Mercurial > repos > iuc > lexicmap

comparison lexicmap.xml @ 0:2e6641136004 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/lexicmap commit d966ed462a49d1949345717ae4fdb685c6a1450a
author iuc
date Tue, 16 Sep 2025 13:51:46 +0000
parents
children 73accf8f68a9
comparison
equal deleted inserted replaced
-1:000000000000 0:2e6641136004
1 <tool id="lexicmap_search" name="LexicMap Search" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE_VERSION@">
2 <description>nucleotide sequence tool for querying genomes</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="bio_tools"/>
7 <expand macro="requirements"/>
8
9 <command detect_errors="exit_code"><![CDATA[
10
11 lexicmap search
12
13 --threads "\${GALAXY_SLOTS:-1}"
14
15 ${load_whole_seeds}
16 ${all}
17
18 #if $db_opts.db_opts_selector == "histdb"
19 --index '${db_opts.histdb.extra_files_path}'
20 #else:
21 --index '${db_opts.lexicmap_index.fields.path}'
22 #end if
23
24 '$query' --out-file '$out_file'
25
26 --top-n-genomes '$top_n_genomes'
27
28 --align-band '$align_band'
29 --align-ext-len '$align_ext_len'
30 --align-max-gap '$align_max_gap'
31 --align-min-match-len '$align_min_match_len'
32 --align-min-match-pident '$align_min_match_pident'
33 --max-evalue '$max_evalue'
34 --max-query-conc '$max_query_conc'
35 --seed-max-dist '$seed_max_dist'
36 --seed-max-gap '$seed_max_gap'
37 --seed-min-prefix '$seed_min_prefix'
38 --seed-min-single-prefix '$seed_min_single_prefix'
39
40 #if $min_qcov_per_genome
41 --min-qcov-per-genome '$min_qcov_per_genome'
42 #end if
43
44 #if $min_qcov_per_hsp
45 --min-qcov-per-hsp '$min_qcov_per_hsp'
46 #end if
47
48 ]]></command>
49 <inputs>
50 <param name="query" type="data" format="fasta.gz" label="LexicMap query file" multiple="true" help=""/>
51 <conditional name="db_opts">
52 <param name="db_opts_selector" type="select" label="LexiMap index source">
53 <option value="histdb" selected="true">From your history</option>
54 <option value="db">Locally installed LexicMap indexes</option>
55 </param>
56 <when value="histdb">
57 <param name="histdb" type="data" format="lexicmap_index" optional="false" label="LexicMap index" />
58 </when>
59 <when value="db">
60 <param name="lexicmap_index" type="select" optional="false" label="LexicMap index file">
61 <options from_data_table="lexicmap_index"/>
62 </param>
63 </when>
64 </conditional>
65 <param argument="--top-n-genomes" type="integer" value="0" label="Keep top N genome matches for a query (0 for all)" />
66 <section name="advanced_settings" title="Advanced settings" expanded="false">
67 <param argument="--align-band" value="100" type="integer" label="Align band" help="Band size in backtracking the score matrix (pseudo alignment" />
68 <param argument="-align-ext-len" min="0" value="1000" type="integer" label="Align extend length" help="Extend length of upstream and downstream of seed regions, for extracting query and target sequences for alignment. It should be &lt;= contig interval length in database." />
69 <param argument="-align-max-gap" value="20" type="integer" label="Align max gap" help="Maximum gap in a HSP segment." />
70 <param argument="--align-min-match-len" value="50" type="integer" label="Align min match length" help="Minimum aligned length in a HSP segment." />
71 <param argument="--align-min-match-pident" value="70" type="float" label="Align min match pident" help="Minimum base identity (percentage) in a HSP segment." />
72 <param argument="--all" type="boolean" truevalue="--all" falsevalue="" checked="false" label="All all columns" help="Output more columns, e.g., matched sequences. Use this if you want to output blast-style format with 'lexicmap utils 2blast'." />
73 <param argument="--load-whole-seeds" type="boolean" truevalue="--load-whole-seeds" falsevalue="" checked="false" label="Load whole seeds" help="Load the whole seed data into memory for faster search" />
74 <param argument="--max-evalue" value="10" type="float" label="Max evalue" help="Maximum evalue of a HSP segment." />
75 <param argument="--max-query-conc" value="12" type="integer" label="Max query conc" help="Maximum number of concurrent queries. Bigger values do not improve the batch searching speed and consume much memory." />
