<tool id="blast_plus_remote_blastp" name="NCBI BLAST+ remote blastp" version="1.0">
    <description>Search protein database with protein query sequence(s)</description>
    <!-- If job splitting is enabled, break up the query file into four (This only works if output is tabular) -->
    <parallelism method="multi" split_inputs="query" split_mode="number_of_parts" split_size="4" shared_inputs="subject" merge_outputs="output1"></parallelism>
    <version_command>blastp -version</version_command>
    <requirements>
        <requirement type="package" version="333">binaries_for_blast_plus</requirement>
    </requirements>
    <command>
## The command is a Cheetah template which allows some Python based syntax.
## Lines starting hash hash are comments. Galaxy will turn newlines into spaces
blastp
-query "$query"
#if $db_opts.db_opts_selector == "db":
  -db "${db_opts.database.fields.path}"
#elif $db_opts.db_opts_selector == "remote":
  -db $db_opts.database
  -remote
  #set $txids = []
  #set $ntxids = []
  #for $i, $org in enumerate($db_opts.taxid_repeat):
    #if $org.exclude:
      #set $ntxids = $ntxids + ["txid" + $org.taxid.__str__]
    #else
      #set $txids = $txids + ["txid" + $org.taxid.__str__]
    #end if
  #end for
  #if (len($txids) + len($ntxids)) > 0:
    #set $entrez_query = ''
    #if len($txids) > 0:
      #set $entrez_query = $entrez_query + '(' + ' OR '.join($txids) + ')'
    #end if
    #if len($ntxids) > 0:
      #set $entrez_query = $entrez_query + ' NOT (' + ' OR '.join($ntxids) + ')'
    #end if
    -entrez_query '$entrez_query'
  #end if
#else:
  -subject "$db_opts.subject"
#end if
-task $blast_type
-evalue $evalue_cutoff
-out blast_output
##Set the extended list here so if/when we add things, saved workflows are not affected
#if str($fmt_opt.out_format)=="text":
  -outfmt "$fmt_opt.outfmt" $fmt_opt.html
  #if $fmt_opt.num_descriptions.__str__.strip() != '':
    -num_descriptions $fmt_opt.num_descriptions
  #end if
  #if $fmt_opt.num_alignments.__str__.strip() != '':
    -num_alignments $fmt_opt.num_alignments
  #end if
#else:
  -outfmt "$fmt_opt.outfmt"
  #if $fmt_opt.max_target_seqs.__str__.strip() != '':
    -max_target_seqs $fmt_opt.max_target_seqs
  #end if
#end if
#if $db_opts.db_opts_selector != "remote":
  -num_threads 8
#end if
#if $adv_opts.adv_opts_selector=="advanced":
  $adv_opts.filter_query
  -matrix $adv_opts.scoring.matrix
  $adv_opts.scoring.gap_costs

  #if $adv_opts.word_size.__str__.strip() != '':
    -word_size $adv_opts.word_size
  #end if

  #if $adv_opts.window_size.__str__.strip() != '':
    -window_size $adv_opts.window_size
  #end if

  #if $adv_opts.threshold.__str__.strip() != '':
    -threshold $adv_opts.threshold
  #end if

  #if $adv_opts.comp_based_stats.__str__.strip() != '':
    -comp_based_stats $adv_opts.comp_based_stats
  #end if

