while read line
do
    if [[ $line =~ ^\>.* ]]
    then
        echo $line | sed 's/>//' | tr -d '\n'
        echo -e -n '\t'
    else
        echo $line | sed 's/[^-]//g' | awk '{{ print length }}'
    fi
done < "${1:-/dev/stdin}"

import pandas as pd
import sys
from tabulate import tabulate

# usage
usage = '''
repseqs_lengths_describe.py repseqs_lengths_tsv repseqs_lengths_md

'''

if len(sys.argv) < 1:
    print(usage)
    sys.exit()

# input paths
IN = sys.argv[1]

# output paths
OUT = sys.argv[2] # 'repseqs_lengths_describe.md'

s = pd.read_csv(IN, header=None, index_col=0, sep='\t')
t = s.describe()
outstr = tabulate(t.iloc[1:], tablefmt="pipe", headers=['Statistic (n=%s)' % t.iloc[0].values[0].astype(int), 'Sequence length'])
with open(OUT, 'w') as target:
    target.write(outstr)
    target.write('\n')

import pandas as pd
from tabulate import tabulate
import sys

# usage
usage = '''
summarize_metadata.py metadata output1_md output2_txt

'''

if len(sys.argv) < 2:
    print(usage)
    sys.exit()

# input paths
metadata = sys.argv[1]

# output paths
output1 = sys.argv[2] # 'manifest_pe.csv'
output2 = sys.argv[3] # 'manifest_se.csv'

df = pd.read_csv(metadata, sep='\t')
cols = df.columns
df2 = pd.DataFrame(columns =[0,1], index=cols)
for col in cols:
    if col in df.columns:
        vc = df[col].value_counts()
        if vc.index.shape == (0,):
            df2.loc[col, 0] = '(no values in column)'
            df2.loc[col, 1] = '--'
        else:
            df2.loc[col, 0] = vc.index[0]
            df2.loc[col, 1] = vc.values[0]
    else:
        df2.loc[col, 0] = '(column not provided)'
        df2.loc[col, 1] = '--'
df2.columns = ['Most common value', 'Count']
df2.index.name = 'Column name'
outstr = tabulate(df2, tablefmt="pipe", headers="keys")
with open(output1, 'w') as target:
    target.write(outstr)
    target.write('\n')
with open(output2, 'w') as target:
    [target.write('%s\n' % i) for i in cols]

shell:
    "if [ -r '00-data/metadata.tsv' ]; then "
    "    echo 'OK: Metadata file 00-data/metadata.tsv found.'; "
    "else echo 'Error: Metadata file 00-data/metadata.tsv not found.' && exit 1; "
    "fi; "

shell:
    "python scripts/summarize_metadata.py {input.metadata} {output[0]} {output[1]}"

