Skip to content

Update FastQC/Falco wrappers to generate 2 outputs in case of pair inputs #7874

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
lldelisle wants to merge 19 commits into from
+2,436 −80
Closed

Update FastQC/Falco wrappers to generate 2 outputs in case of pair inputs #7874

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
5ad780e
handle differently pairs to enable to keep both identifiers in report
lldelisle Mar 27, 2026
e396f5e
Apply suggestion from @mvdbeek
lldelisle Mar 27, 2026
70686c2
fix URL
lldelisle Mar 27, 2026
7f51cdb
apply same changes to falco
lldelisle Mar 27, 2026
6bb1899
run falco/fastqc on both inputs at the same time
lldelisle Mar 30, 2026
24a5a49
Apply suggestions from code review
lldelisle Mar 31, 2026
c8b48b8
do not mention slower
lldelisle Apr 10, 2026
850c0c1
do not allow bam/sam in paired mode
lldelisle Apr 10, 2026
9a0fcbe
Improve selector label
lldelisle Apr 10, 2026
c38a1e4
improve selector label in fastqc
lldelisle Apr 10, 2026
9d27e2d
use regex in from_work_dir rather than mv steps from @wm75 suggestion
lldelisle Apr 10, 2026
03b426f
use regex also for summary
lldelisle Apr 10, 2026
8af05ac
do symetric tests between fastqc and falco
lldelisle Apr 10, 2026
bd2688c
add png to zip of html
lldelisle Apr 10, 2026
b9e2c9a
fix the Images copy
lldelisle Apr 10, 2026
5024d02
fix linting
lldelisle Apr 10, 2026
29d923e
change output to individual outputs instead of collections
lldelisle Apr 10, 2026
ace8e70
propagate strategy to falco
lldelisle Apr 10, 2026
6d236ba
fix number of outputs
lldelisle Apr 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
180 changes: 148 additions & 32 deletions tools/falco/falco.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,21 @@
<tool id="falco" name="Falco" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
<description>An alternative, more performant implementation of FastQC for high throughput sequence quality control</description>
<macros>
<token name="@TOOL_VERSION@">1.2.4</token>
<token name="@TOOL_VERSION@">1.2.5</token>
<token name="@VERSION_SUFFIX@">0</token>
<token name="@LN_S@">
<![CDATA[
#if 'bam' in $input_file.ext:
#set format = 'bam'
#elif 'sam' in $input_file.ext:
#set format = 'sam'
#elif 'gz' in $input_file.ext:
#set format = 'fastq.gz'
#else
#set format = 'fastq'
#end if
ln -s '${input_file}' '${input_file_sl}' &&
]]></token>
</macros>
<xrefs>
<xref type="bio.tools">falco</xref>
Expand All @@ -12,19 +25,22 @@
</requirements>
<command detect_errors="aggressive"><![CDATA[
#import re
#set input_name_sl = re.sub('[^\w\-\s]', '_', str($input_file.element_identifier))

#if 'bam' in $input_file.ext:
#set format = 'bam'
#elif 'sam' in $input_file.ext:
#set format = 'sam'
#elif 'gz' in $input_file.ext:
#set format = 'fastq.gz'
#set $input_files=[]
#if str($input_type_select.input_type) == 'individually'
#set input_file = $input_type_select.input_file
#set input_file_sl = re.sub('[^\w\-\s]', '_', str($input_file.element_identifier))
@LN_S@
#set $input_files += [$input_file_sl]
#else
#set format = 'fastq'
#set input_file = $input_type_select.input_col['forward']
#set input_file_sl = re.sub('[^\w\-\s]', '_', str($input_type_select.input_col.element_identifier)) + '_forward'
@LN_S@
#set $input_files += [$input_file_sl]
#set input_file = $input_type_select.input_col['reverse']
#set input_file_sl = re.sub('[^\w\-\s]', '_', str($input_type_select.input_col.element_identifier)) + '_reverse'
@LN_S@
#set $input_files += [$input_file_sl]
#end if

