Python get_sequence_hash示例

示例#1

文件： get-sequence-between-genes.py 项目： lierhan/bioinformatics

def main( args ):
  gfhash = gff3.get_gff_hash(args['gffile'])
  sys.stderr.write("gff loaded ")
  gid, startpos, endpos = get_coordinates(gfhash, args['genes'])
  sys.stderr.write("| coordinates identified ")
  if not args['rv']: print ">%s_%s:%s" %(gid, startpos, endpos)
  else: print ">%s_%s:%s" %(gid, endpos, startpos)
  
  seqhash = fasta.get_sequence_hash(args['fastafile'])
  sys.stderr.write("| fasta loaded ")
  seq = seqhash[gid][startpos-1:endpos]
  if args['rv']: seq = Seq(seq).reverse_complement().tostring()
  sys.stderr.write("| subsequence extracted ")
  print seq
  sys.stderr.write("\n")

示例#2

文件： muscle.py 项目： lierhan/bioinformatics

def align(sequences, ids, outfile=False):
  h, infile = tempfile.mkstemp()
  os.close(h)
  fw = open(infile, 'w')
  for i in range(len(sequences)): fw.write(">" + ids[i] + "\n" + sequences[i] + "\n")
  fw.close()
  h, outfile = tempfile.mkstemp()
  os.close(h)
  os.system("muscle -in %s -out %s -quiet 2> /dev/null" %(infile, outfile))
  os.unlink(infile)
  aligned_sequences = []
  alnhash = fasta.get_sequence_hash(outfile)
  for gid in ids: aligned_sequences.append(alnhash[gid])
  os.unlink(outfile)
  return aligned_sequences

示例#3

def main(args):
    gfhash = gff3.get_gff_hash(args['gffile'])
    sys.stderr.write("gff loaded ")
    gid, startpos, endpos = get_coordinates(gfhash, args['genes'])
    sys.stderr.write("| coordinates identified ")
    if not args['rv']: print ">%s_%s:%s" % (gid, startpos, endpos)
    else: print ">%s_%s:%s" % (gid, endpos, startpos)

    seqhash = fasta.get_sequence_hash(args['fastafile'])
    sys.stderr.write("| fasta loaded ")
    seq = seqhash[gid][startpos - 1:endpos]
    if args['rv']: seq = Seq(seq).reverse_complement().tostring()
    sys.stderr.write("| subsequence extracted ")
    print seq
    sys.stderr.write("\n")

示例#4

def align(sequences, ids, outfile=False):
    h, infile = tempfile.mkstemp()
    os.close(h)
    fw = open(infile, 'w')
    for i in range(len(sequences)):
        fw.write(">" + ids[i] + "\n" + sequences[i] + "\n")
    fw.close()
    h, outfile = tempfile.mkstemp()
    os.close(h)
    os.system("muscle -in %s -out %s -quiet 2> /dev/null" % (infile, outfile))
    os.unlink(infile)
    aligned_sequences = []
    alnhash = fasta.get_sequence_hash(outfile)
    for gid in ids:
        aligned_sequences.append(alnhash[gid])
    os.unlink(outfile)
    return aligned_sequences

示例#5

def get_seq_lengths(fastafile):
    lenhash = {}
    seqhash = fasta.get_sequence_hash(fastafile)
    for gid, seq in seqhash.iteritems():
        lenhash[gid] = len(seq)
    return lenhash

示例#6

def prefetch_sequences(pepfile):
    return fasta.get_sequence_hash(pepfile)

示例#7

文件： paralogs-from-selfblast.py 项目： lierhan/bioinformatics

def get_seq_lengths(fastafile):
  lenhash = {}
  seqhash = fasta.get_sequence_hash(fastafile)
  for gid, seq in seqhash.iteritems(): lenhash[gid] = len(seq)
  return lenhash

示例#8

文件： paralogs-from-selfblast.py 项目： lierhan/bioinformatics

def prefetch_sequences(pepfile):
  return fasta.get_sequence_hash(pepfile)

示例#9

文件： fasta2flat.py 项目： sjjose2/bioinformatics

def main(args):
    for gid, seq in fasta.get_sequence_hash(args['fastafile']).iteritems():
        print string.join([gid, seq], "\t")