76 <param argument="--min-qcov-per-genome" type="float" optional="true" help="Minimum query coverage (percentage) per genome." />
77 <param argument="--min-qcov-per-hsp" type="float" optional="true" help="Minimum query coverage (percentage) per HSP." />
78 <param argument="--seed-max-dist" value="1000" type="integer" label="Seed max dist" help="Minimum distance between seeds in seed chaining. It should be &lt;= contig interval length in database." />
79 <param argument="--seed-max-gap" value="1000" type="integer" label="Seed max gap" help="Minimum gap in seed chaining." />
80 <param argument="--seed-min-prefix" value="15" type="integer" label="Seed min prefix" help="Minimum (prefix/suffix) length of matched seeds (anchors)." />
81 <param argument="--seed-min-single-prefix" value="17" type="integer" label="Seed min single prefix" help="Minimum (prefix/suffix) length of matched seeds (anchors) if there's only one pair of seeds matched." />
82 </section>
83 </inputs>
84 <outputs>
85 <data name="out_file" format="tabular">
86 <actions>
87 <conditional name="advanced_settings.all">
88 <when value="true">
89 <action name="column_names" type="metadata" default="Qquery,qlen,hits,sgenome,sseqid,qcovGnm,cls,hsp,qcovHSP,alenHSP,pident,gaps,qstart,qend,sstart,send,sstr,slen,evalue,bitscore,cigar,qseq,sseq,align" />
90 </when>
91 <when value="false">
92 <action name="column_names" type="metadata" default="Qquery,qlen,hits,sgenome,sseqid,qcovGnm,cls,hsp,qcovHSP,alenHSP,pident,gaps,qstart,qend,sstart,send,sstr,slen,evalue,bitscore" />
93 </when>
94 </conditional>
95 </actions>
96 </data>
97 </outputs>
98 <tests>
99 <test expect_num_outputs="1">
100 <conditional name="db_opts">
101 <param name="db_opts_selector" value="db"/>
102 <param name="lexicmap_index" value="LexicMapIndex1" />
103 </conditional>
104 <param name="query" value="lexicmap_query.fasta.gz" />
105 <section name="advanced_settings">
106 <param name="load_whole_seeds" value="true" />
107 </section>
108 <output name="out_file" value="lexicmap_query_result.tsv" />
109 </test>
110 <test expect_num_outputs="1">
111 <conditional name="db_opts">
112 <param name="db_opts_selector" value="histdb"/>
113 <param name="histdb" ftype="lexicmap_index" class="Directory" value="db.lmi" />
114 </conditional>
115 <param name="top_n_genomes" value="0" />
116 <param name="query" value="lexicmap_query.fasta.gz" />
117 <section name="advanced_settings">
118 <param name="load_whole_seeds" value="true" />
119 </section>
120 <output name="out_file" value="lexicmap_query_result.tsv" />
121 </test>
122 </tests>
123 <help><![CDATA[
124
125 Search sequences against an LexicMap index Database. For more information about settings
126 please visit: https://bioinf.shenwei.me/LexicMap/usage/search
127
128 Output format:
129 Tab-delimited format with 20+ columns, with 1-based positions.
130
131 1. query, Query sequence ID.
132 2. qlen, Query sequence length.
133 3. hits, Number of subject genomes.
134 4. sgenome, Subject genome ID.
135 5. sseqid, Subject sequence ID.
136 6. qcovGnm, Query coverage (percentage) per genome: $(aligned bases in the genome)/$qlen.
137 7. cls, Nth HSP cluster in the genome. (just for improving readability)
138 It's useful to show if multiple adjacent HSPs are collinear.
139 8. hsp, Nth HSP in the genome. (just for improving readability)
140 9. qcovHSP Query coverage (percentage) per HSP: $(aligned bases in a HSP)/$qlen.
141 10. alenHSP, Aligned length in the current HSP.
142 11. pident, Percentage of identical matches in the current HSP.
143 12. gaps, Gaps in the current HSP.
144 13. qstart, Start of alignment in query sequence.
145 14. qend, End of alignment in query sequence.
146 15. sstart, Start of alignment in subject sequence.
147 16. send, End of alignment in subject sequence.
148 17. sstr, Subject strand.
149 18. slen, Subject sequence length.
150 19. evalue, Expect value.
151 20. bitscore, Bit score.
152 21. cigar, CIGAR string of the alignment. (optional with --all)
153 22. qseq, Aligned part of query sequence. (optional with --all)
154 23. sseq, Aligned part of subject sequence. (optional with --all)
155 24. align, Alignment text ("|" and " ") between qseq and sseq. (optional with --all)
156
157 @info@
158 ]]></help>
159 <expand macro="citations" />
160 </tool>