Python pysam.asTuple函数代码示例

 def test_tabix_multi_ps_open(self):
     with open(self.tabix_ref,"rb") as fh1:
         with open(self.tabix_ref,"rb") as fh2:
             ps1 = pysam.tabix_file_iterator(fh1,pysam.asTuple())
             ps2 = pysam.tabix_file_iterator(fh2,pysam.asTuple())
             reader = MockReader(ps1,ps2,self.tabix_ref,tabix=True)
             for expected, found in zip(reader,self.bed_lines+self.bed_lines):
                 self.assertEqual(expected.strip("\n"),found.strip("\n"))

def parse_annotations(chrom, pos):

    AF_supAFR = CSQ = 'NA'

    if chrom == 'X':
        if pos <= 2699520:
            replace = 'X_PAR1'
        elif pos >= 154931044:
            replace = 'X_PAR2'
        else:
            replace = 'X_nonPAR'
    else:
        replace = chrom
    path_vcf = '../../../SHAPEIT/out_annotate_2016Dec28/{}.minAC1.no_mask.without_related.vcf.gz'.format(replace)
    tbx = pysam.TabixFile(path_vcf)
    for row in tbx.fetch(chrom, pos - 1, pos, parser=pysam.asTuple()):
        for _ in row[7].split(';'):
            if _ == 'DB':
                continue
            k, v = _.split('=')
            if k == 'AF_supAFR':
                AF_supAFR = v
            elif k == 'CSQ':
                CSQ = v

    return AF_supAFR, CSQ

def load_segmented_data(filepath, interval):
	
	res = genomic_interval_set()

	tabix = pysam.TabixFile(filepath)
	for row in tabix.fetch(interval.chrom, interval.start, interval.end, parser = pysam.asTuple()):
		
		chrom=row[0]
		start = int(row[1])
		end = int(row[2])
		
		try:
			name=row[3]
		except:
			name='.'

		try:
			score=float(row[4])
		except:
			score=-np.inf
	
		try:
			strand=row[5]
		except:
			strand='+'

		res += genomic_interval(chrom, start, end, name=name, score=score, strand=strand) 
	
	tabix.close()

	return res

def annotate_variants_list(args, select_cursor, update_cursor):
    """
    Populate a new, user-defined column in the variants
    table with a INTEGER indicating the count of overlaps
    between the variant and the 
    annotation file.
    """
    add_requested_column(args.col_name, update_cursor)

    # For each, use Tabix to count overlaps with the user-defined
    # annotation file.  Update the variant row with the count.
    annos = pysam.Tabixfile(args.anno_file)
    select_cursor.execute("SELECT chrom, start, end, variant_id FROM variants")
    for row in select_cursor:
        hit_list = []
        for hit in annos.fetch(str(row['chrom']), int(row['start']), int(row['end']),
                               parser=pysam.asTuple()):
            try:
                hit_list.append(hit[int(args.col_extract) - 1])
            except IndexError:
                sys.exit("Column " + args.col_extract + " exceeds \
                          the number of columns in your \
                          annotation file. Exiting.")
                          
        hits = ",".join(hit_list)
        if len(hit_list):
            update_qry = "UPDATE variants SET " + args.col_name + " = '" + hits + \
                        "' WHERE variant_id = " + str(row['variant_id'])
        else:
            update_qry = "UPDATE variants SET " + args.col_name + " = NULL" + \
                        " WHERE variant_id = " + str(row['variant_id'])
        update_cursor.execute(update_qry)

    def testTabixIndexedTsvCreation(self):
        inFile = "testdata/ESP6500SI-V2.chr1.snps_indels.head.25.txt"
        destDir = "out"

        # chr, startPos, endPos
        resultIndexedFile = TabixIndexer.index(destDir=destDir, inputFilename=inFile, fileColumnNumList=[0, 1, 1])
        self.assertTrue(os.path.exists(resultIndexedFile), "No index file was generated.")

        chrom = "1"
        start = "69594"
        end = "69594"
        tsvRecords = None
        tsvReader = pysam.Tabixfile(filename=resultIndexedFile)  # initialize the tsv reader
        try:
            tsvRecords = tsvReader.fetch(chrom, int(start)-1, int(end), parser=pysam.asTuple())
        except ValueError:
            pass

        tsvRecord = None
        for tsvRecord in tsvRecords:
            self.assertEqual(tsvRecord[5], "2,6190", "Value in column sixth does not match the expected value.")

