Skip to content

Update semibin2 to 2.1.0 #6503

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

Open
wants to merge 14 commits into
base: main
Choose a base branch
from
+2,482 −99
Open

Update semibin2 to 2.1.0 #6503

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
652f648
update semibin2 to 2.1.0
Oct 31, 2024
35dddea
remove deprecated fraggenscan option
Oct 31, 2024
724571d
update
Jan 6, 2025
1d5d850
tests failing
Jan 8, 2025
5d89a9a
text alignment files work
Jan 15, 2025
b587808
add test data
Jan 15, 2025
976856f
fix one test
Jan 15, 2025
932d285
update to new changes for just semibin.xml so far
Jun 4, 2025
13b1555
add help text about known errors, fix one test
Jun 8, 2025
f9d4239
Merge remote-tracking branch 'origin/main' into semibin2_update
dannon Jun 8, 2025
9104958
remove file count with known issues
Jun 8, 2025
870ef79
remove test lines for outputs with variable counts across hardware, k…
Jun 8, 2025
b09f757
typo
Jun 9, 2025
b6e558d
Update tools/semibin/semibin.xml
astrovsky01 Jun 30, 2025
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
148 changes: 126 additions & 22 deletions tools/semibin/generate_sequence_features.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,18 +10,29 @@
<expand macro="version"/>
<command detect_errors="exit_code"><![CDATA[
#import re
@BAM_FILES@
#if $input_type_select.input_type == "bam":
@BAM_FILES@
#else:
#for $e in $input_type_select.mode.abundance:
#set $identifier = re.sub('[^\s\w\-\\.]', '_', str($e.element_identifier))
ln -s '$e' '${identifier}.txt' &&
#end for
#end if
@FASTA_FILES@

SemiBin2
#if $mode.select == 'single' or $mode.select == 'co'
#if $input_type_select.mode.select == 'single' or $input_type_select.mode.select == 'co'
generate_sequence_features_single
#else
generate_sequence_features_multi
--separator '$separator'
#end if
--input-fasta 'contigs.fasta'
#if $input_type_select.input_type == "bam"
--input-bam *.bam
#else:
-a *.txt
#end if
--output 'output'
--threads \${GALAXY_SLOTS:-1}
@MIN_LEN@
Expand All @@ -30,7 +41,18 @@ SemiBin2
#end if
]]></command>
<inputs>
<expand macro="mode_fasta_bam"/>
<conditional name="input_type_select">
<param name="input_type" type="select" label="Use BAM or strobealign abundance information?">
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

you have that as a macro below?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Input type picks which macro to open -- bam or strobealign

<option value="bam">BAM file</option>
<option value="txt">strobealign-aemb files</option>
</param>
<when value="bam">
<expand macro="mode_fasta_bam"/>
</when>
<when value="txt">
<expand macro="mode_fasta_strobealign"/>
</when>
</conditional>
<expand macro="min_len"/>
<expand macro="ml-threshold"/>
<param name="extra_output" type="select" multiple="true" label="Extra outputs" help="In addition to the training data">
Expand All @@ -45,10 +67,13 @@ SemiBin2
</outputs>
<tests>
<test expect_num_outputs="4">
<conditional name="mode">
<param name="select" value="single"/>
<param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
<param name="input_bam" ftype="bam" value="input_single.bam"/>
<conditional name="input_type_select">
<param name="input_type" value="bam"/>
<conditional name="mode">
<param name="select" value="single"/>
<param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
<param name="input_bam" ftype="bam" value="input_single.bam"/>
</conditional>
</conditional>
<conditional name="min_len">
<param name="method" value="automatic"/>
Expand Down Expand Up @@ -83,10 +108,13 @@ SemiBin2
</output>
</test>
<test expect_num_outputs="4">
<conditional name="mode">
<param name="select" value="co"/>
<param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
<param name="input_bam" ftype="bam" value="input_coassembly_sorted1.bam,input_coassembly_sorted2.bam,input_coassembly_sorted3.bam,input_coassembly_sorted4.bam,input_coassembly_sorted5.bam"/>
<conditional name="input_type_select">
<param name="input_type" value="bam"/>
<conditional name="mode">
<param name="select" value="co"/>
<param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
<param name="input_bam" ftype="bam" value="input_coassembly_sorted1.bam,input_coassembly_sorted2.bam,input_coassembly_sorted3.bam,input_coassembly_sorted4.bam,input_coassembly_sorted5.bam"/>
</conditional>
</conditional>
<conditional name="min_len">
<param name="method" value="automatic"/>
Expand Down Expand Up @@ -138,13 +166,16 @@ SemiBin2
</output_collection>
</test>
<test expect_num_outputs="7">
<conditional name="mode">
<param name="select" value="multi"/>
<conditional name="multi_fasta">
<param name="select" value="concatenated"/>
<param name="input_fasta" ftype="fasta" value="input_multi.fasta.gz"/>
<conditional name="input_type_select">
<param name="input_type" value="bam"/>
<conditional name="mode">
<param name="select" value="multi"/>
<conditional name="multi_fasta">
<param name="select" value="concatenated"/>
<param name="input_fasta" ftype="fasta" value="input_multi.fasta.gz"/>
</conditional>
<param name="input_bam" ftype="bam" value="input_multi_sorted1.bam,input_multi_sorted2.bam,input_multi_sorted3.bam,input_multi_sorted4.bam,input_multi_sorted5.bam,input_multi_sorted6.bam,input_multi_sorted7.bam,input_multi_sorted8.bam,input_multi_sorted9.bam,input_multi_sorted10.bam"/>
</conditional>
<param name="input_bam" ftype="bam" value="input_multi_sorted1.bam,input_multi_sorted2.bam,input_multi_sorted3.bam,input_multi_sorted4.bam,input_multi_sorted5.bam,input_multi_sorted6.bam,input_multi_sorted7.bam,input_multi_sorted8.bam,input_multi_sorted9.bam,input_multi_sorted10.bam"/>
</conditional>
<conditional name="min_len">
<param name="method" value="automatic"/>
Expand Down Expand Up @@ -224,14 +255,87 @@ SemiBin2
</element>
</output_collection>
</test>

