Python SearchIO.index方法代码示例

# 需要导入模块: from Bio import SearchIO [as 别名]
# 或者: from Bio.SearchIO import index [as 别名]
    def check_raw(self, filename, id, raw, **kwargs):
        """Index filename using keyword arguments, check get_raw(id)==raw."""
        idx = SearchIO.index(filename, self.fmt, **kwargs)
        raw = _as_bytes(raw)
        # Anticipate cases where the raw string and/or file uses different
        # newline characters ~ we set everything to \n.
        new = idx.get_raw(id)
        self.assertTrue(isinstance(new, bytes),
                        "Didn't get bytes from %s get_raw" % self.fmt)
        self.assertEqual(raw.replace(b'\r\n', b'\n'),
                         new.replace(b'\r\n', b'\n'))
        idx.close()

        # Now again, but using SQLite backend
        if sqlite3:
            idx = SearchIO.index_db(":memory:", filename, self.fmt, **kwargs)
            new = idx.get_raw(id)
            self.assertTrue(isinstance(new, bytes),
                            "Didn't get bytes from %s get_raw" % self.fmt)
            self.assertEqual(raw.replace(b'\r\n', b'\n'),
                             new.replace(b'\r\n', b'\n'))
            idx.close()

        if os.path.isfile(filename + ".bgz"):
            # Do the tests again with the BGZF compressed file
            print("[BONUS %s.bgz]" % filename)
            self.check_raw(filename + ".bgz", id, raw, **kwargs)

# 需要导入模块: from Bio import SearchIO [as 别名]
# 或者: from Bio.SearchIO import index [as 别名]
    def check_index(self, filename, format, **kwargs):
        # check if Python3 installation has sqlite3
        try:
            import sqlite3
        except ImportError:
            sqlite3 = None

        parsed = list(SearchIO.parse(filename, format, **kwargs))
        # compare values by index
        indexed = SearchIO.index(filename, format, **kwargs)
        self.assertEqual(len(parsed), len(indexed.keys()))
        # compare values by index_db, only if sqlite3 is present
        if sqlite3 is not None:
            db_indexed = SearchIO.index_db(':memory:', [filename], format, **kwargs)
            self.assertEqual(len(parsed), len(db_indexed.keys()))

        for qres in parsed:
            idx_qres = indexed[qres.id]
            # parsed and indexed qresult are different objects!
            self.assertNotEqual(id(qres), id(idx_qres))
            # but they should have the same attribute values
            self.assertTrue(compare_search_obj(qres, idx_qres))
            # sqlite3 comparison, only if it's present
            if sqlite3 is not None:
                dbidx_qres = db_indexed[qres.id]
                self.assertNotEqual(id(qres), id(dbidx_qres))
                self.assertTrue(compare_search_obj(qres, dbidx_qres))

        indexed._proxy._handle.close()  # TODO - Better solution
        if sqlite3 is not None:
            db_indexed.close()
            db_indexed._con.close()

# 需要导入模块: from Bio import SearchIO [as 别名]
# 或者: from Bio.SearchIO import index [as 别名]
    def check_index(self, filename, format, **kwargs):
        # check if Python3 installation has sqlite3
        try:
            import sqlite3
        except ImportError:
            sqlite3 = None

        if filename.endswith(".bgz"):
            handle = gzip.open(filename)
            parsed = list(SearchIO.parse(handle, format, **kwargs))
            handle.close()
        else:
            parsed = list(SearchIO.parse(filename, format, **kwargs))
        # compare values by index
        indexed = SearchIO.index(filename, format, **kwargs)
        self.assertEqual(len(parsed), len(indexed),
                         "Should be %i records in %s, index says %i"
                         % (len(parsed), filename, len(indexed)))
        # compare values by index_db, only if sqlite3 is present
        if sqlite3 is not None:
            db_indexed = SearchIO.index_db(':memory:', [filename], format, **kwargs)
            self.assertEqual(len(parsed), len(db_indexed),
                             "Should be %i records in %s, index_db says %i"
                             % (len(parsed), filename, len(db_indexed)))

        for qres in parsed:
            idx_qres = indexed[qres.id]
            # parsed and indexed qresult are different objects!
            self.assertNotEqual(id(qres), id(idx_qres))
            # but they should have the same attribute values
            self.assertTrue(compare_search_obj(qres, idx_qres))
            # sqlite3 comparison, only if it's present
            if sqlite3 is not None:
                dbidx_qres = db_indexed[qres.id]
                self.assertNotEqual(id(qres), id(dbidx_qres))
                self.assertTrue(compare_search_obj(qres, dbidx_qres))

        indexed.close()
        if sqlite3 is not None:
            db_indexed.close()
            db_indexed._con.close()

        if os.path.isfile(filename + ".bgz"):
            # Do the tests again with the BGZF compressed file
            print("[BONUS %s.bgz]" % filename)
            self.check_index(filename + ".bgz", format, **kwargs)

