comparison minimap2.xml @ 9:8c6cd2650d1f draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/minimap2 commit ffcf3989e7b05726341bbd0457a2e58448361554"
author iuc
date Thu, 04 Jun 2020 22:29:50 -0400
parents 53c0b7a1a0c3
children 77b2770508f6
comparison
equal deleted inserted replaced
8:53c0b7a1a0c3 9:8c6cd2650d1f
1 <?xml version="1.0"?> 1 <?xml version="1.0"?>
2 <tool id="minimap2" name="Map with minimap2" version="@TOOL_VERSION@+galaxy1" profile="17.01"> 2 <tool id="minimap2" name="Map with minimap2" version="@TOOL_VERSION@+galaxy2" profile="17.01">
3 <description>A fast pairwise aligner for genomic and spliced nucleotide sequences</description> 3 <description>A fast pairwise aligner for genomic and spliced nucleotide sequences</description>
4 <macros> 4 <macros>
5 <token name="@TOOL_VERSION@">2.17</token> 5 <token name="@TOOL_VERSION@">2.17</token>
6 <xml name="pe_anaylsis_fixed_selector">
7 <param name="analysis_type_selector" type="select"
8 label="Presets for PE reads alignment"
9 help="These are the minimap2 preset options for PE alignment of short reads. You can customize these and other settings in the indexing, mapping and alignment options sections below.">
10 <option value="sr">Short reads without splicing (-k21 -w11 --sr -F800 -A2 -B8 -O12,32 -E2,1 -r50 -p.5 -N20 -f1000,5000 -n2 -m20 -s40 -g200 -2K50m --heap-sort=yes --secondary=no) (sr)</option>
11 </param>
12 </xml>
6 </macros> 13 </macros>
7 <requirements> 14 <requirements>
8 <requirement type="package" version="@TOOL_VERSION@">minimap2</requirement> 15 <requirement type="package" version="@TOOL_VERSION@">minimap2</requirement>
9 <requirement type="package" version="1.9">samtools</requirement> 16 <requirement type="package" version="1.9">samtools</requirement>
10 </requirements> 17 </requirements>
18 <stdio>
19 <exit_code range="1:" level="fatal" />
20 <regex match="\[ERROR\]" source="stderr" level="fatal" />
21 </stdio>
11 <version_command>minimap2 --version</version_command> 22 <version_command>minimap2 --version</version_command>
12 <command> 23 <command>
13 <![CDATA[ 24 <![CDATA[
14 #if $reference_source.reference_source_selector == 'history': 25 #if $reference_source.reference_source_selector == 'history':
15 ln -f -s '$reference_source.ref_file' reference.fa && 26 ln -f -s '$reference_source.ref_file' reference.fa &&
16 #else: 27 #else:
17 ln -f -s '$reference_source.ref_file.fields.path' reference.fa && 28 ln -f -s '$reference_source.ref_file.fields.path' reference.fa &&
18 #end if 29 #end if
19 minimap2 30 minimap2
20 #if str($analysis_type_selector) == 'self-homology': 31 #if str($fastq_input.analysis_type_selector) == 'self-homology':
21 -DP -k19 -w19 -m200 32 -DP -k19 -w19 -m200
22 #else 33 #elif $fastq_input.analysis_type_selector:
23 -x $analysis_type_selector 34 -x ${fastq_input.analysis_type_selector}
24 #end if 35 #end if
36
25 ## indexing options 37 ## indexing options
26 $indexing_options.H 38 $indexing_options.H
27 #if $indexing_options.k: 39 #if str($indexing_options.k):
28 -k $indexing_options.k 40 -k $indexing_options.k
29 #end if 41 #end if
30 #if $indexing_options.w: 42 #if str($indexing_options.w):
31 -w $indexing_options.w 43 -w $indexing_options.w
32 #end if 44 #end if
33 #if $indexing_options.I: 45 #if str($indexing_options.I):
34 -I $indexing_options.I 46 -I $indexing_options.I
35 #end if 47 #end if
48
36 ## Mapping options 49 ## Mapping options
37 #if $mapping_options.f: 50 #if str($mapping_options.f):
38 -f $mapping_options.f 51 -f $mapping_options.f
39 #end if 52 #end if
40 #if $mapping_options.min_occ_floor: 53 #if str($mapping_options.min_occ_floor):
41 --min-occ-floor $min_occ_floor 54 --min-occ-floor $min_occ_floor
42 #end if 55 #end if
43 #if $mapping_options.g: 56 #if str($mapping_options.g):
44 -g $mapping_options.g 57 -g $mapping_options.g
45 #end if 58 #end if
46 #if $mapping_options.G: 59 #if str($mapping_options.r):
47 -G $mapping_options.G
48 #end if
49 #if $mapping_options.F:
50 -F $mapping_options.F
51 #end if
52 #if $mapping_options.r:
53 -r $mapping_options.r 60 -r $mapping_options.r
54 #end if 61 #end if
55 #if $mapping_options.n: 62 #if str($mapping_options.n):
56 -n $mapping_options.n 63 -n $mapping_options.n
57 #end if 64 #end if
58 #if $mapping_options.m: 65 #if str($mapping_options.m):
