Skip to content

Commit

Permalink
Update Nanopolish to v0.14 (#1359)
Browse files Browse the repository at this point in the history 
* fix lint error + version upgrade

* Explicit untar of .tar.xz

* Adapt tests to multithreading and code refactoring
  • Loading branch information
@tuncK
tuncK authored Nov 30, 2023
1 parent 37305ce commit de2370d
Show file tree
Hide file tree
Showing 5 changed files with 156 additions and 194 deletions.
51 changes: 50 additions & 1 deletion tools/nanopolish/macros.xml
View file
Original file line number Diff line number Diff line change
@@ -1,5 +1,8 @@
<macros>
<token name="@VERSION@">0.13.2</token>
<token name="@VERSION@">0.14.0</token>
<token name="@VERSION_SUFFIX@">0</token>
<token name="@PROFILE@">22.01</token>

<xml name="requirements">
<requirements>
<requirement type="package" version="@VERSION@">nanopolish</requirement>
Expand All @@ -19,6 +22,52 @@
<output name="output_index_readdb" file="reads.fasta.index.readdb" />
-->


<token name="@PREPROCESS_INPUTS@"><![CDATA[
ln -s '$input_merged' reads.fasta &&
mkdir fast5_files &&
#if $input_reads_raw.extension == 'fast5':
ln -s '$input_reads_raw' fast5_files/read1.fast5 &&
#else if $input_reads_raw.extension == 'fast5.tar':
ln -s '$input_reads_raw' fast5_files.tar &&
tar -xf fast5_files.tar -C fast5_files &&
#else if $input_reads_raw.extension == 'fast5.tar.bz2':
ln -s '$input_reads_raw' fast5_files.tar.bz2 &&
tar -xjf fast5_files.tar.bz2 -C fast5_files &&
#else if $input_reads_raw.extension == 'fast5.tar.xz':
ln -s '$input_reads_raw' fast5_files.tar.xz &&
tar -xf fast5_files.tar.xz -C fast5_files &&
#else if $input_reads_raw.extension == 'fast5.tar.gz':
ln -s '$input_reads_raw' fast5_files.tar.gz &&
tar -xzf fast5_files.tar.gz -C fast5_files &&
#else:
echo 'Unsupported fast5 input type' &&
exit 1 &&
#end if
nanopolish index
-d fast5_files/
#if $adv.input_seq_summary:
-s '$adv.input_seq_summary'
#end if
reads.fasta &&
ln -s '$b' reads.bam &&
ln -s '${b.metadata.bam_index}' reads.bam.bai &&
#if $reference_source.reference_source_selector == 'history':
ln -f -s '$reference_source.ref_file' genome.fa &&
#else:
ln -f -s '$reference_source.ref_file.fields.path' genome.fa &&
#end if
]]></token>