        self.assertIsNotNone(tsvRecord, "No record for %s:%s-%s was found." % (chrom, start, end))

        os.remove(resultIndexedFile)

    def annotate(self,bedline,genome):
        c = bedline.rstrip().rsplit("\t")
        chr   = c[0]
        start = c[1]
        end   = c[2]

        if not re.search('chr',chr):
            raise LookupError("chromosome names must start with chr: " + chr)
            return []
        if (self.genome != genome):
            raise LookupError("tried to compare a %s bedfile to a %s annotation." % (genome,self.genome))
            return []
        else:
            annotations = []
            if (chr and start and end):
                if self.tabixContigs.has_key(chr):
                    tabixTupleParse = self.tabix.fetch(reference=chr,
                                                       start=int(start),
                                                       end=int(end),
                                                       parser=pysam.asTuple())
                    for tabixTuple in tabixTupleParse:
                        annotations.append(tabixTuple[3])
                    return uniqann(annotations)
                else:
                    return []
            else:
                raise LookupError("can't find chr,start,end. File must be tab-delimited")
                return []

    def testIteratorUncompressed(self):
        '''test iteration from uncompressed file.'''
        tmpfilename = 'tmp_testIteratorUncompressed'
        infile = gzip.open(self.filename, "rb")
        outfile = open(tmpfilename, "wb")
        outfile.write(infile.read())
        outfile.close()
        infile.close()

        with open(tmpfilename) as infile:
            for x, r in enumerate(pysam.tabix_iterator(
                    infile, pysam.asTuple())):
                self.assertEqual(self.compare[x], list(r))
                self.assertEqual(len(self.compare[x]), len(r))

                # test indexing
                for c in range(0, len(r)):
                    self.assertEqual(self.compare[x][c], r[c])

                # test slicing access
                for c in range(0, len(r) - 1):
                    for cc in range(c + 1, len(r)):
                        self.assertEqual(self.compare[x][c:cc],
                                         r[c:cc])

        os.unlink(tmpfilename)

def get_snp_data(*args, **kwargs):
    '''
    proxy for TabixFile.fetch
    '''
    kwargs['multiple_iterators'] = True
    return TabixFile(SNP_FILE, parser=asTuple()).\
            fetch(*args, **kwargs)

    def testTuple( self ):

        for x, r in enumerate(self.tabix.fetch( parser = pysam.asTuple() )):
            self.assertEqual( self.compare[x], list(r) )

            self.assertEqual( len(self.compare[x]), len(r) )
            for c in range(0,len(r)):
                self.assertEqual( self.compare[x][c], r[c] )

    def testCopy(self):
        a = self.tabix.fetch(parser=pysam.asTuple()).next()
        b = copy.copy(a)
        self.assertEqual(a, b)

        a = self.tabix.fetch(parser=pysam.asGTF()).next()
        b = copy.copy(a)
        self.assertEqual(a, b)

 def testUnset( self ):
     for x, r in enumerate(self.tabix.fetch( parser = pysam.asTuple() )):
         self.assertEqual( self.compare[x], list(r) )
         c = list(r)
         e = list(r)
         for y in range(len(r)):
             r[y] = c[y] = None
             e[y] = ""
             self.assertEqual( c, list(r) )
             self.assertEqual( "\t".join(e), str(r) )

    def get_gapped_wnds(self,chr,tbx_gaps):
        
        gapped_wnds = []

        for t in tbx_gaps.fetch(chr,parser=pysam.asTuple()):
            _chr,start,end = t
            wnd_start = np.searchsorted(self.starts,start) 
            wnd_end = np.searchsorted(self.starts,end) 
            gapped_wnds.append(tuple([wnd_start,wnd_end]))
        
        return gapped_wnds 

def get_ref_alt_from_dbSNP(chrom, pos, path_vcf):

    tbx = pysam.TabixFile(path_vcf)
    for row in tbx.fetch(chrom, pos - 1, pos, parser=pysam.asTuple()):
        if len(row[3]) == 1 and 1 in map(len, row[4].split(',')):
            break
    else:
        stop_not_found_in_dbSNP

    assert ',' not in row[4], row

    return row[3], row[4]

 def get_overlapping_wnds(self,chr,tbx):
     wnd_starts, wnd_ends = self.get_wnds_by_chr(chr)
     bnds = np.array([ [int(l[1]),int(l[2])] 
                         for l in tbx.fetch(chr,parser=pysam.asTuple()) ])
      
     start_idxs = np.searchsorted(wnd_starts,bnds[:,0])
     end_idxs = np.searchsorted(wnd_starts,bnds[:,1])
     #print start_idxs
     #print end_idxs
     ret = np.c_[start_idxs,end_idxs]
     
     return ret

 def __init__(self, task_queue, results_queue, family, args):
     multiprocessing.Process.__init__(self)
     self.task_queue = task_queue
     self.family = family
     self.results_queue = results_queue
     self.verbosity = args.verbose
     self.phased = args.phased
     self.cadd_file = args.cadd_file[0]
     self.chr_prefix = args.chr_prefix
                 
     if self.cadd_file:
         self.cadd_file = Tabixfile(self.cadd_file, parser = asTuple())