  ##Ungapped disabled for now - see comments below
  ##$adv_opts.ungapped
  $adv_opts.use_sw_tback
  $adv_opts.parse_deflines
  ## End of advanced options:
#end if
    </command>
    <inputs>
        <param name="query" type="data" format="fasta" label="Protein query sequence(s)"/>
        <conditional name="db_opts">
            <param name="db_opts_selector" type="select" label="Subject database/sequences">
              <option value="db" selected="True">Local BLAST Database</option>
              <option value="file">Local FASTA file</option>
              <option value="remote">NCBI Remote Database</option>
            </param>
            <when value="db">
                <param name="database" type="select" label="Protein BLAST database">
                    <options from_file="blastdb_p.loc">
                      <column name="value" index="0"/>
                      <column name="name" index="1"/>
                      <column name="path" index="2"/>
                    </options>
                </param>
                <param name="subject" type="hidden" value="" />
            </when>
            <when value="file">
                <param name="database" type="hidden" value="" />
                <param name="subject" type="data" format="fasta" label="Protein FASTA file to use as database"/>
            </when>
            <when value="remote">
                <param name="database" type="select" label="Protein BLAST database">
                    <option value="nr" selected="selected" >Non-redundant protein sequences (nr)</option>
                    <option value="refseq_protein"  >Reference proteins (refseq_protein)</option>
                    <option value="swissprot"  >UniProtKB/Swiss-Prot(swissprot)</option>
                    <option value="pat"  >Patented protein sequences(pat)</option>
                    <option value="pdb"  >Protein Data Bank proteins(pdb)</option>
                    <option value="env_nr"  >Metagenomic proteins(env_nr)</option>
                </param>
                <repeat name="taxid_repeat" title="Search Organism Restriction" min="0">
                    <param name="taxid" type="integer" value="" label="NCBI Taxon ID" help="For example: Human is 9606 (see: http://www.ncbi.nlm.nih.gov/taxonomy ) ">
                        <dsvalidator type="in_range" min="0" />
                    </param>
                    <param name="exclude" type="boolean" checked="false" label="Exclude this NCBI Taxon ID" help=""/>
                </repeat>
            </when>
        </conditional>
        <param name="blast_type" type="select" display="radio" label="Type of BLAST">
            <option value="blastp">blastp</option>
            <option value="blastp-short">blastp-short</option>
        </param>
        <param name="evalue_cutoff" type="float" size="15" value="0.001" label="Set expectation value cutoff" />
        <conditional name="fmt_opt">
            <param name="out_format" type="select" label="Output format">
                <option value="tabular" selected="True">Tabular</option>
                <option value="blastxml">BLAST XML</option>
                <option value="text">Text Report</option>
            </param>
            <when value="tabular">
                <param name="outfmt" type="select" label="Tabular columns">
                  <option value="6" selected="True">Tabular (standard 12 columns)</option>
                  <option value="7">Tabular (standard 12 columns) with comments</option>
                  <option value="6 std sallseqid score nident positive gaps ppos qframe sframe qseq sseq qlen slen">Tabular (extended 24 columns)</option>
                </param>
                <param name="max_target_seqs" type="integer" value="500" optional="true" label="Maximum hits to show" help="Use zero for default limits">
                    <validator type="in_range" min="0" />
                </param>
            </when>
            <when value="blastxml">
                <param name="outfmt" type="hidden" value="5"/>
                <param name="max_target_seqs" type="integer" value="500" optional="true" label="Maximum hits to show" help="Use zero for default limits">
                    <validator type="in_range" min="0" />
                </param>
            </when>
            <when value="text">
                <param name="outfmt" type="select" label="Text format">
                    <option value="0">Pairwise text</option>
                    <option value="1">Query-anchored text showing identitites</option>
                    <option value="2">Query-anchored text</option>
                    <option value="3">Flat query-anchored text showing identitites</option>
                    <option value="4">Flat query-anchored text</option>
                </param>
                <param name="html" type="boolean" label="Html" truevalue="-html" falsevalue="" checked="true" />
                <param name="num_descriptions" type="integer" value="500" optional="true" label="Maximum Decriptions to show" help="Show one-line descriptions for this number of database sequences.">
                    <validator type="in_range" min="0" />
                </param>
                <param name="num_alignments" type="integer" value="250" optional="true" label="Maximum alignments to show" help="Show alignments for this number of database sequences.">
                    <validator type="in_range" min="0" />
                </param>
            </when>
        </conditional>
        <conditional name="adv_opts">
            <param name="adv_opts_selector" type="select" label="Advanced Options">
              <option value="basic" selected="True">Hide Advanced Options</option>
              <option value="advanced">Show Advanced Options</option>
            </param>
            <when value="basic" />
            <when value="advanced">
                <!-- Could use a select (yes, no, other) where other allows setting 'window locut hicut' -->
                <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="false" />
                <conditional name="scoring">
                    <param name="matrix" type="select" label="Scoring matrix">
                        <option value="BLOSUM90">BLOSUM90</option>
                        <option value="BLOSUM80">BLOSUM80</option>
                        <option value="BLOSUM62" selected="true">BLOSUM62 (default)</option>
                        <option value="BLOSUM50">BLOSUM50</option>
                        <option value="BLOSUM45">BLOSUM45</option>
                        <option value="PAM250">PAM250</option>
                        <option value="PAM70">PAM70</option>
                        <option value="PAM30">PAM30</option>
                    </param>
                    <when value="BLOSUM90">
                        <param name="gap_costs" type="select" label="Gap Costs">
                            <option value="">Use Defaults</option>
                            <option value="-gapopen 9 -gapextend 2">Existense: 9  Extension: 2</option>
                            <option value="-gapopen 8 -gapextend 2">Existense: 8  Extension: 2</option>
                            <option value="-gapopen 7 -gapextend 2">Existense: 7  Extension: 2</option>
                            <option value="-gapopen 6 -gapextend 2">Existense: 6  Extension: 2</option>
                            <option value="-gapopen 11 -gapextend 1">Existense: 11  Extension: 1</option>
                            <option value="-gapopen 10 -gapextend 1" selected="true">Existense: 10  Extension: 1 (default)</option>
                            <option value="-gapopen 9 -gapextend 1">Existense: 9  Extension: 1</option>
                        </param>