<xml name="citations">
<citations>
<citation type="doi">10.1038/nmeth.3444</citation>
Expand Down
110 changes: 47 additions & 63 deletions tools/nanopolish/nanopolish_eventalign.xml
View file
Original file line number Diff line number Diff line change
@@ -1,74 +1,42 @@
<tool id="nanopolish_eventalign" name="Nanopolish eventalign" version="@VERSION@+galaxy1">
<tool id="nanopolish_eventalign" name="Nanopolish eventalign" version="@VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
<description>- Align nanopore events to reference k-mers</description>
<macros>
<import>macros.xml</import>
</macros>
<expand macro="requirements" />
<command detect_errors="exit_code"><![CDATA[
ln -s '$input_merged' reads.fasta &&
#if $input_reads_raw.extension == 'fast5':
mkdir fast5_files && ln -s '$input_reads_raw' fast5_files/read1.fast5 &&
#else if $input_reads_raw.extension == 'fast5.tar':
ln -s '$input_reads_raw' fast5_files.tar &&
mkdir fast5_files && tar -xf fast5_files.tar -C fast5_files &&
#else if $input_reads_raw.extension == 'fast5.tar.bz2':
ln -s '$input_reads_raw' fast5_files.tar.bz2 &&
mkdir fast5_files && tar -xjf fast5_files.tar.bz2 -C fast5_files &&
#else:
ln -s '$input_reads_raw' fast5_files.tar.gz &&
mkdir fast5_files && tar -xzf fast5_files.tar.gz -C fast5_files &&
#end if
nanopolish index
-d fast5_files/
#if $adv.input_seq_summary:
-s '$adv.input_seq_summary'
#end if
reads.fasta &&
ln -s '$b' reads.bam &&
ln -s '${b.metadata.bam_index}' reads.bam.bai &&
#if $reference_source.reference_source_selector == 'history':
ln -f -s '$reference_source.ref_file' genome.fa &&
#else:
ln -f -s '$reference_source.ref_file.fields.path' genome.fa &&
#end if
@PREPROCESS_INPUTS@
nanopolish eventalign
-r reads.fasta
-b reads.bam
-g genome.fa
#if str($min_mapping_quality):
-q $min_mapping_quality
#end if
--threads "\${GALAXY_SLOTS:-4}"
$samples
$scale_events
$signal_index
$sam
$print_read_names
#if $w and str($w).strip():
-w "${w}"
#end if
#if $input_models_fofn:
--models-fofn '$input_models_fofn'
#end if
#if $summary:
--summary eventalign-summary.txt
#end if
> eventalign.out
-r reads.fasta
-b reads.bam
-g genome.fa
#if str($min_mapping_quality):
-q $min_mapping_quality
#end if
--threads "\${GALAXY_SLOTS:-4}"
$samples
$scale_events
$signal_index
$sam
$print_read_names
#if $w and str($w).strip():
-w "${w}"
#end if
#if $input_models_fofn:
--models-fofn '$input_models_fofn'
#end if
#if $summary:
--summary eventalign-summary.txt
#end if
> eventalign.out
]]></command>
<inputs>
<!-- index inputs -->
<param type="data" name="input_merged" format="fasta,fastq" label="Basecalled merged reads.fa"/>
<param type="data" name="input_reads_raw" format="fast5.tar.gz,fast5.tar.bz2,fast5.tar" label="Flat archive file of raw fast5 files"/>
<param type="data" name="input_reads_raw" format="fast5.tar.xz,fast5.tar.gz,fast5.tar.bz2,fast5.tar,fast5" label="Flat archive file of raw fast5 files"/>

<!-- variants consensus inputs -->
<param type="data" argument="-b" format="bam" label="Reads aligned to the reference genome" />
Expand Down Expand Up @@ -109,17 +77,16 @@
label="Summarize the alignment of each read/strand" />
<param argument="--samples" type="boolean" truevalue="--samples" falsevalue="" checked="false"
label="Write the raw samples for the event to the tsv output" />
<param name="scale_events" argument="--scale-events" type="boolean" truevalue="--scale-events" falsevalue="" checked="false"
<param argument="--scale-events" type="boolean" truevalue="--scale-events" falsevalue="" checked="false"
label="Scale events to the model, rather than vice-versa" />
<param name="signal_index" argument="--signal-index" type="boolean" truevalue="--signal-index" falsevalue="" checked="false"
<param argument="--signal-index" type="boolean" truevalue="--signal-index" falsevalue="" checked="false"
label="write the raw signal start and end index values for the event to the tsv output" />


<param argument="--sam" type="boolean" truevalue="--sam" falsevalue="" checked="false"
label="write output in SAM format" />
<param name="print_read_names" argument="--print-read-names" type="boolean" truevalue="--print-read-names" falsevalue="" checked="false"
<param argument="--print-read-names" type="boolean" truevalue="--print-read-names" falsevalue="" checked="false"
label="Print read names instead of indexes" />