shell:
    "if [ -r '01-imported/fastq_pe.qza' ]; then "
    "    echo 'OK: FASTQ archive 01-imported/fastq_pe.qza found; FASTQ manifest file 00-data/manifest_pe.csv not required.'; "
    "elif [ -r '00-data/manifest_pe.csv' ]; then "
    "    echo 'OK: FASTQ manifest file 00-data/manifest_pe.csv found; it will be used to create FASTQ archive 01-imported/fastq_pe.qza.'; "
    "else echo 'Error: FASTQ sequence data not found; either 00-data/manifest_pe.csv or 01-imported/fastq_pe.qza is required.' && exit 1; "
    "fi; "
    "if [ {params.classifymethod} = naive-bayes ]; then "
    "    if [ -r '01-imported/classifier.qza' ]; then "
    "        echo 'OK: Reference sequences classifier 01-imported/classifier.qza found; reference sequences FASTA file 00-data/refseqs.fna not required.'; "
    "    elif [ -r '01-imported/refseqs.qza' ]; then "
    "        echo 'OK: Reference sequences archive 01-imported/refseqs.qza found; reference sequences FASTA file 00-data/refseqs.fna not required.'; "
    "    elif [ -r '00-data/refseqs.fna' ]; then "
    "        echo 'OK: Reference sequences FASTA file 00-data/refseqs.fna found; it will be used to create reference sequences archive 01-imported/refseqs.qza.'; "
    "    else echo 'Error: Reference sequences not found; either 01-imported/classifier.qza or 00-data/refseqs.fna or 01-imported/refseqs.qza is required.' && exit 1; "
    "    fi; "
    "elif [ -r '01-imported/refseqs.qza' ]; then "
    "    echo 'OK: Reference sequences archive 01-imported/refseqs.qza found; reference sequences FASTA file 00-data/refseqs.fna not required.'; "
    "elif [ -r '00-data/refseqs.fna' ]; then "
    "    echo 'OK: Reference sequences FASTA file 00-data/refseqs.fna found; it will be used to create reference sequences archive 01-imported/refseqs.qza.'; "
    "else echo 'Error: Reference sequences not found; either 00-data/refseqs.fna or 01-imported/refseqs.qza is required.' && exit 1; "
    "fi; "
    "if [ {params.classifymethod} != naive-bayes ]; then "
    "    if [ -r '01-imported/reftax.qza' ]; then "
    "        echo 'OK: Reference taxonomy archive 01-imported/reftax.qza found; reference taxonomy file 00-data/reftax.tsv not required.'; "
    "    elif [ -r '00-data/reftax.tsv' ]; then "
    "        echo 'OK: Reference taxonomy file 00-data/reftax.tsv found; it will be used to create reference taxonomy archive 01-imported/reftax.qza.'; "
    "    else echo 'Error: Reference taxonomy not found; either 00-data/reftax.tsv or 01-imported/reftax.qza is required.' && exit 1; "
    "    fi; "
    "fi; "
    "if grep -q ^{params.column}$ {input}; then "
    "    echo 'OK: Metadata contains the column \"{params.column}\" that is specified as beta_group_column in config.yaml.'; "
    "else echo 'Error: Metadata does not contain the column \"{params.column}\" that is specified as beta_group_column in config.yaml.' && exit 1; "
    "fi"

shell:
    "if [ -r '01-imported/fastq_se.qza' ]; then "
    "    echo 'OK: FASTQ archive 01-imported/fastq_se.qza found; FASTQ manifest file 00-data/manifest_se.csv not required.'; "
    "elif [ -r '00-data/manifest_se.csv' ]; then "
    "    echo 'OK: FASTQ manifest file 00-data/manifest_se.csv found; it will be used to create FASTQ archive 01-imported/fastq_se.qza.'; "
    "else echo 'Error: FASTQ sequence data not found; either 00-data/manifest_se.csv or 01-imported/fastq_se.qza is required.' && exit 1; "
    "fi; "
    "if [ {params.classifymethod} = naive-bayes ]; then "
    "    if [ -r '01-imported/classifier.qza' ]; then "
    "        echo 'OK: Reference sequences classifier 01-imported/classifier.qza found; reference sequences FASTA file 00-data/refseqs.fna not required.'; "
    "    elif [ -r '01-imported/refseqs.qza' ]; then "
    "        echo 'OK: Reference sequences archive 01-imported/refseqs.qza found; reference sequences FASTA file 00-data/refseqs.fna not required.'; "
    "    elif [ -r '00-data/refseqs.fna' ]; then "
    "        echo 'OK: Reference sequences FASTA file 00-data/refseqs.fna found; it will be used to create reference sequences archive 01-imported/refseqs.qza.'; "
    "    else echo 'Error: Reference sequences not found; either 01-imported/classifier.qza or 00-data/refseqs.fna or 01-imported/refseqs.qza is required.' && exit 1; "
    "    fi; "
    "elif [ -r '01-imported/refseqs.qza' ]; then "
    "    echo 'OK: Reference sequences archive 01-imported/refseqs.qza found; reference sequences FASTA file 00-data/refseqs.fna not required.'; "
    "elif [ -r '00-data/refseqs.fna' ]; then "
    "    echo 'OK: Reference sequences FASTA file 00-data/refseqs.fna found; it will be used to create reference sequences archive 01-imported/refseqs.qza.'; "
    "else echo 'Error: Reference sequences not found; either 00-data/refseqs.fna or 01-imported/refseqs.qza is required.' && exit 1; "
    "fi; "
    "if [ {params.classifymethod} != naive-bayes ]; then "
    "    if [ -r '01-imported/reftax.qza' ]; then "
    "        echo 'OK: Reference taxonomy archive 01-imported/reftax.qza found; reference taxonomy file 00-data/reftax.tsv not required.'; "
    "    elif [ -r '00-data/reftax.tsv' ]; then "
    "        echo 'OK: Reference taxonomy file 00-data/reftax.tsv found; it will be used to create reference taxonomy archive 01-imported/reftax.qza.'; "
    "    else echo 'Error: Reference taxonomy not found; either 00-data/reftax.tsv or 01-imported/reftax.qza is required.' && exit 1; "
    "    fi; "
    "fi; "
    "if grep -q ^{params.column}$ {input}; then "
    "    echo 'OK: Metadata contains the column \"{params.column}\" that is specified as beta_group_column in config.yaml.'; "
    "else echo 'Error: Metadata does not contain the column \"{params.column}\" that is specified as beta_group_column in config.yaml.' && exit 1; "
    "fi"

