Python ExPASy.get_sprot_raw方法代码示例

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
def gen_uniprot_features_for_pdb(infile):
  for line in open(infile,'r'):
    (pdb_dom, count, uniprot_ids) = line.replace('\n','').split('\t')
    uniprot_ids = uniprot_ids.split('|')
    for uniprot_id in uniprot_ids:
      data = SwissProt.read(ExPASy.get_sprot_raw(uniprot_id)).__dict__  
      keep = False
      go = []; interpro = ''; evo_trace = ''
      for xref in data['cross_references']:
        if xref[0] == 'GO':
          go.append(xref[1])
        if xref[0] == 'InterPro':
          interpro = xref[1]
        if xref[0] == 'EvolutionaryTrace':
          evo_trace = xref[1]
        if xref[0] == 'PDB' and xref[1].lower() == pdb_dom.lower():
          keep = True
      if keep == False:
        continue
      organism = data['organism']
      loc = ''
      for comment in data['comments']:
        if comment.startswith('SUBCELLULAR LOCATION'):
          loc = comment
      print '%s\t%s\t%s\t%s\t%s\t%s\t%s' %(pdb_dom,uniprot_id,'|'.join(go),interpro,evo_trace,organism,loc)

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
def get_SwissProt(dict,accession):
    try:
        handle = ExPASy.get_sprot_raw(accession)
        record = SwissProt.read(handle)
        dict[accession] = record
    except urllib2.HTTPError, error:
        print accession + ": protein not found on UniProt . "

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
def download_aa_dist_per_gene(UPID_list_fname, cutoff):
    UPID_list = []
    for row in open(UPID_list_fname, 'r'):
        if row:
            UPID_list.append(row[48:54])
    
    if cutoff > 0:
        UPID_list = UPID_list[0:min(cutoff, len(UPID_list))]    
    
    # a dictionary containing the aa_dist for each uniprot ID
    UPID_to_aa_dist = {}
    
    for i, UPID in enumerate(UPID_list):  
        print i, "\t", UPID
    
        # initialize a dictionary for amino acids frequency in each protein
        aa_dist = dict([(aa, 0) for aa in AA_LETTERS])
        
        # call for aa sequence for each uniprot from swiss prot - biopython tool
        handle = ExPASy.get_sprot_raw(UPID)
        seq_record = SeqIO.read(handle, "swiss")
        
        # count frequency for each aa in each UPID
        # update aa_frequency in aa_dict - to avoid bugs where for example an aa seq from
        # swiss prot may contain weired letters such as 'X'
        for aa in list(seq_record):
            if aa in AA_LETTERS:
                aa_dist[aa] += 1
        
        UPID_to_aa_dist[UPID] = np.array([aa_dist[aa] for aa in AA_LETTERS])
    return UPID_to_aa_dist

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
def main(argv):
    # input() reads stdin
    handle = ExPASy.get_sprot_raw(input().strip()) #you can give several IDs separated by commas
    record = SwissProt.read(handle) # use SwissProt.parse for multiple proteins
    
    # there ought to be a better way to pull GO information from the record! maybe there is...
    for p in filter(lambda x:x[0]=='GO' and x[2].startswith('P:'),record.cross_references):
        print(p[2][2:])

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
def main():
    with open("dbpr") as f:
        handle = ExPASy.get_sprot_raw(f.readline().strip())
        record = SwissProt.read(handle)
        record = [x[2] for x in record.cross_references if x[0] == 'GO']
        record = [x[2:] for x in record if x[0] == 'P']
        sys.stdout = open("dbpr.out","w")
        print "\n".join(record)

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
	def __init__(self, seq_id=None, seq_type=None):
		"sets variables for instance"
		if seq_type is 'uniprot':
			handle = ExPASy.get_sprot_raw(seq_id)
			self.seq_record = SeqIO.read(handle, "swiss")
		elif seq_type is 'genbank':
			handle = Entrez.efetch(db='protein', rettype='genbank', id=seq_id)
			self.seq_record = SeqIO.read(handle, "genbank")
		handle.close()