</inputs>

<outputs>
Expand All @@ -136,8 +103,25 @@
<param name="ref_file" value="draft.fa" />
<param name="w" value="tig00000001:200000-200010" />
<param name="sam" value="true" />
<output name="output_summary" file="eventalign-summary.txt" />
<output name="output_eventalign" file="reads-draft.eventalign.sam"/>
<output name="output_summary" file="eventalign-summary.txt" compare="sim_size">
<assert_contents>
<has_n_lines n="144"/>
<has_n_columns n="14"/>
<has_line_matching expression="read_index\sread_name\sfast5_path\smodel_name\sstrand\snum_events\snum_steps\snum_skips\snum_stays\stotal_duration\sshift\sscale\sdrift\svar"/>
<has_text text="d57afb7d-903e-46cf-a43d-0e17fb0949d8"/>
<has_text text="15727"/>
<has_text text="fast5_files//odw_genlab4209_20161213_FN_MN16303_sequencing_run_sample_id_32395_ch378_read5665_strand.fast5"/>
</assert_contents>
</output>
<output name="output_eventalign" file="reads-draft.eventalign.sam" compare="sim_size">
<assert_contents>
<has_n_lines n="148"/>
<has_line_matching expression="@SQ\sSN:tig00000001\sLN:4376233"/>
<has_text text="d57afb7d-903e-46cf-a43d-0e17fb0949d8"/>
<has_text text="191118"/>
<has_text text="274S1M2I3M1I2M2I9M1I1M1I1M1I9M6I3M1I1M2I2M2I2M1"/>
</assert_contents>
</output>
</test>
<test>
<param name="input_merged" ftype="fasta" value="reads.fasta" />
Expand Down
56 changes: 12 additions & 44 deletions tools/nanopolish/nanopolish_methylation.xml
View file
Original file line number Diff line number Diff line change
@@ -1,55 +1,23 @@
<tool id="nanopolish_methylation" name="Nanopolish methylation" version="@VERSION@+galaxy0">
<tool id="nanopolish_methylation" name="Nanopolish methylation" version="@VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
<description>- Classify nucleotides as methylated or not.</description>
<macros>
<import>macros.xml</import>
</macros>
<expand macro="requirements" />
<command detect_errors="exit_code"><![CDATA[
ln -s '$input_merged' reads.fasta &&
#if $input_reads_raw.extension == 'fast5':
mkdir fast5_files && ln -s '$input_reads_raw' fast5_files/read1.fast5 &&
#else if $input_reads_raw.extension == 'fast5.tar':
ln -s '$input_reads_raw' fast5_files.tar &&
mkdir fast5_files && tar -xf fast5_files.tar -C fast5_files &&
#else if $input_reads_raw.extension == 'fast5.tar.bz2':
ln -s '$input_reads_raw' fast5_files.tar.bz2 &&
mkdir fast5_files && tar -xjf fast5_files.tar.bz2 -C fast5_files &&
#else:
ln -s '$input_reads_raw' fast5_files.tar.gz &&
mkdir fast5_files && tar -xzf fast5_files.tar.gz -C fast5_files &&
#end if
nanopolish index
-d fast5_files/
#if $adv.input_seq_summary:
-s '$adv.input_seq_summary'
#end if
reads.fasta &&
ln -s '$b' reads.bam &&
ln -s '${b.metadata.bam_index}' reads.bam.bai &&
#if $reference_source.reference_source_selector == 'history':
ln -f -s '$reference_source.ref_file' genome.fa &&
#else:
ln -f -s '$reference_source.ref_file.fields.path' genome.fa &&
#end if
@PREPROCESS_INPUTS@
nanopolish call-methylation
-r reads.fasta
-b reads.bam
-g genome.fa
#if str($batchsize):
-K $batchsize
#end if
--threads "\${GALAXY_SLOTS:-4}"
#if $w and str($w).strip():
-w "${w}"
#end if
-r reads.fasta
-b reads.bam
-g genome.fa
#if str($batchsize):
-K $batchsize
#end if
--threads "\${GALAXY_SLOTS:-4}"
#if $w and str($w).strip():
-w "${w}"
#end if
> methylation_calls.tsv
]]></command>
<inputs>
Expand Down
83 changes: 39 additions & 44 deletions tools/nanopolish/nanopolish_polya.xml
View file
Original file line number Diff line number Diff line change
@@ -1,52 +1,20 @@
<tool id="nanopolish_polya" name="Nanopolish polyA" version="@VERSION@+galaxy0">
<tool id="nanopolish_polya" name="Nanopolish polyA" version="@VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
<description>- Estimate the length of the poly-A tail on direct RNA reads.</description>
<macros>
<import>macros.xml</import>
</macros>
<expand macro="requirements" />