shell:
    "qiime tools import "
    "--type 'FeatureData[Sequence]' "
    "--input-path {input} "
    "--output-path {output}"

shell:
    "qiime tools import "
    "--type 'FeatureData[Taxonomy]' "
    "--input-format HeaderlessTSVTaxonomyFormat "
    "--input-path {input} "
    "--output-path {output}"

shell:
    "qiime tools import "
    "--type 'SampleData[PairedEndSequencesWithQuality]' "
    "--input-path {input[0]} "
    "--output-path {output} "
    "--input-format PairedEndFastqManifestPhred33"

shell:
    "qiime tools import "
    "--type 'SampleData[SequencesWithQuality]' "
    "--input-path {input[0]} "
    "--output-path {output} "
    "--input-format SingleEndFastqManifestPhred33"

shell:
    "qiime demux summarize "
    "--i-data {input[0]} "
    "--o-visualization {output}"

shell:
    "qiime demux summarize "
    "--i-data {input[0]} "
    "--o-visualization {output}"

shell:
    "unzip -qq -o {input} -d temp0; "
    "mv temp0/*/data/per-sample-fastq-counts.tsv {output}; "
    "/bin/rm -r temp0"

shell:
    "python scripts/describe_fastq_counts.py {input} {output}"

shell:
    "qiime dada2 denoise-paired "
    "--i-demultiplexed-seqs {input[0]} "
    "--p-trunc-len-f {params.trunclenf} "
    "--p-trunc-len-r {params.trunclenr} "
    "--p-trim-left-f {params.trimleftf} "
    "--p-trim-left-r {params.trimleftr} "
    "--p-max-ee-f {params.maxeef} "
    "--p-max-ee-r {params.maxeer} "
    "--p-trunc-q {params.truncq} "
    "--p-pooling-method {params.poolingmethod} "
    "--p-chimera-method {params.chimeramethod} "
    "--p-min-fold-parent-over-abundance {params.minfoldparentoverabundance} "
    "--p-n-reads-learn {params.nreadslearn} "
    "--p-n-threads {threads} "
    "{params.hashedfeatureids} "
    "--o-table {output.table} "
    "--o-representative-sequences {output.repseqs} "
    "--o-denoising-stats {output.stats} "
    "--verbose"

