comparison parse.xml @ 2:d8e28fa369e1 draft

planemo upload for repository https://github.com/open2c/pairtools commit abd18c860877b2100e02019b4b597d6d2569994e
author iuc
date Thu, 18 Sep 2025 05:56:54 +0000
parents 3b5ee2bf3679
children
comparison
equal deleted inserted replaced
1:43b10ccf53b6 2:d8e28fa369e1
1 <tool id="pairtools_parse" name="Pairtools parse" version="@TOOL_VERSION@+galaxy@SUFFIX_VERSION@" profile="23.2" license="MIT"> 1 <tool id="pairtools_parse" name="Pairtools parse" version="@TOOL_VERSION@+galaxy@SUFFIX_VERSION@" profile="@PROFILE_VERSION@" license="MIT">
2 <description>Find ligation pairs in alignments and create pairs.</description> 2 <description>Find ligation pairs in alignments and create pairs.</description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="requirements"/> 6 <expand macro="requirements"/>
7 <command detect_errors="exit_code"><![CDATA[ 7 <command detect_errors="exit_code"><![CDATA[
8 #set $output = "output" + str($compress_output)
9 ln -s '$output_parsed_pairs' '$output' &&
8 pairtools parse 10 pairtools parse
9 '$sam_path' 11 '$sam_path'
10 -c '$chroms_path' 12 -c '$chroms_path'
11 #if str($assembly_name).strip(): 13 #if str($assembly_name).strip():
12 --assembly '$assembly_name' 14 --assembly '$assembly_name'
13 #end if 15 #end if
14 -o '$output_parsed_pairs'
15 --min-mapq '$min_mapq' 16 --min-mapq '$min_mapq'
16 --max-molecule-size '$max_molecule_size' 17 --max-molecule-size '$max_molecule_size'
17 $drop_readid 18 $drop_readid
18 $drop_seq 19 $drop_seq
19 $output_stats
20 $drop_sam 20 $drop_sam
21 #if $output_stats: 21 #if $output_stats:
22 '$parsed_pairs_stats' 22 --output-stats '$parsed_pairs_stats'
23 #end if
24 #if $select_add_columns.add_columns_selection == "yes":
25 --add-columns '$select_add_columns.add_columns'
23 #end if 26 #end if
24 --walks-policy '$walks_policy' 27 --walks-policy '$walks_policy'
25 --max-inter-align-gap '$max_inter_algn_gap' 28 --max-inter-align-gap '$max_inter_algn_gap'
26 --nproc-in \${GALAXY_SLOTS:-4} 29 --nproc-in \${GALAXY_SLOTS:-4}
27 --nproc-out \${GALAXY_SLOTS:-4} 30 --nproc-out \${GALAXY_SLOTS:-4}
31 #if $sort_output:
32 |
33 pairtools sort -o '$output'
34 --nproc-in \${GALAXY_SLOTS:-4}
35 --nproc-out \${GALAXY_SLOTS:-4}
36 #else
37 -o '$output'
38 #end if
39
28 ]]></command> 40 ]]></command>
29 <inputs> 41 <inputs>
30 <param name="sam_path" type="data" format="sam,qname_input_sorted.bam,qname_sorted.bam" label="Input SAM/BAM file" help="Input SAM or BAM (unsorted/name-sorted) file with paired-end sequence alignments of Hi-C molecules."/> 42 <param name="sam_path" type="data" format="sam,qname_input_sorted.bam,qname_sorted.bam" label="Input SAM/BAM file" help="Input SAM or BAM (unsorted/name-sorted) file with paired-end sequence alignments of Hi-C molecules."/>
31 <param name="chroms_path" argument="-c" type="data" format="tabular" label="Input a chromosome order file" help="Chromosome order used to flip interchromosomal mates. Any scaffolds not listed will be ordered lexicographically."/> 43 <param name="chroms_path" argument="-c" type="data" format="tabular" label="Input a chromosome order file" help="Chromosome order used to flip interchromosomal mates. Any scaffolds not listed will be ordered lexicographically."/>
32 <param name="assembly_name" type="text" value="" label="Input a name of genome assembly" help="Name of genome assembly (e.g. hg19, mm10) to store in the pairs header"></param> 44 <param name="assembly_name" type="text" value="" label="Input a name of genome assembly" help="Name of genome assembly (e.g. hg19, mm10) to store in the pairs header"></param>
34 <param argument="--max-molecule-size" type="integer" min="0" value="750" label="Input the maximal size of a Hi-C molecule" help="The maximal size of a Hi-C molecule; used to rescue single ligations(from molecules with three alignments) and to rescue complex ligations."></param> 46 <param argument="--max-molecule-size" type="integer" min="0" value="750" label="Input the maximal size of a Hi-C molecule" help="The maximal size of a Hi-C molecule; used to rescue single ligations(from molecules with three alignments) and to rescue complex ligations."></param>
