Skip to content

Commit

Permalink
Add genomes on server functionality
Browse files Browse the repository at this point in the history
  • Loading branch information
@elischberg
elischberg committed Feb 6, 2024
1 parent 2dd12dc commit 529458c
Showing 1 changed file with 140 additions and 123 deletions.
263 changes: 140 additions & 123 deletions tools/ncbi_blast_plus/ncbi_makeblastdb.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,14 +17,19 @@ python $__tool_directory__/check_no_duplicates.py
##makeblastdb -in <(gunzip -c gzipped_fasta_file)
##therefore we're cramming everything
##into a single cat command below
cat
#for i in $input_file:
#if $i.is_of_type('fasta.gz') and $i.ext != "fasta":
<(gunzip -c ${i})
#else:
${i}
#end if
#end for
## insert genome on server - option
#if str($input_selection.source) == "history":
cat
#for i in $input_file:
#if $i.is_of_type('fasta.gz') and $i.ext != "fasta":
<(gunzip -c ${i})
#else:
${i}
#end if
#end for
#else:
'$input_selection.ifile.fields.path'
#end if
| makeblastdb -out '${os.path.join($outfile.files_path, "blastdb")}'
-blastdb_version 4
$parse_seqids
Expand Down Expand Up @@ -60,52 +65,64 @@ $hash_index
> '$outfile'
]]></command>
<inputs>
<param argument="-dbtype" type="select" display="radio" label="Molecule type of input">
<option value="prot">protein</option>
<option value="nucl">nucleotide</option>
<param argument="-dbtype" type="select" display="radio" label="Molecule type of input">
<option value="prot">protein</option>
<option value="nucl">nucleotide</option>
</param>
<!-- TODO Allow merging of existing BLAST databases (conditional on the database type)?
NOTE Double check the new database would be self contained first
-->
<!-- Note this is a mandatory parameter - default should be most recent FASTA file -->
<conditional name="input_selection">
<param name="source" type="select" label="Input is a">
<option value="history">Dataset in history</option>
<option value="cached">Genome on server</option>
</param>
<!-- TODO Allow merging of existing BLAST databases (conditional on the database type)?
NOTE Double check the new database would be self contained first
-->
<!-- Note this is a mandatory parameter - default should be most recent FASTA file -->
<param name="input_file" argument="-in" type="data" multiple="true" optional="false" format="fasta,fasta.gz" label="Input FASTA files(s)" help="One or more FASTA files" />
<param argument="-title" type="text" value="" label="Title for BLAST database" help="This is the database name shown in BLAST search output" />
<param argument="-parse_seqids" type="boolean" truevalue="-parse_seqids" falsevalue="" checked="false" label="Parse the sequence identifiers" help="This is only advised if your FASTA file follows the NCBI naming conventions using pipe '|' symbols" />
<param argument="-hash_index" type="boolean" truevalue="-hash_index" falsevalue="" checked="true" label="Enable the creation of sequence hash values" help="These hash values can then be used to quickly determine if a given sequence data exists in this BLAST database." />
<!-- SEQUENCE MASKING OPTIONS -->
<!-- Note this is an optional parameter - default should be NO files -->
<param name="mask_data_file" argument="-mask_data" type="data" multiple="true" optional="true" value="" format="maskinfo-asn1,maskinfo-asn1-binary" label="Optional ASN.1 file(s) containing masking data" help="As produced by NCBI masking applications (e.g. dustmasker, segmasker, windowmasker)" />
<!-- TODO - Option to create GI indexed masking data? via -gi_mask and -gi_mask_name? -->
<!-- TAXONOMY OPTIONS -->
<conditional name="tax">
<param name="taxselect" type="select" label="Taxonomy options">
<option value="">Do not assign a Taxonomy ID to the sequences</option>
<option value="id">Assign the same Taxonomy ID to all the sequences</option>
<!--
<option value="map">Supply text file mapping sequence IDs to taxnomy IDs</option>
TODO - Can we use a tabular file for the taxonomy mapping?
-->
</param>
<when value="">
</when>
<when value="id">
<param argument="-taxid" type="integer" min="0" value="" label="NCBI taxonomy ID" help="Integer &gt;=0, e.g. 9606 for Homo sapiens" />
</when>
<!-- TODO: File format?