shell:
    "qiime dada2 denoise-single "
    "--i-demultiplexed-seqs {input[0]} "
    "--p-trunc-len {params.trunclen} "
    "--p-trim-left {params.trimleft} "
    "--p-max-ee {params.maxee} "
    "--p-trunc-q {params.truncq} "
    "--p-pooling-method {params.poolingmethod} "
    "--p-chimera-method {params.chimeramethod} "
    "--p-min-fold-parent-over-abundance {params.minfoldparentoverabundance} "
    "--p-n-reads-learn {params.nreadslearn} "
    "--p-n-threads {threads} "
    "{params.hashedfeatureids} "
    "--o-table {output.table} "
    "--o-representative-sequences {output.repseqs} "
    "--o-denoising-stats {output.stats} "
    "--verbose"

shell:
    "qiime deblur denoise-other "
    "--i-demultiplexed-seqs {input.seqs} "
    "--i-reference-seqs {input.refseqs} "
    "--p-trim-length {params.trimlength} "
    "{params.samplestats} "
    "--p-mean-error {params.meanerror} "
    "--p-indel-prob {params.indelprob} "
    "--p-indel-max {params.indelmax} "
    "--p-min-reads {params.minreads} "
    "--p-min-size {params.minsize} "
    "--p-jobs-to-start {threads} "
    "{params.hashedfeatureids} "
    "--o-table {output.table} "
    "--o-representative-sequences {output.repseqs} "
    "--o-stats {output.stats} "
    "--verbose"

shell:
    "qiime feature-table summarize "
    "--i-table {input.table} "
    "--m-sample-metadata-file {input.metadata} "
    "--o-visualization {output}"

shell:
    "qiime metadata tabulate "
    "--m-input-file {input.stats} "
    "--o-visualization {output}"

shell:
    "qiime tools export "
    "--input-path {input} "
    "--output-path {output} "
    "--output-format BIOMV210Format"

shell:
    "biom summarize-table "
    "--input-fp {input} "
    "--output-fp {output}; "
    "cat {output} | sed 's/observation/feature/g' | sed 's/.000$//' > temp; "
    "mv temp {output}"

shell:
    "biom summarize-table "
    "--observations "
    "--input-fp {input} "
    "--output-fp {output}; "
    "cat {output} | sed 's/observation/feature/g' | sed 's/Counts\/sample/Counts\/feature/g' | sed 's/.000$//' > temp; "
    "mv temp {output}"

shell:
    "qiime feature-table tabulate-seqs "
    "--i-data {input} "
    "--o-visualization {output}"

shell:
    "qiime tools export "
    "--input-path {input} "
    "--output-path {output} "
    "--output-format DNAFASTAFormat"

shell:
    "python scripts/detect_amplicon_locus.py -i {input} > {output}"

shell:
    "perl scripts/fastaLengths.pl {input} > {output}"

shell:
    "python scripts/repseqs_lengths_describe.py {input} {output}"

shell:
    "echo classify_method: {params.classifymethod}; "
    "if [ {params.classifymethod} = naive-bayes ]; then "
    "    if [ ! -r 01-imported/classifier.qza ]; then "
    "        qiime feature-classifier fit-classifier-naive-bayes "
    "        --i-reference-reads {params.refseqs} "
    "        --i-reference-taxonomy {params.reftax} "
    "        --o-classifier 01-imported/classifier.qza; "
    "    fi; "
    "    qiime feature-classifier classify-sklearn "
    "    --i-classifier 01-imported/classifier.qza "
    "    --i-reads {input.repseqs} "
    "    --o-classification {output} "
    "    --p-n-jobs {threads} "
    "    {params.classifyparams}; "
    "elif [ {params.classifymethod} = consensus-blast ]; then "
    "    qiime feature-classifier classify-consensus-blast "
    "    --i-reference-reads {params.refseqs} "
    "    --i-reference-taxonomy {params.reftax} "
    "    --i-query {input.repseqs} "
    "    --o-classification {output} "
    "    --o-search-results {params.searchout} "
    "    {params.classifyparams}; "
    "elif [ {params.classifymethod} = consensus-vsearch ]; then "
    "    qiime feature-classifier classify-consensus-vsearch "
    "    --i-reference-reads {params.refseqs} "
    "    --i-reference-taxonomy {params.reftax} "
    "    --i-query {input.repseqs} "
    "    --o-classification {output} "
    "    --o-search-results {params.searchout} "
    "    --p-threads {threads} "
    "    {params.classifyparams}; "
    "fi"