                    </when>
                    <when value="BLOSUM80">
                        <param name="gap_costs" type="select" label="Gap Costs">
                            <option value="">Use Defaults</option>
                            <option value="-gapopen 8 -gapextend 2">Existense: 8  Extension: 2</option>
                            <option value="-gapopen 7 -gapextend 2">Existense: 7  Extension: 2</option>
                            <option value="-gapopen 6 -gapextend 2">Existense: 6  Extension: 2</option>
                            <option value="-gapopen 11 -gapextend 1">Existense: 11  Extension: 1</option>
                            <option value="-gapopen 10 -gapextend 1" selected="true">Existense: 10  Extension: 1 (default)</option>
                            <option value="-gapopen 9 -gapextend 1">Existense: 9  Extension: 1</option>
                        </param>
                    </when>
                    <when value="BLOSUM62">
                        <param name="gap_costs" type="select" label="Gap Costs">
                            <option value="">Use Defaults</option>
                            <option value="-gapopen 11 -gapextend 2">Existense: 11  Extension: 2</option>
                            <option value="-gapopen 10 -gapextend 2">Existense: 10  Extension: 2</option>
                            <option value="-gapopen 9 -gapextend 2">Existense: 9  Extension: 2</option>
                            <option value="-gapopen 8 -gapextend 2">Existense: 8  Extension: 2</option>
                            <option value="-gapopen 7 -gapextend 2">Existense: 7  Extension: 2</option>
                            <option value="-gapopen 6 -gapextend 2">Existense: 6  Extension: 2</option>
                            <option value="-gapopen 13 -gapextend 1">Existense: 13  Extension: 1</option>
                            <option value="-gapopen 12 -gapextend 1">Existense: 12  Extension: 1</option>
                            <option value="-gapopen 11 -gapextend 1" selected="true">Existense: 11  Extension: 1 (default)</option>
                            <option value="-gapopen 10 -gapextend 1">Existense: 10  Extension: 1</option>
                            <option value="-gapopen 9 -gapextend 1">Existense: 9  Extension: 1</option>
                        </param>