<when value="map">
<param name="taxmap" argument="-taxid_map" type="data" format="txt" label="Seq ID : Tax ID mapping file" help="Format: SequenceId TaxonomyId" />
</when>
-->
</conditional>
<when value="history">
<param name="input_file" argument="-in" type="data" multiple="true" optional="false" format="fasta,fasta.gz" label="Input FASTA files(s)" help="One or more FASTA files" />
</when>
<when value="cached">
<param name="ifile" type="select" label="installed genome">
<options from_data_table="all_fasta"/>
</param>
</when>
</conditional>
<param argument="-title" type="text" value="" label="Title for BLAST database" help="This is the database name shown in BLAST search output" />
<param argument="-parse_seqids" type="boolean" truevalue="-parse_seqids" falsevalue="" checked="false" label="Parse the sequence identifiers" help="This is only advised if your FASTA file follows the NCBI naming conventions using pipe '|' symbols" />
<param argument="-hash_index" type="boolean" truevalue="-hash_index" falsevalue="" checked="true" label="Enable the creation of sequence hash values" help="These hash values can then be used to quickly determine if a given sequence data exists in this BLAST database." />
<!-- SEQUENCE MASKING OPTIONS -->
<!-- Note this is an optional parameter - default should be NO files -->
<param name="mask_data_file" argument="-mask_data" type="data" multiple="true" optional="true" value="" format="maskinfo-asn1,maskinfo-asn1-binary" label="Optional ASN.1 file(s) containing masking data" help="As produced by NCBI masking applications (e.g. dustmasker, segmasker, windowmasker)" />
<!-- TODO - Option to create GI indexed masking data? via -gi_mask and -gi_mask_name? -->
<!-- TAXONOMY OPTIONS -->
<conditional name="tax">
<param name="taxselect" type="select" label="Taxonomy options">
<option value="">Do not assign a Taxonomy ID to the sequences</option>
<option value="id">Assign the same Taxonomy ID to all the sequences</option>
<!--
<option value="map">Supply text file mapping sequence IDs to taxnomy IDs</option>
TODO - Can we use a tabular file for the taxonomy mapping?
-->
</param>
<when value=""/>
<when value="id">
<param argument="-taxid" type="integer" min="0" value="" label="NCBI taxonomy ID" help="Integer &gt;=0, e.g. 9606 for Homo sapiens" />
</when>
<!-- TODO: File format?
<when value="map">
<param name="taxmap" argument="-taxid_map" type="data" format="txt" label="Seq ID : Tax ID mapping file" help="Format: SequenceId TaxonomyId" />
</when>
-->
</conditional>
</inputs>
<outputs>
<!-- If we only accepted one FASTA file, we could use its human name here... -->
<data name="outfile" format="data" label="${dbtype.value_label} BLAST database from ${on_string}">
<change_format>
<when input="dbtype" value="nucl" format="blastdbn" />
<when input="dbtype" value="prot" format="blastdbp" />
</change_format>
</data>
<data name="outfile" format="data" label="${dbtype.value_label} BLAST database from ${on_string}">
<change_format>
<when input="dbtype" value="nucl" format="blastdbn" />
<when input="dbtype" value="prot" format="blastdbp" />
</change_format>
</data>
</outputs>
<tests>
<!-- Note the (two line) PIN file is not reproducible run to run.
Expand All @@ -114,79 +131,79 @@ $hash_index
With and without the masking makes no difference.
With and without the taxid the only real difference is in the *.phr file.
