annotate interproscan.xml @ 36:2201c5d61f16 draft default tip

planemo upload commit 16d0bc526ad02361a7c13231d4c50479c42d8d0f-dirty

<tool id="DInterproscan" name="Interproscan" version="1.0.0">
	<description>Interproscan annotation for SAPP</description>
	<requirements>
		<container type="docker">jjkoehorst/sappdocker:INTERPROSCAN</container>
	</requirements>
	<command interpreter="docker">java -jar /interproscan/interproscanRDF-0.0.1-SNAPSHOT-jar-with-dependencies.jar
		'-input' '$input' '-format' 'TURTLE'
		'-applications' '$appl'
		'-output'
		'$outfile' -v '$version' '$disable'
	</command>
	<inputs>
		<param format="ttl" label="genome rdf file with orf prediction" name="input" type="data"/>
		<param display="checkboxes" help="Select your programm." label="Applications to run" multiple="True" name="appl" type="select">
			<option selected="true" value="TIGRFAM">TIGRFAM: protein families
				based on Hidden Markov Models or HMMs
			</option>
			<option selected="false" value="PIRSF">PIRSF: non-overlapping
				clustering of UniProtKB sequences into a hierarchical order
				(evolutionary relationships)
			</option>
			<option selected="true" value="ProDom">ProDom: set of protein domain
				families generated from the UniProtKB
			</option>
			<option selected="true" value="SMART">SMART: identification and
				analysis of domain architectures based on Hidden Markov Models or
				HMMs
			</option>
			<option selected="false" value="PrositeProfiles">PROSITE Profiles:
				protein domains, families and functional sites as well as associated
				profiles to identify them
			</option>
			<option selected="true" value="PrositePatterns">PROSITE Pattern:
				protein domains, families and functional sites as well as associated
				patterns to identify them
			</option>
			<option selected="false" value="HAMAP">HAMAP: High-quality Automated
				Annotation of Microbial Proteomes
			</option>
			<option selected="true" value="PfamA">PfamA: protein families, each
				represented by multiple sequence alignments and hidden Markov models
			</option>
			<option selected="true" value="PRINTS">PRINTS: group of conserved
				motifs (fingerprints) used to characterise a protein family
			</option>
			<option selected="true" value="SuperFamily">SUPERFAMILY: database of
				structural and functional annotation
			</option>
			<option selected="true" value="Coils">Coils: Prediction of Coiled
				Coil Regions in Proteins
			</option>
			<option selected="true" value="Gene3d">Gene3d: Structural assignment
				for whole genes and genomes using the CATH domain structure database
			</option>
		</param>
		<param label="Version selection" name="version" type="select">
			<option value="interproscan-5.17-56.0">interproscan-5.17-56.0</option>
		</param>
		<param checked="false" falsevalue="-disableprecalc" help="You need to setup your own lookup server as the EBI version can differ. Look at interproscan configuration file for more info" label="Perform lookup of InterPro at defined server address" name="disable" truevalue="" type="boolean"/>
	</inputs>
	<outputs>
		<data format="ttl" label="IPR: ${input.name}" name="outfile"/>
	</outputs>
	<help>Interproscan annotation suite. Select your RDF genome with
		protein annotation.
		This can be either from a converted GenBank/EMBL
		file or from a
		Prodigal prediction.
		The output will be an RDF file with
		protein domain annotation from
		InterPro.
	</help>
	<citations>
		<citation type="bibtex">@article{Mitchell26112014,
			author = {Mitchell,
			Alex and Chang, Hsin-Yu and Daugherty, Louise and
			Fraser, Matthew and
			Hunter, Sarah and Lopez, Rodrigo and McAnulla,
			Craig and McMenamin,
			Conor and Nuka, Gift and Pesseat, Sebastien and
			Sangrador-Vegas, Amaia
			and Scheremetjew, Maxim and Rato, Claudia and
			Yong, Siew-Yit and
			Bateman, Alex and Punta, Marco and Attwood, Teresa
			K. and Sigrist,
			Christian J.A. and Redaschi, Nicole and Rivoire,
			Catherine and
			Xenarios, Ioannis and Kahn, Daniel and Guyot, Dominique
			and Bork, Peer
			and Letunic, Ivica and Gough, Julian and Oates, Matt
			and Haft, Daniel
			and Huang, Hongzhan and Natale, Darren A. and Wu,
			Cathy H. and Orengo,
			Christine and Sillitoe, Ian and Mi, Huaiyu and
			Thomas, Paul D. and
			Finn, Robert D.},
			title = {The InterPro protein families database: the
			classification
			resource after 15 years},
			year = {2014},
			doi =
			{10.1093/nar/gku1243},
			abstract ={The InterPro database
			(http://www.ebi.ac.uk/interpro/) is a freely
			available resource that
			can be used to classify sequences into
			protein families and to predict
			the presence of important domains and
			sites. Central to the InterPro
			database are predictive models, known
			as signatures, from a range of
			different protein family databases
			that have different biological
			focuses and use different
			methodological approaches to classify
			protein families and domains.
			InterPro integrates these signatures,
			capitalizing on the respective
			strengths of the individual databases,
			to produce a powerful protein
			classification resource. Here, we report
			on the status of InterPro as
			it enters its 15th year of operation, and
			give an overview of new
			developments with the database and its
			associated Web interfaces and
			software. In particular, the new domain
			architecture search tool is
			described and the process of mapping of
			Gene Ontology terms to
			InterPro is outlined. We also discuss the
			challenges faced by the
			resource given the explosive growth in
			sequence data in recent years.
			InterPro (version 48.0) contains 36 766
			member database signatures
			integrated into 26 238 InterPro entries, an
			increase of over 3993
			entries (5081 signatures), since 2012.},
			URL =
			{http://nar.oxfordjournals.org/content/early/2014/11/26/nar.gku1243.abstract},
			eprint =
			{http://nar.oxfordjournals.org/content/early/2014/11/26/nar.gku1243.full.pdf+html},
			journal = {Nucleic Acids Research}
			}
		</citation>
	</citations>
</tool>