annotate instrain_profile.xml @ 3:7dc2de2e43fa draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/instrain commit aa7c7a35834f36dad6e72d5f54089a578be60731
author iuc
date Thu, 02 Nov 2023 14:59:54 +0000
parents c332659ecdcc
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
1 <tool id="instrain_profile" name="InStrain Profile" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
2 <description>Creates an inStrain profile (microdiversity analysis) from a mapping file </description>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
3 <macros>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
4 <import>macros.xml</import>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
5 </macros>
3
7dc2de2e43fa planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/instrain commit aa7c7a35834f36dad6e72d5f54089a578be60731
iuc
parents: 2
diff changeset
6 <expand macro="biotools"/>
2
c332659ecdcc planemo upload for repository https://github.com/MrOlm/inStrain commit ef9562d6883ba5bca59050ac2477e346f76583f9
iuc
parents: 0
diff changeset
7 <expand macro="requirements"/>
0
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
8 <version_command>inStrain profile --version</version_command>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
9 <command detect_errors="exit_code"><![CDATA[
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
10 #set ext=$mapping_input.datatype.file_ext
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
11 ln -s '$mapping_input' 'inputbam.$ext'
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
12 #if $gene_profiling.gene_file
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
13 &&
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
14 ln -s '$gene_profiling.gene_file' 'gene_file.fna'
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
15 #end if
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
16 #if $stb
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
17 &&
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
18 ln -s '$stb' 'stb_file.stb'
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
19 #end if
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
20 &&
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
21 inStrain profile
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
22 'inputbam.$ext'
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
23 '$sequence_input'
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
24 --output 'inStrain.IS'
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
25 $use_full_fasta_header
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
26 --processes "\${GALAXY_SLOTS:-6}"
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
27 --min_mapq $read_filtering.min_mapq
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
28 --max_insert_relative $read_filtering.max_insert_relative
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
29 --min_insert $read_filtering.min_insert
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
30 --pairing_filter '$read_filtering.pairing_filter'
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
31 #if $priority_reads
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
32 --priority_reads '$read_filtering.priority_reads'
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
33 #end if
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
34 $output.detailed_mapping_info
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
35 --min_cov $variant_calling.min_cov
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
36 --min_freq $variant_calling.min_freq
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
37 --fdr $variant_calling.fdr
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
38 #if $gene_file
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
39 --gene_file 'gene_file.fna'
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
40 #end if
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
41 #if $stb
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
42 --stb 'stb_file.stb'
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
43 #end if
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
44 $mm_level
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
45 #if $profile.database_mode
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
46 $profile.database_mode
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
47 #else
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
48 --min_read_ani $read_filtering.min_read_ani
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
49 --min_genome_coverage $profile.min_genome_coverage
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
50 $skip_mm_profiling
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
51 #end if
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
52 --min_scaffold_reads $profile.min_scaffold_reads
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
53 --min_snp $profile.min_snp
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
54 $profile.store_everything
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
55 #if $profile.scaffolds_to_profile
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
56 --scaffolds_to_profile '$profile.scaffolds_to_profile'
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
57 #end if
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
58 --rarefied_coverage $profile.rarefied_coverage
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
59 --window_length $profile.window_length
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
60 $output.skip_genome_wide
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
61 $output.skip_plot_generation
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
62 &&
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
63 cd ./inStrain.IS && zip -r ../inStrain.IS.zip *
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
64 ]]></command>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
65 <inputs>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
66 <param name="mapping_input" type="data" format="bam,sam" label="A file containing metagenomic reads mapped to a DNA sequence" help="Sorted Bam file"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
67 <param name="sequence_input" type="data" format="fasta" label="A file containing a DNA sequence."/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
68 <param argument="--use_full_fasta_header" type="boolean" truevalue="--use_full_fasta_header" falsevalue="" checked="false" label="Use full fasta header" help="Instead of using the fasta ID (space in header before space), use the full header. Needed for some mapping tools (including bbMap)"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
69 <section name="read_filtering" title="Read Filtering" expanded="true">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
70 <param argument="--min_read_ani" type="float" value="0.95" min="0" max="1" label="Minimum percent identity" help=" Minimum percent identity of read pairs to consensus to use the reads. Must be >, not >="/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
71 <param argument="--min_mapq" type="integer" value="-1" label="Minimum mapq score" help="Minimum mapq score of EITHER read in a pair to use that pair. Must be >, not >="/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
72 <param argument="--max_insert_relative" type="integer" value="3" label="Maximum insert relative" help="Multiplier to determine maximum insert size between two reads - default is to use 3x median insert size. Must be >, not >="/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
73 <param argument="--min_insert" type="integer" value="50" label="Minimum insert" help="Minimum insert size between two reads - default is 50 bp. If two reads are 50bp each and overlap completely, their insert will be 50. Must be >, not >="/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