35 <param argument="--drop-readid" type="boolean" truevalue="--drop-readid" falsevalue="" checked="False" label="Do not add read ids to the output"></param> 47 <param argument="--drop-readid" type="boolean" truevalue="--drop-readid" falsevalue="" checked="False" label="Do not add read ids to the output"></param>
36 <param argument="--drop-seq" type="boolean" truevalue="--drop-seq" falsevalue="" checked="False" label="remove sequences and PHREDs from the sam fields"></param> 48 <param argument="--drop-seq" type="boolean" truevalue="--drop-seq" falsevalue="" checked="False" label="remove sequences and PHREDs from the sam fields"></param>
37 <param argument="--output-stats" type="boolean" truevalue="--output-stats" falsevalue="" checked="False" label="Generate various statistics of pairs file"></param> 49 <param argument="--output-stats" type="boolean" truevalue="--output-stats" falsevalue="" checked="False" label="Generate various statistics of pairs file"></param>
38 <param argument="--drop-sam" type="boolean" truevalue="--drop-sam" falsevalue="" checked="False" label="Do not add sams to the output"></param> 50 <param argument="--drop-sam" type="boolean" truevalue="--drop-sam" falsevalue="" checked="False" label="Do not add sams to the output"></param>
51 <conditional name="select_add_columns">
52 <param name="add_columns_selection" type="select" label="Add additional columns to the output" help="Select if additional columns needs to be added to the output pairs file.">
53 <option value="no" selected="true">No</option>
54 <option value="yes">Yes</option>
55 </param>
56 <when value="yes">
57 <param argument="--add-columns" type="select" multiple="true" label="Select extra columns describing alignments" help="Multiple options can be selected.">
58 <option value="mapq">MAPQ</option>
59 <option value="pos5">POS5</option>
60 <option value="pos3">POS3</option>
61 <option value="cigar">CIGAR</option>
62 <option value="read_len">Read length</option>
63 <option value="matched_bp">Matched bp</option>
64 <option value="algn_ref_span">algn_ref_span</option>
65 <option value="dist_to_5">dist_to_5</option>
66 <option value="dist_to_3">dist_to_3</option>
67 <option value="seq">seq</option>
68 <option value="mismatches">mismatches</option>
69 <option value="read_side">read_side</option>
70 <option value="algn_idx">algn_idx</option>
71 <option value="same_side_algn_count">same_side_algn_count</option>
72 </param>
73 </when>
74 <when value="no"/>
75 </conditional>
39 <param argument="--walks-policy" type="select" label="Walks Policy" help="The policy for reporting unrescuable walks."> 76 <param argument="--walks-policy" type="select" label="Walks Policy" help="The policy for reporting unrescuable walks.">
40 <expand macro="walks_policy_options"/> 77 <expand macro="walks_policy_options"/>
41 </param> 78 </param>
79 <param name="compress_output" type="boolean" truevalue=".gz" falsevalue="" checked="false" label="Compress output file" />
80 <param name="sort_output" type="boolean" checked="true" label="generate sorted output file" />
42 <param argument="max_inter_algn_gap" type="integer" min="0" value="30" label="Max alignment gap" help="read segments that are not covered by any alignment and longer than the specified value are treated as null alignments."/> 81 <param argument="max_inter_algn_gap" type="integer" min="0" value="30" label="Max alignment gap" help="read segments that are not covered by any alignment and longer than the specified value are treated as null alignments."/>
43 </inputs> 82 </inputs>
44 <outputs> 83 <outputs>
45 <data name="output_parsed_pairs" format="4dn_pairs" label="${tool.name} on ${on_string}: .pairs"/> 84 <data name="output_parsed_pairs" format="4dn_pairsam" label="${tool.name} on ${on_string}: .pairs">
46 <data name="parsed_pairs_stats" format="txt,tabular" label="${tool.name} on ${on_string}: parsed.stats"> 85 <change_format>