                    </when>
                    <when value="BLOSUM50">
                        <param name="gap_costs" type="select" label="Gap Costs">
                            <option value="">Use Defaults</option>
                            <option value="-gapopen 13 -gapextend 3">Existense: 13  Extension: 3</option>
                            <option value="-gapopen 12 -gapextend 3">Existense: 12  Extension: 3</option>
                            <option value="-gapopen 11 -gapextend 3">Existense: 11  Extension: 3</option>
                            <option value="-gapopen 10 -gapextend 3">Existense: 10  Extension: 3</option>
                            <option value="-gapopen 9 -gapextend 3">Existense: 9  Extension: 3</option>
                            <option value="-gapopen 16 -gapextend 2">Existense: 16  Extension: 2</option>
                            <option value="-gapopen 15 -gapextend 2">Existense: 15  Extension: 2</option>
                            <option value="-gapopen 14 -gapextend 2">Existense: 14  Extension: 2</option>
                            <option value="-gapopen 13 -gapextend 2" selected="true">Existense: 13  Extension: 2 (default)</option>
                            <option value="-gapopen 12 -gapextend 2">Existense: 12  Extension: 2</option>
                            <option value="-gapopen 19 -gapextend 1">Existense: 19  Extension: 1</option>
                            <option value="-gapopen 18 -gapextend 1">Existense: 18  Extension: 1</option>
                            <option value="-gapopen 17 -gapextend 1">Existense: 17  Extension: 1</option>
                            <option value="-gapopen 16 -gapextend 1">Existense: 16  Extension: 1</option>
                            <option value="-gapopen 15 -gapextend 1">Existense: 15  Extension: 1</option>
                        </param>

                    </when>
                    <when value="BLOSUM45">
                        <param name="gap_costs" type="select" label="Gap Costs">
                            <option value="">Use Defaults</option>
                            <option value="-gapopen 13 -gapextend 3">Existense: 13  Extension: 3</option>
                            <option value="-gapopen 12 -gapextend 3">Existense: 12  Extension: 3</option>
                            <option value="-gapopen 11 -gapextend 3">Existense: 11  Extension: 3</option>
                            <option value="-gapopen 10 -gapextend 3">Existense: 10  Extension: 3</option>
                            <option value="-gapopen 15 -gapextend 2" selected="true">Existense: 15  Extension: 2 (default)</option>
                            <option value="-gapopen 14 -gapextend 2">Existense: 14  Extension: 2</option>
                            <option value="-gapopen 13 -gapextend 2">Existense: 13  Extension: 2</option>
                            <option value="-gapopen 12 -gapextend 2">Existense: 12  Extension: 2</option>
                            <option value="-gapopen 19 -gapextend 1">Existense: 19  Extension: 1</option>
                            <option value="-gapopen 18 -gapextend 1">Existense: 18  Extension: 1</option>
                            <option value="-gapopen 17 -gapextend 1">Existense: 17  Extension: 1</option>
                            <option value="-gapopen 16 -gapextend 1">Existense: 16  Extension: 1</option>
                        </param>
                    </when>
                    <when value="PAM250">
                        <param name="gap_costs" type="select" label="Gap Costs">
                            <option value="">Use Defaults</option>
                            <option value="-gapopen 15 -gapextend 3">Existense: 15  Extension: 3</option>
                            <option value="-gapopen 14 -gapextend 3">Existense: 14  Extension: 3</option>
                            <option value="-gapopen 13 -gapextend 3">Existense: 13  Extension: 3</option>
                            <option value="-gapopen 12 -gapextend 3">Existense: 12  Extension: 3</option>
                            <option value="-gapopen 17 -gapextend 2">Existense: 17  Extension: 2</option>
                            <option value="-gapopen 16 -gapextend 2">Existense: 16  Extension: 2</option>
                            <option value="-gapopen 15 -gapextend 2">Existense: 15  Extension: 2</option>
                            <option value="-gapopen 14 -gapextend 2" selected="true">Existense: 14  Extension: 2 (default)</option>
                            <option value="-gapopen 13 -gapextend 2">Existense: 13  Extension: 2</option>
                            <option value="-gapopen 21 -gapextend 1">Existense: 21  Extension: 1</option>
                            <option value="-gapopen 20 -gapextend 1">Existense: 20  Extension: 1</option>
                            <option value="-gapopen 19 -gapextend 1">Existense: 19  Extension: 1</option>
                            <option value="-gapopen 18 -gapextend 1">Existense: 18  Extension: 1</option>
                            <option value="-gapopen 17 -gapextend 1">Existense: 17  Extension: 1</option>
                        </param>

