Mercurial > repos > jjohnson > ensembl_cdna_translate
changeset 0:a8218b11216f draft
Uploaded
| author | jjohnson |
|---|---|
| date | Wed, 29 Nov 2017 15:55:59 -0500 |
| parents | |
| children | 0f70b1b92161 |
| files | ._ensembl_cdna_translate.py ._ensembl_cdna_translate.xml digest.py ensembl_cdna_translate.py ensembl_cdna_translate.xml test-data/human_transcripts.bed |
| diffstat | 6 files changed, 851 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/digest.py Wed Nov 29 15:55:59 2017 -0500 @@ -0,0 +1,158 @@ +# Copyright 2012 Anton Goloborodko, Lev Levitsky +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import re +from collections import deque +import itertools as it + +def cleave(sequence, rule, missed_cleavages=0, min_length=None): + """Cleaves a polypeptide sequence using a given rule. + + Parameters + ---------- + sequence : str + The sequence of a polypeptide. + + .. note:: + The sequence is expected to be in one-letter uppercase notation. + Otherwise, some of the cleavage rules in :py:data:`expasy_rules` + will not work as expected. + + rule : str or compiled regex + A regular expression describing the site of cleavage. It is recommended + to design the regex so that it matches only the residue whose C-terminal + bond is to be cleaved. All additional requirements should be specified + using `lookaround assertions + <http://www.regular-expressions.info/lookaround.html>`_. + :py:data:`expasy_rules` contains cleavage rules for popular cleavage agents. + missed_cleavages : int, optional + Maximum number of allowed missed cleavages. Defaults to 0. + min_length : int or None, optional + Minimum peptide length. Defaults to :py:const:`None`. + + ..note :: + This checks for string length, which is only correct for one-letter + notation and not for full *modX*. Use :py:func:`length` manually if + you know what you are doing and apply :py:func:`cleave` to *modX* + sequences. + + Returns + ------- + out : set + A set of unique (!) peptides. + + Examples + -------- + >>> cleave('AKAKBK', expasy_rules['trypsin'], 0) == {'AK', 'BK'} + True + >>> cleave('GKGKYKCK', expasy_rules['trypsin'], 2) == \ + {'CK', 'GKYK', 'YKCK', 'GKGK', 'GKYKCK', 'GK', 'GKGKYK', 'YK'} + True + + """ + return set(_cleave(sequence, rule, missed_cleavages, min_length)) + +def _cleave(sequence, rule, missed_cleavages=0, min_length=None): + """Like :py:func:`cleave`, but the result is a list. Refer to + :py:func:`cleave` for explanation of parameters. + """ + peptides = [] + ml = missed_cleavages+2 + trange = range(ml) + cleavage_sites = deque([0], maxlen=ml) + cl = 1 + for i in it.chain([x.end() for x in re.finditer(rule, sequence)], + [None]): + cleavage_sites.append(i) + if cl < ml: + cl += 1 + for j in trange[:cl-1]: + seq = sequence[cleavage_sites[j]:cleavage_sites[-1]] + if seq: + if min_length is None or len(seq) >= min_length: + peptides.append(seq) + return peptides + +def num_sites(sequence, rule, **kwargs): + """Count the number of sites where `sequence` can be cleaved using + the given `rule` (e.g. number of miscleavages for a peptide). + + Parameters + ---------- + sequence : str + The sequence of a polypeptide. + rule : str or compiled regex + A regular expression describing the site of cleavage. It is recommended + to design the regex so that it matches only the residue whose C-terminal + bond is to be cleaved. All additional requirements should be specified + using `lookaround assertions + <http://www.regular-expressions.info/lookaround.html>`_. + labels : list, optional + A list of allowed labels for amino acids and terminal modifications. + + Returns + ------- + out : int + Number of cleavage sites. + """ + return len(_cleave(sequence, rule, **kwargs)) - 1 + +expasy_rules = { + 'arg-c': r'R', + 'asp-n': r'\w(?=D)', + 'bnps-skatole' : r'W', + 'caspase 1': r'(?<=[FWYL]\w[HAT])D(?=[^PEDQKR])', + 'caspase 2': r'(?<=DVA)D(?=[^PEDQKR])', + 'caspase 3': r'(?<=DMQ)D(?=[^PEDQKR])', + 'caspase 4': r'(?<=LEV)D(?=[^PEDQKR])', + 'caspase 5': r'(?<=[LW]EH)D', + 'caspase 6': r'(?<=VE[HI])D(?=[^PEDQKR])', + 'caspase 7': r'(?<=DEV)D(?=[^PEDQKR])', + 'caspase 8': r'(?<=[IL]ET)D(?=[^PEDQKR])', + 'caspase 9': r'(?<=LEH)D', + 'caspase 10': r'(?<=IEA)D', + 'chymotrypsin high specificity' : r'([FY](?=[^P]))|(W(?=[^MP]))', + 'chymotrypsin low specificity': + r'([FLY](?=[^P]))|(W(?=[^MP]))|(M(?=[^PY]))|(H(?=[^DMPW]))', + 'clostripain': r'R', + 'cnbr': r'M', + 'enterokinase': r'(?<=[DE]{3})K', + 'factor xa': r'(?<=[AFGILTVM][DE]G)R', + 'formic acid': r'D', + 'glutamyl endopeptidase': r'E', + 'granzyme b': r'(?<=IEP)D', + 'hydroxylamine': r'N(?=G)', + 'iodosobenzoic acid': r'W', + 'lysc': r'K', + 'ntcb': r'\w(?=C)', + 'pepsin ph1.3': r'((?<=[^HKR][^P])[^R](?=[FLWY][^P]))|' + r'((?