<test expect_num_outputs="5">
<conditional name="input_type_select">
<param name="input_type" value="txt"/>
<conditional name="mode">
<param name="select" value="multi"/>
<conditional name="multi_fasta">
<param name="select" value="concatenated"/>
<param name="input_fasta" ftype="fasta" value="input_multi.fasta.gz"/>
</conditional>
<param name="abundance" ftype="txt" value="strobealign_1.txt,strobealign_2.txt,strobealign_3.txt,strobealign_4.txt,strobealign_5.txt"/>
</conditional>
</conditional>
<conditional name="min_len">
<param name="method" value="automatic"/>
</conditional>
<param name="ml_threshold" value="4000"/>
<param name="extra_output" value="coverage,contigs"/>
<output_collection name="multi_data" count="10">
<element name="S1" ftype="csv">
<assert_contents>
<has_n_lines n="21"/>
<has_text text="g1k_0"/>
</assert_contents>
</element>
</output_collection>
<output_collection name="multi_data_split" count="10">
<element name="S1" ftype="csv">
<assert_contents>
<has_n_lines n="41"/>
<has_text text="g1k_0_1"/>
</assert_contents>
</element>
</output_collection>
<output_collection name="multi_cov_sample" count="10">
<element name="S1" ftype="csv">
<assert_contents>
<has_n_lines n="21"/>
<has_text text="g1k_0"/>
</assert_contents>
</element>
</output_collection>
<output_collection name="multi_split_cov_txt" count="10">
<element name="S1" ftype="csv">
<assert_contents>
<has_n_lines n="41"/>
<has_text text="g1k_5_1"/>
</assert_contents>
</element>
<element name="S9" ftype="csv">
<assert_contents>
<has_n_lines n="41"/>
<has_text text="g1k_5_1"/>
</assert_contents>
</element>
</output_collection>
<output_collection name="multi_contigs" count="10">
<element name="S1" ftype="fasta">
<assert_contents>
<has_text text=">g1k_0"/>
</assert_contents>
</element>
<element name="S9" ftype="fasta">
<assert_contents>
<has_text text=">g1k_0"/>
</assert_contents>
</element>
</output_collection>
</test>

<test expect_num_outputs="2">
<conditional name="mode">
<param name="select" value="multi"/>
<conditional name="multi_fasta">
<conditional name="input_type_select">
<param name="input_type" value="bam"/>
<conditional name="mode">
<param name="select" value="multi"/>
<param name="input_fasta" ftype="fasta" value="S1.fasta,S2.fasta,S3.fasta,S4.fasta,S5.fasta,S6.fasta,S7.fasta,S8.fasta,S9.fasta,S10.fasta"/>
<conditional name="multi_fasta">
<param name="select" value="multi"/>
<param name="input_fasta" ftype="fasta" value="S1.fasta,S2.fasta,S3.fasta,S4.fasta,S5.fasta,S6.fasta,S7.fasta,S8.fasta,S9.fasta,S10.fasta"/>
</conditional>
<param name="input_bam" ftype="bam" value="input_multi_sorted1.bam,input_multi_sorted2.bam,input_multi_sorted3.bam,input_multi_sorted4.bam,input_multi_sorted5.bam,input_multi_sorted6.bam,input_multi_sorted7.bam,input_multi_sorted8.bam,input_multi_sorted9.bam,input_multi_sorted10.bam"/>
</conditional>
<param name="input_bam" ftype="bam" value="input_multi_sorted1.bam,input_multi_sorted2.bam,input_multi_sorted3.bam,input_multi_sorted4.bam,input_multi_sorted5.bam,input_multi_sorted6.bam,input_multi_sorted7.bam,input_multi_sorted8.bam,input_multi_sorted9.bam,input_multi_sorted10.bam"/>
</conditional>
<conditional name="min_len">
<param name="method" value="automatic"/>
Expand Down
Loading