--- a/mob_typer.xml	Thu Aug 05 21:53:36 2021 +0000
+++ b/mob_typer.xml	Fri Feb 21 18:41:14 2025 +0000
@@ -3,6 +3,7 @@
   <macros>
     <import>macros.xml</import>
   </macros>
+  <expand macro="bio_tools"/>
   <expand macro="requirements"/>
   <version_command>mob_typer --version</version_command>
   <command detect_errors="exit_code">
@@ -60,6 +61,11 @@
    #if $adv_param.debug
    --debug
    #end if
+   
+   #if $adv_param.biomarker_report_file
+   --biomarker_report_file biomarker_report.txt
+   #end if
+   
 
    --out_file plasmid_report.txt;
 
@@ -68,31 +74,34 @@
   <inputs>
     <param name="input" type="data" format="fasta" label="Input" help="FASTA file with contig(s)"/>
     <section name="adv_param" title="Advanced parameters" expanded="False">
-      <param name="multi" type="boolean" truevalue="true" falsevalue="" checked="false" label="Treat each input sequence as an independant plasmid?" />
-      <param name="min_rep_evalue_value" type="float" value="0.00001" min="0.00001" max="1" label="Minimum evalue threshold for replicon blastn"/> 
-      <param name="min_mob_evalue_value" type="float" value="0.00001" min="0.00001" max="1" label="Minimum evalue threshold for relaxase tblastn"/> 
-      <param name="min_con_evalue_value" type="float" value="0.00001" min="0.00001" max="1" label="Minimum evalue threshold for contig blastn"/> 
-      <param name="min_length" type="integer" value="1000" label="Minimum length of contigs to classify"/> 
-      <param name="min_rep_ident" label="Minimum sequence identity for replicons" type="integer"  min="0" max="100" value="80"/>
-      <param name="min_mob_ident" label="Minimum sequence identity for relaxases" type="integer"  min="0" max="100" value="80"/>
-      <param name="min_con_ident" label="Minimum sequence identity for contigs" type="integer"  min="0" max="100" value="80"/>
-      <param name="min_rep_cov" label="Minimum percentage coverage of replicon query by input assembly" type="integer"  min="0" max="100" value="80"/>
-      <param name="min_mob_cov" label="Minimum percentage coverage of relaxase query by input assembly" type="integer"  min="0" max="100" value="80"/>
-      <param name="min_con_cov" label="Minimum percentage coverage of assembly contig by the plasmid reference database to be considered" type="integer"  min="0" max="100" value="70"/>
-      <param name="min_overlap" label="Minimum overlap of fragments" type="integer"  min="0" max="100" value="10"/>
-      <param name="debug" type="boolean" truevalue="true" falsevalue="" checked="false" label="Provide debug information?" />
-      <param name="plasmid_db" optional="true" type="data" format="fasta" label="Reference Database of complete plasmids" help=""/>
-      <param name="plasmid_mash_db" optional="true" type="data" format="binary" label="Custom MASH database of plasmids" help="Companion MASH database of reference database"/>
-      <param name="plasmid_meta" type="data" optional="true" format="text" label="Plasmid cluster metadata file" help="MOB-cluster plasmid cluster formatted metadata file matched to the reference plasmid db"/>
-      <param name="plasmid_replicons" type="data" optional="true" format="fasta" label="FASTA file with plasmid replicons" help="FASTA of plasmid replicons"/>
-      <param name="repetitive_mask" type="data" optional="true" format="fasta" label="FASTA of known repetitive elements" help="FASTA of known repetitive elements"/>
-      <param name="plasmid_mob" type="data" optional="true" format="fasta" label="FASTA of plasmid relaxases" help="FASTA of plasmid relaxases"/>
-      <param name="plasmid_mpf" type="data" optional="true" format="fasta" label="FASTA of known plasmid mate-pair proteins" help="FASTA of known plasmid mate-pair proteins"/>
-      <param name="plasmid_orit" type="data" optional="true" format="fasta" label="FASTA of known plasmid oriT dna sequences" help="FASTA of known plasmid oriT dna sequences"/>
+      <param name="multi" type="boolean" truevalue="true" falsevalue="" checked="false" label="Treat each input sequence as an independent plasmid?" help="Treat each sequence in the FASTA file as a separate input (--multi)" />
+      <param name="biomarker_report_file" type="boolean" truevalue="true" falsevalue="" checked="false" label="Output BLAST biomarker report?" help="The report will report all biomarkers identified in a given query plasmid (--biomarker_report_file)" />
+
+      <param name="min_rep_evalue_value" type="float" value="0.00001" min="0.00001" max="1" label="Minimum evalue threshold for replicon blastn" help="(--min_rep_evalue)"/> 
+      <param name="min_mob_evalue_value" type="float" value="0.00001" min="0.00001" max="1" label="Minimum evalue threshold for relaxase tblastn" help="(--min_mob_evalue)"/> 
+      <param name="min_con_evalue_value" type="float" value="0.00001" min="0.00001" max="1" label="Minimum evalue threshold for contig blastn" help="(--min_con_evalue)"/> 
+      <param name="min_length" type="integer" value="1000" label="Minimum length of contigs to classify (bp)" help="(--min_length)"/> 
+      <param name="min_rep_ident" label="Minimum sequence identity for replicons" type="integer"  min="0" max="100" value="80" help="(--min_rep_ident)"/>
+      <param name="min_mob_ident" label="Minimum sequence identity for relaxases" type="integer"  min="0" max="100" value="80" help="(--min_mob_ident)"/>
+      <param name="min_con_ident" label="Minimum sequence identity for contigs" type="integer"  min="0" max="100" value="80" help="(--min_con_ident)"/>
+      <param name="min_rep_cov" label="Minimum percentage coverage of replicon query by input assembly" type="integer"  min="0" max="100" value="80" help="(--min_rep_ident)"/>
+      <param name="min_mob_cov" label="Minimum percentage coverage of relaxase query by input assembly" type="integer"  min="0" max="100" value="80" help="(--min_mob_cov)"/>
+      <param name="min_con_cov" label="Minimum percentage coverage of assembly contig by the plasmid reference database to be considered" type="integer"  min="0" max="100" value="70" help="(--min_con_cov)"/>
+      <param name="min_overlap" label="Minimum overlap of fragments (bp)" type="integer"  min="0" max="100" value="10" help="(--min_overlap)"/>
+      <param name="debug" type="boolean" truevalue="true" falsevalue="" checked="false" label="Provide debug information?" help="(--debug)"/>
+      <param name="plasmid_db" optional="true" type="data" format="fasta" label="Reference Database of complete plasmids" help="(--plasmid_db)"/>
+      <param name="plasmid_mash_db" optional="true" type="data" format="binary" label="Custom MASH database of plasmids" help="Custom MASH plasmid reference database (--plasmid_mash_db)"/>
+      <param name="plasmid_meta" type="data" optional="true" format="text" label="Plasmid cluster metadata file" help="MOB-cluster plasmid cluster formatted metadata file matched to the reference plasmid database (--plasmid_meta)"/>
+      <param name="plasmid_replicons" type="data" optional="true" format="fasta" label="FASTA file with plasmid replicons" help="FASTA of plasmid replicons custom database (--plasmid_replicons)"/>
+      <param name="repetitive_mask" type="data" optional="true" format="fasta" label="FASTA of known repetitive elements" help="FASTA of known repetitive elements custom database (--repetitive_mask)"/>
+      <param name="plasmid_mob" type="data" optional="true" format="fasta" label="FASTA of plasmid relaxases" help="FASTA of plasmid relaxases custom database (--plasmid_mob)"/>
+      <param name="plasmid_mpf" type="data" optional="true" format="fasta" label="FASTA of known plasmid mate-pair proteins" help="FASTA of known plasmid mate-pair proteins custom database (--plasmid_mpf)"/>
+      <param name="plasmid_orit" type="data" optional="true" format="fasta" label="FASTA of known plasmid oriT dna sequences" help="FASTA of known plasmid oriT DNA sequences custom database (--plasmid_orit)"/>
     </section>
   </inputs>
   <outputs>
     <data name="plasmid_report" from_work_dir="plasmid_report.txt" label="${tool.name}: Plasmid report on ${input.element_identifier}"  format="tabular" />
+    <data name="biomarker_report" from_work_dir="biomarker_report.txt" label="${tool.name}: Biomarker report on ${input.element_identifier}"  format="tabular" />
   </outputs>
   <tests>
     <test>
@@ -114,7 +123,7 @@
 
