[2] | 1 | <tool id="ncbi_tblastn_wrapper" name="NCBI BLAST+ tblastn" version="0.0.1"> |
---|
| 2 | <description>Search translated nucleotide database with protein query sequence(s)</description> |
---|
| 3 | <command> |
---|
| 4 | ## The command is a Cheetah template which allows some Python based syntax. |
---|
| 5 | ## Lines starting hash hash are comments. Galaxy will turn newlines into spaces |
---|
| 6 | tblastn |
---|
| 7 | -query "$query" |
---|
| 8 | #if $db_opts.db_opts_selector == "db": |
---|
| 9 | -db "$db_opts.database" |
---|
| 10 | #else: |
---|
| 11 | -subject "$db_opts.subject" |
---|
| 12 | #end if |
---|
| 13 | -evalue $evalue_cutoff |
---|
| 14 | $adv_opts.filter_query |
---|
| 15 | $adv_opts.matrix |
---|
| 16 | -out $output1 |
---|
| 17 | $out_format |
---|
| 18 | -num_threads 8 |
---|
| 19 | ## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string |
---|
| 20 | ## Note -max_target_seqs overrides -num_descriptions and -num_alignments |
---|
| 21 | #if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0): |
---|
| 22 | -max_target_seqs $adv_opts.max_hits |
---|
| 23 | #end if |
---|
| 24 | #if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0): |
---|
| 25 | -word_size $adv_opts.word_size |
---|
| 26 | #end if |
---|
| 27 | ##Ungapped disabled for now - see comments below |
---|
| 28 | ##$adv_opts.ungapped |
---|
| 29 | </command> |
---|
| 30 | <inputs> |
---|
| 31 | <param name="query" type="data" format="fasta" label="Protein query sequence(s)"/> |
---|
| 32 | <conditional name="db_opts"> |
---|
| 33 | <param name="db_opts_selector" type="select" label="Subject database/sequences"> |
---|
| 34 | <option value="db" selected="True">BLAST Database</option> |
---|
| 35 | <option value="file">FASTA file</option> |
---|
| 36 | </param> |
---|
| 37 | <when value="db"> |
---|
| 38 | <param name="database" type="select" label="Nucleotide BLAST database"> |
---|
| 39 | <options from_file="blastdb.loc"> |
---|
| 40 | <column name="name" index="0"/> |
---|
| 41 | <column name="value" index="1"/> |
---|
| 42 | </options> |
---|
| 43 | </param> |
---|
| 44 | <param name="subject" type="hidden" value="" /> |
---|
| 45 | </when> |
---|
| 46 | <when value="file"> |
---|
| 47 | <param name="database" type="hidden" value="" /> |
---|
| 48 | <param name="subject" type="data" format="fasta" label="Nucleotide FASTA file to use as database"/> |
---|
| 49 | </when> |
---|
| 50 | </conditional> |
---|
| 51 | <param name="evalue_cutoff" type="float" size="15" value="0.001" label="set expectation value cutoff" /> |
---|
| 52 | <param name="out_format" type="select" label="Output format"> |
---|
| 53 | <option value="-outfmt 6" selected="True">Tabular</option> |
---|
| 54 | <option value="-outfmt 5">BLAST XML</option> |
---|
| 55 | <option value="-outfmt 0">Pairwise text</option> |
---|
| 56 | <option value="-outfmt 0 -html">Pairwise HTML</option> |
---|
| 57 | <option value="-outfmt 2">Query-anchored text</option> |
---|
| 58 | <option value="-outfmt 2 -html">Query-anchored HTML</option> |
---|
| 59 | <option value="-outfmt 4">Flat query-anchored text</option> |
---|
| 60 | <option value="-outfmt 4 -html">Flat query-anchored HTML</option> |
---|
| 61 | <!-- |
---|
| 62 | <option value="-outfmt 11">BLAST archive format (ASN.1)</option> |
---|
| 63 | --> |
---|
| 64 | </param> |
---|
| 65 | <conditional name="adv_opts"> |
---|
| 66 | <param name="adv_opts_selector" type="select" label="Advanced Options"> |
---|
| 67 | <option value="basic" selected="True">Hide Advanced Options</option> |
---|
| 68 | <option value="advanced">Show Advanced Options</option> |
---|
| 69 | </param> |
---|
| 70 | <when value="basic"> |
---|
| 71 | <param name="filter_query" type="hidden" value="" /> |
---|
| 72 | <param name="matrix" type="hidden" value="" /> |
---|
| 73 | <param name="max_hits" type="hidden" value="" /> |
---|
| 74 | <param name="word_size" type="hidden" value="" /> |
---|
| 75 | <!-- |
---|
| 76 | Ungapped disabled for now, see comments below |
---|
| 77 | <param name="ungapped" type="hidden" value="" /> |
---|
| 78 | --> |
---|
| 79 | </when> |
---|
| 80 | <when value="advanced"> |
---|
| 81 | <!-- Could use a select (yes, no, other) where other allows setting 'window locut hicut' --> |
---|
| 82 | <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" /> |
---|
| 83 | <param name="matrix" type="select" label="Scoring matrix"> |
---|
| 84 | <option value="-matrix BLOSUM90">BLOSUM90</option> |
---|
| 85 | <option value="-matrix BLOSUM80">BLOSUM80</option> |