shell:
    "qiime metadata tabulate "
    "--m-input-file {input} "
    "--o-visualization {output}"

shell:
    "qiime taxa barplot "
    "--i-table {input.table} "
    "--i-taxonomy {input.taxonomy} "
    "--m-metadata-file {input.metadata} "
    "--o-visualization {output}"

shell:
    "qiime taxa collapse "
    "--i-table {input.table} "
    "--i-taxonomy {input.taxonomy} "
    "--p-level {params.taxalevel} "
    "--o-collapsed-table tempfile_collapsed.qza;"
    "qiime tools export "
    "--input-path tempfile_collapsed.qza "
    "--output-path temp_export;"
    "biom convert "
    "-i temp_export/feature-table.biom "
    "-o {output} "
    "--to-tsv;"
    "/bin/rm -r tempfile_collapsed.qza temp_export/"

shell:
    "qiime feature-table transpose "
    "--i-table {input.table} "
    "--o-transposed-feature-table transposed-table.qza; "
    "qiime metadata tabulate "
    "--m-input-file {input.repseqs} "
    "--m-input-file {input.taxonomy} "
    "--m-input-file transposed-table.qza "
    "--o-visualization merged-data.qzv; "
    "qiime tools export "
    "--input-path merged-data.qzv "
    "--output-path {output}; "
    "mv {output}/metadata.tsv temp; "
    "rm -r {output}; "
    "sed -e '2d' temp | sed '1 s|id\\t|featureid\\t|' | sed '1 s|Taxon|taxonomy|' | sed '1 s|Sequence|sequence|' > {output}; "
    "/bin/rm -r temp transposed-table.qza merged-data.qzv"

shell:
    "qiime tools export "
    "--input-path {input} "
    "--output-path {output} "
    "--output-format TSVTaxonomyFormat"

shell:
    "qiime tools import "
    "--type 'FeatureData[Taxonomy]' "
    "--input-format TSVTaxonomyFormat "
    "--input-path {input} "
    "--output-path {output}"

shell:
    "qiime phylogeny midpoint-root "
    "--i-tree {input} "
    "--o-rooted-tree {output}"

shell:
    "qiime empress community-plot "
    "--i-tree {input.tree} "
    "--i-feature-table {input.table} "
    "--m-sample-metadata-file {input.metadata} "
    "--m-feature-metadata-file {input.taxonomy} "
    "--m-feature-metadata-file {input.outliers} "
    "--o-visualization {output}"

shell:
    "bash scripts/alignment_count_gaps.sh < {input} > {output}"

shell:
    "Rscript --vanilla scripts/run_odseq.R {input} {params.metric} {params.replicates} {params.threshold} temp_odseq; "
    "cat temp_odseq | sed 's/^X//' > {output}; "
    "/bin/rm temp_odseq"

shell:
    "python scripts/plot_repseq_properties.py {input.lengths} {input.gaps} {input.outliers} {input.taxonomy} "
    "{input.table} {output.proptsv} {output.propdescribe} {output.proppdf} {output.outliersforqza}"

shell:
    "qiime tools import "
    "--type 'FeatureData[Importance]' "
    "--input-path {input} "
    "--output-path {output}"

shell:
    "cat {input.proptsv} | grep -i 'outlier\|true' | cut -f1,4 > {output.outliers}; "
    "cat {input.proptsv} | grep -i 'taxonomy\|unassigned' | cut -f1,5 > {output.unassigned}"

shell:
    "python scripts/filter_taxonomy.py {input.taxonomy} {input.repseqs} {output.taxonomytsv} {output.taxonomyqza}"

shell:
    "qiime diversity alpha-rarefaction "
    "--i-table {input.table} "
    "--i-phylogeny {input.phylogeny} "
    "--p-max-depth {params.maxdepth} "
    "--p-metrics faith_pd "
    "--p-metrics observed_features "
    "--p-metrics shannon "
    "--p-metrics pielou_e "
    "--m-metadata-file {input.metadata} "
    "--o-visualization {output}"