<=[^HKR][^P])[FLWY](?=\w[^P]))', + 'pepsin ph2.0': r'((?<=[^HKR][^P])[^R](?=[FL][^P]))|' + r'((?<=[^HKR][^P])[FL](?=\w[^P]))', + 'proline endopeptidase': r'(?<=[HKR])P(?=[^P])', + 'proteinase k': r'[AEFILTVWY]', + 'staphylococcal peptidase i': r'(?<=[^E])E', + 'thermolysin': r'[^DE](?=[AFILMV])', + 'thrombin': r'((?<=G)R(?=G))|' + r'((?<=[AFGILTVM][AFGILTVWA]P)R(?=[^DE][^DE]))', + 'trypsin': r'([KR](?=[^P]))|((?<=W)K(?=P))|((?<=M)R(?=P))' + } +""" +This dict contains regular expressions for cleavage rules of the most +popular proteolytic enzymes. The rules were taken from the +`PeptideCutter tool +<http://ca.expasy.org/tools/peptidecutter/peptidecutter_enzymes.html>`_ +at Expasy. +""" +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ensembl_cdna_translate.py Wed Nov 29 15:55:59 2017 -0500 @@ -0,0 +1,426 @@ +#!/usr/bin/env python +""" +# +#------------------------------------------------------------------------------ +# University of Minnesota +# Copyright 2017, Regents of the University of Minnesota +#------------------------------------------------------------------------------ +# Author: +# +# James E Johnson +# +#------------------------------------------------------------------------------ +""" + +import argparse +import sys +from time import sleep + +from Bio.Seq import translate + +import requests + +import digest + + +server = "https://rest.ensembl.org" +ext = "/info/assembly/homo_sapiens?" +max_region = 5000000 + + +def ensembl_rest(ext, headers): + if True: print >> sys.stderr, "%s" % ext + r = requests.get(server+ext, headers=headers) + if r.status_code == 429: + print >> sys.stderr, "response headers: %s\n" % r.headers + if 'Retry-After' in r.headers: + sleep(r.headers['Retry-After']) + r = requests.get(server+ext, headers=headers) + if not r.ok: + r.raise_for_status() + return r + + +def get_species(): + results = dict() + ext = "/info/species" + req_header = {"Content-Type": "application/json"} + r = ensembl_rest(ext, req_header) + for species in r.json()['species']: + results[species['name']] = species + print >> sys.stdout,\ + "%s\t%s\t%s\t%s\t%s"\ + % (species['name'], species['common_name'], + species['display_name'], + species['strain'], + species['taxon_id']) + return results + + +def get_biotypes(species): + biotypes = [] + ext = "/info/biotypes/%s?" % species + req_header = {"Content-Type": "application/json"} + r = ensembl_rest(ext, req_header) + for entry in r.json(): + if 'biotype' in entry: + biotypes.append(entry['biotype']) + return biotypes + + +def get_toplevel(species): + coord_systems = dict() + ext = "/info/assembly/%s?" % species + req_header = {"Content-Type": "application/json"} + r = ensembl_rest(ext, req_header) + toplevel = r.json() + for seq in toplevel['top_level_region']: + if seq['coord_system'] not in coord_systems: + coord_systems[seq['coord_system']] = dict() + coord_system = coord_systems[seq['coord_system']] + coord_system[seq['name']] = int(seq['length']) + return coord_systems + + +def get_transcripts_bed(species, refseq, start, length,params=None): + bed = [] + param = params if params else '' + req_header = {"Content-Type": "text/x-bed"} + regions = range(start, length, max_region) + if not regions or regions[-1] < length: + regions.append(length) + for end in regions[1:]: + ext = "/overlap/region/%s/%s:%d-%d?feature=transcript;%s"\ + % (species, refseq, start, end, param) + start = end + 1 + r = ensembl_rest(ext, req_header) + if r.text: + bed += r.text.splitlines() + return bed + + +def get_seq(id, seqtype,params=None): + param = params if params else '' + ext = "/sequence/id/%s?type=%s;%s" % (id, seqtype,param) + req_header = {"Content-Type": "text/plain"} + r = ensembl_rest(ext, req_header) + return r.text + + +def get_cdna(id,params=None): + return get_seq(id, 'cdna',params=params) + + +def get_cds(id,params=None): + return get_seq(id, 'cds',params=params) + + +def bed_from_line(line): + fields = line.rstrip('\r\n').split('\t') + (chrom, chromStart, chromEnd, name, score, strand, + thickStart, thickEnd, itemRgb, + blockCount, blockSizes, blockStarts) = fields[0:12] + bed_entry = BedEntry(chrom=chrom, chromStart=chromStart, chromEnd=chromEnd, + name=name, score=score, strand=strand, + thickStart=thickStart, thickEnd=thickEnd, + itemRgb=itemRgb, + blockCount=blockCount, + blockSizes=blockSizes.rstrip(','), + blockStarts=blockStarts.rstrip(',')) + return bed_entry + + +class BedEntry(object): + def __init__(self, chrom=None, chromStart=None, chromEnd=None, + name=None, score=None, strand=None, + thickStart=None, thickEnd=None, itemRgb=None, + blockCount=None, blockSizes=None, blockStarts=None): + self.chrom = chrom + self.chromStart = int(chromStart) + self.chromEnd = int(chromEnd) + self.name = name + self.score = int(score) if score is not None else 0 + self.strand = '-' if str(strand).startswith('-') else '+' + self.thickStart = int(thickStart) if thickStart else self.chromStart + self.thickEnd = int(thickEnd) if thickEnd else self.chromEnd + self.itemRgb = str(itemRgb) if itemRgb is not None else r'100,100,100' + self.blockCount = int(blockCount) + if isinstance(blockSizes, str) or isinstance(blockSizes, unicode): + self.blockSizes = [int(x) for x in blockSizes.split(',')] + elif isinstance(blockSizes, list): + self.blockSizes = [int(x) for x in blockSizes] + else: + self.blockSizes = blockSizes + if isinstance(blockStarts, str) or isinstance(blockSizes, unicode): + self.blockStarts = [int(x) for x in blockStarts.split(',')] + elif isinstance(blockStarts, list): + self.blockStarts = [int(x) for x in blockStarts] + else: + self.blockStarts = blockStarts + self.seq = None + self.pep = None + + def __str__(self): + return '%s\t%d\t%d\t%s\t%d\t%s\t%d\t%d\t%s\t%d\t%s\t%s' % ( + self.chrom, self.chromStart, self.chromEnd, + self.name, self.score, self.strand, + self.thickStart, self.thickEnd, str(self.itemRgb), self.blockCount, + ','.join([str(x) for x in self.blockSizes]), + ','.join([str(x) for x in self.blockStarts])) + + # (start, end) + def get_subrange(self, tstart, tstop, debug=False): + chromStart = self.chromStart + chromEnd = self.chromEnd + if debug: + print >> sys.stderr, "%s" % (str(self)) + r = range(self.blockCount) + if self.strand == '-': + r.reverse() + bStart = 0 + bEnd = 0 + for x in r: + bEnd = bStart + self.blockSizes[x] + if bStart <= tstart < bEnd: + if self.strand == '+': + chromStart = self.chromStart + self.blockStarts[x] +\ + (tstart - bStart) + else: + chromEnd = self.chromStart + self.blockStarts[x] +\ + self.blockSizes[x] - (tstart - bStart) + if bStart <= tstop < bEnd: + if self.strand == '+': + chromEnd = self.chromStart + self.blockStarts[x] +\ + (tstop - bStart) + else: + chromStart = self.chromStart + self.blockStarts[x] +\ + self.blockSizes[x] - (tstop - bStart) + if debug: + print >> sys.stderr,\ + "%3d %s\t%d\t%d\t%d\t%d\t%d\t%d"\ + % (x, self.strand, bStart, bEnd, + tstart, tstop, chromStart, chromEnd) + bStart += self.blockSizes[x] + return(chromStart, chromEnd) + + # get the blocks for sub range + def get_blocks(self, chromStart, chromEnd): + tblockCount = 0 + tblockSizes = [] + tblockStarts = [] + for x in range(self.blockCount): + bStart = self.chromStart + self.blockStarts[x] + bEnd = bStart + self.blockSizes[x] + if bStart > chromEnd: + break + if bEnd < chromStart: + continue + cStart = max(chromStart, bStart) + tblockStarts.append(cStart - chromStart) + tblockSizes.append(min(chromEnd, bEnd) - cStart) + tblockCount += 1 + return (tblockCount, tblockSizes, tblockStarts) + + def trim(self, tstart, tstop, debug=False): + (tchromStart, tchromEnd) =\ + self.get_subrange(tstart, tstop, debug=debug) + (tblockCount, tblockSizes, tblockStarts) =\ + self.get_blocks(tchromStart, tchromEnd) + tbed = BedEntry( + chrom=self.chrom, chromStart=tchromStart, chromEnd=tchromEnd, + name=self.name, score=self.score, strand=self.strand, + thickStart=tchromStart, thickEnd=tchromEnd, itemRgb=self.itemRgb, + blockCount=tblockCount, + blockSizes=tblockSizes, blockStarts=tblockStarts) + if self.seq: + ts = tchromStart-self.chromStart + te = tchromEnd - tchromStart + ts + tbed.seq = self.seq[ts:te] + return tbed + + +def __main__(): + parser = argparse.ArgumentParser( + description='Retrieve Ensembl cDNAs and three frame translate') + parser.add_argument( + '-s', '--species', default='human', + help='Ensembl Species to retrieve') + parser.add_argument( + '-B', '--biotypes', action='append', default=[], + help='Restrict Ensembl biotypes to retrieve') + parser.add_argument( + '-i', '--input', default=None, + help='Use BED instead of retrieving cDNA from ensembl (-) for stdin') + parser.add_argument( + '-t', '--transcripts', default=None, + help='Path to output cDNA transcripts.bed (-) for stdout') + parser.add_argument( + '-r', '--raw', action='store_true', + help='Report transcript exacty as returned from Ensembl') + parser.add_argument( + '-f', '--fasta', default=None, + help='Path to output translations.fasta') + parser.add_argument( + '-b', '--bed', default=None, + help='Path to output translations.bed') + parser.add_argument( + '-m', '--min_length', type=int, default=7, + help='Minimum length of protein translation to report') + parser.add_argument( + '-e', '--enzyme', default=None, + help='Digest translation with enzyme') + parser.add_argument( + '-a', '--all', action='store_true', + help='Include reference protein translations') + parser.add_argument('-v', '--verbose', action='store_true', help='Verbose') + parser.add_argument('-d', '--debug', action='store_true', help='Debug') + args = parser.parse_args() + # print >> sys.stderr, "args: %s" % args + species = args.species + input_rdr = None + if args.input is not None: + input_rdr = open(args.input, 'r') if args.input != '-' else sys.stdin + tx_wtr = None + if args.transcripts is not None: + tx_wtr = open(args.transcripts, 'w')\ + if args.transcripts != '-' else sys.stdout + fa_wtr = open(args.fasta, 'w') if args.fasta is not None else None + bed_wtr = open(args.bed, 'w') if args.bed is not None else None + + enzyme = digest.expasy_rules.get(args.enzyme,args.enzyme) + + # print >> sys.stderr, "args biotypes: %s" % args.biotypes + biotypea = ['biotype=%s' % bt.strip() for biotype in args.biotypes for bt in biotype.split(',')] + # print >> sys.stderr, "args biotypes: %s" % biotypea + biotypes = ';'.join(['biotype=%s' % bt.strip() for biotype in args.biotypes for bt in biotype.split(',') if bt.strip()]) + # print >> sys.stderr, "biotypes: %s" % biotypes + + translations = dict() # start : end : seq + + def unique_prot(tbed, seq): + if tbed.chromStart not in translations: + translations[tbed.chromStart] = dict() + translations[tbed.chromStart][tbed.chromEnd] = [] + translations[tbed.chromStart][tbed.chromEnd].append(seq) + elif tbed.chromEnd not in translations[tbed.chromStart]: + translations[tbed.chromStart][tbed.chromEnd] = [] + translations[tbed.chromStart][tbed.chromEnd].append(seq) + elif seq not in translations[tbed.chromStart][tbed.chromEnd]: + translations[tbed.chromStart][tbed.chromEnd].append(seq) + else: + return False + return True + + def translate_bed(bed): + translate_count = 0 + if any([fa_wtr, bed_wtr]): + transcript_id = bed.name + refprot = None + if not args.all: + try: + cds = get_cds(transcript_id) + if len(cds) % 3 != 0: + cds = cds[:-(len(cds) % 3)] + refprot = translate(cds) if cds else None + except: + refprot = None + cdna = get_cdna(transcript_id) + cdna_len = len(cdna) + for offset in range(3): + seqend = cdna_len - (cdna_len - offset) % 3 + aaseq = translate(cdna[offset:seqend]) + aa_start = 0 + while aa_start < len(aaseq): + aa_end = aaseq.find('*', aa_start) + if aa_end < 0: + aa_end = len(aaseq) + prot = aaseq[aa_start:aa_end] + if enzyme and refprot: + frags = digest._cleave(prot,enzyme) + for frag in reversed(frags): + if frag in refprot: + prot = prot[:prot.rfind(frag)] + else: + break + if len(prot) < args.min_length: + pass + elif refprot and prot in refprot: + pass + else: + tstart = aa_start*3+offset + tend = aa_end*3+offset + prot_acc = "%s_%d_%d" % (transcript_id, tstart, tend) + tbed = bed.trim(tstart, tend) + if args.all or unique_prot(tbed, prot): + translate_count += 1 + tbed.name = prot_acc + bed_wtr.write("%s\t%s\n" % (str(tbed), prot)) + bed_wtr.flush() + fa_id = ">%s\n" % (prot_acc) + fa_wtr.write(fa_id) + fa_wtr.write(prot) + fa_wtr.write("\n") + fa_wtr.flush() + aa_start = aa_end + 1 + return translate_count + + if input_rdr: + translation_count = 0 + for i, bedline in enumerate(input_rdr): + try: + bed = bed_from_line(bedline) + translation_count += translate_bed(bed) + except: + print >> sys.stderr, "BED format error: %s\n" % bedline + if args.debug or (args.verbose and any([fa_wtr, bed_wtr])): + print >> sys.stderr,\ + "%s\tcDNA translations:%d" % (species, translation_count) + else: + coord_systems = get_toplevel(species) + if 'chromosome' in coord_systems: + for ref in sorted(coord_systems['chromosome'].keys()): + length = coord_systems['chromosome'][ref] + if not any([tx_wtr, fa_wtr, bed_wtr]): + print >> sys.stderr,\ + "%s\t%s\tlength: %d" % (species, ref, length) + continue + if args.debug: + print >> sys.stderr,\ + "Retrieving transcripts: %s\t%s\tlength: %d"\ + % (species, ref, length) + translation_count = 0 + start = 0 + regions = range(start, length, max_region) + if not regions or regions[-1] < length: + regions.append(length) + for end in regions[1:]: + bedlines = get_transcripts_bed(species, ref, start, end, params=biotypes) + if args.verbose or args.debug: + print >> sys.stderr,\ + "%s\t%s\tstart: %d\tend: %d\tcDNA transcripts:%d"\ + % (species, ref, start, end, len(bedlines)) + # start, end, seq + for i, bedline in enumerate(bedlines): + try: + bed = bed_from_line(bedline)\ + if any([not args.raw, fa_wtr, bed_wtr])\ + else None + if tx_wtr: + tx_wtr.write(bedline if args.raw else str(bed)) + tx_wtr.write("\n") + tx_wtr.flush() + if bed: + translation_count += translate_bed(bed) + except Exception as e: + print >> sys.stderr,\ + "BED error (%s) : %s\n" % (e, bedline) + start = end + 1 + + if args.debug or (args.verbose and any([fa_wtr, bed_wtr])): + print >> sys.stderr,\ + "%s\t%s\tlength: %d\tcDNA translations:%d"\ + % (species, ref, length, translation_count) + + +if __name__ == "__main__": + __main__()