59 -m $mapping_options.m 66 -m $mapping_options.m
60 #end if 67 #end if
68 #if str($mapping_options.max_chain_skip):
69 --max-chain-skip $mapping_options.max_chain_skip
70 #end if
71 #if str($mapping_options.max_chain_iter):
72 --max-chain-iter $mapping_options.max_chain_iter
73 #end if
61 $mapping_options.X 74 $mapping_options.X
62 #if $mapping_options.p: 75 #if str($mapping_options.p):
63 -p $mapping_options.p 76 -p $mapping_options.p
64 #end if 77 #end if
65 #if $mapping_options.N: 78 #if str($mapping_options.N):
66 -N $mapping_options.N 79 -N $mapping_options.N
67 #end if 80 #end if
81
68 ## Alignment options 82 ## Alignment options
69 #if $alignment_options.A: 83 #if str($alignment_options.splicing.splice_mode) == '--splice':
84 --frag=no --splice
85 #if str($alignment_options.splicing.G):
86 -G $alignment_options.splicing.G
87 #end if
88 #if str($alignment_options.splicing.C):
89 -C $alignment_options.splicing.C
90 #end if
91 #if $alignment_options.splicing.u:
92 -u $alignment_options.splicing.u
93 #end if
94 $alignment_options.splicing.splice_flank
95 #if str($alignment_options.splicing.splice_site_annotations.use_annotations) == 'yes':
96 --junc-bed '$alignment_options.splicing.splice_site_annotations.junc_bed'
97 --junc-bonus $alignment_options.splicing.splice_site_annotations.junc_bonus
98 #end if
99 #elif str($mapping_options.F) and 'splice' not in str($fastq_input.analysis_type_selector):
100 --frag=yes -F $mapping_options.F
101 #end if
102 #if str($alignment_options.A):
70 -A $alignment_options.A 103 -A $alignment_options.A
71 #end if 104 #end if
72 #if $alignment_options.B: 105 #if str($alignment_options.B):
73 -B $alignment_options.B 106 -B $alignment_options.B
74 #end if 107 #end if
75 #if $alignment_options.O: 108 #if str($alignment_options.O):
76 #if $alignment_options.O2: 109 #if str($alignment_options.O2):
77 -O $alignment_options.O,$alignment_options.O2 110 -O $alignment_options.O,$alignment_options.O2
78 #end if 111 #else
79 -O $alignment_options.O 112 -O $alignment_options.O
80 #end if 113 #end if
81 #if $alignment_options.E: 114 #end if
82 #if $alignment_options.E2: 115 #if str($alignment_options.E):
116 #if str($alignment_options.E2):
83 -E $alignment_options.E,$alignment_options.E2 117 -E $alignment_options.E,$alignment_options.E2
84 #else 118 #else
85 -E $alignment_options 119 -E $alignment_options.E
86 #end if 120 #end if
87 #end if 121 #end if
88 #if $alignment_options.z: 122 #if str($alignment_options.z):
89 $alignment_options.z 123 #if str($alignment_options.z2):
90 #end if 124 -z $alignment_options.z,$alignment_options.z2
91 #if $alignment_options.s: 125 #else
126 -z $alignment_options.z
127 #end if
128 #end if
129 #if str($alignment_options.s):
92 -s $alignment_options.s 130 -s $alignment_options.s
93 #end if 131 #end if
94 #if $alignment_options.u: 132 $alignment_options.no_end_flt
95 -u $alignment_options.u
96 #end if
97 ## Output options 133 ## Output options
98 $io_options.Q 134 $io_options.Q
99 $io_options.L 135 $io_options.L
100 $io_options.c 136 $io_options.c
101 #if $io_options.cs: 137 #if $io_options.cs:
152 </when> 188 </when>
153 <when value="history"> 189 <when value="history">
154 <param name="ref_file" type="data" format="fasta,fastq" label="Use the following dataset as the reference sequence" help="You can upload a FASTA or FASTQ sequence to the history and use it as reference" /> 190 <param name="ref_file" type="data" format="fasta,fastq" label="Use the following dataset as the reference sequence" help="You can upload a FASTA or FASTQ sequence to the history and use it as reference" />
155 </when> 191 </when>
156 </conditional> 192 </conditional>
157 <section name="indexing_options" title="Indexing options">
158 <param argument="-H" name="H" type="boolean" optional="true" truevalue="-H" falsevalue="" label="Use homopolymer-compressed k-mer ?"/>
159 <param argument="-k" type="integer" min="4" max="28" optional="true" label="k-mer size" help=""/>
160 <param argument="-w" type="integer" min="1" optional="true" label="minimizer window size" help=""/>
161 <param argument="-I" type="integer" min="1" optional="true" label="split index for every N input gigabases" help=""/>
162 </section>
163 <!-- start unchanged copy from bwa-mem --> 193 <!-- start unchanged copy from bwa-mem -->