shell:
    "qiime diversity core-metrics-phylogenetic "
    "--i-table {input.table} "
    "--i-phylogeny {input.phylogeny} "
    "--p-sampling-depth {params.samplingdepth} "
    "--m-metadata-file {input.metadata} "
    "--o-rarefied-table {output.rarefiedtable} "
    "--o-faith-pd-vector {output.faithpdvector} "
    "--o-observed-features-vector {output.observedfeaturesvector} "
    "--o-shannon-vector {output.shannonvector} "
    "--o-evenness-vector {output.evennessvector} "
    "--o-unweighted-unifrac-distance-matrix {output.unweightedunifracdistancematrix} "
    "--o-weighted-unifrac-distance-matrix {output.weightedunifracdistancematrix} "
    "--o-jaccard-distance-matrix {output.jaccarddistancematrix} "
    "--o-bray-curtis-distance-matrix {output.braycurtisdistancematrix} "
    "--o-unweighted-unifrac-pcoa-results {output.unweightedunifracpcoaresults} "
    "--o-weighted-unifrac-pcoa-results {output.weightedunifracpcoaresults} "
    "--o-jaccard-pcoa-results {output.jaccardpcoaresults} "
    "--o-bray-curtis-pcoa-results {output.braycurtispcoaresults} "
    "--o-unweighted-unifrac-emperor {output.unweightedunifracemperor} "
    "--o-weighted-unifrac-emperor {output.weightedunifracemperor} "
    "--o-jaccard-emperor {output.jaccardemperor} "
    "--o-bray-curtis-emperor {output.braycurtisemperor} "
    "--p-n-jobs-or-threads {threads}"

shell:
    "qiime diversity alpha-group-significance "
    "--i-alpha-diversity {input.alphadiversity} "
    "--m-metadata-file {input.metadata} "
    "--o-visualization {output}"

shell:
    "qiime diversity beta-group-significance "
    "--i-distance-matrix {input.distancematrix} "
    "--m-metadata-file {input.metadata} "
    "--m-metadata-column {params.column} "
    "--p-method {params.method} "
    "{params.pairwise} "
    "--o-visualization {output}"

shell:
    "qiime deicode auto-rpca "
    "--i-table {input.table} "
    "--p-min-sample-count {params.minsamplecount} "
    "--p-min-feature-count {params.minfeaturecount} "
    "--p-min-feature-frequency {params.minfeaturefrequency} "
    "--p-max-iterations {params.maxiterations} "
    "--o-biplot {output.biplot} "
    "--o-distance-matrix {output.distancematrix}"

shell:
    "qiime emperor biplot "
    "--i-biplot {input.biplot} "
    "--m-sample-metadata-file {input.metadata} "
    "--o-visualization {output.emperor} "
    "--p-number-of-features {params.numfeatures}"

