Mercurial > repos > iuc > ncbi_entrez_direct_einfo
changeset 0:c66f2400ecf8 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ncbi_entrez_direct commit 8f96f378620bb663dcce2845ecb14355413f7afa"
| author | iuc |
|---|---|
| date | Tue, 22 Mar 2022 22:30:36 +0000 |
| parents | |
| children | c06dcadf986c |
| files | README.rst __efetch_build_options.py einfo.xml macros.xml |
| diffstat | 4 files changed, 448 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README.rst Tue Mar 22 22:30:36 2022 +0000 @@ -0,0 +1,17 @@ +Galaxy NCBI Entrez Direct Tools +=============================== + +This repo requires a readme as administrators should very aware of some +restrictions NCBI places on the use of the Entrez service. + +NCBI requests that you please limit large jobs to either weekends or +between 9:00 PM and 5:00 AM Eastern time during weekdays. This is not a +request that the Galaxy tool can easily service, so we've included it in +the disclaimer on every tool quite prominently. + +Failure to comply with NCBI's policies may result in an block. + +Note that these are *IP* level blocks so the Galaxy tools uses a +concatenation of the administrator's emails, and the user email, in +hopes that NCBI will contact all relevant parties should their system be +abused.
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/__efetch_build_options.py Tue Mar 22 22:30:36 2022 +0000 @@ -0,0 +1,225 @@ +#!/usr/bin/env python + +# Daniel Blankenberg +# Creates the options for tool interface + +# http://eutils.ncbi.nlm.nih.gov/entrez/eutils/einfo.fcgi +db_list = '''<DbName>pubmed</DbName> +<DbName>protein</DbName> +<DbName>nuccore</DbName> +<DbName>nucleotide</DbName> +<DbName>nucgss</DbName> +<DbName>nucest</DbName> +<DbName>structure</DbName> +<DbName>genome</DbName> +<DbName>annotinfo</DbName> +<DbName>assembly</DbName> +<DbName>bioproject</DbName> +<DbName>biosample</DbName> +<DbName>blastdbinfo</DbName> +<DbName>books</DbName> +<DbName>cdd</DbName> +<DbName>clinvar</DbName> +<DbName>clone</DbName> +<DbName>gap</DbName> +<DbName>gapplus</DbName> +<DbName>grasp</DbName> +<DbName>dbvar</DbName> +<DbName>gene</DbName> +<DbName>gds</DbName> +<DbName>geoprofiles</DbName> +<DbName>homologene</DbName> +<DbName>medgen</DbName> +<DbName>mesh</DbName> +<DbName>ncbisearch</DbName> +<DbName>nlmcatalog</DbName> +<DbName>omim</DbName> +<DbName>orgtrack</DbName> +<DbName>pmc</DbName> +<DbName>popset</DbName> +<DbName>probe</DbName> +<DbName>proteinclusters</DbName> +<DbName>pcassay</DbName> +<DbName>biosystems</DbName> +<DbName>pccompound</DbName> +<DbName>pcsubstance</DbName> +<DbName>pubmedhealth</DbName> +<DbName>seqannot</DbName> +<DbName>snp</DbName> +<DbName>sra</DbName> +<DbName>taxonomy</DbName> +<DbName>unigene</DbName> +<DbName>gencoll</DbName> +<DbName>gtr</DbName>'''.replace("<DbName>", "").replace("</DbName>", "").split("\n") + + +help = ''' (all) + docsum DocumentSummarySet XML + docsum json DocumentSummarySet JSON + full Same as native except for mesh + uid Unique Identifier List + url Entrez URL + xml Same as -format full -mode xml + + bioproject + native BioProject Report + native xml RecordSet XML + + biosample + native BioSample Report + native xml BioSampleSet XML + + biosystems + native xml Sys-set XML + + gds + native xml RecordSet XML + summary Summary + + gene + gene_table Gene Table + native Gene Report + native asn.1 Entrezgene ASN.1 + native xml Entrezgene-Set XML + tabular Tabular Report + + homologene + alignmentscores Alignment Scores + fasta FASTA + homologene Homologene Report + native Homologene List + native asn.1 HG-Entry ASN.1 + native xml Entrez-Homologene-Set XML + + mesh + full Full Record + native MeSH Report + native xml RecordSet XML + + nlmcatalog + native Full Record + native xml NLMCatalogRecordSet XML + + pmc + medline MEDLINE + native xml pmc-articleset XML + + pubmed + abstract Abstract + medline MEDLINE + native asn.1 Pubmed-entry ASN.1 + native xml PubmedArticleSet XML + + (sequences) + acc Accession Number + est EST Report + fasta FASTA + fasta xml TinySeq XML + fasta_cds_aa FASTA of CDS Products + fasta_cds_na FASTA of Coding Regions + ft Feature Table + gb GenBank Flatfile + gb xml GBSet XML + gbc xml INSDSet XML + gbwithparts GenBank with Contig Sequences + gene_fasta FASTA of Gene + gp GenPept Flatfile + gp xml GBSet XML + gpc xml INSDSet XML + gss GSS Report + ipg Identical Protein Report + ipg xml IPGReportSet XML + native text Seq-entry ASN.1 + native xml Bioseq-set XML + seqid Seq-id ASN.1 + + snp + chr Chromosome Report + docset Summary + fasta FASTA + flt Flat File + native asn.1 Rs ASN.1 + native xml ExchangeSet XML + rsr RS Cluster Report + ssexemplar SS Exemplar List + + sra + native xml EXPERIMENT_PACKAGE_SET XML + runinfo xml SraRunInfo XML + + structure + mmdb Ncbi-mime-asn1 strucseq ASN.1 + native MMDB Report + native xml RecordSet XML + + taxonomy + native Taxonomy List + native xml TaxaSet XML'''.split("\n") + +db = {} +name = None +all = "(all)" +for line in help: + if line.strip() and line[2] != ' ': + name = line.strip() + db[name] = {} + elif line.strip(): + format = line[0:len(" docsum ")].strip() + mode = line[len(" docsum "):len(" docsum json ")].strip() + if format not in db[name]: + db[name][format] = [] + db[name][format].append(mode) + +for name in db_list: + if name not in db: + db[name] = {} + +db["sequences"] = db["(sequences)"] +del db["(sequences)"] + +print('<conditional name="db">') +print(' <param name="db" type="select" label="Database" argument="-db">') +for name in sorted(db.keys()): + if name == all: + continue + print(' <option value="%s">%s</option>' % (name, name)) +print(' <option value="">Manual Entry</option>') +print(' </param>') + +for name in sorted(db.keys()): + if name == all: + continue + my_dict = db[all].copy() + + for format, modes in db[name].items(): + if format in my_dict: + for mode in modes: + if mode not in my_dict[format]: + my_dict[format].append(mode) + else: + my_dict[format] = modes + if "" not in my_dict: + my_dict[""] = [""] + print(' <when value="%s">' % name) + print(' <conditional name="format">') + print(' <param name="format" type="select" label="Format" argument="-format">') + for format in sorted(my_dict.keys()): + print(' <option value="%s">%s</option>' % (format, format or "None")) + print(' </param>') + for format in sorted(my_dict.keys()): + print(' <when value="%s">' % format) + print(' <param name="mode" type="select" label="Mode" argument="-mode">') + if "" not in my_dict[format]: + my_dict[format].append("") + for mode in sorted(my_dict[format]): + print(' <option value="%s">%s</option>' % (mode, mode or "None")) + print(' </param>') + print(' </when>') + print(' </conditional>') + print(' </when>') +print(' <when value="">') +print(' <param name="db_manual" type="text" label="Database" argument="-db"/>') +print(' <param name="format" type="text" label="Format" argument="-format"/>') +print(' <param name="mode" type="text" label="Mode" argument="-mode"/>') +print(' </when>') +print('</conditional>')
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/einfo.xml Tue Mar 22 22:30:36 2022 +0000 @@ -0,0 +1,104 @@ +<tool id="ncbi_entrez_direct_einfo" name="NCBI EInfo" version="@TOOL_VERSION@"> + <description>fetch NCBI database metadata</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <version_command>einfo -version</version_command> + <command detect_errors="exit_code"><![CDATA[ + @ECONTACT@ + einfo + #if str( $db.target ) == "dbs": + -dbs + #else: + -db "${db.db}" + #end if + > '${output_xml}' + ]]> +</command> + <inputs> + <conditional name="db"> + <param name="target" type="select" label="List DBs or Info on a DB"> + <option value="db" selected="True">DB info</option> + <option value="dbs">List of DBs</option> + </param> + <when value="dbs"/> + <when value="db"> + <param name="db" type="select" label="Choose your DB" argument="-db"> + <option value="annotinfo">annotinfo</option> + <option value="assembly">assembly</option> + <option value="bioproject">bioproject</option> + <option value="biosample">biosample</option> + <option value="biosystems">biosystems</option> + <option value="blastdbinfo">blastdbinfo</option> + <option value="books">books</option> + <option value="cdd">cdd</option> + <option value="clinvar">clinvar</option> + <option value="clone">clone</option> + <option value="dbvar">dbvar</option> + <option value="gap">gap</option> + <option value="gapplus">gapplus</option> + <option value="gds">gds</option> + <option value="gencoll">gencoll</option> + <option value="gene">gene</option> + <option value="genome">genome</option> + <option value="geoprofiles">geoprofiles</option> + <option value="grasp">grasp</option> + <option value="gtr">gtr</option> + <option value="homologene">homologene</option> + <option value="medgen">medgen</option> + <option value="mesh">mesh</option> + <option value="ncbisearch">ncbisearch</option> + <option value="nlmcatalog">nlmcatalog</option> + <option value="nuccore">nuccore</option> + <option value="nucest">nucest</option> + <option value="nucgss">nucgss</option> + <option value="nucleotide">nucleotide</option> + <option value="omim">omim</option> + <option value="orgtrack">orgtrack</option> + <option value="pcassay">pcassay</option> + <option value="pccompound">pccompound</option> + <option value="pcsubstance">pcsubstance</option> + <option value="pmc">pmc</option> + <option value="popset">popset</option> + <option value="probe">probe</option> + <option value="protein">protein</option> + <option value="proteinclusters">proteinclusters</option> + <option value="pubmed">pubmed</option> + <option value="pubmedhealth">pubmedhealth</option> + <option value="seqannot">seqannot</option> + <option value="snp">snp</option> + <option value="sra">sra</option> + <option value="structure">structure</option> + <option value="taxonomy">taxonomy</option> + <option