164 <conditional name="fastq_input"> 194 <conditional name="fastq_input">
165 <param name="fastq_input_selector" type="select" label="Single or Paired-end reads" help="Select between paired and single end data"> 195 <param name="fastq_input_selector" type="select" label="Single or Paired-end reads" help="Select between paired and single end data">
166 <option value="single">Single</option> 196 <option value="single">Single</option>
167 <option value="paired">Paired</option> 197 <option value="paired">Paired</option>
168 <option value="paired_collection">Paired Collection</option> 198 <option value="paired_collection">Paired Collection</option>
169 <option value="paired_iv">Paired Interleaved</option> 199 <option value="paired_iv">Paired Interleaved</option>
170 </param> 200 </param>
201 <!-- below, preset options are only offered for single-end input
202 because paired-end alignment in minimap2 is only enabled with -x sr
203 (see https://github.com/lh3/minimap2/issues/190) -->
204 <when value="single">
205 <param name="fastq_input1" type="data" format="fastqsanger,fastqsanger.gz,fasta" label="Select fastq dataset" help="Specify dataset with single reads"/>
206 <param name="analysis_type_selector" type="select" optional="True"
207 label="Select a profile of preset options"
208 help="Each profile comes with the preconfigured settings mentioned in parentheses. You can customize each profile further in the indexing, mapping and alignment options sections below. If you do not select a profile here, the tool will use the per-parameter defaults listed in the below sections unless you customize them." >
209 <option value="map-pb">PacBio/Oxford Nanopore read to reference mapping (-Hk19) (map-pb)</option>
210 <option value="map-ont">Oxford Nanopore read to reference mapping. Slightly more sensitive for Oxford Nanopore to reference mapping (-k15). For PacBio reads, HPC minimizers consistently leads to faster performance and more sensitive results in comparison to normal minimizers. For Oxford Nanopore data, normal minimizers are better, though not much. The effectiveness of HPC is determined by the sequencing error mode. (map-ont)</option>
211 <option value="ava-pb">PacBio all-vs-all overlap mapping (-Hk19 -Xw5 -m100 -g10000 --max-chain-skip 25) (ava-pb)</option>
212 <option value="ava-ont">Oxford Nanopore all-vs-all overlap mapping (-k15 -Xw5 -m100 -g10000 -r2000 --max-chain-skip 25). Similarly, the major difference from ava-pb is that this preset is not using HPC minimizers. (ava-ont)</option>
213 <option value="asm5">Long assembly to reference mapping (-k19 -w19 -A1 -B19 -O39,81 -E3,1 -s200 -z200 --min-occ-floor=100). Typically, the alignment will not extend to regions with 5% or higher sequence divergence. Only use this preset if the average divergence is far below 5%. (asm5)</option>
214 <option value="asm10">Long assembly to reference mapping (-k19 -w19 -A1 -B9 -O16,41 -E2,1 -s200 -z200 --min-occ-floor=100). Up to 10% sequence divergence. (asm10)</option>
215 <option value="asm20">Long assembly to reference mapping (-k19 -w10 -A1 -B6 -O6,26 -E2,1 -s200 -z200 --min-occ-floor=100). Up to 20% sequence divergence. (asm20)</option>
216 <option value="splice">Long-read spliced alignment (-k15 -w5 --splice -g2000 -G200k -A1 -B2 -O2,32 -E1,0 -C9 -z200 -ub --splice-flank=yes). In the splice mode, 1) long deletions are taken as introns and represented as the `N' CIGAR operator 2) long insertions are disabled 3) deletion and insertion gap costs are different during chaining 4) the computation of the `ms` tag ignores introns to demote hits to pseudogenes. (splice)</option>
217 <option value="splice:hq">Long-read splice alignment for PacBio CCS reads (same as `splice` but with -C5 -O6,24 -B4) (splice:hq)</option>
218 <option value="sr">Short single-end reads without splicing (-k21 -w11 --sr -A2 -B8 -O12,32 -E2,1 -r50 -p.5 -N20 -f1000,5000 -n2 -m20 -s40 -g200 -2K50m --heap-sort=yes --secondary=no) (sr)</option>
219 <option value="self-homology">Construct a self-homology map - use same genome as query and reference (-DP -k19 -w19 -m200) (self-homology)</option>
220 </param>
221 </when>
171 <when value="paired"> 222 <when value="paired">