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ensembl_cdna_translate.xml Wed Nov 29 15:55:59 2017 -0500 @@ -0,0 +1,248 @@ +<tool id="ensembl_cdna_translate" name="Ensembl cDNA Translations" version="0.1.0"> + <description>using Ensembl REST API</description> + <requirements> + <requirement type="package" version="0.4.10">requests-cache</requirement> + <requirement type="package" version="1.62">biopython</requirement> + </requirements> + <stdio> + <exit_code range="1:" /> + </stdio> + <command><![CDATA[ + #if $input: + cat '$input' + #else + python '$__tool_directory__/ensembl_cdna_translate.py' + #if $species: + --species '$species' + #end if + $transcript_raw + #if $biotypes: + --biotypes '$biotypes' + #end if + #if str($output_choice).find('transcript_bed') >= 0: + --transcripts + #if str($output_choice).find('translation') >= 0: + '-' | tee '$transcript_bed' + #else + '$transcript_bed' + #end if + #elif str($output_choice).find('translation') >= 0: + --transcripts '-' + #end if + #end if + #if str($output_choice).find('translation') >= 0: + | python '$__tool_directory__/ensembl_cdna_translate.py' -i '-' + #if $input and str($output_choice).find('transcript_bed') >= 0: + --transcripts '$transcript_bed + #end if + #if str($output_choice).find('translation_bed') >= 0: + --bed '$translation_bed' + #end if + #if str($output_choice).find('translation_fasta') >= 0: + --fasta '$translation_fasta' + #end if + #if $enzyme: + --enzyme '$enzyme' + #end if + #end if + + ]]></command> + <inputs> + <param name="species" type="text" value="" label="Ensembl species" > + <help> + </help> + <option value="homo_sapiens">homo_sapiens (Human) taxon_id: 9606</option> + <option value="mus_musculus">mus_musculus (Mouse) taxon_id: 10090</option> + <option value="ailuropoda_melanoleuca">ailuropoda_melanoleuca (Panda) taxon_id: 9646</option> + <option value="anas_platyrhynchos">anas_platyrhynchos (Duck) taxon_id: 8839</option> + <option value="anolis_carolinensis">anolis_carolinensis (Anole lizard) taxon_id: 28377</option> + <option value="astyanax_mexicanus">astyanax_mexicanus (Cave fish) taxon_id: 7994</option> + <option value="bos_taurus">bos_taurus (Cow) taxon_id: 9913</option> + <option value="caenorhabditis_elegans">caenorhabditis_elegans (Caenorhabditis elegans) taxon_id: 6239</option> + <option value="callithrix_jacchus">callithrix_jacchus (Marmoset) taxon_id: 9483</option> + <option value="canis_familiaris">canis_familiaris (Dog) taxon_id: 9615</option> + <option value="carlito_syrichta">carlito_syrichta (Tarsier) taxon_id: 1868482</option> + <option value="cavia_aperea">cavia_aperea (Brazilian guinea pig) taxon_id: 37548</option> + <option value="cavia_porcellus">cavia_porcellus (Guinea Pig) taxon_id: 10141</option> + <option value="chinchilla_lanigera">chinchilla_lanigera (Long-tailed chinchilla) taxon_id: 34839</option> + <option value="chlorocebus_sabaeus">chlorocebus_sabaeus (Vervet-AGM) taxon_id: 60711</option> + <option value="choloepus_hoffmanni">choloepus_hoffmanni (Sloth) taxon_id: 9358</option> + <option value="ciona_intestinalis">ciona_intestinalis (C.intestinalis) taxon_id: 7719</option> + <option value="ciona_savignyi">ciona_savignyi (C.savignyi) taxon_id: 51511</option> + <option value="cricetulus_griseus_chok1gshd">cricetulus_griseus_chok1gshd (Chinese hamster CHOK1GS) taxon_id: 10029</option> + <option value="cricetulus_griseus_crigri">cricetulus_griseus_crigri (Chinese hamster CriGri) taxon_id: 10029</option> + <option value="danio_rerio">danio_rerio (Zebrafish) taxon_id: 7955</option> + <option value="dasypus_novemcinctus">dasypus_novemcinctus (Armadillo) taxon_id: 9361</option> + <option value="dipodomys_ordii">dipodomys_ordii (Kangaroo rat) taxon_id: 10020</option> + <option value="drosophila_melanogaster">drosophila_melanogaster (Fruitfly) taxon_id: 7227</option> + <option value="echinops_telfairi">echinops_telfairi (Lesser hedgehog tenrec) taxon_id: 9371</option> + <option value="equus_caballus">equus_caballus (Horse) taxon_id: 9796</option> + <option value="erinaceus_europaeus">erinaceus_europaeus (Hedgehog) taxon_id: 9365</option> + <option value="felis_catus">felis_catus (Cat) taxon_id: 9685</option> + <option value="ficedula_albicollis">ficedula_albicollis (Flycatcher) taxon_id: 59894</option> + <option value="fukomys_damarensis">fukomys_damarensis (Damara mole rat) taxon_id: 885580</option> + <option value="gadus_morhua">gadus_morhua (Cod) taxon_id: 8049</option> + <option value="gallus_gallus">gallus_gallus (Chicken) taxon_id: 9031</option> + <option value="gasterosteus_aculeatus">gasterosteus_aculeatus (Stickleback) taxon_id: 69293</option> + <option