--- a/mageck_test.xml	Sat Feb 17 10:41:53 2018 -0500
+++ b/mageck_test.xml	Wed Apr 04 11:03:59 2018 -0400
@@ -24,20 +24,39 @@
 -n output
 
 $out.normcounts
+
 $out.pdfreport
 
---norm-method $adv.norm_method
---gene-test-fdr-threshold $adv.fdr_threshold
---adjust-method $adv.adjust_method
+#if $adv.norm_method:
+    --norm-method $adv.norm_method
+#end if
+
+#if $adv.fdr_threshold:
+    --gene-test-fdr-threshold $adv.fdr_threshold
+#end if
+
+#if $adv.adjust_method:
+    --adjust-method $adv.adjust_method
+#end if
+
 $adv.var_samples
---sort-criteria $adv.sort_criteria
+
+#if $adv.sort_criteria:
+    --sort-criteria $adv.sort_criteria
+#end if
 
---remove-zero $adv.remove_zero
+#if $adv.remove_zero:
+    --remove-zero $adv.remove_zero
+#end if
+
 #if $adv.remove_zero_threshold:
     --remove-zero-threshold $adv.remove_zero_threshold
 #end if
 
---gene-lfc-method $adv.lfc_method
+#if $adv.lfc_method:
+    --gene-lfc-method $adv.lfc_method
+#end if
+
 #if $adv.control_sgrna:
     --control-sgrna $adv.control_sgrna
 #end if
@@ -60,46 +79,50 @@
                 <option value="control">Control sample</option>
             </param>
             <when value="treated">
-                <param name="treatment_id" argument="--treatment-id" type="text" label="Treated Sample Labels (or Indexes)" help="If sample label is provided, the labels must match the labels in the first line of the count table, separated by comma (,); for example, HL60.final,KBM7.final. For sample index, 0,2 means the 1st and 3rd samples are treatment experiments. See Help below for a detailed description." />
+                <param name="treatment_id" argument="--treatment-id" type="text" label="Treated Sample Labels (or Indexes)" help="If sample label is provided, the labels must match the labels in the first line of the count table, separated by comma (,); for example, HL60.final,KBM7.final. For sample index, 0,2 means the 1st and 3rd samples are treatment experiments. See Help below for a detailed description.">
+                    <validator type="regex" message="Please only use letters, numbers or underscores in sample labels, and separate labels by commas">^[\w,]+$</validator>
+                </param>
             </when>
             <when value="control">
-            <param name="day0_label" argument="--day0-label" type="text" optional="true" value="" label="Control Sample Label" help="Specify the label for the control sample. For every other sample label, the module will treat it as a treatment condition and compare with control sample (usually day 0 or plasmid)" />
+                <param name="day0_label" argument="--day0-label" type="text" optional="true" value="" label="Control Sample Label" help="Specify the label for the control sample. For every other sample label, the module will treat it as a treatment condition and compare with control sample (usually day 0 or plasmid)">
+                    <validator type="regex" message="Please only use letters, numbers or underscores in sample label">^[\w]+$</validator>
+                </param>
             </when>
         </conditional>
-        <param name="control_id" argument="--control-id" type="text" optional="true" label="Control Sample Labels (or Indexes)" help="If sample label is provided, the labels must match the labels in the first line of the count table, separated by comma (,). Default is all the samples not specified in treatment experiments. See Help below for a detailed description." />
-
+        <param name="control_id" argument="--control-id" type="text" optional="true" label="Control Sample Labels (or Indexes)" help="If sample label is provided, the labels must match the labels in the first line of the count table, separated by comma (,). Default is all the samples not specified in treatment experiments. See Help below for a detailed description.">
+            <validator type="regex" message="Please only use letters, numbers or underscores in sample labels, and separate labels by commas">^[\w,]+$</validator>
+        </param>
         <section name="out" title="Output Options">
             <param name="normcounts" argument="--normcounts-to-file" type="boolean" truevalue="--normcounts-to-file" falsevalue="" checked="false" optional="true" label="Output normalized counts file" help="Default: No"  />
-            <param name="pdfreport" argument="--pdf-report" type="boolean" truevalue="--pdf-report" falsevalue="" checked="false" optional="true" label="Output PDF report" help="Generate pdf report of the input file. Default: No" />
-            <param name="rscriptOpt" type="boolean" truevalue="True" falsevalue="" checked="false" optional="true" label="Output R script" help="Output the R script used to generate the plots in the pdf report. Default: No" />
+            <param name="pdfreport" argument="--pdf-report" type="boolean" truevalue="--pdf-report" falsevalue="" checked="false" optional="true" label="Output plots" help="Generate PDF of the plots. Default: No" />
+            <param name="rfilesOpt" type="boolean" truevalue="True" falsevalue="" checked="false" optional="true" label="Output R files" help="Output the .R and .Rnw files to generate the PDF report. The gene summary file will also be output as it is required to regenerate the report. Default: No" />
             <param name="out_log" type="boolean" truevalue="True" falsevalue="" checked="false" label="Output Log file" help="This file includes the logging information during the execution. Default: No" />
         </section>
 