 **Syntax**
 
-This tool provides *in-silico* predictions on plasmid typing including identification of replicon, relaxase and mate-pair formation protein types. MOB-typer also predicts mobility of a plasmid (Conjugative, Mobilizable, Non-mobilizable). Do not include multiple unrelated plasmids in the input FASTA file as they will be treated as a single plasmid.
+This tool provides *in silico* predictions on plasmid typing including identification of replicon, relaxase and mate-pair formation protein types. MOB-typer also predicts mobility of a plasmid (Conjugative, Mobilizable, Non-mobilizable) and potential host range. 
 
 For more information please visit https://github.com/phac-nml/mob-suite/. 
 
@@ -127,9 +136,9 @@
 
 **Output:**
 
-Tab-delimited report listing identified plasmid(s) and their predicted mobility. Refer to https://github.com/phac-nml/mob-suite#mob-typer-report-file-format for the description of each column.
+Tab-delimited report listing identified plasmid(s) and their predicted mobility and host range and optionally a biomarker report (if selected). Refer to https://github.com/phac-nml/mob-suite#mob-typer-report-file-format for the description of each column.
 
-
+**Note:** Do not include multiple unrelated plasmids in the input FASTA file as they will be treated as a single plasmid or turn on the **--multi** parameter (i.e. *Treat each input sequence as an independent plasmid?*).
   </help>
   <citations>
     <citation type="bibtex">