value="gorilla_gorilla">gorilla_gorilla (Gorilla) taxon_id: 9595</option> + <option value="heterocephalus_glaber_female">heterocephalus_glaber_female (Naked mole-rat female) taxon_id: 10181</option> + <option value="heterocephalus_glaber_male">heterocephalus_glaber_male (Naked mole-rat male) taxon_id: 10181</option> + <option value="ictidomys_tridecemlineatus">ictidomys_tridecemlineatus (Squirrel) taxon_id: 43179</option> + <option value="jaculus_jaculus">jaculus_jaculus (Lesser Egyptian jerboa) taxon_id: 51337</option> + <option value="latimeria_chalumnae">latimeria_chalumnae (Coelacanth) taxon_id: 7897</option> + <option value="lepisosteus_oculatus">lepisosteus_oculatus (Spotted gar) taxon_id: 7918</option> + <option value="loxodonta_africana">loxodonta_africana (Elephant) taxon_id: 9785</option> + <option value="macaca_mulatta">macaca_mulatta (Macaque) taxon_id: 9544</option> + <option value="meleagris_gallopavo">meleagris_gallopavo (Turkey) taxon_id: 9103</option> + <option value="mesocricetus_auratus">mesocricetus_auratus (Golden Hamster) taxon_id: 10036</option> + <option value="microcebus_murinus">microcebus_murinus (Mouse Lemur) taxon_id: 30608</option> + <option value="microtus_ochrogaster">microtus_ochrogaster (Prairie vole) taxon_id: 79684</option> + <option value="monodelphis_domestica">monodelphis_domestica (Opossum) taxon_id: 13616</option> + <option value="mus_caroli">mus_caroli (Ryukyu mouse) taxon_id: 10089</option> + <option value="mus_musculus_129s1svimj">mus_musculus_129s1svimj (Mouse 129S1/SvImJ) taxon_id: 10090</option> + <option value="mus_musculus_aj">mus_musculus_aj (Mouse A/J) taxon_id: 10090</option> + <option value="mus_musculus_akrj">mus_musculus_akrj (Mouse AKR/J) taxon_id: 10090</option> + <option value="mus_musculus_balbcj">mus_musculus_balbcj (Mouse BALB/cJ) taxon_id: 10090</option> + <option value="mus_musculus_c3hhej">mus_musculus_c3hhej (Mouse C3H/HeJ) taxon_id: 10090</option> + <option value="mus_musculus_c57bl6nj">mus_musculus_c57bl6nj (Mouse C57BL/6NJ) taxon_id: 10090</option> + <option value="mus_musculus_casteij">mus_musculus_casteij (Mouse CAST/EiJ) taxon_id: 10091</option> + <option value="mus_musculus_cbaj">mus_musculus_cbaj (Mouse CBA/J) taxon_id: 10090</option> + <option value="mus_musculus_dba2j">mus_musculus_dba2j (Mouse DBA/2J) taxon_id: 10090</option> + <option value="mus_musculus_fvbnj">mus_musculus_fvbnj (Mouse FVB/NJ) taxon_id: 10090</option> + <option value="mus_musculus_lpj">mus_musculus_lpj (Mouse LP/J) taxon_id: 10090</option> + <option value="mus_musculus_nodshiltj">mus_musculus_nodshiltj (Mouse NOD/ShiLtJ) taxon_id: 10090</option> + <option value="mus_musculus_nzohlltj">mus_musculus_nzohlltj (Mouse NZO/HlLtJ) taxon_id: 10090</option> + <option value="mus_musculus_pwkphj">mus_musculus_pwkphj (Mouse PWK/PhJ) taxon_id: 39442</option> + <option value="mus_musculus_wsbeij">mus_musculus_wsbeij (Mouse WSB/EiJ) taxon_id: 10092</option> + <option value="mus_pahari">mus_pahari (Shrew mouse) taxon_id: 10093</option> + <option value="mus_spretus_spreteij">mus_spretus_spreteij (Algerian mouse) taxon_id: 10096</option> + <option value="mustela_putorius_furo">mustela_putorius_furo (Ferret) taxon_id: 9669</option> + <option value="myotis_lucifugus">myotis_lucifugus (Microbat) taxon_id: 59463</option> + <option value="nannospalax_galili">nannospalax_galili (Upper Galilee mountains blind mole rat) taxon_id: 1026970</option> + <option value="nomascus_leucogenys">nomascus_leucogenys (Gibbon) taxon_id: 61853</option> + <option value="notamacropus_eugenii">notamacropus_eugenii (Wallaby) taxon_id: 9315</option> + <option value="ochotona_princeps">ochotona_princeps (Pika) taxon_id: 9978</option> + <option value="octodon_degus">octodon_degus (Degu) taxon_id: 10160</option> + <option value="oreochromis_niloticus">oreochromis_niloticus (Tilapia) taxon_id: 8128</option> + <option value="ornithorhynchus_anatinus">ornithorhynchus_anatinus (Platypus) taxon_id: 9258</option> + <option value="oryctolagus_cuniculus">oryctolagus_cuniculus (Rabbit) taxon_id: 9986</option> + <option value="oryzias_latipes">oryzias_latipes (Medaka) taxon_id: 8090</option> + <option value="otolemur_garnettii">otolemur_garnettii (Bushbaby) taxon_id: 30611</option> + <option value="ovis_aries">ovis_aries (Sheep) taxon_id: 9940</option> + <option value="pan_troglodytes">pan_troglodytes (Chimpanzee) taxon_id: 9598</option> + <option value="papio_anubis">papio_anubis (Olive baboon) taxon_id: 9555</option> + <option value="pelodiscus_sinensis">pelodiscus_sinensis (Chinese softshell turtle) taxon_id: 13735</option> + <option value="peromyscus_maniculatus_bairdii">peromyscus_maniculatus_bairdii (Northern American deer mouse) taxon_id: 