comparison tools/ncbi_blast_plus/ncbi_blastdbcmd_wrapper.xml @ 22:6f386c5dc4fb draft

v0.2.01 add -max_hsps, -use_sw_tback; lists args; internal updates

21:7538e2bfcd41

    <macros>
        <token name="@BINARY@">blastdbcmd</token>
        <import>ncbi_macros.xml</import>
    </macros>
    <expand macro="preamble" />
    <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
blastdbcmd -dbtype $db_opts.db_type -db "${db_opts.database.fields.path}"

##TODO: What about -ctrl_a and -target_only as advanced options?

#if $id_opts.id_type=="file":
-entry_batch "$id_opts.entries"
#else:
##Perform some simple search/replaces to remove whitespace
##and make it comma separated. Quoted so don't escape pipes.
-entry "$id_opts.entries.replace('\r',',').replace('\n',',').replace(' ','').replace(',,',',').replace(',,',',').strip(',')"
#end if

##
##We remove the NCBI's lcl|... or gnl|BL_ORD_ID|123 prefixes
##using sed, however the exact syntax differs for Mac OS X's sed

#if str($outfmt)=="blastid":
-out "$seq"
#else if sys.platform == "darwin":
| sed -E 's/^>(lcl\||gnl\|BL_ORD_ID\|[0-9]* )/>/1' > "$seq"
#else:
| sed 's/>\(lcl|\|gnl|BL_ORD_ID|[0-9]* \)/>/1' > "$seq"
#end if
    </command>
    <inputs>
        <expand macro="input_conditional_choose_db_type" />
        <conditional name="id_opts">
            <param name="id_type" type="select" label="Type of identifier list">
              <option value="file">From file</option>
              <option value="prompt">User entered</option>
            </param>
            <when value="file">
                <param name="entries" type="data" format="txt,tabular" label="Sequence identifier(s)" help="Plain text file with one ID per line (i.e. single column tabular file)"/>
            </when>
            <when value="prompt">
                <param name="entries" type="text" label="Sequence identifier(s)" help="Comma or new line separated list." optional="False" area="True" size="10x30"/>
            </when>
        </conditional>
        <param name="outfmt" type="select" label="Output format">
          <option value="original">FASTA with original identifiers</option>
          <option value="blastid">FASTA with BLAST assigned identifiers</option>

            <param name="outfmt" value="original" />
            <output name="seq" file="rhodopsin_bufo.fasta" ftype="fasta" />
        </test>
    </tests>
    <help>
    
**What it does**

Extracts FASTA formatted sequences from a BLAST database
using the NCBI BLAST+ blastdbcmd command line tool.

If you use this Galaxy tool in work leading to a scientific publication please
cite the following papers:

@REFERENCES@
    </help>
    <expand macro="blast_citations" />    
</tool>

22:6f386c5dc4fb

    <macros>
        <token name="@BINARY@">blastdbcmd</token>
        <import>ncbi_macros.xml</import>
    </macros>
    <expand macro="preamble" />
    <command detect_errors="aggressive" strict="true">
## The command is a Cheetah template which allows some Python based syntax.
## Lines starting hash hash are comments. Galaxy will turn newlines into spaces
blastdbcmd -dbtype $db_opts.db_type -db "${db_opts.database.fields.path}"

##TODO: What about -ctrl_a and -target_only as advanced options?

#if $id_opts.id_type=="file":
-entry_batch '$id_opts.entries'
#else:
##Perform some simple search/replaces to remove whitespace
##and make it comma separated. Quoted so don't escape pipes.
-entry "$id_opts.entries.replace('\r',',').replace('\n',',').replace(' ','').replace(',,',',').replace(',,',',').strip(',')"
#end if

##
##We remove the NCBI's lcl|... or gnl|BL_ORD_ID|123 prefixes
##using sed, however the exact syntax differs for Mac OS X's sed

#if str($outfmt)=="blastid":
-out '$seq'
#else if sys.platform == "darwin":
| sed -E 's/^>(lcl\||gnl\|BL_ORD_ID\|[0-9]* )/>/1' > "$seq"
#else:
| sed 's/>\(lcl|\|gnl|BL_ORD_ID|[0-9]* \)/>/1' > "$seq"
#end if
    </command>
    <inputs>
        <expand macro="input_conditional_choose_db_type" />
        <conditional name="id_opts">
            <param name="id_type" type="select" label="Type of identifier list">
              <option value="file">From file</option>
              <option value="prompt">User entered</option>
            </param>
            <when value="file">
                <param name="entries" argument="-entry_batch" type="data" format="txt,tabular" label="Sequence identifier(s)" help="Plain text file with one ID per line (i.e. single column tabular file)"/>
            </when>
            <when value="prompt">
                <param name="entries" argument="-entry" type="text" optional="false" area="true" size="10x30" label="Sequence identifier(s)" help="Comma or new line separated list"/>
            </when>
        </conditional>
        <param name="outfmt" type="select" label="Output format">
          <option value="original">FASTA with original identifiers</option>
          <option value="blastid">FASTA with BLAST assigned identifiers</option>

            <param name="outfmt" value="original" />
            <output name="seq" file="rhodopsin_bufo.fasta" ftype="fasta" />
        </test>
    </tests>
    <help>

**What it does**

Extracts FASTA formatted sequences from a BLAST database
using the NCBI BLAST+ blastdbcmd command line tool.

If you use this Galaxy tool in work leading to a scientific publication please
cite the following papers:

@REFERENCES@
    </help>
    <expand macro="blast_citations" />
</tool>