74 <param argument="--pairing_filter" type="select" label="How should paired reads be handled?">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
75 <option value="paired_only" selected="true">Only paired reads are retained</option>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
76 <option value="non_discordant">Keep all paired reads and singleton reads that map to a single scaffold</option>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
77 <option value="all_reads">Keep all reads regardless of pairing status (NOT RECOMMENDED; See documentation for deatils)</option>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
78 </param>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
79 <param argument="--priority_reads" type="data" format="fastqsanger,fastqsanger.gz" optional="true" label="The location of a list of reads that should be retained regardless of pairing status" help="For example long reads or merged reads. This can be a .fastq file or text file with list of read names (will assume file is compressed if ends in .gz"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
80 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
81 <section name="variant_calling" title="Variant Calling" expanded="true">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
82 <param argument="--min_cov" type="integer" value="5" label="Minimum coverage" help=" Minimum coverage to call a variant"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
83 <param argument="--min_freq" type="float" value="0.05" label="Minimum SNP frequency" help="Minimum SNP frequency to confirm a SNV (both this AND the FDR snp count cutoff must be true to call a SNP)."/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
84 <param argument="--fdr" type="float" value="1e-06" min="0" max="1" label="FDR" help="SNP false discovery rate- based on simulation data with a 0.1 percent error rate (Q30)"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
85 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
86 <section name="gene_profiling" title="Gene Profiling" expanded="true">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
87 <param argument="--gene_file" type="data" format="fasta,genbank" optional="true" label="Path to prodigal .fna genes file. If file ends in .gb or .gbk, will treat as a genbank file" help="EXPERIMENTAL; the name of the gene must be in the gene qualifier"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
88 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
89 <param argument="--stb" type="data" format="tabular" optional="true" label="Scaffold to bin" help="This can be a file with each line listing a scaffold and a bin name, tab-seperated. This can also be a space-seperated list of .fasta files, with one genome per .fasta file. If nothing is provided, all scaffolds will be treated as belonging to the same genome"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
90 <param argument="--mm_level" type="boolean" truevalue="--mm_level" falsevalue="" checked="false" label="Create output files on the mm level"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
91 <param argument="--skip_mm_profiling" type="boolean" truevalue="--skip_mm_profiling" falsevalue="" checked="false" label ="Skip mm profiling" help="Dont perform analysis on an mm level; saves RAM and time; impacts plots and raw_data"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
92 <section name="profile" title="Profile" expanded="true">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
93 <param argument="--database_mode" type="boolean" truevalue="--database_mode" falsevalue="" checked="false" label="Database mode" help="Set a number of parameters to values appropriate for mapping to a large fasta file."/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
94 <param argument="--min_scaffold_reads" type="integer" value="1" label="Minimum scaffold reads" help="Minimum number of reads mapping to a scaffold to proceed with profiling it"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
95 <param argument="--min_genome_coverage" type="integer" value="0" label="Minimum genome coverage" help="Minimum number of reads mapping to a genome to proceed with profiling it. MUST profile .stb if this is set"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
96 <param argument="--min_snp" type="integer" value="20" label="Minimum SNP" help="Absolute minimum number of reads connecting two SNPs to calculate LD between them."/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
97 <param argument="--store_everything" type="boolean" truevalue="--store_everything" falsevalue="" checked="false" label="Store everything" help="Store intermediate dictionaries in the pickle file; will result in significantly more RAM and disk usage"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
98 <param argument="--scaffolds_to_profile" type="data" format="fasta" optional="true" label="Scaffolds to profile" help="File containing a list of scaffolds to profile- if provided will ONLY profile those scaffolds"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
99 <param argument="--rarefied_coverage" type="integer" value="50" label="Rarefied coverage" help="When calculating nucleotide diversity, also calculate a rarefied version with this much coverage"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
100 <param argument="--window_length" type="integer" value="10000" label ="Window length" help="Break scaffolds into windows of this length when profiling"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
101 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
102 <section name="output" title="Set Output Parameters" expanded="true">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
103 <param argument="--detailed_mapping_info" type="boolean" truevalue="--detailed_mapping_info" falsevalue="" checked="false" label="Detailed mapping info" help="Make a detailed read report indicating deatils about each individual mapped read"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
104 <param argument="--skip_genome_wide" type="boolean" truevalue="--skip_genome_wide" falsevalue="" checked="false" label="Skip genome wide" help="Do not generate tables that consider groups of scaffolds belonging to genomes"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
105 <param argument="--skip_plot_generation" type="boolean" truevalue="--skip_plot_generation" falsevalue="" checked="false" label="Skip plot generation" help="Do not make plots"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
106 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
107 </inputs>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
108 <outputs>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
109 <data format="zip" name="inStrain_zip" from_work_dir="inStrain.IS.zip" label="inStrain Profile IS zip" />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
110 <data name="scaffold_info" format="tabular" from_work_dir="inStrain.IS/output/inStrain.IS_scaffold_info.tsv" label="Scoffold Info, This gives basic information about the scaffolds in your sample at the highest allowed level of read identity." />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
111 <data name="mapping_info" format="tabular" from_work_dir="inStrain.IS/output/inStrain.IS_mapping_info.tsv" label="Mapping Info, This provides an overview of the number of reads that map to each scaffold, and some basic metrics about their quality." />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
112 <data name="SNVs" format="tabular" from_work_dir="inStrain.IS/output/inStrain.IS_SNVs.tsv" label="SNV, This describes the SNVs and SNSs that are detected in this mapping." />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
113 <data format="tabular" name="linkage" from_work_dir="inStrain.IS/output/inStrain.IS_linkage.tsv" label="Linkage, This describes the linkage between pairs of SNPs in the mapping that are found on the same read pair at least min_snp times." />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