230844</option> + <option value="petromyzon_marinus">petromyzon_marinus (Lamprey) taxon_id: 7757</option> + <option value="poecilia_formosa">poecilia_formosa (Amazon molly) taxon_id: 48698</option> + <option value="pongo_abelii">pongo_abelii (Orangutan) taxon_id: 9601</option> + <option value="procavia_capensis">procavia_capensis (Hyrax) taxon_id: 9813</option> + <option value="pteropus_vampyrus">pteropus_vampyrus (Megabat) taxon_id: 132908</option> + <option value="rattus_norvegicus">rattus_norvegicus (Rat) taxon_id: 10116</option> + <option value="saccharomyces_cerevisiae">saccharomyces_cerevisiae (Saccharomyces cerevisiae) taxon_id: 4932</option> + <option value="sarcophilus_harrisii">sarcophilus_harrisii (Tasmanian devil) taxon_id: 9305</option> + <option value="sorex_araneus">sorex_araneus (Shrew) taxon_id: 42254</option> + <option value="sus_scrofa">sus_scrofa (Pig) taxon_id: 9823</option> + <option value="taeniopygia_guttata">taeniopygia_guttata (Zebra Finch) taxon_id: 59729</option> + <option value="takifugu_rubripes">takifugu_rubripes (Fugu) taxon_id: 31033</option> + <option value="tetraodon_nigroviridis">tetraodon_nigroviridis (Tetraodon) taxon_id: 99883</option> + <option value="tupaia_belangeri">tupaia_belangeri (Tree Shrew) taxon_id: 37347</option> + <option value="tursiops_truncatus">tursiops_truncatus (Dolphin) taxon_id: 9739</option> + <option value="vicugna_pacos">vicugna_pacos (Alpaca) taxon_id: 30538</option> + <option value="xenopus_tropicalis">xenopus_tropicalis (Xenopus) taxon_id: 8364</option> + <option value="xiphophorus_maculatus">xiphophorus_maculatus (Platyfish) taxon_id: 8083</option> + + </param> + <param name="biotypes" type="text" value="" optional="true" label="Restrict to these biotypes" > + <help><![CDATA[ +Example biotypes: +protein_coding, non_coding, pseudogene, nonsense_mediated_decay, non_stop_decay, +translated_processed_pseudogene, transcribed_processed_pseudogene, transcribed_unitary_pseudogene, transcribed_unprocessed_pseudogene, +polymorphic_pseudogene, processed_pseudogene, unprocessed_pseudogene, unitary_pseudogene, processed_transcript, +retained_intron, ccds_gene, sense_overlapping, sense_intronic, cdna_update, antisense, +LRG_gene, IG_C_gene, IG_D_gene, IG_J_gene, IG_LV_gene IG_V_gene, TR_C_gene, TR_D_gene, TR_J_gene, TR_V_gene, +IG_pseudogene, IG_C_pseudogene, IG_D_pseudogene, IG_J_pseudogene, IG_V_pseudogene, TR_J_pseudogene, TR_V_pseudogene, TEC, +ribozyme, RNase_P_RNA, guide_RNA, macro_lncRNA, bidirectional_promoter_lncRNA, 3prime_overlapping_ncRNA, antisense_RNA, vaultRNA, Y_RNA, SRP_RNA, RNase_MRP_RNA, IG_C_pseudogene, lncRNA, lincRNA, miRNA, snRNA, sRNA, telomerase_RNA, Mt_tRNA, Mt_rRNA, scaRNA, misc_RNA, rRNA, tRNA, scRNA, snoRNA, other + ]]></help> + </param> + <param name="input" type="data" format="bed" optional="true" label="A BED file with 12 columns, thickStart and thickEnd define protein coding region"/> + <param name="translate_all" type="boolean" truevalue="--all" falsevalue="" checked="false" + label="Report all translations (Default is non reference protein sequences)"/> + <param name="transcript_raw" type="boolean" truevalue="--raw" falsevalue="" checked="true" + label="Keep extra columns from ensembl BED"/> + <param name="output_choice" type="select" multiple="true" display="checkboxes" label="Outputs"> + <option value="transcript_bed">transcripts.bed</option> + <option value="translation_bed">translation.bed</option> + <option value="translation_fasta">translation.fasta</option> + </param> + <param name="min_length" type="integer" value="7" min="1" label="Minimum length of protein translation to report"/> + <param name="enzyme" type="select" optional="true" label="Digest enzyme" + help="Remove frags that are in a reference protein"> + <option value="trypsin">trypsin: ([KR](?=[^P]))|((?<=W)K(?=P))|((?<=M)R(?=P))</option> + </param> + </inputs> + <outputs> + <data name="transcript_bed" format="bed" label="Ensembl $species transcripts.bed"> + <filter>'transcript_bed' in output_choice</filter> + </data> + <data name="translation_bed" format="bed" label="Ensembl $species translation.bed"> + <filter>'translation_bed' in output_choice</filter> + </data> + <data name="translation_fasta" format="fasta" label="Ensembl $species translation.fasta"> + <filter>'translation_fasta' in output_choice</filter> + </data> + </outputs> + <tests> + <test> + <param name="species" value="human"/> + <param name="input" value="human_transcripts.bed" ftype="bed"/> + <param name="output_choice" value="translation_bed,translation_fasta"/> + <output name="translation_bed"> + <assert_contents> + <has_text text="ENST00000641515" /> + </assert_contents> + </output> + <output name="translation_fasta"> + <assert_contents> + <has_text