annotate PanExplorer_workflow/PanExplorer.xml @ 1:032f6b3806a3 draft

Uploaded
author dereeper
date Thu, 30 May 2024 11:16:08 +0000
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
1 <tool id="PanExplorer2" name="PanExplorer2" version="2.0">
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
2 <description> Bacterial pan-genome analysis </description>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
3 <requirements>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
4 <!--
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
5 <requirement type="package" version="2.2.26">blast-legacy</requirement>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
6 <requirement type="package" version="7.480">mafft</requirement>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
7 <requirement type="package" version="14.137">mcl</requirement>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
8 <requirement type="package" version="3.697">phylip</requirement>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
9 <requirement type="package" version="1.7.2">perl-bioperl</requirement>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
10 -->
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
11 <requirement type="package" version="2.4.2">singularity</requirement>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
12
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
13 </requirements>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
14
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
15 <command><![CDATA[
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
16 module load system/singularity/3.6.0;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
17 export PANEX_PATH=${__tool_directory__};
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
18
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
19 perl ${__tool_directory__}/Perl/generateConfig.pl '$private_genomes' '$input' config.yaml '$private_genomes_fasta';
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
20
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
21 cat config.yaml >$logfile;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
22
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
23
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
24
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
25 #if $software=="pgap"
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
26 sed "s/identity\=80/identity\=$min_identity/g" \$PANEX_PATH/Snakemake_files/Snakefile_wget_PGAP_heatmap_upset_COG >snakefile;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
27 #else if $software=="roary"
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
28 sed "s/identity\=80/identity\=$min_identity/g" \$PANEX_PATH/Snakemake_files/Snakefile_wget_roary_heatmap_upset_COG >snakefile;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
29 #else if $software=="orthofinder"
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
30 sed "s/identity\=80/identity\=$min_identity/g" \$PANEX_PATH/Snakemake_files/Snakefile_orthofinder_heatmap_upset >snakefile;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
31 #else if $software=="cactus"
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
32 cp -rf \$PANEX_PATH/Snakemake_files/Snakefile_wget_cactus_heatmap_upset_COG2 snakefile;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
33 #else if $software=="pggb"
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
34 sed "s/identity\=30/identity\=$min_identity/g" \$PANEX_PATH/Snakemake_files/Snakefile_wget_pggb_heatmap_upset_COG >snakefile;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
35 #else
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
36 sed "s/identity\=80/identity\=$min_identity/g" \$PANEX_PATH/Snakemake_files/Snakefile_wget_panacota_heatmap_upset_COG >snakefile;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
37 #end if
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
38
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
39 singularity exec \$PANEX_PATH/panexplorer.sif snakemake --cores 1 -s snakefile >>$logfile 2>&1;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
40
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
41
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
42 cp -rf outputs/upsetr.svg $upset;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
43 cp -rf outputs/pav_matrix.tsv $output;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
44 cp -rf outputs/heatmap.svg.gz $heatmap;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
45 cp -rf outputs/heatmap.svg.heatmap_plotly.html $heatmap_html;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
46 cp -rf outputs/rarefaction_curves.txt $rarefaction_curves;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
47 cp -rf outputs/rarefaction_curves.svg $rarefaction_curves_svg;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
48 cp -rf outputs/heaps.tsv $heaps;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
49 cp -rf outputs/heatmap.svg.complete.pdf.distance_matrix.txt $distance_matrix;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
50 cp -rf outputs/heatmap.svg.complete.pdf.distance_matrix.hclust.newick $njtree;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
51
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
52 #if $software!="orthofinder"
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
53 cp -rf outputs/GCskew.txt $gcfile;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
54 cp -rf outputs/cog_output.txt $cogfile;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
55 cp -rf outputs/cog_stats.txt $outcog_stat;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
56 cp -rf outputs/cog_stats2.txt $outcog_stat2;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
57 cp -rf outputs/cog_of_clusters.txt $outcog_clusters;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
58 cp -rf outputs/genomes/genes.txt $genes;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
59 cp -rf outputs/fastani.out.matrix.complete $fastani;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
60 cp -rf outputs/fastani.out.svg $ani_svg;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
61 #end if
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
62
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
63 #if $software=="pggb"
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
64 cp -rf outputs/all_genomes.vcf $vcf;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
65 #else
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
66 touch $vcf;
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
67 #end if
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
68 ]]></command>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
69
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
70
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
71 <inputs>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
72 <param name="input" type="text" multiple="true" label="List of genbank identifiers" help="Coma separated list (ex: CP000235.1,CP001079.1,CP001759.1,CP015994.2)"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
73 <param name="private_genomes" type="data" format="zip" label="Zip of genbank or GFF files" optional="true"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
74 <param name="private_genomes_fasta" type="data" format="zip" label="Zip of Fasta files" optional="true"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
75 <param name="min_identity" type="text" value="80" label="Minimum percentage identity for BlastP" />
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
76 <param type="select" name="software" label="Choose the pan-genome software">
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
77 <option value="pgap">PGAP</option>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
78 <option value="roary">Roary</option>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
79 <option value="panacota">PanACoTA</option>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
80 <option value="orthofinder">OrthoFinder</option>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
81 <option value="cactus">Minigraph-Cactus</option>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
82 <option value="pggb">PanGenome Graph Builder (PGGB)</option>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
83 </param>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
84 </inputs>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
85
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
86 <outputs>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
87 <data format="txt" name="output" label="Pangenome presence absence matrix"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
88 <data format="newick" name="njtree" label="PanBased NJ tree"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
89 <data format="txt" name="genes" label="Genes"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
90 <data format="txt" name="cogfile" label="COG assignation"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
91 <data format="txt" name="gcfile" label="GC_percent"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
92 <data format="svg" name="upset" label="Upset Diagram"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
93 <data format="svg" name="heatmap" label="Presence Absence Heatmap"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
94 <data format="html" name="heatmap_html" label="Presence Absence Heatmap interactive"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
95 <data format="tabular" name="outcog_stat" label="COG category counts"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
96 <data format="tabular" name="outcog_stat2" label="COG category 2 counts"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
97 <data format="tabular" name="outcog_clusters" label="COG of clusters"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
98 <data format="tabular" name="fastani" label="ANI" />
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
99 <data format="svg" name="ani_svg" label="ANI heatmap" />
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
100 <data format="txt" name="rarefaction_curves" label="Rarefaction curves data"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
101 <data format="svg" name="rarefaction_curves_svg" label="Rarefaction curves"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
102 <data format="txt" name="heaps" label="Heaps law alpha"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
103 <data format="txt" name="distance_matrix" label="Accessory based distance matrix"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
104 <data format="vcf" name="vcf" label="VCF file"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
105 <data format="txt" name="logfile" label="Logfile"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
106 <data format="txt" name="roary_log" label="Roary Logfile"/>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
107 </outputs>
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
108
032f6b3806a3 Uploaded
dereeper
parents:
diff changeset
109 </tool>