86 <when input="compress_output" value=".gz" format="4dn_pairsam.gz"/>
87 </change_format>
88 </data>
89 <data name="parsed_pairs_stats" format="tabular" label="${tool.name} on ${on_string}: parsed.stats">
47 <filter>output_stats</filter> 90 <filter>output_stats</filter>
48 </data> 91 </data>
49 </outputs> 92 </outputs>
50 <tests> 93 <tests>
51 <!--Test 01 with SAM file as input and default parameters--> 94 <!--Test 01 with SAM file as input and default parameters-->
53 <param name="sam_path" value="test.sam"/> 96 <param name="sam_path" value="test.sam"/>
54 <param name="chroms_path" value="test.genome"/> 97 <param name="chroms_path" value="test.genome"/>
55 <param name="min_mapq" value="1"/> 98 <param name="min_mapq" value="1"/>
56 <param name="walks_policy" value="mask"/> 99 <param name="walks_policy" value="mask"/>
57 <param name="max_inter_algn_gap" value="20"/> 100 <param name="max_inter_algn_gap" value="20"/>
58 <output name="output_parsed_pairs" ftype="4dn_pairs" file="output_parsed_pairs_sam.pairs" lines_diff="10"/> 101 <param name="sort_output" value="false"/>
59 </test> 102 <output name="output_parsed_pairs" ftype="4dn_pairsam" file="output_parsed_pairs_sam.pairs" lines_diff="10"/>
60 <!--Test 02 with BAM file as input and default parameters--> 103 </test>
61 <test expect_num_outputs="1"> 104 <!--Test 02 with SAM file as input and sorted output default parameters-->
62 <param name="sam_path" value="test.bam"/> 105 <test expect_num_outputs="1">
63 <param name="chroms_path" value="test.reduced.chrom.sizes"/> 106 <param name="sam_path" value="test.sam"/>
64 <param name="min_mapq" value="1"/> 107 <param name="chroms_path" value="test.genome"/>
65 <param name="walks_policy" value="mask"/> 108 <param name="min_mapq" value="1"/>
66 <param name="max_inter_algn_gap" value="20"/> 109 <param name="walks_policy" value="mask"/>
67 <output name="output_parsed_pairs" ftype="4dn_pairs" file="output_parsed_pairs_bam.pairs" lines_diff="10"/> 110 <param name="max_inter_algn_gap" value="20"/>
68 </test> 111 <param name="sort_output" value="true"/>
69 <!--Test 03 with BAM file as input and minimal mapq of 40--> 112 <output name="output_parsed_pairs" ftype="4dn_pairsam" file="output_parsed_pairs_sam.sorted.pairs" lines_diff="10"/>
70 <test expect_num_outputs="1"> 113 </test>
71 <param name="sam_path" value="test.bam"/> 114 <!--Test 03 with BAM file as input and default parameters-->
72 <param name="chroms_path" value="test.reduced.chrom.sizes"/> 115 <test expect_num_outputs="1">
73 <param name="min_mapq" value="40"/> 116 <param name="sam_path" value="test.bam"/>
74 <param name="walks_policy" value="mask"/> 117 <param name="chroms_path" value="test.reduced.chrom.sizes"/>
75 <param name="max_inter_algn_gap" value="20"/> 118 <param name="min_mapq" value="1"/>
76 <output name="output_parsed_pairs" ftype="4dn_pairs" file="output_parsed_pairs_bam_min_mapq_40.pairs" lines_diff="10"/> 119 <param name="walks_policy" value="mask"/>
77 </test> 120 <param name="max_inter_algn_gap" value="20"/>
78 <!--Test 04 with BAM file as input and walk policy of 5unique--> 121 <param name="sort_output" value="false"/>
79 <test expect_num_outputs="1"> 122 <output name="output_parsed_pairs" ftype="4dn_pairsam" file="output_parsed_pairs_bam.pairs" lines_diff="10"/>
80 <param name="sam_path" value="test.bam"/> 123 </test>
81 <param name="chroms_path" value="test.reduced.chrom.sizes"/> 124 <!--Test 04 with BAM file as input and minimal mapq of 40-->
82 <param name="min_mapq" value="40"/> 125 <test expect_num_outputs="1">
83 <param name="walks_policy" value="5unique"/> 126 <param name="sam_path" value="test.bam"/>
84 <param name="max_inter_algn_gap" value="20"/> 127 <param name="chroms_path" value="test.reduced.chrom.sizes"/>
85 <output name="output_parsed_pairs" ftype="4dn_pairs" file="output_parsed_pairs_bam_5unique.pairs" lines_diff="10"/> 128 <param name="min_mapq" value="40"/>
86 </test> 129 <param name="walks_policy" value="mask"/>
87 <!--Test 05 with BAM file as input and read id dropped--> 130 <param name="max_inter_algn_gap" value="20"/>
