Mercurial > repos > rnateam > aresite2
changeset 0:6d3269dc319e draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/rna_tools/aresite2 commit f437f5e8c6c856c6f0bb8d8ea6e34f5441ee088f
| author | rnateam |
|---|---|
| date | Thu, 02 Feb 2017 19:33:27 -0500 |
| parents | |
| children | 138ff4068d27 |
| files | aresite2.py aresite2.xml test-data/AREsite2_Rest_ATTTA_cxcl2_Homo_sapiens.bed |
| diffstat | 3 files changed, 177 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/aresite2.py Thu Feb 02 19:33:27 2017 -0500 @@ -0,0 +1,113 @@ +# A simple tool to connect to the AREsite server and retrieve feature +# information using the AREsite REST Interface. +# Parts of this code are from https://toolshed.g2.bx.psu.edu/repos/earlhaminst/ensembl_get_feature_info +import json +import optparse +import sys +import urllib.request, urllib.parse, urllib.error +import urllib.request, urllib.error, urllib.parse +import time +import requests +from six.moves.urllib.parse import urljoin + +usage = "usage: %prog [options] arg1 arg2" +parser = optparse.OptionParser(usage=usage) +parser.add_option('-g', '--gene', help='Gene ID to search for') +parser.add_option('-m', '--motif', help='Motif to look for', default='ATTTA', type=str) +parser.add_option('-s', '--species', type='choice', + choices=['Homo_sapiens', 'Mus_musculus', 'Danio_rerio', 'Drosophila_melanogaster', 'Caenorhabditis_elegans'], default='Homo_sapiens', + help='Specify the species to investigate') +options, args = parser.parse_args() + +if options.gene is None: + raise Exception('- Specify the gene you want to look for!') + +if "," in options.motif : + raise Exception('- Please only search for single motifs at once') + +class AREsiteRestClient(object): + def __init__(self, server='http://rna.tbi.univie.ac.at/AREsite2/api/', reqs_per_sec=1): + self.server = server + self.reqs_per_sec = reqs_per_sec + self.req_count = 0 + self.last_req = 0 + + def perform_rest_action(self, endpoint, hdrs=None, params=None): + if hdrs is None: + hdrs = {} + + if 'Content-Type' not in hdrs: + hdrs['Content-Type'] = 'application/json' + + if params: + endpoint += '?' + urllib.parse.urlencode(params) + + data = None + + # check if we need to rate limit ourselves + if self.req_count >= self.reqs_per_sec: + delta = time.time() - self.last_req + if delta < 1: + time.sleep(1 - delta) + self.last_req = time.time() + self.req_count = 0 + + try: + request = urllib.request.Request(self.server + endpoint, headers=hdrs) + response = urllib.request.urlopen(request) + content = response.read().decode('utf-8') + if content: + data = json.loads(content) + self.req_count += 1 + + except urllib2.HTTPError as e: + # check if we are being rate limited by the server + if e.code == 429: + if 'Retry-After' in e.headers: + retry = e.headers['Retry-After'] + time.sleep(float(retry)) + self.perform_rest_action(endpoint, hdrs, params) + else: + sys.stderr.write('Request failed for {0}: Status code: {1.code} Reason: {1.reason}\n'.format(endpoint, e)) + + return data + + def get_motifs(self, species, gene, motifs): + query = str('?query={0}&species={1}&list={2}'.format(gene, species, motifs)) + if query: + aresite = self.perform_rest_action( + query + ) + return aresite + return None + +def run(species, gene, motifs): + client = AREsiteRestClient() + aresite = client.get_motifs(species, gene, motifs) + if aresite: + + mots = aresite["exact_motifs"] + starts = aresite["motif_starts"] + ends = aresite["motif_ends"] + chrs = aresite["chromosomes"] + strands = aresite["strands"] + transcripts = aresite["transcripts"] + genes = aresite["genes"] + evh = aresite["hur_evidence"] + evt = aresite["ttp_evidence"] + eva = aresite["auf_evidence"] + anno = aresite["annotation"] + + aresite = zip(chrs,starts,ends,mots,anno,strands,genes,transcripts,evh,evt,eva) + + def getKey(item): + return item[1] + + aresite = sorted(aresite, key=getKey) + + for site in aresite: + print("\t".join(site)) + + +if __name__ == '__main__': + run(options.species, options.gene, options.motif)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/aresite2.xml Thu Feb 02 19:33:27 2017 -0500 @@ -0,0 +1,53 @@ +<tool id="AREsite2_REST" name="Get motifs from AREsite2" version="0.1.2"> + <description>AREsite2 REST Interface</description> + <requirements> + <requirement type="package" version="2.12.4">requests</requirement> + <requirement type="package" version="1.10.0">six</requirement> + </requirements> + <command> +<![CDATA[ +python '$__tool_directory__/aresite2.py' +-g '$gene' +-m '$motif' +-s '$species_selector' +> '$AREsite2_REST_out' +]]> + </command> + + <inputs> + <param name="gene" type="text" label="Gene ID to search for" help="Try e.g. cxcl2" /> + <param name="species_selector" type="select" label="Select species"> + <option value="Homo_sapiens" selected="true"></option> + <option value="Mus_musculus"></option> + <option value="Danio_rerio"></option> + <option value="Drosophila_melanogaster"></option> + <option value="Caenorhabditis_elegans"></option> + </param> + <param name="motif" type="text" label="Motif to search for" help="Choose a single motif, e.g. ATTTA" /> + </inputs> + + <outputs> + <data name="AREsite2_REST_out" label="AREsite2_Rest_${motif}_${gene}_${species_selector}" format="bed" /> + </outputs> + + <tests> + <test> + <param name="species" value="Homo_sapiens" /> + <param name="motif" value="ATTTA" /> + <param name="gene" value="Cxcl2" /> + <output name="outputFile" file="AREsite2_Rest_ATTTA_cxcl2_Homo_sapiens.bed" /> + </test> + </tests> + + <help> +<![CDATA[ +**What it does** + +Retrieve motif information in BED format from AREsite2 using its REST API. + +]]> + </help> + <citations> + <citation type="doi">10.1093/nar/gkv1238</citation> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/AREsite2_Rest_ATTTA_cxcl2_Homo_sapiens.bed Thu Feb 02 19:33:27 2017 -0500 @@ -0,0 +1,11 @@ +chr4 74097045 74097050 ATTTA Exon^3UTR - ENSG00000081041 ENST00000508487 NA NA NA +chr4 74097083 74097088 ATTTA Exon^3UTR - ENSG00000081041 ENST00000508487 NA NA NA +chr4 74097257 74097262 ATTTA Exon^3UTR - ENSG00000081041 ENST00000508487 NA NA NA +chr4 74097449 74097454 ATTTA Exon^3UTR - ENSG00000081041 ENST00000508487 NA NA NA +chr4 74097499 74097504 ATTTA Exon^3UTR - ENSG00000081041 ENST00000508487 NA <a href="http://www.genomebiology.com/content/supplementary/gb-2014-15-1-r12-s2.csv">http://www.genomebiology.com/content/supplementary/gb-2014-15-1-r12-s2.csv</a> NA +chr4 74097589 74097594 ATTTA Exon^3UTR - ENSG00000081041 ENST00000508487 NA NA NA +chr4 74097593 74097598 ATTTA Exon^3UTR - ENSG00000081041 ENST00000508487 NA NA NA +chr4 74097597 74097602 ATTTA Exon^3UTR - ENSG00000081041 ENST00000508487 NA NA NA +chr4 74097601 74097606 ATTTA Exon^3UTR - ENSG00000081041 ENST00000508487 NA NA NA +chr4 74097605 74097610 ATTTA Exon^3UTR - ENSG00000081041 ENST00000508487 NA NA NA +chr4 74098127 74098132 ATTTA Intron^CDS - ENSG00000081041 ENST00000508487 NA NA NA