         <section name="adv" title="Advanced Options">
-            <param name="norm_method" argument="--norm-method" type="select" label="Method for normalization"
-                help="If control is specified, the size factor will be estimated using control sgRNAs specified in --control-sgrna option. Default: Median" >
+            <param name="norm_method" argument="--norm-method" optional="true" type="select" label="Method for normalization" help="If control is specified, the size factor will be estimated using control sgRNAs specified in --control-sgrna option. Default: Median" >
+            <option value="median" selected="True">Median</option>
             <option value="none">None</option>
-            <option value="median" selected="True">Median</option>
             <option value="total">Total</option>
             <option value="control">Control</option>
         </param>
-        <param name="fdr_threshold" argument="--gene-test-fdr-threshold" type="float" value="0.25" min="0" max="1" label="Gene test FDR-adjusted Threshold" help="FDR threshold for gene test. Default: 0.25"/>
-        <param name="adjust_method" argument="--adjust-method" type="select" label="P-Value Adjustment Method" help="Method for sgRNA-level p-value adjustment, including False Discovery Rate (FDR), Holm's method (Holm), or Pounds's method (Pounds). Default: FDR">
+        <param name="fdr_threshold" argument="--gene-test-fdr-threshold" type="float" min="0" max="1" optional="true" label="Gene test FDR-adjusted Threshold" help="FDR threshold for gene test. Default: 0.25"/>
+        <param name="adjust_method" argument="--adjust-method" type="select" optional="true" label="P-Value Adjustment Method" help="Method for sgRNA-level p-value adjustment, including False Discovery Rate (FDR), Holm's method (Holm), or Pounds's method (Pounds). Default: FDR">
             <option value="fdr" selected="True">FDR</option>
             <option value="holm">Holm</option>
             <option value="pounds">Pounds</option>
         </param>
         <param name="var_samples" argument="--variance-from-all-samples" type="boolean" truevalue="--variance-from-all-samples" falsevalue="" checked="false" optional="true" label="Estimate the variance from all samples, instead of from only control samples" help="Use this option only if you believe there are relatively few essential sgRNAs or genes between control and treatment samples" />
         <expand macro="sort_criteria" />
-        <param name="remove_zero" argument="--remove-zero" type="select" label="Remove zero" help="Remove sgRNAs whose mean value is zero in Control, Treatment, Both control/treatment, or Any control/treatment sample. Default: Both (remove those sgRNAs that are zero in both control and treatment samples)" >
+        <param name="remove_zero" argument="--remove-zero" type="select" optional="true" label="Remove zero" help="Remove sgRNAs whose mean value is zero in Control, Treatment, Both control/treatment, or Any control/treatment sample. Default: Both (remove those sgRNAs that are zero in both control and treatment samples)" >
             <option value="none" >None</option>
             <option value="control">Control</option>
             <option value="treatment">Treatment</option>
             <option value="both" selected="True">Both</option>
             <option value="any">Any</option>
         </param>
-        <param name="remove_zero_threshold" argument="--remove-zero-threshold" type="float" value="0" label="Remove zero Threshold" help="sgRNA normalized count threshold to be considered removed in the --remove-zero option. Default: 0"/>
-        <param name="lfc_method" argument="--gene-lfc-method" type="select" label="Gene Log-Fold Change Method." help="Method to calculate gene log fold changes (LFC) from sgRNA LFCs. Available methods include the median/mean of all sgRNAs (median/mean), or the median/mean sgRNAs that are ranked in front of the alpha cutoff in RRA (alphamedian/alphamean), or the sgRNA that has the second strongest LFC (secondbest). In the alphamedian/alphamean case, the number of sgRNAs correspond to the goodsgrna column in the output, and the gene LFC will be set to 0 if no sgRNA is in front of the alpha cutoff. Default: Median. (new since v0.5.5)">
+        <param name="remove_zero_threshold" argument="--remove-zero-threshold" type="float" optional="true" label="Remove zero Threshold" help="sgRNA normalized count threshold to be considered removed in the --remove-zero option. Default: 0"/>