text=">ENST00000641515" /> + </assert_contents> + </output> + </test> + </tests> + <help><![CDATA[ + usage: ensembl_cdna_translate.py [-h] [-s SPECIES] [-i INPUT] [-t TRANSCRIPTS] + [-r] [-f FASTA] [-b BED] [-m MIN_LENGTH] [-a] + [-v] [-d] + +Retrieve Ensembl cDNAs and three frame translate + +optional arguments: + -h, --help show this help message and exit + -s SPECIES, --species SPECIES + Ensembl Species to retrieve + -i INPUT, --input INPUT + Use this bed instead of retrieving cDNA from ensembl + (-) for stdin + -t TRANSCRIPTS, --transcripts TRANSCRIPTS + Path to output cDNA transcripts.bed (-) for stdout + -r, --raw Report transcript exacty as returned from Ensembl + -f FASTA, --fasta FASTA + Path to output translations.fasta + -b BED, --bed BED Path to output translations.bed + -m MIN_LENGTH, --min_length MIN_LENGTH + Minimum length of protein translation to report + -a, --all Report all translations (Default is non reference + protein sequences) + -v, --verbose Verbose + -d, --debug Debug + +Esmebl REST API returns a 20 BED format with these additional columns:: + + second_name, cds_start_status, cds_end_status, exon_frames, type, gene_name, second_gene_name, gene_type + + ]]></help> + <citations> + <citation type="doi">10.1093/bioinformatics/btu613</citation> + <citation type="doi">10.1093/nar/gku1010</citation> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/human_transcripts.bed Wed Nov 29 15:55:59 2017 -0500 @@ -0,0 +1,19 @@ +chr1 14403 29570 ENST00000488147 1000 - 14402 14402 0,0,0 11 98,34,152,159,198,136,137,147,99,154,37, 0,601,1392,2203,2454,2829,3202,3511,3864,10334,15130, WASH7P-201 none none -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1, unprocessed_pseudogene ENSG00000227232 WASH7P unprocessed_pseudogene +chr1 29553 31097 ENST00000473358 1000 + 29552 29552 0,0,0 3 486,104,122, 0,1010,1422, MIR1302-2HG-202 none none -1,-1,-1, lincRNA ENSG00000243485 MIR1302-2HG lincRNA +chr1 30266 31109 ENST00000469289 1000 + 30265 30265 0,0,0 2 401,134, 0,709, MIR1302-2HG-201 none none -1,-1, lincRNA ENSG00000243485 MIR1302-2HG lincRNA +chr1 30365 30503 ENST00000607096 1000 + 30364 30364 0,0,0 1 138, 0, MIR1302-2-201 none none -1, miRNA ENSG00000284332 MIR1302-2 miRNA +chr1 34553 36081 ENST00000417324 1000 - 34552 34552 0,0,0 3 621,205,361, 0,723,1167, FAM138A-201 none none -1,-1,-1, lincRNA ENSG00000237613 FAM138A lincRNA +chr1 35244 36073 ENST00000461467 1000 - 35243 35243 0,0,0 2 237,353, 0,476, FAM138A-202 none none -1,-1, lincRNA ENSG00000237613 FAM138A lincRNA +chr1 52472 53312 ENST00000606857 1000 + 52471 52471 0,0,0 1 840, 0, AL627309.6-201 none none -1, unprocessed_pseudogene ENSG00000268020 AL627309.6 unprocessed_pseudogene +chr1 57597 64116 ENST00000642116 1000 + 57596 57596 0,0,0 3 56,157,1201, 0,1102,5318, OR4G11P-202 none none -1,-1,-1, processed_transcript ENSG00000240361 OR4G11P transcribed_unprocessed_pseudogene +chr1 62948 63887 ENST00000492842 1000 + 62947 62947 0,0,0 1 939, 0, OR4G11P-201 none none -1, transcribed_unprocessed_pseudogene ENSG00000240361 OR4G11P transcribed_unprocessed_pseudogene +chr1 65418 71585 ENST00000641515 1000 + 69090 70008 0,0,0 3 15,54,2549, 0,101,3618, OR4F5-202 cmpl cmpl -1,-1,0, protein_coding ENSG00000186092 OR4F5 protein_coding +chr1 69054 70108 ENST00000335137 1000 + 69090 70008 0,0,0 1 1054, 0, OR4F5-201 cmpl cmpl 0, protein_coding ENSG00000186092 OR4F5 protein_coding +chr1 131024 134836 ENST00000442987 1000 + 131023 131023 0,0,0 1 3812, 0, CICP27-201 none none -1, processed_pseudogene ENSG00000233750 CICP27 processed_pseudogene +chr1 139789 140339 ENST00000493797 1000 - 139788 139788 0,0,0 2 58,265, 0,285, AL627309.2-201 none none -1,-1, antisense_RNA ENSG00000239906 AL627309.2 antisense_RNA +chr1 157783 157887 ENST00000410691 1000 - 157782 157782 0,0,0 1 104, 0, RNU6-1100P-201 none none -1, snRNA ENSG00000222623 RNU6-1100P snRNA +chr1 187890 187958 ENST00000612080 1000 - 187889 187889 0,0,0 1 68, 0, MIR6859-2-201 none none -1, miRNA ENSG00000273874 MIR6859-2 miRNA +chr1 263014 297502 ENST00000424587 1000 - 263013 263013 0,0,0 4 5190,150,105,158, 0,5652,26251,34330, AP006222.1-206 none none -1,-1,-1,-1, processed_transcript ENSG00000228463 AP006222.1 transcribed_processed_pseudogene +chr1 347981 348366 ENST00000458203 1000 - 347980 347980 0,0,0 1 385, 0, RPL23AP24-201 none none -1, processed_pseudogene ENSG00000236679 RPL23AP24 processed_pseudogene +chr1 439869 440232 ENST00000437905 1000 + 439868 439868 0,0,0 1 363, 0, WBP1LP7-201 none none -1, processed_pseudogene ENSG00000269732 WBP1LP7 processed_pseudogene +chr1 450702 451697 ENST00000426406 1000 - 450739 451678 0,0,0 1 995, 0, OR4F29-201 cmpl cmpl 0, protein_coding ENSG00000284733 OR4F29 protein_coding