Logo Search packages:      
Sourcecode: python-biopython version File versions  Download package


# Copyright 2004 by Cymon J. Cox and Frank Kauff.  All rights reserved.
# Copyright 2008 by Michiel de Hoon.  All rights reserved.
# Revisions copyright 2009 by Cymon J. Cox.  All rights reserved.
# Revisions copyright 2009 by Peter Cock.  All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license.  Please see the LICENSE file that should have been included
# as part of this package.
Parser for PHD files output by PHRED and used by PHRAP and CONSED.

This module can be used used directly which will return Record objects
which should contain all the original data in the file.

Alternatively, using Bio.SeqIO with the "phd" format will call this module
internally.  This will give SeqRecord objects for each contig sequence.

from Bio import Seq
from Bio.Alphabet import generic_dna


00026 class Record:
    """Hold information from a PHD file."""
    def __init__(self):
        self.file_name = ''
        self.comments = {}
        for kw in CKEYWORDS:
            self.comments[kw.lower()] = None
        self.sites = []
        self.seq = ''
        self.seq_trimmed = ''

def read(handle):
    """Reads the next PHD record from the file, returning it as a Record object.

    This function reads PHD file data line by line from the handle,
    and returns a single Record object.
    for line in handle:
        if line.startswith("BEGIN_SEQUENCE"):
            record = Record()
            record.file_name = line[15:].rstrip() 
        return # No record found

    for line in handle:
        if line.startswith("BEGIN_COMMENT"):
        raise ValueError("Failed to find BEGIN_COMMENT line")
    for line in handle:
        line = line.strip()
        if not line:
        if line=="END_COMMENT":
        keyword, value = line.split(":", 1)
        keyword = keyword.lower()
        value = value.strip()
        if keyword in ('chromat_file',
            record.comments[keyword] = value
        elif keyword in ('abi_thumbprint',
            record.comments[keyword] = int(value)
        elif keyword=='trace_peak_area_ratio':
            record.comments[keyword] = float(value)
        elif keyword=='trim':
            first, last, prob = value.split()
            record.comments[keyword] = (int(first), int(last), float(prob))
        raise ValueError("Failed to find END_COMMENT line")

    for line in handle:
        if line.startswith('BEGIN_DNA'):
        raise ValueError("Failed to find BEGIN_DNA line")

    for line in handle:
        if line.startswith('END_DNA'):
            # Line is: "site quality peak_location"
            # Peak location is optional according to
            # David Gordon (the Consed author)
            parts = line.split()
            if len(parts) in [2,3]:
                raise ValueError("DNA line must contain a base and quality "
                                 "score, and optionally a peak location.")

    for line in handle:
        if line.startswith("END_SEQUENCE"):
        raise ValueError("Failed to find END_SEQUENCE line")

    record.seq = Seq.Seq(''.join([n[0] for n in record.sites]), generic_dna)
    if record.comments['trim'] is not None:
        first, last = record.comments['trim'][:2]
        record.seq_trimmed = record.seq[first:last]

    return record

def parse(handle):
    """Iterates over a file returning multiple PHD records.

    The data is read line by line from the handle. The handle can be a list
    of lines, an open file, or similar; the only requirement is that we can
    iterate over the handle to retrieve lines from it.

    Typical usage:

    records = parse(handle)
    for record in records:
        # do something with the record object
    while True:
        record = read(handle)
        if not record:
        yield record

Generated by  Doxygen 1.6.0   Back to index