131 <param name="sort_output" value="false"/>
132 <output name="output_parsed_pairs" ftype="4dn_pairsam" file="output_parsed_pairs_bam_min_mapq_40.pairs" lines_diff="10"/>
133 </test>
134 <!--Test 05 with BAM file as input and walk policy of 5unique-->
135 <test expect_num_outputs="1">
136 <param name="sam_path" value="test.bam"/>
137 <param name="chroms_path" value="test.reduced.chrom.sizes"/>
138 <param name="min_mapq" value="40"/>
139 <param name="walks_policy" value="5unique"/>
140 <param name="max_inter_algn_gap" value="20"/>
141 <param name="sort_output" value="false"/>
142 <output name="output_parsed_pairs" ftype="4dn_pairsam" file="output_parsed_pairs_bam_5unique.pairs" lines_diff="10"/>
143 </test>
144 <!--Test 06 with BAM file as input and read id dropped-->
88 <test expect_num_outputs="1"> 145 <test expect_num_outputs="1">
89 <param name="sam_path" value="test.bam"/> 146 <param name="sam_path" value="test.bam"/>
90 <param name="chroms_path" value="test.reduced.chrom.sizes"/> 147 <param name="chroms_path" value="test.reduced.chrom.sizes"/>
91 <param name="min_mapq" value="40"/> 148 <param name="min_mapq" value="40"/>
92 <param name="walks_policy" value="5unique"/> 149 <param name="walks_policy" value="5unique"/>
93 <param name="max_inter_algn_gap" value="20"/> 150 <param name="max_inter_algn_gap" value="20"/>
94 <param name="drop_readid" value="true"></param> 151 <param name="drop_readid" value="true"></param>
95 <output name="output_parsed_pairs" ftype="4dn_pairs" file="output_parsed_pairs_bam_readid_dropped.pairs" lines_diff="10"/> 152 <param name="sort_output" value="false"/>
96 </test> 153 <output name="output_parsed_pairs" ftype="4dn_pairsam" file="output_parsed_pairs_bam_readid_dropped.pairs" lines_diff="10"/>
97 <!--Test 06 with SAM file as input and drop_seq enabled--> 154 </test>
155 <!--Test 07 with SAM file as input and drop_seq enabled-->
98 <test expect_num_outputs="1"> 156 <test expect_num_outputs="1">
99 <param name="sam_path" value="test.sam"/> 157 <param name="sam_path" value="test.sam"/>
100 <param name="chroms_path" value="test.genome"/> 158 <param name="chroms_path" value="test.genome"/>
101 <param name="min_mapq" value="40"/> 159 <param name="min_mapq" value="40"/>
102 <param name="walks_policy" value="5unique"/> 160 <param name="walks_policy" value="5unique"/>
103 <param name="max_inter_algn_gap" value="20"/> 161 <param name="max_inter_algn_gap" value="20"/>
104 <param name="drop_seq" value="true"></param> 162 <param name="drop_seq" value="true"></param>
105 <output name="output_parsed_pairs" ftype="4dn_pairs" file="output_parsed_pairs_bam_readid_dropped_seq.pairs" lines_diff="10"/> 163 <param name="sort_output" value="false"/>
106 </test> 164 <output name="output_parsed_pairs" ftype="4dn_pairsam" file="output_parsed_pairs_bam_readid_dropped_seq.pairs" lines_diff="10"/>
107 <!--Test 07 with SAM file as input and output_stats enabled--> 165 </test>
166 <!--Test 08 with SAM file as input and output_stats enabled-->
108 <test expect_num_outputs="2"> 167 <test expect_num_outputs="2">
109 <param name="sam_path" value="test.sam"/> 168 <param name="sam_path" value="test.sam"/>
110 <param name="chroms_path" value="test.genome"/> 169 <param name="chroms_path" value="test.genome"/>
111 <param name="min_mapq" value="40"/> 170 <param name="min_mapq" value="40"/>
112 <param name="walks_policy" value="5unique"/> 171 <param name="walks_policy" value="5unique"/>
113 <param name="max_inter_algn_gap" value="20"/> 172 <param name="max_inter_algn_gap" value="20"/>
114 <param name="output_stats" value="true"></param> 173 <param name="output_stats" value="true"></param>
115 <output name="parsed_pairs_stats" file="output_parsed_pairs.stats" lines_diff="10"/> 174 <output name="parsed_pairs_stats" file="output_parsed_pairs.stats" lines_diff="10"/>
116 </test> 175 </test>
117 <!--Test 08 with SAM file as input and default parameters and assembly name --> 176 <!--Test 09 with SAM file as input and default parameters and assembly name -->