ln -s '${input_file}' '${input_name_sl}' &&
falco
#if $contaminants:
--contaminants '${contaminants}'
Expand All @@ -45,16 +61,31 @@
$nogroup
## --kmers $kmers
-f '${format}'
'${input_name_sl}'
#if $subsample > 1:
-subsample $subsample
-subsample $subsample
#end if
$bisulfite
$reverse_complement
$generate_summary
#for $input_file_sl in $input_files
'${input_file_sl}'
#end for
]]></command>
<inputs>
<param format="fastq,fastq.gz,bam,sam" name="input_file" type="data" label="Raw read data from your current history"/>
<conditional name="input_type_select">
<param name="input_type" type="select" label="How is your input data organized?">
<option value="individually">As separate datasets (single-end fastq or sam/bam)</option>
<option value="paired">As a paired collection of forward and reverse reads</option>
</param>
<when value="individually">
<param format="fastq,fastq.gz,bam,sam" name="input_file" type="data"
label="Raw read data from your current history" />
</when>
<when value="paired">
<param format="fastq,fastq.gz" name="input_col" type="data_collection"
collection_type="paired" label="Raw read data from your current history in paired collections"/>
</when>
</conditional>
<param name="contaminants" type="data" format="tabular" optional="true" label="Contaminant list" help="tab delimited file with 2 columns: name and sequence. For example: Illumina Small RNA RT Primer&#x9;CAAGCAGAAGACGGCATACGA"/>
<param argument="--adapters" type="data" format="tabular" optional="true" label="Adapter list" help="List of adapters adapter sequences which will be explicity searched against the library. It should be a tab-delimited file with 2 columns: name and sequence."/>
<param name="limits" type="data" format="txt" optional="true" label="Submodule and Limit specifing file" help="a file that specifies which submodules are to be executed (default=all) and also specifies the thresholds for the each submodules warning parameter."/>
Expand All @@ -67,16 +98,40 @@
<param name="generate_summary" type="boolean" truevalue="" falsevalue="-skip-summary" checked="False" label="Generate summary output of QC test results"/>
</inputs>
<outputs>
<data format="html" name="html_file" from_work_dir="fastqc_report.html" label="${tool.name} on ${on_string}: Webpage"/>
<data format="txt" name="text_file" from_work_dir="fastqc_data.txt" label="${tool.name} on ${on_string}: RawData"/>
<data format="html" name="html_file" from_work_dir="fastqc_report.html" label="${tool.name} on ${on_string}: Webpage" >
<filter>input_type_select['input_type'] == 'individually'</filter>
</data>
<data format="txt" name="text_file" from_work_dir="fastqc_data.txt" label="${tool.name} on ${on_string}: RawData" >
<filter>input_type_select['input_type'] == 'individually'</filter>
</data>
<data format="txt" name="summary_file" from_work_dir="summary.txt" label="${tool.name} on ${on_string}: SummaryData">
<filter>generate_summary</filter>
<filter>input_type_select['input_type'] == 'individually' and generate_summary</filter>
</data>
<data format="html" name="html_file_forward" from_work_dir="*forward_fastqc_report.html" label="${tool.name} on ${on_string}: Webpage forward" >
<filter>input_type_select['input_type'] == 'paired'</filter>
</data>
<data format="txt" name="text_file_forward" from_work_dir="*forward_fastqc_data.txt" label="${tool.name} on ${on_string}: RawData forward" >
<filter>input_type_select['input_type'] == 'paired'</filter>
</data>
<data format="txt" name="summary_file_forward" from_work_dir="*forward_summary.txt" label="${tool.name} on ${on_string}: SummaryData forward">
<filter>input_type_select['input_type'] == 'paired' and generate_summary</filter>
</data>
<data format="html" name="html_file_reverse" from_work_dir="*reverse_fastqc_report.html" label="${tool.name} on ${on_string}: Webpage reverse" >
<filter>input_type_select['input_type'] == 'paired'</filter>
</data>
<data format="txt" name="text_file_reverse" from_work_dir="*reverse_fastqc_data.txt" label="${tool.name} on ${on_string}: RawData reverse" >
<filter>input_type_select['input_type'] == 'paired'</filter>
</data>
<data format="txt" name="summary_file_reverse" from_work_dir="*reverse_summary.txt" label="${tool.name} on ${on_string}: SummaryData reverse">
<filter>input_type_select['input_type'] == 'paired' and generate_summary</filter>
</data>
</outputs>
<tests>
<!-- Test with fastq input -->
<test expect_num_outputs="2">
<param name="input_file" value="1000trimmed.fastq"/>
<conditional name="input_type_select">
<param name="input_file" value="1000trimmed.fastq"/>
</conditional>
<output name="html_file" ftype="html">
<assert_contents>
<has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt; 1000trimmed_fastq - report.+"/>
Expand All @@ -87,7 +142,9 @@
</test>
<!-- Test with fastq.gz input -->
<test expect_num_outputs="2">
<param name="input_file" value="1000trimmed.fastq.gz"/>
<conditional name="input_type_select">
<param name="input_file" value="1000trimmed.fastq.gz"/>
</conditional>
<output name="html_file" ftype="html">
<assert_contents>
<has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt; 1000trimmed_fastq_gz - report.+"/>
Expand All @@ -98,7 +155,9 @@
</test>
<!-- Test with BAM input -->
<test expect_num_outputs="2">
<param name="input_file" value="hisat_output_1.bam"/>
<conditional name="input_type_select">
<param name="input_file" value="hisat_output_1.bam"/>
</conditional>