172 <param name="fastq_input1" type="data" format="fastqsanger,fastqsanger.gz,fasta" label="Select first set of reads" help="Specify dataset with forward reads"/> 223 <param name="fastq_input1" type="data" format="fastqsanger,fastqsanger.gz,fasta" label="Select first set of reads" help="Specify dataset with forward reads"/>
173 <param name="fastq_input2" type="data" format="fastqsanger,fastqsanger.gz,fasta" label="Select second set of reads" help="Specify dataset with reverse reads"/> 224 <param name="fastq_input2" type="data" format="fastqsanger,fastqsanger.gz,fasta" label="Select second set of reads" help="Specify dataset with reverse reads"/>
174 </when> 225 <expand macro="pe_anaylsis_fixed_selector" />
175 <when value="single">
176 <param name="fastq_input1" type="data" format="fastqsanger,fastqsanger.gz,fasta" label="Select fastq dataset" help="Specify dataset with single reads"/>
177 </when> 226 </when>
178 <when value="paired_collection"> 227 <when value="paired_collection">
179 <param name="fastq_input1" format="fastqsanger,fastqsanger.gz,fasta" type="data_collection" collection_type="paired" label="Select a paired collection" help="See help section for an explanation of dataset collections"/> 228 <param name="fastq_input1" format="fastqsanger,fastqsanger.gz,fasta" type="data_collection" collection_type="paired" label="Select a paired collection" help="See help section for an explanation of dataset collections"/>
229 <expand macro="pe_anaylsis_fixed_selector" />
180 </when> 230 </when>
181 <when value="paired_iv"> 231 <when value="paired_iv">
182 <param name="fastq_input1" type="data" format="fastqsanger,fastqsanger.gz,fasta" label="Select fastq dataset" help="Specify dataset with interleaved reads"/> 232 <param name="fastq_input1" type="data" format="fastqsanger,fastqsanger.gz,fasta" label="Select fastq dataset" help="Specify dataset with interleaved reads"/>
233 <expand macro="pe_anaylsis_fixed_selector" />
183 </when> 234 </when>
184 </conditional> 235 </conditional>
185 <!-- end unchanged copy from bwa-mem --> 236 <section name="indexing_options" title="Indexing options">
186 <param name="analysis_type_selector" type="select" label="Select analysis mode (sets default)"> 237 <param argument="-H" name="H" type="boolean" optional="true" truevalue="-H" falsevalue="" label="Use homopolymer-compressed k-mer ?"/>
187 <option value="map-pb">PacBio/Oxford Nanopore read to reference mapping (-Hk19) (map-pb)</option> 238 <param argument="-k" type="integer" min="4" max="28" optional="true" label="k-mer size" help=""/>
188 <option value="map-ont">Oxford Nanopore read to reference mapping. Slightly more sensitive for Oxford Nanopore to reference mapping (-k15). For PacBio reads, HPC minimizers consistently leads to faster performance and more sensitive results in comparison to normal minimizers. For Oxford Nanopore data, normal minimizers are better, though not much. The effectiveness of HPC is determined by the sequencing error mode. (map-ont)</option> 239 <param argument="-w" type="integer" min="1" optional="true" label="minimizer window size" help=""/>
189 <option value="ava-pb">PacBio all-vs-all overlap mapping (-Hk19 -Xw5 -m100 -g10000 --max-chain-skip 25) (ava-pb)</option> 240 <param argument="-I" type="integer" min="1" optional="true" label="split index for every N input gigabases" help=""/>
190 <option value="ava-ont">Oxford Nanopore all-vs-all overlap mapping (-k15 -Xw5 -m100 -g10000 -r2000 --max-chain-skip 25). Similarly, the major difference from ava-pb is that this preset is not using HPC minimizers. (ava-ont)</option> 241 </section>
191 <option value="asm5">Long assembly to reference mapping (-k19 -w19 -A1 -B19 -O39,81 -E3,1 -s200 -z200 --min-occ-floor=100). Typically, the alignment will not extend to regions with 5% or higher sequence divergence. Only use this preset if the average divergence is far below 5%. (asm5)</option> 242 <section name="mapping_options" title="Mapping options" help="Sets -f, -g, -F, -r, -n, -m, -X, -p, -N and --min-occ-floor options." expanded="False">
192 <option value="asm10">Long assembly to reference mapping (-k19 -w19 -A1 -B9 -O16,41 -E2,1 -s200 -z200 --min-occ-floor=100). Up to 10% sequence divergence. (asm10)</option> 243 <param argument="-N" type="integer" min="0" optional="true" label="retain at most INT secondary alignments" help="default=5"/>