114 <data format="tabular" name="gene_info" from_work_dir="inStrain.IS/output/inStrain.IS_gene_info.tsv" label="Gene Info, This describes some basic information about the genes being profiled" />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
115 <data format="tabular" name="genome_info" from_work_dir="inStrain.IS/output/inStrain.IS_genome_info.tsv" label="Genome Info, This Describes many of the above metrics on a genome-by-genome level, rather than a scaffold-by-scaffold level." >
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
116 <filter>(output['skip_genome_wide'] is False)</filter>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
117 </data>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
118 <collection name="figures_pdfs" type="list" label="Figures" >
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
119 <discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="inStrain.IS/figures/" format="pdf"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
120 <filter>(output['skip_plot_generation'] is False)</filter>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
121 </collection>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
122 </outputs>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
123 <tests>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
124 <test expect_num_outputs="6">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
125 <param name="mapping_input" value="SmallScaffold.fa.sorted.bam"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
126 <param name="sequence_input" value="SmallScaffold.fa"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
127 <param name="use_full_fasta_header" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
128 <param name="mm_level" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
129 <param name="skip_mm_profiling" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
130 <section name="read_filtering">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
131 <param name="min_read_ani" value="0.95"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
132 <param name="min_mapq" value="-1"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
133 <param name="max_insert_relative" value="3"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
134 <param name="min_insert" value="50"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
135 <param name="pairing_filter" value="paired_only"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
136 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
137 <section name="variant_calling">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
138 <param name="min_cov" value="5"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
139 <param name="min_freq" value="0.05"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
140 <param name="fdr" value="1e-06"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
141 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
142 <section name="profile">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
143 <param name="database_mode" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
144 <param name="min_scaffold_reads" value="1"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
145 <param name="min_genome_coverage" value="0"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
146 <param name="min_snp" value="20"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
147 <param name="store_everything" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
148 <param name="rarefied_coverage" value="50"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
149 <param name="window_length" value="10000"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
150 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
151 <section name="output">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
152 <param name="detailed_mapping_info" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
153 <param name="skip_genome_wide" value="true"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
154 <param name="skip_plot_generation" value="true"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
155 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
156 <output name="inStrain_zip">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
157 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
158 <has_size value="21606" delta="1000" />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
159 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
160 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
161 <output name="scaffold_info">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
162 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
163 <has_text text="length"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
164 <has_n_lines n="2"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
165 <has_n_columns n="21"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
166 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
167 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
168 <output name="mapping_info">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
169 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
170 <has_text text="scaffold"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
171 <has_n_lines n="5"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
172 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
173 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
174 <output name="SNVs">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
175 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
176 <has_text text="position"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
177 <has_n_lines n="5"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
178 <has_n_columns n="16"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
179 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
180 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
181 <output name="linkage">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
182 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
183 <has_n_lines n="1"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
184 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
185 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
186 <output name="gene_info">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
187 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
188 <has_n_lines n="0"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
189 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
190 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
191 </test>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
192 <test expect_num_outputs="8">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
193 <param name="mapping_input" value="SmallScaffold.fa.sorted.bam"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
194 <param name="sequence_input" value="SmallScaffold.fa"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
195 <param name="use_full_fasta_header" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
196 <param name="mm_level" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
197 <param name="skip_mm_profiling" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
198 <section name="read_filtering">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
199 <param name="min_read_ani" value="0.95"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
200 <param name="min_mapq" value="-1"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
201 <param name="max_insert_relative" value="3"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
202 <param name="min_insert" value="50"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
203 <param name="pairing_filter" value="paired_only"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