<output name="html_file" ftype="html">
<assert_contents>
<has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt; hisat_output_1_bam - report.+"/>
Expand All @@ -109,7 +168,9 @@
</test>
<!-- Test summary file option -->
<test expect_num_outputs="3">
<param name="input_file" value="1000trimmed.fastq"/>
<conditional name="input_type_select">
<param name="input_file" value="1000trimmed.fastq"/>
</conditional>
<param name="generate_summary" value="true"/>
<output name="html_file" ftype="html">
<assert_contents>
Expand All @@ -120,7 +181,9 @@
<output name="summary_file" file="fastqc_data_summary.txt" ftype="txt"/>
</test>
<test expect_num_outputs="2">
<param name="input_file" value="1000trimmed.fastq"/>
<conditional name="input_type_select">
<param name="input_file" value="1000trimmed.fastq"/>
</conditional>
<param name="contaminants" value="contaminant_list.txt" ftype="tabular"/>
<output name="html_file" ftype="html">
<assert_contents>
Expand All @@ -130,7 +193,9 @@
<output name="text_file" file="fastqc_data_contaminants.txt" ftype="txt" lines_diff="2"/>
</test>
<test expect_num_outputs="2">
<param name="input_file" value="1000trimmed.fastq"/>
<conditional name="input_type_select">
<param name="input_file" value="1000trimmed.fastq"/>
</conditional>
<param name="adapters" value="adapter_list.txt" ftype="tabular"/>
<output name="html_file" ftype="html">
<assert_contents>
Expand All @@ -140,7 +205,9 @@
<output name="text_file" file="fastqc_data_adapters.txt" ftype="txt" lines_diff="2"/>
</test>
<test expect_num_outputs="3">
<param name="input_file" value="1000trimmed.fastq"/>
<conditional name="input_type_select">
<param name="input_file" value="1000trimmed.fastq"/>
</conditional>
<param name="limits" value="limits.txt" ftype="txt"/>
<param name="generate_summary" value="true"/>
<output name="html_file" ftype="html">
Expand Down Expand Up @@ -170,8 +237,10 @@
<output name="text_file" file="fastqc_data_min_length.txt" ftype="txt"/>
</test> -->
<test expect_num_outputs="2">
<param name="input_file" value="1000trimmed.fastq" ftype="fastq"/>
<param name="nogroup" value="--nogroup"/>
<conditional name="input_type_select">
<param name="input_file" value="1000trimmed.fastq" ftype="fastq"/>
</conditional>
<param name="nogroup" value="true"/>
<output name="html_file" ftype="html">
<assert_contents>
<has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt; 1000trimmed_fastq - report.+"/>
Expand All @@ -180,7 +249,9 @@
<output name="text_file" file="fastqc_data_nogroup.txt" ftype="txt" lines_diff="2"/>
</test>
<test expect_num_outputs="3">
<param name="input_file" value="1000trimmed.fastq"/>
<conditional name="input_type_select">
<param name="input_file" value="1000trimmed.fastq"/>
</conditional>
<param name="subsample" value="10"/>
<param name="generate_summary" value="true"/>
<output name="html_file" ftype="html">
Expand All @@ -192,8 +263,10 @@
<output name="summary_file" file="fastqc_report_subsample_summary.txt" ftype="txt"/>
</test>
<test expect_num_outputs="3">
<param name="input_file" value="1000trimmed.fastq"/>
<param name="bisulfite" value="-bisulfite"/>
<conditional name="input_type_select">
<param name="input_file" value="1000trimmed.fastq"/>
</conditional>
<param name="bisulfite" value="true"/>
<param name="generate_summary" value="true"/>
<output name="html_file" ftype="html">
<assert_contents>
Expand All @@ -204,15 +277,58 @@
<output name="summary_file" file="fastqc_report_bisulfite_summary.txt" ftype="txt"/>
</test>
<test expect_num_outputs="2">
<param name="input_file" value="1000trimmed.fastq"/>
<param name="reverse_complement" value="-reverse-complement"/>
<conditional name="input_type_select">
<param name="input_file" value="1000trimmed.fastq"/>
</conditional>
<param name="reverse_complement" value="true"/>
<output name="html_file" ftype="html">
<assert_contents>
<has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt; 1000trimmed_fastq - report.+"/>
</assert_contents>
</output>
<output name="text_file" file="fastqc_report_reverse_complement.txt" ftype="txt" lines_diff="2"/>
</test>
<!-- Test summary file option paired input -->
<test expect_num_outputs="6">
<conditional name="input_type_select">
<param name="input_type" value="paired"/>
<param name="input_col">
<collection type="paired" name="1000trimmed">
<element name="forward" value="1000trimmed.fastq" />
<element name="reverse" value="1000trimmed.fastq" />
</collection>
</param>
</conditional>
<param name="generate_summary" value="true"/>
<output name="html_file_forward">
<assert_contents>
<has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt; 1000trimmed_forward - report.+"/>
</assert_contents>
</output>
<output name="html_file_reverse">
<assert_contents>
<has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt; 1000trimmed_reverse - report.+"/>
</assert_contents>
</output>
<output name="text_file_forward" value="forward_fastqc_data.txt" />
<output name="text_file_reverse">
<assert_contents>
<has_text text="1000trimmed_reverse" />
</assert_contents>
</output>
<output name="summary_file_forward">
<assert_contents>
<has_text text="1000trimmed_forward" />
<has_n_lines n="11" />
</assert_contents>
</output>
<output name="summary_file_reverse">
<assert_contents>
<has_text text="1000trimmed_reverse" />
<has_n_lines n="11" />
</assert_contents>
</output>
</test>
</tests>
<help><![CDATA[
**What it does**
Expand Down
Loading
Loading