annotate tidecluster.xml @ 9:440796be7576 draft

planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 398baa926d7864efeb2c349c52827fd6988e60e6-dirty
author petr-novak
date Tue, 28 Nov 2023 14:31:07 +0000
parents af85dfc8676d
children 971dbc97e607
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
1 <tool id="tidecluster" name="TideCluster" version="@TOOL_VERSION@">
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
2 <macros>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
3 <import>macros.xml</import>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
4 </macros>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
5 <description>Identify tandem repeats in genome assemblies</description>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
6 <expand macro="requirements" />
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
7 <command detect_errors="exit_code"><![CDATA[
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
8 mkdir -p output && cd output &&
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
9 TideCluster.py run_all
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
10 -f '$fasta'
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
11 -pr 'tidecluster'
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
12 #if $library:
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
13 -l '$library'
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
14 #end if
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
15 -m $min_length
5
af85dfc8676d planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 06d2db65d620a49e796b90a37c55f89e1e275e5d
petr-novak
parents: 2
diff changeset
16 -T ' -p $min_period -P $max_period -e $max_diverg -c $min_copy'
af85dfc8676d planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 06d2db65d620a49e796b90a37c55f89e1e275e5d
petr-novak
parents: 2
diff changeset
17 $no_dust
0
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
18 -c \${GALAXY_SLOTS:-1}
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
19 -M $min_total_length
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
20 &&
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
21 cp tidecluster_tidehunter.gff3 '$gff3_tidehunter'
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
22 &&
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
23 cp tidecluster_clustering.gff3 '$gff3_clustering'
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
24 &&
5
af85dfc8676d planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 06d2db65d620a49e796b90a37c55f89e1e275e5d
petr-novak
parents: 2
diff changeset
25 if [ -f tidecluster_tarean_report.html ]; then cp tidecluster_tarean_report.html '$tarean_report'; fi
0
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
26 &&
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
27 mkdir -p ${tarean_report.extra_files_path}
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
28 &&
5
af85dfc8676d planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 06d2db65d620a49e796b90a37c55f89e1e275e5d
petr-novak
parents: 2
diff changeset
29 if [ -d tidecluster_tarean ]; then cp -r tidecluster_tarean ${tarean_report.extra_files_path}/; fi
0
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
30 &&
5
af85dfc8676d planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 06d2db65d620a49e796b90a37c55f89e1e275e5d
petr-novak
parents: 2
diff changeset
31 if [ -f tidecluster_consensus_dimer_library.fasta ]; then cp tidecluster_consensus_dimer_library.fasta ${trc_library}; fi
2
299f14a6050a planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 65066fa2cd844c8ae882c4ba9bc4e124eada8ffd
petr-novak
parents: 0
diff changeset
32 &&
0
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
33 zip -r output.zip *
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
34 #if $library:
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
35 &&
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
36 cp tidecluster_annotation.gff3 '$gff3_annotation'
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
37 &&
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
38 cp tidecluster_annotation.tsv '$csv_annotation'
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
39 #end if
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
40 &&
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
41 mv output.zip '$output_archive'
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
42
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
43 ]]></command>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
44 <inputs>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
45 <param type="data" name="fasta" format="fasta" label="Reference fasta"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
46 help="Path to reference sequence in fasta format"/>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
47 <param type="data" name="library" format="fasta" label="Library"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
48 help="Path to library of tandem repeats" optional="true"/>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
49 <param type="integer" name="min_length" value="5000"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
50 label="Minimum length of tandem repeat"/>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
51 <param type="integer" name="min_period" value="40"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
52 label="Minimum period size of tandem repeat" min="2"/>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
53 <param type="integer" name="max_period" value="3000"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
54 label="Maximum period size of tandem repeat" max="20000"/>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
55 <param type="float" name="max_diverg" value="0.25"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
56 label="Maximum allowed divergence rate between two consecutive repeats"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
57 min="0" max="1"/>
5
af85dfc8676d planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 06d2db65d620a49e796b90a37c55f89e1e275e5d
petr-novak
parents: 2
diff changeset
58 <param type="integer" name="min_copy" value="5"
af85dfc8676d planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 06d2db65d620a49e796b90a37c55f89e1e275e5d
petr-novak
parents: 2
diff changeset
59 label="minimum copy number of tandem repeat" min="2"/>
0
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
60 <param type="boolean" name="no_dust" truevalue="--no_dust" falsevalue=""
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
61 checked="false" label="Do not use dust filter in blastn when clustering"/>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
62 <param type="integer" name="min_total_length" value="50000"
5
af85dfc8676d planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 06d2db65d620a49e796b90a37c55f89e1e275e5d
petr-novak
parents: 2
diff changeset
63 label="Minimum combined length of tandem repeat arrays within a single cluster"
af85dfc8676d planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 06d2db65d620a49e796b90a37c55f89e1e275e5d
petr-novak