193 <option value="asm20">Long assembly to reference mapping (-k19 -w10 -A1 -B6 -O6,26 -E2,1 -s200 -z200 --min-occ-floor=100). Up to 20% sequence divergence. (asm20)</option> 244 <param argument="-F" type="integer" min="0" value="" optional="true"
194 <option value="splice">Long-read spliced alignment (-k15 -w5 --splice -g2000 -G200k -A1 -B2 -O2,32 -E1,0 -C9 -z200 -ub --splice-flank=yes). In the splice mode, 1) long deletions are taken as introns and represented as the `N' CIGAR operator 2) long insertions are disabled 3) deletion and insertion gap costs are different during chaining 4) the computation of the `ms' tag ignores introns to demote hits to pseudogenes. (splice)</option> 245 label="Max fragment length for PE alignment"
195 <option value="sr">Short single-end reads without splicing (-k21 -w11 --sr --frag=yes -A2 -B8 -O12,32 -E2,1 -r50 -p.5 -N20 -f1000,5000 -n2 -m20 -s40 -g200 -2K50m --heap-sort=yes --secondary=no) (sr)</option> 246 help="The maximum apparent fragment length up to which paired-end reads are aligned together; at higher fragment lengths the mates will be aligned independent of each other; effective only for paired-end data and when spliced alignment mode is turned off; default=800" />
196 <option value="self-homology">Construct a self-homology map - use same genome as query and reference (-DP -k19 -w19 -m200) (self-homology)</option>
197 </param>
198 <section name="mapping_options" title="Set advanced mapping options" help="Sets -f, -g, -G, -F, -r, -n, -m, -X, -p, -N and --min-occ-floor options." expanded="False">
199 <param argument="-f" type="float" value="" optional="true" label="filter out top FLOAT fraction of repetitive minimizers" help="default=0.0002"/> 247 <param argument="-f" type="float" value="" optional="true" label="filter out top FLOAT fraction of repetitive minimizers" help="default=0.0002"/>
200 <param argument="--min-occ-floor" name="min_occ_floor" type="integer" label="force minimap2 to always use k-mers occuring this many times or fewer" help="Maximum occurence is the number of repetitive minimizers determined by '-f' or this value, whichever is higher." optional="true" /> 248 <param argument="--min-occ-floor" name="min_occ_floor" type="integer" label="force minimap2 to always use k-mers occuring this many times or fewer" help="Maximum occurence is the number of repetitive minimizers determined by '-f' or this value, whichever is higher." optional="true" />
201 <param argument="-g" type="integer" value="" optional="true" label="stop chain enlongation if there are no minimizers in INT-bp" help="default=5000"/> 249 <param argument="-g" type="integer" value="" optional="true" label="stop chain enlongation if there are no minimizers in INT-bp" help="default=5000"/>
202 <param argument="-G" type="integer" value="" optional="true" label="max intron length in thousand (effective with -xsplice; changing -r)" help="default=200"/>
203 <param argument="-F" type="integer" value="" optional="true" label="max fragment length (effective with -xsr or in the fragment mode)" help="default=800" />
204 <param argument="-r" type="integer" value="" optional="true" label="bandwidth used in chaining and DP-based alignment" help="default=500" /> 250 <param argument="-r" type="integer" value="" optional="true" label="bandwidth used in chaining and DP-based alignment" help="default=500" />
205 <param argument="-n" type="integer" value="" optional="true" label="minimal number of minimizers on a chain" help="default=3"/> 251 <param argument="-n" type="integer" value="" optional="true" label="minimal number of minimizers on a chain" help="default=3"/>
206 <param argument="-m" type="integer" value="" optional="true" label="minimal chaining score (matching bases minus log gap penalty)" help="default=40"/> 252 <param argument="-m" type="integer" value="" optional="true" label="minimal chaining score (matching bases minus log gap penalty)" help="default=40"/>
253 <param argument="--max-chain-skip" type="integer" value="" optional="true"
254 label="Maximum seed skips during chaining"
255 help="A heuristics that stops chaining early. Minimap2 uses dynamic programming for chaining. The time complexity is quadratic in the number of seeds. This option makes minimap2 exit the inner loop if it repeatedly sees seeds already on chains. Set to a large number to switch off this heurstics effectively. default=25" />
256 <param argument="--max-chain-iter" type="integer" value="" optional="true"
257 label="Maximum number of partial chains checked during chaining"
258 help="A heuristics to avoid quadratic time complexity in the worst case. default=5000" />
207 <param argument="-X" type="boolean" truevalue="-X" falsevalue="" optional="true" label="skip self and dual mappings (for the all-vs-all mode)"/> 259 <param argument="-X" type="boolean" truevalue="-X" falsevalue="" optional="true" label="skip self and dual mappings (for the all-vs-all mode)"/>
208 <param argument="-p" type="float" value="" max="1" optional="true" label="min secondary-to-primary score ratio" help="default=0.8"/> 260 <param argument="-p" type="float" value="" max="1" optional="true" label="min secondary-to-primary score ratio" help="default=0.8"/>
209 <param argument="-N" type="integer" min="0" optional="true" label="retain at most INT secondary alignments" help="default=5"/>
210 </section> 261 </section>
211 <section name="alignment_options" title="Set advanced alignment options" help="Sets -A, -B, -O, -E, -z, -s and -u options." expanded="False"> 262 <section name="alignment_options" title="Alignment options" help="Sets -A, -B, -O, -E, -z, -s, and spliced alignments options." expanded="False">
212 <param argument="-A" type="integer" optional="true" label="Score for a sequence match" help="default=2"/> 263 <conditional name="splicing">
213 <param argument="-B" type="integer" optional="true" label="Penalty for a mismatch" help="-B; default=4" /> 264 <param name="splice_mode" type="select"
214 <param argument="-O" type="integer" min="0" optional="true" label="Gap open penalties for deletions" help="-O; default=4"/> 265 label="Customize spliced alignment mode?"
215 <param name="-O2" type="integer" min="0" optional="true" label="Gap open penalties for insertions" help="-O; default=24"/> 266 help="Warning: Minimap2 cannot currently perform spliced alignments of read pairs. If you enable spliced alignment for paired-end data it will be treated as single-end!" >
216 <param argument="-E" type="integer" min="0" optional="true" label="Gap extension penalties; a gap of size k cost &#39;-O + -E*k&#39;. If two numbers are specified, the first is the penalty of extending a deletion and the second for extending an insertion" help="-E; default=2"/> 267 <option value="preset">No, use profile setting or leave turned off</option>
217 <param name="E2" type="integer" min="0" optional="true" label="Gap extension penalty for extending an insertion; if left empty uses the value specified for Gap extension penalties above" help="-E; default=1"/> 268 <option value="">Disable spliced alignments (overwrite profile setting if necessary)</option>
218 <param argument="-z" type="integer" optional="true" label="Z-drop score" help="default=400"/> 269 <option value="--splice">Yes, enable spliced alignments (--splice)</option>
219 <param argument="-s" type="integer" optional="true" label="minimal peak DP alignment score" help="default=80"/> 270 </param>
220 <param argument="-u" type="select" optional="true" label="how to find GT-AG"> 271 <when value="preset" />
221 <option value="n">don't match GT-AG</option> 272 <when value="" />
222 <option value="f">transcript strand</option> 273 <when value="--splice">
223 <option value="b">both strands</option> 274 <param argument="-G" type="integer" value="" optional="true"
224 </param> 275 label="Maximum allowed gap on the reference"
276 help="Higher values cause slower spliced alignment. When in use, this option causes -r (in mapping options) to be set to the same value. default=200k" />
277 <param argument="-C" type="integer" min="0" optional="true"
278 label="Cost of non-canonical (non-GT-AG) splicing"
279 help="default=0" />
280 <param argument="-u" type="select" optional="true"
281 label="how to find GT-AG"
282 help="default=n (don't match GT-AG)">
283 <option value="n">don't match GT-AG (-un)</option>
284 <option value="f">transcript strand (-uf)</option>
285 <option value="b">both strands (-ub)</option>
286 </param>
287 <param argument="--splice-flank" type="boolean" truevalue="--splice-flank=yes" falsevalue="--splice-flank=no" checked="true"
288 label="Assume conserved flanking region of splice sites?"
289 help="Assume the next base to a GT donor site tends to be A/G (91% in human and 92% in mouse) and the preceding base to a AG acceptor tends to be C/T. This trend is evolutionarily conserved, all the way to S. cerevisiae (PMID:18688272). Specifying this option generally leads to higher junction accuracy by several percents, so it is applied by default with --splice. However, the SIRV control does not honor this trend (only ~60%) so this option reduces accuracy. If you are benchmarking minimap2 on SIRV data, please disable this option." />
290 <conditional name="splice_site_annotations">
291 <param name="use_annotations" type="select"
292 label="Use previously annotated splice sites to guide the alignment?"
293 help="">
294 <option value="no">No, perform unbiased alignment</option>
295 <option value="yes">Yes, favor annotated splice sites</option>
296 </param>
297 <when value="no" />
298 <when value="yes">
299 <param argument="--junc-bed" type="data" format="bed"
300 label="Dataset with annotated genes or introns"
301 help="Gene annotations should be provided in BED12 (aka 12-column BED), intron positions in 5-column BED format." />
302 <param argument="--junc-bonus" type="integer" min="1" value="1"
303 label="Annotated splice site bonus"
304 help="Score bonus for a splice donor or acceptor found in annotation." />
305 </when>
306 </conditional>
307 </when>
308 </conditional>
309 <param argument="-A" type="integer" min="0" optional="true"
310 label="Score for a sequence match" help="default=2"/>
311 <param argument="-B" type="integer" min="0" optional="true"
312 label="Penalty for a mismatch" help="-B; default=4" />
313 <param argument="-O" type="integer" min="1" optional="true"
314 label="Gap open penalties for deletions" help="-O; default=4"/>
315 <param name="O2" type="integer" min="0" optional="true"
316 label="Gap open penalties for insertions" help="-O; default=24"/>
317 <param argument="-E" type="integer" min="1" optional="true"
318 label="Gap extension penalties; a gap of size k cost &#39;-O + -E*k&#39;. If two numbers are specified, the first is the penalty of extending a deletion and the second for extending an insertion"
319 help="-E; default=2"/>
320 <param name="E2" type="integer" min="0" optional="true"
321 label="Gap extension penalty for extending an insertion; if left empty uses the value specified for Gap extension penalties above"
322 help="-E; default=1"/>
323 <param argument="-z" type="integer" min="0" optional="true"
324 label="Z-drop threshold for truncating an alignment"
325 help="Increase to improve the contiguity of alignments at the cost of poorer alignments in the middle. default=400" />
326 <param name="z2" type="integer" min="0" optional="true"
327 label="Z-drop threshold for reverse-complementing the query"
328 help="Decrease to find small inversions at the cost of performance and false positives. default=200" />
329 <param argument="-s" type="integer" min="0" optional="true"
330 label="minimal peak DP alignment score" help="default=80"/>
331 <param name="no_end_flt" type="boolean" falsevalue="--no-end-flt" truevalue="" checked="true"
332 label="Filter seeds towards the ends of chains before performing base-level alignment?" />
225 </section> 333 </section>
226 <section name="io_options" title="Set advanced output options" help="Sets -Q, -L, -R, -c, --cs and -K options." expanded="False"> 334 <section name="io_options" title="Set advanced output options" help="Sets -Q, -L, -R, -c, --cs and -K options." expanded="False">
227 <param name="output_format" type="select" label="Select an output format"> 335 <param name="output_format" type="select" label="Select an output format">
228 <option value="BAM">BAM</option> 336 <option value="BAM">BAM</option>
229 <option value="CRAM">CRAM</option> 337 <option value="CRAM">CRAM</option>
294 <param name="reference_source_selector" value="history" /> 402 <param name="reference_source_selector" value="history" />
295 <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/> 403 <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
296 <param name="fastq_input_selector" value="paired"/> 404 <param name="fastq_input_selector" value="paired"/>
297 <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fastq1.fq"/> 405 <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fastq1.fq"/>
298 <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/> 406 <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/>
299 <param name="analysis_type_selector" value="sr"/>
300 <output name="alignment_output" ftype="bam" file="minimap2-test1.bam" lines_diff="2" /> 407 <output name="alignment_output" ftype="bam" file="minimap2-test1.bam" lines_diff="2" />
301 </test> 408 </test>
302 <test> 409 <test>
303 <!-- test paired input with one pair compressed --> 410 <!-- test paired input with one pair compressed -->
304 <param name="reference_source_selector" value="history" /> 411 <param name="reference_source_selector" value="history" />
305 <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/> 412 <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
306 <param name="fastq_input_selector" value="paired"/> 413 <param name="fastq_input_selector" value="paired"/>
307 <param name="fastq_input1" ftype="fastqsanger.gz" value="bwa-mem-fastq1.fq.gz"/> 414 <param name="fastq_input1" ftype="fastqsanger.gz" value="bwa-mem-fastq1.fq.gz"/>
308 <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/> 415 <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/>
309 <param name="analysis_type_selector" value="sr"/>
310 <output name="alignment_output" ftype="bam" file="minimap2-test1.bam" lines_diff="2" /> 416 <output name="alignment_output" ftype="bam" file="minimap2-test1.bam" lines_diff="2" />
311 </test> 417 </test>
312 <test> 418 <test>
313 <!-- test collection input --> 419 <!-- test collection input -->
314 <param name="reference_source_selector" value="history" /> 420 <param name="reference_source_selector" value="history" />
318 <collection type="paired"> 424 <collection type="paired">
319 <element name="forward" value="bwa-mem-fastq1.fq" /> 425 <element name="forward" value="bwa-mem-fastq1.fq" />
320 <element name="reverse" value="bwa-mem-fastq2.fq" /> 426 <element name="reverse" value="bwa-mem-fastq2.fq" />
321 </collection> 427 </collection>
322 </param> 428 </param>
323 <param name="analysis_type_selector" value="sr"/>
324 <output name="alignment_output" ftype="bam" file="minimap2-test2.bam" lines_diff="2" /> 429 <output name="alignment_output" ftype="bam" file="minimap2-test2.bam" lines_diff="2" />
325 </test> 430 </test>
326 <test> 431 <test>
327 <!-- test data table reference --> 432 <!-- test data table reference -->
328 <param name="reference_source_selector" value="cached" /> 433 <param name="reference_source_selector" value="cached" />
330 <param name="fastq_input_selector" value="single"/> 435 <param name="fastq_input_selector" value="single"/>
331 <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fasta1.fa"/> 436 <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fasta1.fa"/>
332 <param name="analysis_type_selector" value="sr"/> 437 <param name="analysis_type_selector" value="sr"/>
333 <output name="alignment_output" ftype="bam" file="minimap2-test1-fasta.bam" lines_diff="2" /> 438 <output name="alignment_output" ftype="bam" file="minimap2-test1-fasta.bam" lines_diff="2" />
334 </test> 439 </test>
440 <test>
441 <!-- test alignment options -->
442 <param name="reference_source_selector" value="cached" />
443 <param name="ref_file" value="bwa-mem-mt-genome"/>
444 <param name="fastq_input_selector" value="single"/>
445 <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fasta1.fa"/>
446 <param name="analysis_type_selector" value="sr"/>
447 <section name="alignment_options">
448 <!-- the folowing settings correspond to the defaults for "sr"
449 mode. The purpose is to check that all alignment params get
450 parsed correctly. -->
451 <param name="A" value="2" />
452 <param name="B" value="8" />
453 <param name="O" value="12" />
454 <param name="O2" value="32" />
455 <param name="E" value="2" />
456 <param name="E2" value="1" />
457 <param name="z" value="400" />
458 <param name="s" value="40" />
459 </section>
460 <output name="alignment_output" ftype="bam" file="minimap2-test1-fasta.bam" lines_diff="2" />
461 </test>
335 <test> 462 <test>
336 <!-- test paf output --> 463 <!-- test paf output -->
337 <param name="reference_source_selector" value="history" /> 464 <param name="reference_source_selector" value="history" />
338 <param name="ref_file" ftype="fastqsanger" value="mini_reads.fq" /> 465 <param name="ref_file" ftype="fastqsanger" value="mini_reads.fq" />
339 <param name="fastq_input_selector" value="single"/> 466 <param name="fastq_input_selector" value="single"/>