204 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
205 <section name="variant_calling">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
206 <param name="min_cov" value="5"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
207 <param name="min_freq" value="0.05"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
208 <param name="fdr" value="1e-06"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
209 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
210 <section name="profile">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
211 <param name="database_mode" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
212 <param name="min_scaffold_reads" value="1"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
213 <param name="min_genome_coverage" value="0"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
214 <param name="min_snp" value="20"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
215 <param name="store_everything" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
216 <param name="rarefied_coverage" value="50"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
217 <param name="window_length" value="10000"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
218 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
219 <section name="output">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
220 <param name="detailed_mapping_info" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
221 <param name="skip_genome_wide" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
222 <param name="skip_plot_generation" value="false"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
223 </section>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
224 <output name="inStrain_zip">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
225 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
226 <has_size value="1468006" delta="100000" />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
227 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
228 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
229 <output name="scaffold_info">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
230 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
231 <has_text text="length"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
232 <has_n_lines n="2"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
233 <has_n_columns n="21"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
234 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
235 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
236 <output name="mapping_info">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
237 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
238 <has_text text="scaffold"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
239 <has_n_lines n="5"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
240 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
241 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
242 <output name="SNVs">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
243 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
244 <has_text text="position"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
245 <has_n_lines n="5"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
246 <has_n_columns n="16"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
247 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
248 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
249 <output name="linkage">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
250 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
251 <has_n_lines n="1"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
252 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
253 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
254 <output name="gene_info">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
255 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
256 <has_n_lines n="0"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
257 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
258 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
259 <output name="genome_info">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
260 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
261 <has_text text="nucl_diversity"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
262 <has_n_lines n="2"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
263 <has_n_columns n="26"/>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
264 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
265 </output>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
266 <output_collection name="figures_pdfs" type="list">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
267 <element name="inStrain.IS_CoverageAndBreadth_vs_readMismatch.pdf" ftype="pdf">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
268 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
269 <has_size value="383078" delta="10000" />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
270 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
271 </element>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
272 <element name="inStrain.IS_MajorAllele_frequency_plot.pdf" ftype="pdf">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
273 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
274 <has_size value="383590" delta="10000" />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
275 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
276 </element>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
277 <element name="inStrain.IS_ReadFiltering_plot.pdf" ftype="pdf">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
278 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
279 <has_size value="383078" delta="10000" />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
280 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
281 </element>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
282 <element name="inStrain.IS_ScaffoldInspection_plot.pdf" ftype="pdf">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
283 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
284 <has_size value="208" delta="10" />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
285 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
286 </element>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
287 <element name="inStrain.IS_genomeWide_microdiveristy_metrics.pdf" ftype="pdf">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
288 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
289 <has_size value="208" delta="10" />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
290 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
291 </element>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
292 <element name="inStrain.IS_readANI_distribution.pdf" ftype="pdf">
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
293 <assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
294 <has_size value="382771" delta="10000" />
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
295 </assert_contents>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
296 </element>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
297 </output_collection>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
298 </test>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
299 </tests>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
300 <help><![CDATA[
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
301 @HELP_HEADER@
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
302
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
303 Profile
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
304 =======
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
305
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
306 is the heart of inStrain tool.