parents: 2
diff changeset
64 help="Minimum combined length of tandem repeat arrays within a single cluster, required for inclusion in TAREAN analysis"
af85dfc8676d planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 06d2db65d620a49e796b90a37c55f89e1e275e5d
petr-novak
parents: 2
diff changeset
65 />
0
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
66 </inputs>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
67 <outputs>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
68 <data name="output_archive" format="zip"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
69 label="${tool.name} on ${on_string}: Archive with complete results"/>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
70 <data name="gff3_tidehunter" format="gff3"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
71 label="${tool.name} on ${on_string}: GFF3 TideHunter Output" hidden="true"/>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
72 <data name="gff3_clustering" format="gff3"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
73 label="${tool.name} on ${on_string}: GFF3 TideCluster Output"/>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
74 <data name="gff3_annotation" format="gff3"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
75 label="${tool.name} on ${on_string}: GFF3 TideCluster Annotated Output">
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
76 <filter>library is not None</filter>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
77 </data>
2
299f14a6050a planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 65066fa2cd844c8ae882c4ba9bc4e124eada8ffd
petr-novak
parents: 0
diff changeset
78
0
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
79 <data name="csv_annotation" format="tsv"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
80 label="${tool.name} on ${on_string}: TSV TideCluster Annotated Output">
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
81 <filter>library is not None</filter>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
82 </data>
2
299f14a6050a planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 65066fa2cd844c8ae882c4ba9bc4e124eada8ffd
petr-novak
parents: 0
diff changeset
83
299f14a6050a planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 65066fa2cd844c8ae882c4ba9bc4e124eada8ffd
petr-novak
parents: 0
diff changeset
84 <data name="trc_library" format="fasta"
299f14a6050a planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 65066fa2cd844c8ae882c4ba9bc4e124eada8ffd
petr-novak
parents: 0
diff changeset
85 label="${tool.name} on ${on_string}: Library of tandem repeats"/>
0
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
86 <data name="tarean_report" format="html"
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
87 label="${tool.name} on ${on_string}: TAREAN Report"/>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
88
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
89
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
90
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
91 </outputs>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
92 <help><![CDATA[
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
93 **TideCluster** is a software tool designed to identify tandem repeats in genome assemblies by utilizing Tidehunter to detect tandem repeats clustering these repeats based on similarity using mmseqs2 and NCBI BLAST. The software runs in four steps as outlined below:
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
94
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
95 - **Tidehunter step**: In this initial step, Tidehunter is utilized to identify tandem repeats. As TideHunter's performance diminishes with larger sequences, the input fasta file is divided into smaller overlapping segments, with each segment analyzed individually. Results from individual segments are parsed and merged into a single GFF3 file. Tandem repeats detected in this step are often fragmented into multiple overlapping pieces.
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
96
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
97 - **Clustering step**: Prior to clustering, all arrays that do not meet the minimum length requirement are removed from the analysis and saved in a separate GFF3 file. Arrays exceeding the minimum length requirement are clustered based on similarity. Clustering occurs in two stages. First, mmseqs2 is employed in the initial round of clustering. The second round involves an all-to-all comparison using NCBI-BLAST, followed by graph-based clustering. The GFF3 file from the Tidehunter step is updated to include cluster assignment information. Simple sequence repeats are excluded from the clustering step and are analyzed separately.
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
98
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
99 - **Annotation step**: Consensus sequences from TideHunter for each cluster are examined by RepeatMasker against a library of tandem repeats. The resulting annotation for each tandem repeat is used to update the information in the GFF3 file. This step is optional.
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
100
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
101 - **TAREAN step**: In this final step, the Tandem Repeat Analyzer (TAREAN) estimates consensus sequences using a k-mer-based approach on the original sequences from the reference. Consensus sequences of simple sequence repeats are evaluated separately, as TAREAN performs poorly on tandem repeats with short monomers. The results of the analysis are saved in an HTML summary.
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
102
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
103 **Credits**
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
104
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
105 TideCluster utilizes Tidehunter [https://github.com/Xinglab/TideHunter] for tandem repeat detection and TAREAN for reconstruction of consensus sequences of tandem repeats. If you use TideCluster please cite:
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
106
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
107 - https://github.com/kavonrtep/TideCluster
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
108 - TAREAN: a computational tool for identification and characterization of satellite DNA from unassembled short reads (https://doi.org/10.1093/nar/gkx257)
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
109 - TideHunter: efficient and sensitive tandem repeat detection from noisy long-reads using seed-and-chain (https://doi.org/10.1093/bioinformatics/btz376)
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
110 ]]></help>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
111 <citations>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
112
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
113 </citations>
c701eddc9fec planemo upload for repository https://github.com/kavonrtep/galaxy_packages commit 181f00441ba635991889a85b90fa9741a8c8e978-dirty
petr-novak
parents:
diff changeset
114 </tool>