stat-draw.pl | md5sum | awk '{{print $1}}' >> {output}
        echo "# Trimmomatic" >> {output}
        echo "{config[Preprocessing][trimmomatic][jarfile]}" | grep -Eo '[0-9]+.[0-9]+' >> {output}
        echo "# Sortmerna" >> {output} 2>&1
        sortmerna --version >> {output} 2>&1
        echo "# megahit" >> {output}
        megahit --help > megahit_version 2>&1
        cat megahit_version | head -1 >> {output}
        echo "# bwa" >> {output}
        bwa > bwa_version 2>&1
        cat bwa_version | grep -i "version" >> {output}
        echo "# samtools" >> {output}
        samtools > samtools_version 2>&1
        cat samtools_version | grep "Version" >> {output}
        echo "# bamToFastq" >> {output}
        bamToFastq > bamToFastq_version 2>&1
        cat bamToFastq_version | grep -i "version" >> {output}
        echo "# idba_ud" >> {output}
        echo "# fq2fa" >> {output}
        echo "# cap3"  >> {output}
        echo "# coverageBed"  >> {output}
        echo "# bh_tsne" >> {output}
        echo "# KronaTools" >> {output}

        """

rule _DOWNLOAD_KEGG_INFORMATION:
    log:
        U_LOG
    benchmark:
        "%s/benchmarks/DOWNLOAD_KEGG_INFORMATION.json" % U_OUT
    output:
        "%s/ec2pwy.txt" % U_OUT,
        "%s/pwy2hierarchy.txt" % U_OUT
    shell:
        """
        echo "[x] DOWNLOAD_KEGG_INFORMATION `date +"%Y/%m/%d %H:%M:%S"`" >> {log}
        echo "Preparing EC to KEGG ID mappings"
        python {SRCDIR}/make.ec.to.pwy.kegg.py -o {output[0]}
        echo "Preparing KEGG ID to pathway mappings"
        python {SRCDIR}/make.pwy.hierarchy.kegg.py -o {output[1]}
        """