comparison blastxml_to_gapped_gff3.py @ 2:2c71c9b0214c draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/blastxml_to_gapped_gff3 commit 908f16ea4eb082227437dc93e06e8cb742f5a257

1:f9812943a3c6

import logging
import re
import sys

from BCBio import GFF

logging.basicConfig(level=logging.INFO)
log = logging.getLogger(name='blastxml2gff3')

__author__ = "Eric Rasche"
__version__ = "0.4.0"
__maintainer__ = "Eric Rasche"
__email__ = "[e-mail]"

__doc__ = """
BlastXML files, when transformed to GFF3, do not normally show gaps in the
blast hits. This tool aims to fill that "gap".
"""


def blastxml2gff3(blastxml, min_gap=3, trim=False, trim_end=False):
    from Bio.Blast import NCBIXML
    from Bio.Seq import Seq
    from Bio.SeqRecord import SeqRecord
    from Bio.SeqFeature import SeqFeature, FeatureLocation

    blast_records = NCBIXML.parse(blastxml)
    records = []
    for record in blast_records:
        # http://www.sequenceontology.org/browser/release_2.4/term/SO:0000343
        match_type = {  # Currently we can only handle BLASTN, BLASTP
            'BLASTN': 'nucleotide_match',
            'BLASTP': 'protein_match',
        }.get(record.application, 'match')

        rec = SeqRecord(Seq("ACTG"), id=record.query)
        for hit in record.alignments:
            for hsp in hit.hsps:
                qualifiers = {
                    "source": "blast",
                    "score": hsp.expect,
                    "accession": hit.accession,
                    "hit_id": hit.hit_id,
                    "length": hit.length,
                    "hit_titles": hit.title.split(' >')
                }
                desc = hit.title.split(' >')[0]
                qualifiers['description'] = desc[desc.index(' '):]

                # This required a fair bit of sketching out/match to figure out
                # the first time.

                # may be longer than the parent feature, so we use the supplied
                # subject/hit length to calculate the real ending of the target
                # protein.
                parent_match_end = hsp.query_start + hit.length + hsp.query.count('-')

                # However, if the user requests that we trim the feature, then
                # we need to cut the ``match`` start to 0 to match the parent feature.
                # We'll also need to cut the end to match the query's end. It (maybe)
                # should be the feature end? But we don't have access to that data, so
                # We settle for this.
                if trim:
                    if parent_match_start < 1:
                        parent_match_start = 0

                if trim or trim_end:
                    if parent_match_end > hsp.query_end:
                        parent_match_end = hsp.query_end + 1

                # The ``match`` feature will hold one or more ``match_part``s
                top_feature = SeqFeature(
                    FeatureLocation(parent_match_start, parent_match_end),
                    type=match_type, strand=0,
                    qualifiers=qualifiers
                )

                # Unlike the parent feature, ``match_part``s have sources.
                part_qualifiers = {
                    "source": "blast",
                }
                top_feature.sub_features = []
                for start, end, cigar in generate_parts(hsp.query, hsp.match,
                                                        hsp.sbjct,
                                                        ignore_under=min_gap):
                    part_qualifiers['Gap'] = cigar
                    part_qualifiers['ID'] = hit.hit_id

                    if trim:
                        # If trimming, then we start relative to the
                        # match's start
                        match_part_start = parent_match_start + start
                    else:
                        # Otherwise, we have to account for the subject start's location
                        match_part_start = parent_match_start + hsp.sbjct_start + start - 1

                    # We used to use hsp.align_length here, but that includes
                    # gaps in the parent sequence
                    #
                    # Furthermore align_length will give calculation errors in weird places

                            qualifiers=copy.deepcopy(part_qualifiers))
                    )

                rec.features.append(top_feature)
        rec.annotations = {}
        records.append(rec)
    return records


def __remove_query_gaps(query, match, subject):
    """remove positions in all three based on gaps in query

        return ""


if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Convert Blast XML to gapped GFF3', epilog='')
    parser.add_argument('blastxml', type=open, help='Blast XML Output')
    parser.add_argument('--min_gap', type=int, help='Maximum gap size before generating a new match_part', default=3)
    parser.add_argument('--trim', action='store_true', help='Trim blast hits to be only as long as the parent feature')
    parser.add_argument('--trim_end', action='store_true', help='Cut blast results off at end of gene')
    args = parser.parse_args()

    result = blastxml2gff3(**vars(args))
    GFF.write(result, sys.stdout)

2:2c71c9b0214c

import logging
import re
import sys

from BCBio import GFF
logging.basicConfig(level=logging.INFO)
log = logging.getLogger(name='blastxml2gff3')