shell:
    "echo '# Tourmaline Report' > {output};"
    "echo '' >> {output};"
    "echo 'View this HTML report with [Chrome](https://www.google.com/chrome/){{target=\"_blank\"}} or [Firefox](https://www.mozilla.org/en-US/firefox/new/){{target=\"_blank\"}} for best results.' >> {output};"
    "echo '' >> {output};"
    "echo 'To view the linked files below: ' >> {output};"
    "echo '' >> {output};"
    "echo '* QZV (QIIME 2 visualization): click to download, then drag and drop in [https://view.qiime2.org](https://view.qiime2.org){{target=\"_blank\"}}.' >> {output};"
    "echo '* TSV (tab-separated values): click to download, then open in Microsoft Excel or Tabview (command line tool).' >> {output};"
    "echo '* PDF (portable document format): click to open and view in new tab.' >> {output};"
    "echo '* Markdown and text: click to open and view in new tab.' >> {output};"
    "echo '' >> {output};"
    "echo 'Note: Downloaded files can be deleted after viewing, as they are already stored in your Tourmaline directory.' >> {output};"
    "echo '' >> {output};"
    "echo 'For information on Tourmaline outputs, visit [https://github.com/aomlomics/tourmaline](https://github.com/aomlomics/tourmaline){{target=\"_blank\"}}.' >> {output};"
    "echo '' >> {output};"
    "echo '---' >> {output};"
    "echo '' >> {output};"
    "echo '## Metadata Summary' >> {output};"
    "echo '' >> {output};"
    "echo Markdown: \[{input.mdsummary}\]\(../{input.mdsummary}\){{target=\"_blank\"}} >> {output};"
    "echo '' >> {output};"
    "cat {input.mdsummary} >> {output};"
    "echo '' >> {output};"
    "echo '' >> {output};"
    "echo '---' >> {output};"
    "echo '' >> {output};"
    "echo '## Fastq Sequences Information' >> {output};"
    "echo '' >> {output};"
    "echo '### Fastq Sequences per Sample' >> {output};"
    "echo '' >> {output};"
    "echo Markdown: \[{input.fastq}\]\(../{input.fastq}\){{target=\"_blank\"}} >> {output};"
    "echo '' >> {output};"
    "cat {input.fastq} >> {output};"
    "echo '' >> {output};"
    "echo '### Visualization of Fastq Sequences' >> {output};"
    "echo '' >> {output};"
    "echo QZV: \[{input.visfastq}\]\(../{input.visfastq}\){{target=\"_blank\"}} >> {output};"
    "echo '' >> {output};"
    "echo '---' >> {output};"
    "echo '' >> {output};"
    "echo '## Representative Sequences Information' >> {output};"
    "echo '' >> {output};"
    "echo '### Representative Sequences Properties Table' >> {output};"
    "echo '' >> {output};"
    "echo TSV: \[{input.repseqstsv}\]\(../{input.repseqstsv}\){{target=\"_blank\"}} >> {output};"
    "echo '' >> {output};"
    "echo 'Columns:' >> {output};"
    "echo '' >> {output};"
    "echo '* featureid' >> {output};"
    "echo '* length - length (bp) not including gaps' >> {output};"
    "echo '* gaps - gaps (bp) in multiple sequence alignment' >> {output};"
    "echo '* outlier - outlier (True/False) determined by OD-seq' >> {output};"
    "echo '* taxonomy - domain level' >> {output};"
    "echo '* observations - total observations summed across all samples (unrarefied)' >> {output};"
    "echo '* log10(observations) - log base-10 of total observations' >> {output};"
    "echo '' >> {output};"
    "echo '### Representative Sequences Properties Summary' >> {output};"
    "echo '' >> {output};"
    "echo Markdown: \[{input.repseqsdescribe}\]\(../{input.repseqsdescribe}\){{target=\"_blank\"}} >> {output};"
    "echo '' >> {output};"
    "cat {input.repseqsdescribe} >> {output};"
    "echo '' >> {output};"
    "echo '### Representative Sequences Properties Plot' >> {output};"
    "echo '' >> {output};"
    "echo PDF: \[{input.repseqspdf}\]\(../{input.repseqspdf}\){{target=\"_blank\"}} >> {output};"
    "echo '' >> {output};"

shell:
    "pandoc -i {input} -o {output};"
    "echo '<!DOCTYPE html>' > header.html;"
    "echo '<html>' >> header.html;"
    "echo '<head>' >> header.html;"
    "echo '<link rel=\"stylesheet\" type=\"text/css\" href=\"../css/{params.theme}.css\">' >> header.html;"
    "echo '</head>' >> header.html;"
    "echo '<body>' >> header.html;"
    "echo '' >> header.html;"
    "cat header.html {output} > temp.html;"
    "echo '' >> temp.html;"
    "echo '</body>' >> temp.html;"
    "echo '</html>' >> temp.html;"
    "mv temp.html {output};"
    "/bin/rm header.html"