value="unigene">unigene</option> + </param> + </when> + </conditional> + </inputs> + <outputs> + <data format="xml" name="output_xml"/> + </outputs> + <tests> + <test> + <param name="db|target" value="db"/> + <param name="db|db" value="sra"/> + <output name="output_xml"> + <assert_contents> + <has_text_matching expression="SRA" /> + </assert_contents> + </output> + </test> + </tests> + <help><![CDATA[ +NCBI Entrez EInfo +================= + +Provides the number of records indexed in each field of a given database, the +date of the last update of the database, and the available links from the +database to other Entrez databases. + +@DISCLAIMER@ + ]]></help> + <expand macro="citations"/> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Tue Mar 22 22:30:36 2022 +0000 @@ -0,0 +1,102 @@ +<macros> + <token name="@TOOL_VERSION@">13.3</token> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">entrez-direct</requirement> + </requirements> + </xml> + <token name="@ECONTACT@"><![CDATA[ + #set $__contact_email__ = ';'.join( str( $__admin_users__ ).split( ',' ) ) + #if str( $__user_email__ ): + #set $__contact_email__ = $__contact_email__ + ";" + str( $__user_email__ ) + #end if + econtact -email "${ __contact_email__ }" -tool "galaxy_ncbi_entrez_direct" > /dev/null ; + ]]> + </token> + <token name="@DISCLAIMER@"><![CDATA[ +Usage Guidelines and Requirements +================================= + +Frequency, Timing, and Registration of E-utility URL Requests +------------------------------------------------------------- + +In order not to overload the E-utility servers, NCBI recommends that users +limit large jobs to either weekends or between 9:00 PM and 5:00 AM Eastern time +during weekdays. Failure to comply with this policy may result in an IP address +being blocked from accessing NCBI. + +Minimizing the Number of Requests +--------------------------------- + +If a task requires searching for and/or downloading a large number of +records, it is much more efficient to use the Entrez History to upload +and/or retrieve these records in batches rather than using separate +requests for each record. Please refer to Application 3 in Chapter 3 +for an example. Many thousands of IDs can be uploaded using a single +EPost request, and several hundred records can be downloaded using one +EFetch request. + + +Disclaimer and Copyright Issues +------------------------------- + +In accordance with requirements of NCBI's E-Utilities, we must provide +the following disclaimer: + +Please note that abstracts in PubMed may incorporate material that may +be protected by U.S. and foreign copyright laws. All persons +reproducing, redistributing, or making commercial use of this +information are expected to adhere to the terms and conditions asserted +by the copyright holder. Transmission or reproduction of protected +items beyond that allowed by fair use (PDF) as defined in the copyright +laws requires the written permission of the copyright owners. NLM +provides no legal advice concerning distribution of copyrighted +materials. Please consult your legal counsel. If you wish to do a large +data mining project on PubMed data, you can enter into a licensing +agreement and lease the data for free from NLM. For more information on + +The `full disclaimer <https://www.ncbi.nlm.nih.gov/home/about/policies/>`__ is available on +their website + +Liability +~~~~~~~~~ + +For documents and software available from this server, the +U.S. Government does not warrant or assume any legal liability or +responsibility for the accuracy, completeness, or usefulness of any +information, apparatus, product, or process disclosed. + +Endorsement +~~~~~~~~~~~ + +NCBI does not endorse or recommend any commercial +products, processes, or services. The views and opinions of authors +expressed on NCBI's Web sites do not necessarily state or reflect those +of the U.S. Government, and they may not be used for advertising or +product endorsement purposes. + +External Links +~~~~~~~~~~~~~~ + +Some NCBI Web pages may provide links to other Internet +sites for the convenience of users. NCBI is not responsible for the +availability or content of these external sites, nor does NCBI endorse, +warrant, or guarantee the products, services, or information described +or offered at these other Internet sites. Users cannot assume that the +external sites will abide by the same Privacy Policy to which NCBI +adheres. It is the responsibility of the user to examine the copyright +and licensing restrictions of linked pages and to secure all necessary +permissions. + ]]></token> + <xml name="citations"> + <citations> + <citation type="bibtex">@Book{ncbiEDirect, + author = {Jonathan Kans}, + title = {Entrez Direct: E-utilities on the UNIX Command Line}, + year = {2013}, + publisher = {National Center for Biotechnology Information, Bethesda, Maryland}, + note = {http://www.ncbi.nlm.nih.gov/books/NBK179288/} + }</citation> + </citations> + </xml> +</macros>