<command detect_errors="exit_code"><![CDATA[
ln -s '$input_merged' reads.fasta &&
#if $input_reads_raw.extension == 'fast5':
mkdir fast5_files && ln -s '$input_reads_raw' fast5_files/read1.fast5 &&
#else if $input_reads_raw.extension == 'fast5.tar':
ln -s '$input_reads_raw' fast5_files.tar &&
mkdir fast5_files && tar -xf fast5_files.tar -C fast5_files &&
#else if $input_reads_raw.extension == 'fast5.tar.bz2':
ln -s '$input_reads_raw' fast5_files.tar.bz2 &&
mkdir fast5_files && tar -xjf fast5_files.tar.bz2 -C fast5_files &&
#else:
ln -s '$input_reads_raw' fast5_files.tar.gz &&
mkdir fast5_files && tar -xzf fast5_files.tar.gz -C fast5_files &&
#end if
nanopolish index
-d fast5_files/
#if $adv.input_seq_summary:
-s '$adv.input_seq_summary'
#end if
reads.fasta &&
ln -s '$b' reads.bam &&
ln -s '${b.metadata.bam_index}' reads.bam.bai &&
#if $reference_source.reference_source_selector == 'history':
ln -f -s '$reference_source.ref_file' genome.fa &&
#else:
ln -f -s '$reference_source.ref_file.fields.path' genome.fa &&
#end if
@PREPROCESS_INPUTS@
nanopolish polya
-r reads.fasta
-b reads.bam
-g genome.fa
--threads "\${GALAXY_SLOTS:-4}"
#if $w and str($w).strip():
-w "${w}"
#end if
-r reads.fasta
-b reads.bam
-g genome.fa
--threads "\${GALAXY_SLOTS:-4}"
#if $w and str($w).strip():
-w "${w}"
#end if
> polya_results.tsv
]]></command>
<inputs>
Expand Down Expand Up @@ -93,7 +61,16 @@
<param name="reference_source_selector" value="history" />
<param name="ref_file" value="enolase_reference.fas" />
<!-- <param name="w" value="tig00000001:200000-202000" /> -->
<output name="polya_results" file="30xpolyA-small-subset-results.tsv" />
<output name="polya_results" file="30xpolyA-small-subset-results.tsv" compare="sim_size">
<assert_contents>
<has_n_lines n="14"/>
<has_n_columns n="10"/>
<has_line_matching expression="readname\scontig\sposition\sleader_start\sadapter_start\spolya_start\stranscript_start\sread_rate\spolya_length\sqc_tag"/>
<has_text text="453f3f3e-d22f-4d9c-81a6-8576e23390ed"/>
<has_text text="YHR174W"/>
<has_text text="READ_FAILED_LOAD"/>
</assert_contents>
</output>
</test>
<test>
<param name="input_merged" ftype="fastq" value="30xpolyA-small-subset.fastq" />
Expand All @@ -102,7 +79,16 @@
<param name="reference_source_selector" value="history" />
<param name="ref_file" value="enolase_reference.fas" />
<param name="w" value="YHR174W:600-900" />
<output name="polya_results" file="30xpolyA-small-subset-win-results.tsv" />
<output name="polya_results" file="30xpolyA-small-subset-win-results.tsv" compare="sim_size">
<assert_contents>
<has_n_lines n="12"/>
<has_n_columns n="10"/>
<has_line_matching expression="readname\scontig\sposition\sleader_start\sadapter_start\spolya_start\stranscript_start\sread_rate\spolya_length\sqc_tag"/>
<has_text text="453f3f3e-d22f-4d9c-81a6-8576e23390ed"/>
<has_text text="YHR174W"/>
<has_text text="READ_FAILED_LOAD"/>
</assert_contents>
</output>
</test>
<test>
<param name="input_merged" ftype="fastq" value="30xpolyA-small-subset.fastq" />
Expand All @@ -111,7 +97,16 @@
<param name="reference_source_selector" value="history" />
<param name="ref_file" value="enolase_reference.fas" />
<param name="w" value="YHR174W:600-900" />
<output name="polya_results" file="30xpolyA-small-subset-win-results-t3.tsv" />
<output name="polya_results" file="30xpolyA-small-subset-win-results-t3.tsv" compare="sim_size">
<assert_contents>
<has_n_lines n="12"/>
<has_n_columns n="10"/>
<has_line_matching expression="readname\scontig\sposition\sleader_start\sadapter_start\spolya_start\stranscript_start\sread_rate\spolya_length\sqc_tag"/>
<has_text text="453f3f3e-d22f-4d9c-81a6-8576e23390ed"/>
<has_text text="YHR174W"/>
<has_text text="READ_FAILED_LOAD"/>
</assert_contents>
</output>
</test>
</tests>
<help><![CDATA[
Expand Down
Loading

0 comments on commit de2370d

Please sign in to comment.