                    </when>
                    <when value="PAM70">
                        <param name="gap_costs" type="select" label="Gap Costs">
                            <option value="">Use Defaults</option>
                            <option value="-gapopen 8 -gapextend 2">Existense: 8  Extension: 2</option>
                            <option value="-gapopen 7 -gapextend 2">Existense: 7  Extension: 2</option>
                            <option value="-gapopen 6 -gapextend 2">Existense: 6  Extension: 2</option>
                            <option value="-gapopen 11 -gapextend 1">Existense: 11  Extension: 1</option>
                            <option value="-gapopen 10 -gapextend 1" selected="true">Existense: 10  Extension: 1 (default)</option>
                            <option value="-gapopen 9 -gapextend 1">Existense: 9  Extension: 1</option>
                        </param>

                    </when>
                    <when value="PAM30">
                        <param name="gap_costs" type="select" label="Gap Costs">
                            <option value="">Use Defaults</option>
                            <option value="-gapopen 7 -gapextend 2">Existense: 7  Extension: 2</option>
                            <option value="-gapopen 6 -gapextend 2">Existense: 6  Extension: 2</option>
                            <option value="-gapopen 5 -gapextend 2">Existense: 5  Extension: 2</option>
                            <option value="-gapopen 10 -gapextend 1">Existense: 10  Extension: 1</option>
                            <option value="-gapopen 9 -gapextend 1" selected="true">Existense: 9  Extension: 1 (default)</option>
                            <option value="-gapopen 8 -gapextend 1">Existense: 8  Extension: 1</option>
                        </param>
                    </when>
                <!--
                Can't use '-ungapped' on its own, error back is:
                Composition-adjusted searched are not supported with an ungapped search, please add -comp_based_stats F or do a gapped search
                Tried using '-ungapped -comp_based_stats F' and blastp crashed with 'Attempt to access NULL pointer.'
                <param name="ungapped" type="boolean" label="Perform ungapped alignment only?" truevalue="-ungapped -comp_based_stats F" falsevalue="" checked="false" />
                -->
                </conditional>

                <!-- I'd like word_size to be optional, with minimum 2 for blastp -->
                <param name="word_size" type="integer" value="" optional="true" label="Word size for wordfinder algorithm" help="Recommended: blastp 3, blastp-short 2">
                    <validator type="in_range" min="2" />
                </param>
                <param name="window_size" type="integer" value="" optional="true" label="Multiple hits window size, use 0 to specify 1-hit algorithm." help="Recommended: blastp 40, blastp-short 15">
                    <validator type="in_range" min="0" />
                </param>
                <param name="threshold" type="integer" value="" optional="true" label="Threshold: Minimum score to add a word to the BLAST lookup table." help="Recommended: blastp 11, blastp-short 16">
                    <validator type="in_range" min="1" />
                </param>
                <param name="comp_based_stats" type="select" optional="true" label="Use composition-based statistics"
                       help="Recommended:  blastp: 2   blastp-short: 0">
                    <option value="">Leave Unspecified</option>
                    <option value="0">0 or F (No composition-based statistics)</option>
                    <option value="1">1 (Composition-based statistics as in NAR 29:2994-3005, 2001)</option>
                    <option value="2">2, T,  or D (Composition-based score adjustment as in Bioinformatics 21:902-911, 2005, conditioned on sequence properties)</option>
                    <option value="3">3 (Composition-based score adjustment as in Bioinformatics 21:902-911, 2005, unconditionally)</option>
                </param>

                <param name="use_sw_tback" type="boolean" label="Compute locally optimal Smith-Waterman alignments?" truevalue="-use_sw_tback" falsevalue="" checked="false" />

                <param name="parse_deflines" type="boolean" label="Should the query and subject defline(s) be parsed?" truevalue="-parse_deflines" falsevalue="" checked="false" help="This affects the formatting of the query/subject ID strings"/>
            </when>
        </conditional>
    </inputs>