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
 def test_get_sprot_raw(self):
     """Bio.ExPASy.get_sprot_raw("O23729")"""
     identifier = "O23729"
     handle = ExPASy.get_sprot_raw(identifier)
     record = SeqIO.read(handle, "swiss")
     handle.close()
     self.assertEqual(record.id, identifier)
     self.assertEqual(len(record), 394)
     self.assertEqual(seguid(record.seq), "5Y08l+HJRDIlhLKzFEfkcKd1dkM")

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
 def acession(self):
     self.rec=[]
     for ide in self.ids:
         if ide!='ND':
             results=ExPASy.get_sprot_raw(ide)
             rec=SwissProt.read(results)
             self.rec.append(rec)
         else:
             self.rec.append('ND')
     return self.rec

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
def BiologicalProcesses(UniProtID):
    Handle = ExPASy.get_sprot_raw(UniProtID)
    Record = SwissProt.read(Handle)

    Processes = []
    for i in Record.cross_references:
        if "GO" in i:
            for j in i:
                if re.match("P:.*", j):
                    Processes.append(j[j.rfind(':')+1:])
    return "\n".join(Processes)

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
def get_keywords(lookup):
    try:
        handle = ExPASy.get_sprot_raw(lookup)
    except:
        print("Error in ExPASy")
        sys.exit(1)
    try:
        record = SwissProt.read(handle)
    except ValueError, error:
        print(error)
        sys.exit(1)

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
 def test_get_sprot_raw(self):
     """Bio.ExPASy.get_sprot_raw("O23729")"""
     identifier = "O23729"
     # This is to catch an error page from our proxy:
     handle = UndoHandle(ExPASy.get_sprot_raw(identifier))
     if _as_string(handle.peekline()).startswith("<!DOCTYPE HTML"):
         raise IOError
     record = SeqIO.read(handle, "swiss")
     handle.close()
     self.assertEqual(record.id, identifier)
     self.assertEqual(len(record), 394)
     self.assertEqual(seguid(record.seq), "5Y08l+HJRDIlhLKzFEfkcKd1dkM")

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
def main(protein_id):
    handle = ExPASy.get_sprot_raw(protein_id) #you can give several IDs separated by commas
    record = SwissProt.read(handle) # use SwissProt.parse for multiple proteins

    answer = ""
    for r in record.cross_references:
        print r
        if r[0] == "GO":
            if r[2].split(":")[0] == 'P':
                answer += r[2].split(":")[1] + "\n"

    return answer.strip()

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
def get_seq(source, fmt):
    handle = None
    if fmt == 'fasta':
        handle = open(source)
    elif fmt == 'genbank':
        hanlde = open(sourc)
    elif fmt == 'swiss':
        handle = ExPASy.get_sprot_raw(source)
    else:
        raise TypeError('Need to choose correct file format')

    record_iterator = SeqIO.parse(handle, fmt)
    #handle.close()
    return record_iterator

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
def main():
    #Grab our input id value
    uniprot_id = get_uniprot_id_from_file(arguments['<input>'])
    #Get a handle on the data for the uniprot id
    handle = ExPASy.get_sprot_raw(uniprot_id)
    #Parse our data
    record = SwissProt.read(handle)
    handle.close()
    #Process out the stuff of interest, GO values in this case
    go_refs = [ref[1:] for ref in record.cross_references if ref[0] == 'GO']
    for go_entry in go_refs:
        pre, val = go_entry[1].split(':')
        if pre == 'P':
            print(val)

# 需要导入模块: from Bio import ExPASy [as 别名]
# 或者: from Bio.ExPASy import get_sprot_raw [as 别名]
    def download_entry(self, accession):
        try:
            handle = ExPASy.get_sprot_raw(accession)
            record = SwissProt.read(handle)
        except:
            raise KeyError('{}'.format(accession))

        record_org = record.organism.strip().lower()
        if self.organism not in record_org:
            print('{} ortholog of {} not found.'.format(self.organism, accession))
            raise KeyError('{} ortholog of {} not found.'.format(self.organism, accession))
        else:
            self.records[accession] = record
            return record