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
307
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
308 The functionality of inStrain profile is broken into several steps:
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
309
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
310 First, all reads in the .bam file are filtered to only keep those that map with sufficient quality. All non-paired reads will be filtered out by default, and an additional set of filters are applied to each read pair (not the individual reads):
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
311
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
312 - Pairs must be mapped in the proper orientation with an expected insert size. The minimum insert distance can be set with the tool's corresponding parameter. The maximum insert distance is a multiple of the median insert distance. So if pairs have a median insert size of 500bp, by default all pairs with insert sizes over 1500bp will be excluded. For the max insert cutoff, the median_insert for all scaffolds is used.
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
313 - Pairs must have a minimum mapQ score. MapQ scores are confusing and how they’re calculated varies based on the mapping algorithm being used, but are meant to represent both the number of mismatches in the mapping and how unique that mapping is. With bowtie2, if the read maps equally well to two positions on the genome (multi-mapped read), its mapQ score will be set to 2. The read in the pair with the higher mapQ is used for the pair.
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
314 - Pairs must be above some minimum nucleotide identity (ANI) value. For example if reads in a pair are 100bp each, and each read has a single mismatch, the ANI of that pair would be 0.99
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
315
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
316 Next, using only read pairs that pass filters, a number of microdiversity metrics are calculated on a scaffold-by-scaffold basis. This includes:
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
317
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
318 - Calculate the coverage at each position along the scaffold
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
319 - Calculate the nucleotide diversity at each position along the scaffold in which the coverage is greater than the min_cov argument.
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
320 - Identify SNSs and SNVs. The criteria for being reported as a divergent site are 1) More than min_cov number of bases at that position, 2) More than min_freq percentage of reads that are a variant base, 3) The number of reads with the variant base is more than the null model for that coverage.
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
321 - Calculate linkage between divergent sites on the same read pair. For each pair harboring a divergent site, calculate the linkage of that site with other divergent sites within that same pair. This is only done for pairs of divergent sites that are both on at least MIN_SNP reads
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
322 - Calculate scaffold-level properties. These include things like the overall coverage, breadth of coverage, average nucleotide identity (ANI) between the reads and the reference genome, and the expected breadth of coverage based on that true coverage.
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
323
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
324 Finally, this information is stored as an IS_profile object. This includes the locations of divergent sites, the number of read pairs that passed filters (and other information) for each scaffold, the linkage between SNV pairs, ect.
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
325
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
326 Inputs
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
327 ======
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
328
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
329 A fasta file and a bam/sam file,
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
330
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
331 Output
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
332 ======
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
333
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
334 An IS_profile. (Zip file), Containing:
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
335
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
336 1. scaffold_info.tsv
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
337
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
338 This gives basic information about the scaffolds in your sample at the highest allowed level of read identity.
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
339
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
340 2. mapping_info.tsv
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
341
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
342 This provides an overview of the number of reads that map to each scaffold, and some basic metrics about their quality.
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
343
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
344 3. SNVs.tsv
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
345
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
346 This describes the SNVs and SNSs that are detected in this mapping. While we should refer to these mutations as divergent sites, sometimes SNV is used to refer to both SNVs and SNSs.
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
347
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
348 4. linkage.tsv
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
349
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
350 This describes the linkage between pairs of SNPs in the mapping that are found on the same read pair at least min_snp times.
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
351
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
352 5. gene_info.tsv
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
353
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
354 This describes some basic information about the genes being profiled.
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
355
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
356 6. genome_info.tsv
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
357
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
358 Describes many of the above metrics on a genome-by-genome level, rather than a scaffold-by-scaffold level. (To output it, set --skip_genome_wide to false)
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
359
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
360 7. Figures/Plots (When --skip_plot_generation is set to false):
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
361
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
362 - Coverage and breadth vs. read mismatches
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
363 - Genome-wide microdiversity metrics
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
364 - Read-level ANI distribution
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
365 - Major allele frequencies
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
366 - Linkage decay
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
367 - Read filtering plots
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
368 - Scaffold inspection plot (large)
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
369 - Linkage with SNP type (GENES REQUIRED)
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
370 - Gene histograms (GENES REQUIRED)
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
371
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
372 ]]></help>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
373 <citations>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
374 <citation type="doi">10.1101/2020.01.22.915579</citation>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
375 </citations>
1f3730540302 "planemo upload for repository https://github.com/MrOlm/inStrain commit e6eae71231e551c08aa96afc9f15b8ba87676101"
iuc
parents:
diff changeset
376 </tool>