    <outputs>
        <data name="output_tabular" format="tabular" label="${blast_type.value_label} on ${db_opts.db_opts_selector} ${db_opts.database}" from_work_dir="blast_output">
            <filter>fmt_opt['out_format'] == "tabular"</filter>
        </data>
        <data name="output_xml" format="blastxml" label="${blast_type.value_label} on ${db_opts.db_opts_selector} ${db_opts.database}" from_work_dir="blast_output">
            <filter>fmt_opt['out_format'] == "blastxml"</filter>
        </data>
        <data name="output_txt" format="txt" label="${blast_type.value_label} on ${db_opts.db_opts_selector} ${db_opts.database}" from_work_dir="blast_output">
            <filter>fmt_opt['out_format'] == "text" and not fmt_opt['html']</filter>
        </data>
        <data name="output_html" format="html" label="${blast_type.value_label} on ${db_opts.db_opts_selector} ${db_opts.database}" from_work_dir="blast_output">
            <filter>fmt_opt['out_format'] == "text" and fmt_opt['html']</filter>
        </data>
    </outputs>

    <stdio>
        <exit_code range="1"  level="fatal"   description="Bad input dataset or BLAST options" />
        <exit_code range="2"  level="fatal"   description="Error in BLAST database" />
        <exit_code range="3"  level="fatal"   description="Error in BLAST engine" />
        <exit_code range="4"  level="fatal"   description="Out of Memory" />
        <exit_code range="5:" level="fatal"   description="Unknown Error" />
    </stdio>

    <tests>
        <test>
            <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
            <param name="db_opts_selector" value="file" />
            <param name="subject" value="rhodopsin_proteins.fasta" ftype="fasta" />
            <param name="database" value="" />
            <param name="evalue_cutoff" value="1e-8" />
            <param name="blast_type" value="blastp" />
            <param name="out_format" value="blastxml" />
            <param name="outfmt" value="5" />
            <param name="adv_opts_selector" value="advanced" />
            <param name="filter_query" value="False" />
            <param name="matrix" value="BLOSUM62" />
            <param name="max_target_seqs" value="" />
            <param name="word_size" value="" />
            <param name="parse_deflines" value="True" />
            <output name="output_xml">
              <assert_contents>
                <has_text text="sp|Q9BS26|ERP44_HUMAN"/>
              </assert_contents>
            </output>
        </test>
        <test>
            <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
            <param name="db_opts_selector" value="file" />
            <param name="subject" value="rhodopsin_proteins.fasta" ftype="fasta" />
            <param name="database" value="" />
            <param name="evalue_cutoff" value="1e-8" />
            <param name="blast_type" value="blastp" />
            <param name="out_format" value="tabular" />
            <param name="outfmt" value="6" />
            <param name="adv_opts_selector" value="advanced" />
            <param name="filter_query" value="False" />
            <param name="matrix" value="BLOSUM62" />
            <param name="max_target_seqs" value="" />
            <param name="word_size" value="" />
            <param name="parse_deflines" value="True" />
            <output name="output_tabular">
              <assert_contents>
                <has_text_matching expression="sp.P08100.OPSD_HUMAN\tgi.283855846.gb.ADB45242.1.\t\d+.\d+\t\d+\t\d+\t0\t\d+\t\d+\t\d+\t\d+\t\S+\t\s*\d+" />
                <has_text text="BAB21486.1"/>
              </assert_contents>
            </output>
        </test>
        <test>
            <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
            <param name="db_opts_selector" value="file" />
            <param name="subject" value="rhodopsin_proteins.fasta" ftype="fasta" />
            <param name="database" value="" />
            <param name="evalue_cutoff" value="1e-8" />
            <param name="blast_type" value="blastp" />
            <param name="out_format" value="tabular" />
            <param name="outfmt" value="6 std sallseqid score nident positive gaps ppos qframe sframe qseq sseq qlen slen" />
            <param name="adv_opts_selector" value="advanced" />
            <param name="filter_query" value="False" />
            <param name="matrix" value="BLOSUM62" />
            <param name="max_target_seqs" value="" />
            <param name="word_size" value="" />
            <param name="parse_deflines" value="True" />
            <output name="output_tabular">
              <assert_contents>
                <has_text_matching expression="sp.P08100.OPSD_HUMAN\tgi.283855846.gb.ADB45242.1.\t\d+.\d+\t\d+\t\d+\t\d+\t\d+\t\d+\t\d+\t\d+\t\S+\t\s*\d+\t\S+\t\d+\t\d+\t\d+\t\d+\t\S+\t\d+\t\d+\t\S+\t\S+\t\d+\t\d+" />
              </assert_contents>
            </output>
        </test>
        <test>
            <param name="query" value="rhodopsin_proteins.fasta" ftype="fasta" />
            <param name="db_opts_selector" value="file" />
            <param name="subject" value="four_human_proteins.fasta" ftype="fasta" />
            <param name="database" value="" />
            <param name="evalue_cutoff" value="1e-8" />
            <param name="blast_type" value="blastp" />
            <param name="out_format" value="tabular" />
            <param name="outfmt" value="6" />
            <param name="adv_opts_selector" value="basic" />
            <output name="output_tabular">
              <assert_contents>
                <has_text_matching expression="gi.283855846.gb.ADB45242.1.\tsp.P08100.OPSD_HUMAN\t\d+.\d+\t\d+\t\d+\t0\t\d+\t\d+\t\d+\t\d+\t\S+\t\s*\d+" />
                <has_text text="BAB21486.1"/>
              </assert_contents>
            </output>
        </test>
    </tests>
    <help>

