Blast parser

blast.py

class BlastOut(object):
    def __init__(self, line):
        col = line.strip().split()
        self.col_string = line.strip()
        self.q = col[0]
        self.s = col[1]
        self.identity = float(col[2])
        self.alignment_len = int(col[3])
        self.mismatches = int(col[4])
        self.gap_open = int(col[5])
        self.q_start = int(col[6])
        self.q_end = int(col[7])
        self.s_start = int(col[8])
        self.s_end = int(col[9])
        self.e_value = float(col[10])
        self.bit = float(col[11])

        self.primary_key = uuid.uuid4().hex

        self.q_pair = (self.q_start, self.q_end)
        self.s_pair = (self.s_start, self.s_end)

        if abs(self.q_start - self.q_end) < abs(self.s_start - self.s_end):
            self.pairs = [self.s_pair, self.q_pair]
        else:
            self.pairs = [self.q_pair, self.s_pair]

    def __str__(self):
        return "query: %s, subject: %s" % (self.q, self.s)

class BlastIter(object):
    def __init__(self, _file):
        self.file = _file

    def __iter__(self):
        with open(self.file, "r") as f:
            for line in f:
                yield BlastOut(line)
                

it can be used as follows:

for b in BlastIter("blast/blast.out"):
    ...