-->
<test>
<param name="dbtype" value="prot" />
<param name="input_file" value="four_human_proteins.fasta" ftype="fasta" />
<param name="title" value="Just 4 human proteins" />
<param name="parse_seqids" value="" />
<param name="hash_index" value="true" />
<output name="outfile" compare="contains" file="four_human_proteins.fasta.log.txt" ftype="blastdbp">
<extra_files type="file" value="four_human_proteins.fasta.phr" name="blastdb.phr" />
<extra_files type="file" value="four_human_proteins.fasta.pin" name="blastdb.pin" compare="sim_size" delta="0" />
<extra_files type="file" value="four_human_proteins.fasta.psq" name="blastdb.psq" />
<extra_files type="file" value="four_human_proteins.fasta.pog" name="blastdb.pog" />
<extra_files type="file" value="four_human_proteins.fasta.phd" name="blastdb.phd" />
<extra_files type="file" value="four_human_proteins.fasta.phi" name="blastdb.phi" />
<extra_files type="file" value="four_human_proteins.fasta.psd" name="blastdb.psd" />
<extra_files type="file" value="four_human_proteins.fasta.psi" name="blastdb.psi" />
</output>
</test>
<test>
<param name="dbtype" value="prot" />
<param name="input_file" value="four_human_proteins.fasta" ftype="fasta" />
<param name="title" value="Just 4 human proteins" />
<param name="parse_seqids" value="" />
<param name="hash_index" value="true" />
<param name="taxselect" value="id" />
<param name="taxid" value="9606" />
<output name="outfile" compare="contains" file="four_human_proteins_taxid.fasta.log.txt" ftype="blastdbp">
<extra_files type="file" value="four_human_proteins_taxid.fasta.phr" name="blastdb.phr" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.pin" name="blastdb.pin" compare="sim_size" delta="0" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.psq" name="blastdb.psq" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.pog" name="blastdb.pog" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.phd" name="blastdb.phd" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.phi" name="blastdb.phi" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.psd" name="blastdb.psd" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.psi" name="blastdb.psi" />
</output>
</test>
<test>
<param name="dbtype" value="prot" />
<param name="input_file" value="four_human_proteins.fasta" ftype="fasta" />
<param name="title" value="Just 4 human proteins" />
<param name="parse_seqids" value="" />
<param name="hash_index" value="true" />
<param name="mask_data_file" value="segmasker_four_human.maskinfo-asn1" ftype="maskinfo-asn1" />
<output name="outfile" compare="contains" file="four_human_proteins.fasta.log.txt" ftype="blastdbp">
<extra_files type="file" value="four_human_proteins.fasta.phr" name="blastdb.phr" />
<extra_files type="file" value="four_human_proteins.fasta.pin" name="blastdb.pin" compare="sim_size" delta="0" />
<extra_files type="file" value="four_human_proteins.fasta.psq" name="blastdb.psq" />
<extra_files type="file" value="four_human_proteins.fasta.pog" name="blastdb.pog" />
<extra_files type="file" value="four_human_proteins.fasta.phd" name="blastdb.phd" />
<extra_files type="file" value="four_human_proteins.fasta.phi" name="blastdb.phi" />
<extra_files type="file" value="four_human_proteins.fasta.psd" name="blastdb.psd" />
<extra_files type="file" value="four_human_proteins.fasta.psi" name="blastdb.psi" />
</output>
</test>
<test>
<param name="dbtype" value="nucl" />
<param name="input_file" value="three_human_mRNA.fasta.gz" ftype="fasta.gz" />
<param name="title" value="Just 3 human mRNA sequences" />
<param name="parse_seqids" value="" />
<param name="hash_index" value="true" />
<param name="taxselect" value="id" />
<param name="taxid" value="9606" />
<output name="outfile" compare="contains" file="three_human_mRNA.fasta.log.txt" ftype="blastdbn">
<extra_files type="file" value="three_human_mRNA.fasta.nhr" name="blastdb.nhr" />
<extra_files type="file" value="three_human_mRNA.fasta.nin" name="blastdb.nin" compare="sim_size" delta="8" />
<extra_files type="file" value="three_human_mRNA.fasta.nsq" name="blastdb.nsq" />
<extra_files type="file" value="three_human_mRNA.fasta.nog" name="blastdb.nog" />
<extra_files type="file" value="three_human_mRNA.fasta.nhd" name="blastdb.nhd" />
<extra_files type="file" value="three_human_mRNA.fasta.nhi" name="blastdb.nhi" />
<extra_files type="file" value="three_human_mRNA.fasta.nsd" name="blastdb.nsd" />
<extra_files type="file" value="three_human_mRNA.fasta.nsi" name="blastdb.nsi" />
</output>
</test>
<test>
<param name="dbtype" value="prot" />