.. class:: warningmark

**Note**. Database searches may take a substantial amount of time.
For large input datasets it is advisable to allow overnight processing.

-----

**What it does**

Search a *protein database* using a *protein query*,
using the NCBI BLAST+ blastp command line tool.

The search can be performed using a local database, against a sequence supplied in a fasta file,
or the blast can be performed remotely at NCBI.

The remote operation allows searches to be targeted at specific organisms.

-----

**Output format**

Because Galaxy focuses on processing tabular data, the default output of this
tool is tabular. The standard BLAST+ tabular output contains 12 columns:

====== ========= ============================================
Column NCBI name Description
------ --------- --------------------------------------------
     1 qseqid    Query Seq-id (ID of your sequence)
     2 sseqid    Subject Seq-id (ID of the database hit)
     3 pident    Percentage of identical matches
     4 length    Alignment length
     5 mismatch  Number of mismatches
     6 gapopen   Number of gap openings
     7 qstart    Start of alignment in query
     8 qend      End of alignment in query
     9 sstart    Start of alignment in subject (database hit)
    10 send      End of alignment in subject (database hit)
    11 evalue    Expectation value (E-value)
    12 bitscore  Bit score
====== ========= ============================================

The BLAST+ tools can optionally output additional columns of information,
but this takes longer to calculate. Most (but not all) of these columns are
included by selecting the extended tabular output. The extra columns are
included *after* the standard 12 columns. This is so that you can write
workflow filtering steps that accept either the 12 or 24 column tabular
BLAST output.

====== ============= ===========================================
Column NCBI name     Description
------ ------------- -------------------------------------------
    13 sallseqid     All subject Seq-id(s), separated by a ';'
    14 score         Raw score
    15 nident        Number of identical matches
    16 positive      Number of positive-scoring matches
    17 gaps          Total number of gaps
    18 ppos          Percentage of positive-scoring matches
    19 qframe        Query frame
    20 sframe        Subject frame
    21 qseq          Aligned part of query sequence
    22 sseq          Aligned part of subject sequence
    23 qlen          Query sequence length
    24 slen          Subject sequence length
====== ============= ===========================================

The third option is BLAST XML output, which is designed to be parsed by
another program, and is understood by some Galaxy tools.

You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program).
The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website.
The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query.
The two query anchored outputs show a multiple sequence alignment between the query and all the matches,
and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences).

-------

**References**

Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402.

Schaffer et al. Improving the accuracy of PSI-BLAST protein database searches with composition-based statistics and other refinements. 2001. Nucleic Acids Res. 29:2994-3005.

    </help>
</tool>