__doc__ = """
BlastXML files, when transformed to GFF3, do not normally show gaps in the
blast hits. This tool aims to fill that "gap".
"""


def blastxml2gff3(blastxml, min_gap=3, trim=False, trim_end=False, include_seq=False):
    from Bio.Blast import NCBIXML
    from Bio.Seq import Seq
    from Bio.SeqRecord import SeqRecord
    from Bio.SeqFeature import SeqFeature, FeatureLocation

    blast_records = NCBIXML.parse(blastxml)
    for idx_record, record in enumerate(blast_records):
        # http://www.sequenceontology.org/browser/release_2.4/term/SO:0000343
        match_type = {  # Currently we can only handle BLASTN, BLASTP
            'BLASTN': 'nucleotide_match',
            'BLASTP': 'protein_match',
        }.get(record.application, 'match')

        recid = record.query
        if ' ' in recid:
            recid = recid[0:recid.index(' ')]

        rec = SeqRecord(Seq("ACTG"), id=recid)
        for idx_hit, hit in enumerate(record.alignments):
            for idx_hsp, hsp in enumerate(hit.hsps):
                qualifiers = {
                    "ID": 'b2g.%s.%s.%s' % (idx_record, idx_hit, idx_hsp),
                    "source": "blast",
                    "score": hsp.expect,
                    "accession": hit.accession,
                    "hit_id": hit.hit_id,
                    "length": hit.length,
                    "hit_titles": hit.title.split(' >'),
                }
                if include_seq:
                    qualifiers.update({
                        'blast_qseq': hsp.query,
                        'blast_sseq': hsp.sbjct,
                        'blast_mseq': hsp.match,
                    })

                for prop in ('score', 'bits', 'identities', 'positives',
                             'gaps', 'align_length', 'strand', 'frame',
                             'query_start', 'query_end', 'sbjct_start',
                             'sbjct_end'):
                    qualifiers['blast_' + prop] = getattr(hsp, prop, None)

                desc = hit.title.split(' >')[0]
                qualifiers['description'] = desc[desc.index(' '):]

                # This required a fair bit of sketching out/match to figure out
                # the first time.

                # may be longer than the parent feature, so we use the supplied
                # subject/hit length to calculate the real ending of the target
                # protein.
                parent_match_end = hsp.query_start + hit.length + hsp.query.count('-')

                # If we trim the left end, we need to trim without losing information.
                used_parent_match_start = parent_match_start
                if trim:
                    if parent_match_start < 1:
                        used_parent_match_start = 0

                if trim or trim_end:
                    if parent_match_end > hsp.query_end:
                        parent_match_end = hsp.query_end + 1

                # The ``match`` feature will hold one or more ``match_part``s
                top_feature = SeqFeature(
                    FeatureLocation(used_parent_match_start, parent_match_end),
                    type=match_type, strand=0,
                    qualifiers=qualifiers
                )

                # Unlike the parent feature, ``match_part``s have sources.
                part_qualifiers = {
                    "source": "blast",
                }
                top_feature.sub_features = []
                for idx_part, (start, end, cigar) in \
                        enumerate(generate_parts(hsp.query, hsp.match,
                                                 hsp.sbjct,
                                                 ignore_under=min_gap)):
                    part_qualifiers['Gap'] = cigar
                    part_qualifiers['ID'] = qualifiers['ID'] + ('.%s' % idx_part)

                    # Otherwise, we have to account for the subject start's location
                    match_part_start = parent_match_start + hsp.sbjct_start + start - 1

                    # We used to use hsp.align_length here, but that includes
                    # gaps in the parent sequence
                    #
                    # Furthermore align_length will give calculation errors in weird places

                            qualifiers=copy.deepcopy(part_qualifiers))
                    )

                rec.features.append(top_feature)
        rec.annotations = {}
        yield rec


def __remove_query_gaps(query, match, subject):
    """remove positions in all three based on gaps in query

        return ""


if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Convert Blast XML to gapped GFF3', epilog='')
    parser.add_argument('blastxml', type=argparse.FileType("r"), help='Blast XML Output')
    parser.add_argument('--min_gap', type=int, help='Maximum gap size before generating a new match_part', default=3)
    parser.add_argument('--trim', action='store_true', help='Trim blast hits to be only as long as the parent feature')
    parser.add_argument('--trim_end', action='store_true', help='Cut blast results off at end of gene')
    parser.add_argument('--include_seq', action='store_true', help='Include sequence')
    args = parser.parse_args()

    for rec in blastxml2gff3(**vars(args)):
        if len(rec.features):
            GFF.write([rec], sys.stdout)