118 <test expect_num_outputs="1"> 177 <test expect_num_outputs="1">
119 <param name="sam_path" value="test.sam"/> 178 <param name="sam_path" value="test.sam"/>
120 <param name="chroms_path" value="test.genome"/> 179 <param name="chroms_path" value="test.genome"/>
121 <param name="assembly_name" value="test_assembly"/> 180 <param name="assembly_name" value="test_assembly"/>
122 <param name="min_mapq" value="1"/> 181 <param name="min_mapq" value="1"/>
123 <param name="walks_policy" value="mask"/> 182 <param name="walks_policy" value="mask"/>
124 <param name="max_inter_algn_gap" value="20"/> 183 <param name="max_inter_algn_gap" value="20"/>
125 <output name="output_parsed_pairs" ftype="4dn_pairs" file="output_parsed_pairs_sam_assemblyname.pairs" lines_diff="10"/> 184 <param name="sort_output" value="false"/>
126 </test> 185 <output name="output_parsed_pairs" ftype="4dn_pairsam" file="output_parsed_pairs_sam_assemblyname.pairs" lines_diff="10"/>
127 186 </test>
187 <!--Test 10 with SAM file as input and default parameters and assembly name and compressed output-->
188 <test expect_num_outputs="1">
189 <param name="sam_path" value="test.sam"/>
190 <param name="chroms_path" value="test.genome"/>
191 <param name="assembly_name" value="test_assembly"/>
192 <param name="min_mapq" value="1"/>
193 <param name="walks_policy" value="mask"/>
194 <param name="max_inter_algn_gap" value="20"/>
195 <param name="compress_output" value="true"/>
196 <param name="sort_output" value="false"/>
197 <output name="output_parsed_pairs" ftype="4dn_pairsam.gz" file="output_parsed_pairs_sam_assemblyname.pairs.gz" decompress="true" lines_diff="10"/>
198 </test>
199 <!--Test 11 with SAM file as input and default parameters and assembly name and sorted, compressed output-->
200 <test expect_num_outputs="1">
201 <param name="sam_path" value="test.sam"/>
202 <param name="chroms_path" value="test.genome"/>
203 <param name="assembly_name" value="test_assembly"/>
204 <param name="min_mapq" value="1"/>
205 <param name="walks_policy" value="mask"/>
206 <param name="max_inter_algn_gap" value="20"/>
207 <param name="compress_output" value="true"/>
208 <output name="output_parsed_pairs" ftype="4dn_pairsam.gz" file="output_parsed_pairs_sam_assemblyname.sorted.pairs.gz" decompress="true" lines_diff="10"/>
209 </test>
210 <!--Test 12 with SAM file as input and add columns-->
211 <test expect_num_outputs="1">
212 <param name="sam_path" value="test.sam"/>
213 <param name="chroms_path" value="test.genome"/>
214 <param name="min_mapq" value="1"/>
215 <param name="walks_policy" value="mask"/>
216 <param name="max_inter_algn_gap" value="20"/>
217 <conditional name="select_add_columns">
218 <param name="add_columns_selection" value="yes"/>
219 <param name="add_columns" value="mapq,seq"/>
220 </conditional>
221 <param name="sort_output" value="false"/>
222 <output name="output_parsed_pairs" ftype="4dn_pairsam" file="output_parsed_pairs_sam_mapq.pairs" lines_diff="10"/>
223 </test>
128 </tests> 224 </tests>
129 <help><![CDATA[ 225 <help><![CDATA[
130 **Pairtools parse** 226 **Pairtools parse**
131 227
132 Detects ligation events in the aligned sequences of DNA molecules formed in Hi-C experiments and reports them in the .pairs/.pairsam format. 228 Detects ligation events in the aligned sequences of DNA molecules formed in Hi-C experiments and reports them in the .pairs/.pairsam format.
133 229
134 sam_path : an input .sam/.bam (unsorted/name-sorted) file with paired-end sequence alignments of Hi-C molecules. 230 sam_path : an input .sam/.bam (unsorted/name-sorted) file with paired-end sequence alignments of Hi-C molecules.
135 231
232 By default, the generated .pair/.pairsam output is sorted by piping it through pairtools sort. You can disable this behavior by unchecking the “Generate sorted output file” checkbox.
233
136 ]]></help> 234 ]]></help>
137 <expand macro="citations"/> 235 <expand macro="citations"/>
138 <expand macro="creator"/> 236 <expand macro="creator"/>
139 </tool> 237 </tool>