<param name="input_file" value="four_human_proteins.fasta" ftype="fasta" />
<param name="title" value="Just 4 human proteins" />
<param name="parse_seqids" value="" />
<param name="hash_index" value="true" />
<output name="outfile" compare="contains" file="four_human_proteins.fasta.log.txt" ftype="blastdbp">
<extra_files type="file" value="four_human_proteins.fasta.phr" name="blastdb.phr" />
<extra_files type="file" value="four_human_proteins.fasta.pin" name="blastdb.pin" compare="sim_size" delta="0" />
<extra_files type="file" value="four_human_proteins.fasta.psq" name="blastdb.psq" />
<extra_files type="file" value="four_human_proteins.fasta.pog" name="blastdb.pog" />
<extra_files type="file" value="four_human_proteins.fasta.phd" name="blastdb.phd" />
<extra_files type="file" value="four_human_proteins.fasta.phi" name="blastdb.phi" />
<extra_files type="file" value="four_human_proteins.fasta.psd" name="blastdb.psd" />
<extra_files type="file" value="four_human_proteins.fasta.psi" name="blastdb.psi" />
</output>
</test>
<test>
<param name="dbtype" value="prot" />
<param name="input_file" value="four_human_proteins.fasta" ftype="fasta" />
<param name="title" value="Just 4 human proteins" />
<param name="parse_seqids" value="" />
<param name="hash_index" value="true" />
<param name="taxselect" value="id" />
<param name="taxid" value="9606" />
<output name="outfile" compare="contains" file="four_human_proteins_taxid.fasta.log.txt" ftype="blastdbp">
<extra_files type="file" value="four_human_proteins_taxid.fasta.phr" name="blastdb.phr" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.pin" name="blastdb.pin" compare="sim_size" delta="0" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.psq" name="blastdb.psq" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.pog" name="blastdb.pog" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.phd" name="blastdb.phd" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.phi" name="blastdb.phi" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.psd" name="blastdb.psd" />
<extra_files type="file" value="four_human_proteins_taxid.fasta.psi" name="blastdb.psi" />
</output>
</test>
<test>
<param name="dbtype" value="prot" />
<param name="input_file" value="four_human_proteins.fasta" ftype="fasta" />
<param name="title" value="Just 4 human proteins" />
<param name="parse_seqids" value="" />
<param name="hash_index" value="true" />
<param name="mask_data_file" value="segmasker_four_human.maskinfo-asn1" ftype="maskinfo-asn1" />
<output name="outfile" compare="contains" file="four_human_proteins.fasta.log.txt" ftype="blastdbp">
<extra_files type="file" value="four_human_proteins.fasta.phr" name="blastdb.phr" />
<extra_files type="file" value="four_human_proteins.fasta.pin" name="blastdb.pin" compare="sim_size" delta="0" />
<extra_files type="file" value="four_human_proteins.fasta.psq" name="blastdb.psq" />
<extra_files type="file" value="four_human_proteins.fasta.pog" name="blastdb.pog" />
<extra_files type="file" value="four_human_proteins.fasta.phd" name="blastdb.phd" />
<extra_files type="file" value="four_human_proteins.fasta.phi" name="blastdb.phi" />
<extra_files type="file" value="four_human_proteins.fasta.psd" name="blastdb.psd" />
<extra_files type="file" value="four_human_proteins.fasta.psi" name="blastdb.psi" />
</output>
</test>
<test>
<param name="dbtype" value="nucl" />
<param name="input_file" value="three_human_mRNA.fasta.gz" ftype="fasta.gz" />
<param name="title" value="Just 3 human mRNA sequences" />
<param name="parse_seqids" value="" />
<param name="hash_index" value="true" />
<param name="taxselect" value="id" />
<param name="taxid" value="9606" />
<output name="outfile" compare="contains" file="three_human_mRNA.fasta.log.txt" ftype="blastdbn">
<extra_files type="file" value="three_human_mRNA.fasta.nhr" name="blastdb.nhr" />
<extra_files type="file" value="three_human_mRNA.fasta.nin" name="blastdb.nin" compare="sim_size" delta="8" />
<extra_files type="file" value="three_human_mRNA.fasta.nsq" name="blastdb.nsq" />
<extra_files type="file" value="three_human_mRNA.fasta.nog" name="blastdb.nog" />
<extra_files type="file" value="three_human_mRNA.fasta.nhd" name="blastdb.nhd" />
<extra_files type="file" value="three_human_mRNA.fasta.nhi" name="blastdb.nhi" />
<extra_files type="file" value="three_human_mRNA.fasta.nsd" name="blastdb.nsd" />
<extra_files type="file" value="three_human_mRNA.fasta.nsi" name="blastdb.nsi" />
</output>
</test>
</tests>
<help>
**What it does**
Expand Down

0 comments on commit 529458c

Please sign in to comment.