---|
| 86 | <option value="-matrix BLOSUM62" selected="true">BLOSUM62 (default)</option> |
---|
| 87 | <option value="-matrix BLOSUM50">BLOSUM50</option> |
---|
| 88 | <option value="-matrix BLOSUM45">BLOSUM45</option> |
---|
| 89 | <option value="-matrix PAM250">PAM250</option> |
---|
| 90 | <option value="-matrix PAM70">PAM70</option> |
---|
| 91 | <option value="-matrix PAM30">PAM30</option> |
---|
| 92 | </param> |
---|
| 93 | <!-- Why doesn't optional override a validator? I want to accept an empty string OR a non-negative integer --> |
---|
| 94 | <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits"> |
---|
| 95 | <validator type="in_range" min="0" /> |
---|
| 96 | </param> |
---|
| 97 | <!-- I'd like word_size to be optional, with minimum 2 for blastp --> |
---|
| 98 | <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2."> |
---|
| 99 | <validator type="in_range" min="0" /> |
---|
| 100 | </param> |
---|
| 101 | <!-- |
---|
| 102 | Can't use '-ungapped' on its own, error back is: |
---|
| 103 | Composition-adjusted searched are not supported with an ungapped search, please add -comp_based_stats F or do a gapped search |
---|
| 104 | Tried using '-ungapped -comp_based_stats F' and tblastn crashed with 'Attempt to access NULL pointer.' |
---|
| 105 | <param name="ungapped" type="boolean" label="Perform ungapped alignment only?" truevalue="-ungapped -comp_based_stats F" falsevalue="" checked="false" /> |
---|
| 106 | --> |
---|
| 107 | </when> |
---|
| 108 | </conditional> |
---|
| 109 | </inputs> |
---|
| 110 | <outputs> |
---|
| 111 | <data name="output1" format="tabular" label="tblastn on ${db_opts.db_opts_selector}"> |
---|
| 112 | <change_format> |
---|
| 113 | <when input="out_format" value="-outfmt 0" format="txt"/> |
---|
| 114 | <when input="out_format" value="-outfmt 0 -html" format="html"/> |
---|
| 115 | <when input="out_format" value="-outfmt 2" format="txt"/> |
---|
| 116 | <when input="out_format" value="-outfmt 2 -html" format="html"/> |
---|
| 117 | <when input="out_format" value="-outfmt 4" format="txt"/> |
---|
| 118 | <when input="out_format" value="-outfmt 4 -html" format="html"/> |
---|
| 119 | <when input="out_format" value="-outfmt 5" format="blastxml"/> |
---|
| 120 | </change_format> |
---|
| 121 | </data> |
---|
| 122 | </outputs> |
---|
| 123 | <requirements> |
---|
| 124 | <requirement type="binary">blastn</requirement> |
---|
| 125 | </requirements> |
---|
| 126 | <tests> |
---|
| 127 | </tests> |
---|
| 128 | <help> |
---|
| 129 | |
---|
| 130 | .. class:: warningmark |
---|
| 131 | |
---|
| 132 | **Note**. Database searches may take substantial amount of time. |
---|
| 133 | For large input datasets it is advisable to allow overnight processing. |
---|
| 134 | |
---|
| 135 | ----- |
---|
| 136 | |
---|
| 137 | **What it does** |
---|
| 138 | |
---|
| 139 | Search a *translated nucleotide database* using a *protein query*, |
---|
| 140 | using the NCBI BLAST+ tblastn command line tool. |
---|
| 141 | |
---|
| 142 | ----- |
---|
| 143 | |
---|
| 144 | **Output format** |
---|
| 145 | |
---|
| 146 | Because Galaxy focuses on processing tabular data, the default output of this tool is tabular. This contains 12 columns: |
---|
| 147 | |
---|
| 148 | 1. Id of your sequence |
---|
| 149 | 2. GI of the database hit |
---|
| 150 | 3. % identity |
---|
| 151 | 4. Alignment length |
---|
| 152 | 5. # mismatches |
---|
| 153 | 6. # gaps |
---|
| 154 | 7. Start position in your sequence |
---|
| 155 | 8. End position in your sequence |
---|
| 156 | 9. Start position in database hit |
---|
| 157 | 10. End position in database hit |
---|
| 158 | 11. E-value |
---|
| 159 | 12. Bit score |
---|
| 160 | |
---|
| 161 | The second option is BLAST XML output, which is designed to be parsed by another program, and is understood by other Galaxy tools. |
---|
| 162 | |
---|
| 163 | You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program). |
---|
| 164 | The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website. |
---|
| 165 | The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query. |
---|
| 166 | The two query anchored outputs show a multiple sequence alignment between the query and all the matches, |
---|
| 167 | and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences). |
---|
| 168 | |
---|
| 169 | ------- |
---|
| 170 | |
---|
| 171 | **References** |
---|
| 172 | |
---|
| 173 | Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402. |
---|
| 174 | |
---|
| 175 | </help> |
---|
| 176 | </tool> |
---|