comparison filter_by_fasta_ids.py @ 4:fa59d6fea7f5 draft

planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/t_coffee commit 988b1fc1cb8739e45648465adbf099f3fdaf87f8

3:78dd29aa7fc1

Sequence = collections.namedtuple('Sequence', ['header', 'sequence'])


def FASTAReader_gen(fasta_filename):
    fasta_file = open(fasta_filename)
    line = fasta_file.readline()
    while True:
        if not line:
            return
        assert line.startswith('>'), "FASTA headers must start with >"
        header = line.rstrip()
        sequence_parts = []
        line = fasta_file.readline()
        while line and line[0] != '>':
            sequence_parts.append(line.rstrip())
            line = fasta_file.readline()
        sequence = "".join(sequence_parts)
        yield Sequence(header, sequence)


def target_match(target, search_entry):
    ''' Matches '''
    search_entry = search_entry.upper()

        for line in f_target.readlines():
            targets.append(">%s" % line.strip().upper())

    work_summary['wanted'] = len(targets)

    # output = open(sys.argv[3], "w")
    for entry in FASTAReader_gen(sys.argv[2]):
        target_matched_results = target_match(targets, entry.header)
        if target_matched_results:
            work_summary['found'] += 1
            targets.remove(target_matched_results)

4:fa59d6fea7f5

Sequence = collections.namedtuple('Sequence', ['header', 'sequence'])


def FASTAReader_gen(fasta_filename):
    with open(fasta_filename) as fasta_file:
        line = fasta_file.readline()
        while True:
            if not line:
                return
            assert line.startswith('>'), "FASTA headers must start with >"
            header = line.rstrip()
            sequence_parts = []
            line = fasta_file.readline()
            while line and line[0] != '>':
                sequence_parts.append(line.rstrip())
                line = fasta_file.readline()
            sequence = "".join(sequence_parts)
            yield Sequence(header, sequence)


def target_match(target, search_entry):
    ''' Matches '''
    search_entry = search_entry.upper()

        for line in f_target.readlines():
            targets.append(">%s" % line.strip().upper())

    work_summary['wanted'] = len(targets)

    for entry in FASTAReader_gen(sys.argv[2]):
        target_matched_results = target_match(targets, entry.header)
        if target_matched_results:
            work_summary['found'] += 1
            targets.remove(target_matched_results)