+        <param name="lfc_method" argument="--gene-lfc-method" type="select" optional="true" label="Gene Log-Fold Change Method." help="Method to calculate gene log fold changes (LFC) from sgRNA LFCs. Available methods include the median/mean of all sgRNAs (median/mean), or the median/mean sgRNAs that are ranked in front of the alpha cutoff in RRA (alphamedian/alphamean), or the sgRNA that has the second strongest LFC (secondbest). In the alphamedian/alphamean case, the number of sgRNAs correspond to the goodsgrna column in the output, and the gene LFC will be set to 0 if no sgRNA is in front of the alpha cutoff. Default: Median. (new since v0.5.5)">
             <option value="median" selected="True">Median</option>
             <option value="alphamedian">Alphamedian</option>
             <option value="mean">Mean</option>
@@ -121,35 +144,41 @@
         <data name="normcounts" format="tabular" from_work_dir="output.normalized.txt" label="${tool.name} on ${on_string}: sgRNA Normalized Counts">
             <filter>out['normcounts'] is True</filter>
         </data>
-        <data name="pdfreport" format="pdf" from_work_dir="output.pdf" label="${tool.name} on ${on_string}: PDF Report">
+        <data name="plots" format="pdf" from_work_dir="output.pdf" label="${tool.name} on ${on_string}: PDF Report">
             <filter>out['pdfreport'] is True</filter>
         </data>
-        <data name="rscript" format="txt" from_work_dir="output.R" label="${tool.name} on ${on_string}: RScript">
-            <filter>out['rscriptOpt'] is True</filter>
+        <data name="rscript" format="txt" from_work_dir="output.R" label="${tool.name} on ${on_string}: R file"  >
+            <filter>out['rfilesOpt'] is True</filter>
+        </data>
+        <data name="rnwfile" format="txt" from_work_dir="output_summary.Rnw" label="${tool.name} on ${on_string}: Rnw file"  >
+            <filter>out['rfilesOpt'] is True</filter>
         </data>
     </outputs>
     <tests>
-        <test><!-- Ensure MAGeCK's default output works -->
-            <param name="count_table" value="demo/demo1/sample.txt" ftype="tabular" />
-            <param name="treatment_id" value="HL60.final,KBM7.final" />
-            <param name="control_id" value="HL60.initial,KBM7.initial" />
+        <!-- Ensure MAGeCK's default output works -->
+        <test expect_num_outputs="2">
+            <param name="count_table" value="in.test.sample.txt" ftype="tabular" />
+            <param name="treatment_id" value="HL60_final,KBM7_final" />
+            <param name="control_id" value="HL60_initial,KBM7_initial" />
             <output name="gene_summary" file="out.test.gene_summary.txt"/>
             <output name="sgrna_summary" file="out.test.sgrna_summary.txt"/>
         </test>
-        <test><!-- Ensure MAGeCK's additional outputs works -->
-            <param name="count_table" value="demo/demo1/sample.txt" ftype="tabular" />
-            <param name="treatment_id" value="HL60.final,KBM7.final" />
-            <param name="control_id" value="HL60.initial,KBM7.initial" />
+        <!-- Ensure MAGeCK's additional outputs works -->
+        <test expect_num_outputs="7">
+            <param name="count_table" value="in.test.sample.txt" ftype="tabular" />
+            <param name="treatment_id" value="HL60_final,KBM7_final" />
+            <param name="control_id" value="HL60_initial,KBM7_initial" />
             <param name="out_log" value="True" />
             <param name="normcounts" value="True" />
             <param name="pdfreport" value="True" />
-            <param name="rscriptOpt" value="True" />
+            <param name="rfilesOpt" value="True" />
             <output name="gene_summary" file="out.test.gene_summary.txt"/>
             <output name="sgrna_summary" file="out.test.sgrna_summary.txt"/>
             <output name="normcounts" file="out.test.normalized.txt"/>
             <output name="log" file="out.test.log.txt" compare="sim_size"/>
-            <output name="pdfreport" file="out.test.pdf" compare="sim_size"/>
+            <output name="plots" file="out.test.plots.pdf" compare="sim_size"/>
             <output name="rscript" file="out.test.R" />
+            <output name="rnwfile" file="output_summary.Rnw" />
         </test>
     </tests>
 
@@ -210,6 +239,18 @@
 
 **Outputs**
 
+This tool outputs
+
+    * a ranked sgRNA Summary file
+    * a ranked Gene Summary file
+
+Optionally, under **Output Options** you can choose to output
+
+    * a Normalized Counts table
+    * a PDF of the plots
+    * the .R and .Rnw files to generate the report
+    * a Log file of the analysis
+
 **sgRNA Summary file**
 
 An example of the sgRNA ranking output is as follows: