Mercurial > repos > iuc > smgu_frameshift_deletions_checks
comparison frameshift_deletions_checks.xml @ 1:029d90b0c4f6 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/smallgenomeutilities commit e702dcdbc7c3235ef3c4ee8998c7247d1af49465
author | iuc |
---|---|
date | Fri, 14 Jul 2023 22:07:22 +0000 |
parents | f079716f598c |
children | e8971ca74398 |
comparison
equal
deleted
inserted
replaced
0:f079716f598c | 1:029d90b0c4f6 |
---|---|
9 </requirements> | 9 </requirements> |
10 <!-- once we have version-from-git-tag in 0.4.0: <version_command>frameshift_deletion_checks --version</version_command> --> | 10 <!-- once we have version-from-git-tag in 0.4.0: <version_command>frameshift_deletion_checks --version</version_command> --> |
11 <command detect_errors="exit_code"> | 11 <command detect_errors="exit_code"> |
12 <![CDATA[ | 12 <![CDATA[ |
13 #if $input.is_of_type("cram"): | 13 #if $input.is_of_type("cram"): |
14 echo 'is CRAM' >&2 && | 14 ln -s '$input' input.cram && |
15 ln -vs '$input' 'input.${input.ext}' >&2 && | 15 ln -s '$input.metadata.cram_index' input.cram.crai && |
16 ln -vs '$input.metadata.cram_index' 'input.${input.ext}.crai' >&2 && | |
17 #elif $input.is_of_type("bam"): | 16 #elif $input.is_of_type("bam"): |
18 echo 'is BAM' && | 17 ln -s '$input' input.bam && |
19 ln -s '$input' 'input.${input.ext}' >&2 && | 18 ln -s '$input.metadata.bam_index' input.bam.bai && |
20 ln -s '$input.metadata.bam_index' 'input.${input.ext}.bai' >&2 && | |
21 #else: | 19 #else: |
22 # raise TypeError('Unknown input alignment type ${input.ext}') | 20 # raise TypeError('Unknown input alignment type ${input.ext}') |
23 #end if | 21 #end if |
24 ln -vs '$consensus' 'consensus.${consensus.ext}' >&2 && | 22 ln -s '$consensus' consensus.fasta && |
25 ln -vs '$reference' 'reference.${reference.ext}' >&2 && | 23 #if str($ref_data.choice) == 'custom': |
24 ln -s '$reference' reference.fa && | |
25 #else: | |
26 ln -s '$__tool_directory__/ref_NC_045512.2.fasta' reference.fa && | |
27 #end if | |
26 | 28 |
27 frameshift_deletions_checks | 29 frameshift_deletions_checks |
28 --input='input.${input.ext}' | 30 --input=input.${input.ext} |
29 --consensus='consensus.${consensus.ext}' | 31 --consensus=consensus.fasta |
30 --reference='reference.${reference.ext}' | 32 --reference=reference.fa |
31 --genes='$genes' | 33 #if str($ref_data.choice) == 'standard': |
32 --output='$report' | 34 --genes='$__tool_directory__'/annotations_NC_045512.2.gff3 |
33 #if $orf1ab != '': | 35 --orf1ab='cds-YP_009724389.1' |
34 --orf1ab='$orf1ab' | 36 #else: |
37 --genes='$ref_data.genes' | |
38 --orf1ab='$ref_data.orf1ab' | |
35 #end if | 39 #end if |
36 '$english' | 40 $out_options.english |
37 $zero_based | 41 $out_options.zero_based |
42 --output=report.tsv && | |
43 python '$__tool_directory__/frameshift_deletions_report_fixer.py' report.tsv '$report' | |
38 ]]> | 44 ]]> |
39 <!-- ##cores \${GALAXY_SLOTS:-4} --> | 45 <!-- ##cores \${GALAXY_SLOTS:-4} --> |
40 </command> | 46 </command> |
41 <inputs> | 47 <inputs> |
42 <param argument="--consensus" type="data" format="fasta" label="Consensus" help="Fasta file containing the sample's consensus sequence (majority, with indels)" /> | 48 <param argument="--consensus" type="data" format="fasta" label="Consensus" help="Fasta file containing the sample's consensus sequence (majority, with indels)" /> |
43 <param argument="--input" type="data" format="bam,cram" label="Input BAM" help="Input BAM file with sample's sequencing reads, aligned against the reference" /> | 49 <param argument="--input" type="data" format="bam,cram" label="Input BAM" help="Input BAM file with sample's sequencing reads, aligned against the reference" /> |
44 <param argument="--reference" type="data" format="fasta" label="Reference" help="Fasta file containing the reference sequence (used during alignment) to compare against" /> | 50 <conditional name="ref_data"> |
45 <param argument="--genes" type="data" format="gff" label="Genes GFF" help="GFF file listing genes positions on the reference sequence" /> | 51 <param name="choice" type="select" label="Reference data selection" help="Select built-in genome files to base reported positions and annotations on the SARS-CoV-2 reference sequence NC_045512.2. If you have mapped to a different reference, select custom genome files and provide the reference sequence and genomic feature annotations for it in fasta and gff format, repsectively."> |
46 | 52 <option value="standard">Use built-in genome files</option> |
47 <param argument="--english" type="boolean" truevalue="--english" falsevalue="--no-english" checked="true" optional="true" label="Write Summary Diagnosis?" help="If checked writes english summary diagnosis." /> | 53 <option value="custom">Provide custom genome files</option> |
48 <param argument="--zero-based" type="boolean" truevalue="--zero-based" falsevalue="" checked="false" optional="true" label="Use 0-based Sequence Positions?" help="Use 0-based (python) instead of 1-based (standard) seq positions" /> | 54 </param> |
49 <param argument="--orf1ab" type="text" value="cds-YP_009724389.1" optional="true" label="ORF1AB" help="CDS ID for the full Orf1ab CDS, comprising the ribosomal shift. In the GFF this CDS should consist of 2 entries with the same CDS ID due to the partial overlap caused by the ribosomal shift at translation time."/> | 55 <when value="standard" /> |
56 <when value="custom"> | |
57 <param argument="--reference" type="data" format="fasta" label="Reference" help="Fasta input containing the reference sequence (used during alignment) to compare against" /> | |
58 <param argument="--genes" type="data" format="gff" label="Genes GFF" help="GFF input listing genes positions on the reference sequence" /> | |
59 <param argument="--orf1ab" type="text" value="cds-YP_009724389.1" optional="false" label="Coding sequence containing ribosomal slippage site" help="ID of the full CDS comprising the ribosomal slippage site as it appears in the GFF input. In the GFF this CDS should consist of 2 entries with the same CDS ID due to the partial overlap caused by the ribosomal shift at translation time. Hint: To use the tool with genomes that do not have a ribosomal slippage site, enter an ID that is not present in the GFF."> | |
60 <validator type="expression">value.strip()</validator> | |
61 </param> | |
62 </when> | |
63 </conditional> | |
64 <section name="out_options" title="Output format options" expanded="true"> | |
65 <param argument="--english" type="boolean" truevalue="--english" falsevalue="--no-english" checked="true" label="Write Summary Diagnosis?" help="If checked writes english summary diagnosis." /> | |
66 <param argument="--zero-based" type="boolean" truevalue="--zero-based" falsevalue="" checked="false" optional="true" label="Use 0-based Sequence Positions?" help="Use 0-based instead of 1-based genome positions" /> | |
67 </section> | |
50 </inputs> | 68 </inputs> |
51 <outputs> | 69 <outputs> |
52 <data name="report" format="tabular" /> | 70 <data name="report" format="tabular"> |
71 <actions> | |
72 <conditional name="out_options.english"> | |
73 <!-- The "english" flag removes certain numerical columns and collapses them into new text columns --> | |
74 <when value="--english"> | |
75 <action name="column_names" type="metadata" default="ref_id,start_position,length,VARIANT,gene_region,reads_all,reads_fwd,reads_rev,deletions,freq_del,freq_del_fwd,freq_del_rev,deletions_fwd,deletions_rev,insertions,freq_insert,freq_insert_fwd,freq_insert_rev,insertions_fwd,insertions_rev,stops,freq_stop,freq_stop_fwd,freq_stop_rev,stops_fwd,stops_rev,matches_ref,pos_critical_inserts,pos_critical_dels,homopolymeric,ref_base,cons_id,variant_position_english,variant_diagnosis" /> | |
76 </when> | |
77 <when value="--no-english"> | |
78 <action name="column_names" type="metadata" default="ref_id,start_position,length,VARIANT,gene_region,aa_position,stop_mismatches,stoploss_nt,reads_all,reads_fwd,reads_rev,deletions,freq_del,freq_del_fwd,freq_del_rev,deletions_fwd,deletions_rev,insertions,freq_insert,freq_insert_fwd,freq_insert_rev,insertions_fwd,insertions_rev,stops,freq_stop,freq_stop_fwd,freq_stop_rev,stops_fwd,stops_rev,matches_ref,pos_critical_inserts,pos_critical_dels,homopolymeric,ref_base,cons_id" /> | |
79 </when> | |
80 </conditional> | |
81 </actions> | |
82 </data> | |
53 </outputs> | 83 </outputs> |
54 <tests> | 84 <tests> |
55 <test> | 85 <test> |
56 <param name="consensus" value="consensus.bcftools.fasta.gz" /> | 86 <param name="consensus" value="consensus.bcftools.fasta.gz" /> |
57 <param name="input" value="REF_aln_trim.cram" /> | 87 <param name="input" value="REF_aln_trim.cram" /> |
58 <param name="reference" value="NC_045512.2.fasta.gz" /> | 88 <conditional name="ref_data"> |
59 <param name="genes" value="Genes_NC_045512.2.GFF3" /> | 89 <param name="choice" value="standard" /> |
90 </conditional> | |
91 <output name="report" value="frameshift_deletions_check.tsv" /> | |
92 </test> | |
93 <test> | |
94 <param name="consensus" value="consensus.bcftools.fasta.gz" /> | |
95 <param name="input" value="REF_aln_trim.cram" /> | |
96 <conditional name="ref_data"> | |
97 <param name="choice" value="standard" /> | |
98 </conditional> | |
99 <section name="out_options"> | |
100 <param name="english" value="false" /> | |
101 </section> | |
102 <output name="report" value="frameshift_deletions_check_no_english.tsv" /> | |
103 </test> | |
104 <test> | |
105 <param name="consensus" value="consensus.bcftools.fasta.gz" /> | |
106 <param name="input" value="REF_aln_trim.cram" /> | |
107 <conditional name="ref_data"> | |
108 <param name="choice" value="custom" /> | |
109 <param name="reference" value="NC_045512.2.fasta" /> | |
110 <param name="genes" value="Genes_NC_045512.2.GFF3" /> | |
111 </conditional> | |
60 <output name="report" value="frameshift_deletions_check.tsv" /> | 112 <output name="report" value="frameshift_deletions_check.tsv" /> |
61 </test> | 113 </test> |
62 </tests> | 114 </tests> |
63 <help> | 115 <help> |
64 <![CDATA[ | 116 <![CDATA[ |
69 Columns signification: | 121 Columns signification: |
70 ---------------------- | 122 ---------------------- |
71 | 123 |
72 * *gene_region*: Gene in which the deletion is found according to ``--genes`` argument; | 124 * *gene_region*: Gene in which the deletion is found according to ``--genes`` argument; |
73 * *reads_all*: Total number of reads covering the indel; | 125 * *reads_all*: Total number of reads covering the indel; |
74 * *reads_fwd*: Total nubmer of forward reads covering the indel; | 126 * *reads_fwd*: Total number of forward reads covering the indel; |
75 * *reads_rev*: Total nubmer of reverse reads covering the indel; | 127 * *reads_rev*: Total number of reverse reads covering the indel; |
76 * *deletions/insertions*: Number of reads supporting the deletion/insertion; | 128 * *deletions/insertions*: Number of reads supporting the deletion/insertion; |
77 * *freq_del/freq_insert*: Fraction of reads supporting the deletion/insertion; | 129 * *freq_del/freq_insert*: Fraction of reads supporting the deletion/insertion; |
78 * *matches_ref*: number of reads that matche with the reference base; | 130 * *matches_ref*: number of reads that matche with the reference base; |
79 * *pos_critical_inserts*: Start positions of insertions in the same gene_region that occur in > 40% of reads; | 131 * *pos_critical_inserts*: Start positions of insertions in the same gene_region that occur in > 40% of reads; |
80 * *pos_critical_dels*: Start positions of deletions in the same gene_region that occur in > 40% of reads; | 132 * *pos_critical_dels*: Start positions of deletions in the same gene_region that occur in > 40% of reads; |