<tool id="SAM_Refiner" name="SAM Refiner" version="1.0">
  <description>Provides variant information from mapped reads</description>
  <command>
  python '${__tool_directory__}/SAM_Refiner_Gal.py' -r $ref -S $samfile --min_samp_abund $minsampabund --min_count $mincount --ntabund $ntab --max_dist $maxdist --max_covar $maxcov
#if $use_count
  --use_count 1
#else
  --use_count 0
#end if
#if $seqs
  -o1 $out_file1
#else
  --seq 0
#end if
#if $indels
  -o2 $out_file2
#else
  --indel 0
#end if
#if $ntcalls:
  -o3 $out_file3
#else
  --nt_call 0
#end if
#if $covars
  -o4 $out_file4
#else
  --covar 0
#end if
#if $chimrm
  -o5 $out_file5 --alpha $alpha --foldab $foldab 
#else
  --chim_rm 0
#end if
#if $covdec
  -o6 $out_file6 --beta $beta --autopass $pass
#else
  --deconv 0
#end if
#if $ntvar
  --ntvar 1
  -o7 $out_file7
#end if
#if $AArep
  --AAreport 1
#else
  --AAreport 0
#end if
#if $MNP
  --AAcodonasMNP 1
#else
  --AAcodonasMNP 0
#end if
#if $redist
  --redist 1
#else
  --redist 0
#end if
  --samp '$samp'
#if $WGS
  --wgs 1
#else
  --wgs 0
#end if
  </command>
  <inputs>
    <param format="fasta" name="ref" type="data" label="Reference fasta" />
    <param format="sam" name="samfile" type="data" label="SAM file to be processed" />
    <param name="samp" type="text" value="Sample" label="Sample Title" />
    <param name="use_count" type="boolean" checked="false" label="Use read count in fasta id line (must have format id-count or id=count)" />
    <param name="seqs" type="boolean" checked="true" label="Output Sequence TSV" />
    <param name="indels" type="boolean" checked="true" label="Output Indel TSV" />
    <param name="ntcalls" type="boolean" checked="true" label="Output NT Call TSV" />
    <param name="ntvar" type="boolean" checked="true" label="Output file with only variant NT Calls TSV" />
    <param name="covars" type="boolean" checked="true" label="Output Covariant TSV" />
    <param name="chimrm" type="boolean" checked="true" label="Output Chimeras Removed TSV, requires Sequence TSV output" />
    <param name="covdec" type="boolean" checked="true" label="Output Covariant Deconvolution TSV, requires Sequence and Covariant TSV outputs" />
    <param name="WGS" type="boolean" checked="false" label="Use Whole Genome Sequencing Mode, disables chimera removal outputs, reports sequences with start and end positions" />
    <param name="mincount" type="integer" value="5" min="1" max="20000" label="Minimum number of counts for an output line" />
    <param name="minsampabund" type="float" value=".001" min="0" max=".5" label="Minimum abundance for an output line" />
    <param name="ntab" type="float" value=".001" min="0" max=".5" label="Minimum abundance for an NT call line variant to be reported" />
    <param name="maxdist" type="integer" value="20" min="1" max="40" label="Maximum distance from reference for a sequence to be included in the Covariant output processing (High values may cause memory/computational errors, reduce to avoid)" />
    <param name="maxcov" type="integer" value="8" min="1" max="40" label="Maximum number of polymorphisms to report in each line of the Covariant output" />
    <param name="AArep" type="boolean" checked="true" label="Report Amino Acids as if reference is an inframe ORF. If the reference isn't an in frame ORF, this should be disabled" />
    <param name="MNP" type="boolean" checked="true" label="Report multiple nucleotide changes in a single codon as a single polymorphism, requires reporting of Amino Acids" />
    <param name="redist" type="boolean" checked="true" label="Redistribute counts from chimeric sequecnes to parents in Chimeras Removed Output" />
    <param name="alpha" type="float" value="1.2" min=".1" max="10" label="Modifier for chim_rm chimera checking, default 1.2.  Higher = more sensitive, more false chimeras removed; lower = less sensitive, fewer chimeras removed" />
    <param name="foldab" type="float" value="1.8" min="0" max="20" label="Threshold for potential parent / chimera abundance ratio for chim_rm; default is 1.8" />
    <param name="beta" type="float" value="1" min=".1" max="4" label="Modifier for covar pass checking, default 1.  Higher = more sensitive, more failed checks; lower = less sensitive, fewer failed checks" />
    <param name="pass" type="float" value=".3" min=".1" max="4" label="Threshold for a sequence to automatically pass the covar pass checking" />
  </inputs>

  <outputs>
    <data format="TSV" name="out_file1" label="${tool.name} on ${on_string}: sequences" />
    <data format="TSV" name="out_file2" label="${tool.name} on ${on_string}: indels" />
    <data format="TSV" name="out_file3" label="${tool.name} on ${on_string}: nt calls" />
    <data format="TSV" name="out_file4" label="${tool.name} on ${on_string}: covariants" />
    <data format="TSV" name="out_file5" label="${tool.name} on ${on_string}: chimeras removed" />
    <data format="TSV" name="out_file6" label="${tool.name} on ${on_string}: covariant deconvolution" />
    <data format="TSV" name="out_file7" label="${tool.name} on ${on_string}: variant nt calls" />
  </outputs>
  
  <tests>
    <test>
      <param name="ref" value="SAM_Refiner_test_ref.fa"/>
      <param name="samfile" value="SAM_Refiner_test_sam.sam"/>
      <output name="out_file1" file="SAM_Refiner_test_seqs.tsv"/>
      <output name="out_file2" file="SAM_Refiner_test_indels.tsv"/>
      <output name="out_file3" file="SAM_Refiner_test_nc_calls.tsv"/>
      <output name="out_file4" file="SAM_Refiner_test_covars.tsv"/>
    </test>
  </tests>

  <help>
SAM Refiner provides variant information from mapped reads in a SAM file.  If you use this tool, please reference Gregory, D.A.; Wieberg, C.G.; Wenzel, J.; Lin, C.-H.; Johnson, M.C. Monitoring SARS-CoV-2 Populations in Wastewater by Amplicon Sequencing and Using the Novel Program SAM Refiner. Viruses 2021, 13, 1647. https://doi.org/10.3390/v13081647 


  </help>

</tool>