# 需要导入模块: from Bio import SearchIO [as 别名]
# 或者: from Bio.SearchIO import index [as 别名]
    def check_raw(self, filename, id, raw, **kwargs):
        """Index filename using **kwargs, check get_raw(id)==raw."""
        idx = SearchIO.index(filename, self.fmt, **kwargs)
        raw = _as_bytes(raw)
        self.assertEqual(raw, idx.get_raw(id))
        idx.close()

        #Now again, but using SQLite backend
        if sqlite3:
            idx = SearchIO.index_db(":memory:", filename, self.fmt, **kwargs)
            self.assertEqual(raw, idx.get_raw(id))
            idx.close()

        if os.path.isfile(filename + ".bgz"):
            #Do the tests again with the BGZF compressed file
            print "[BONUS %s.bgz]" % filename
            self.check_raw(filename + ".bgz", id, raw, **kwargs)

# 需要导入模块: from Bio import SearchIO [as 别名]
# 或者: from Bio.SearchIO import index [as 别名]
    if not (os.path.isfile(db_fasta + ".nhr") and \
            os.path.isfile(db_fasta + ".nin") and \
            os.path.isfile(db_fasta + ".nsq")):
        stop_err("Missing BLAST database for %s" % db_fasta)
    cmd = NcbiblastnCommandline(query=query_fasta, db=db_fasta,
                                out=blast_file, outfmt=6,
                                evalue=1e-5)
    print cmd
    stdout, stderr = cmd()
    return

if not os.path.isfile(blast_file):
    do_blast(assembly_fasta, reference_fasta, blast_file)

contigs = SeqIO.index(assembly_fasta, "fasta")
blast_results = SearchIO.index(blast_file, "blast-tab")

reference_parser = SeqIO.parse(reference_fasta, "fasta")

fasta_handle = open(output_fasta, "w")
fasta_saved_count = 0
fasta_short_dropped = 0

offset = 0
ref_offsets = dict()
for record in reference_parser:
    ref_offsets[hack_ncbi_fasta_name(record.id)] = offset
    offset += len(record)

def reverse_complement_hsp_fragment(frag, query_length):
    rev = SearchIO.HSPFragment(hit_id=frag.hit_id, query_id=frag.query_id)

# 需要导入模块: from Bio import SearchIO [as 别名]
# 或者: from Bio.SearchIO import index [as 别名]
filename = "substrates.txt"
with open(filename) as src:
    p = [line.split('\r') for line in src][0]
legdict = {}
for line in p:
    pp = line.split()
    lid = pp[0].lower(),
    alias = pp[1]
    legdict[lid[0]] = {
        "lid": lid[0],
        "alias": alias}

from Bio import SearchIO
result_handle = open("results/blastp_resultAD.txt")
# comments=True)
idx = SearchIO.index('results/blastp_resultAD.txt', 'blast-tab')
idss = (idx.keys())
homs = {}
rec_list_all = []

for ids in idss:
    rec_list = []
    for rec in idx[ids].hsps:
        rec_list.append((rec.hit_id, rec.evalue, rec.ident_pct))
        rec_list_all.append(
            (rec.query_id, rec.hit_id, rec.evalue, rec.ident_pct))
    homs[ids] = {ids: rec_list}
leg_uniq = []
ids = []
for p in sorted(rec_list_all, key=lambda x: x[0][1]):
    if p[2] < 10E-3:

# 需要导入模块: from Bio import SearchIO [as 别名]
# 或者: from Bio.SearchIO import index [as 别名]
from Bio import SearchIO
result_handle = open("results/blastp_resultAD.txt")
idx = SearchIO.index('results/blastp_resultAD.txt', 'blast-tab')# comments=True)
idss = (idx.keys())
homs = {}
rec_list_all = []

for ids in idss:
    rec_list = []
    for rec in idx[ids].hsps:
        rec_list.append((rec.hit_id, rec.evalue, rec.ident_pct))
        rec_list_all.append((rec.query_id, rec.hit_id, rec.evalue, rec.ident_pct))
    homs[ids] = {ids: rec_list}
leg_uniq = []
ids = []
for p in sorted(rec_list_all, key=lambda x: x[0][1]):
    if p[2] < 10E-3 and p[1] not in p[0]:
        if p[1] not in ids:
            ids.append(p[1])
            leg_uniq.append(p)

output = open('results/leg_blastp_hits.txt', 'w')
output.write('id'+'\t'+'blastp_hit'+ '\t' + 'e-value' + '\t' + 'ident_pct' + '\n')
for p in leg_uniq:
    qid = '%s' % p[0]
    hit = '%s' % p[1]
    ev = '%s' % p[2]
    per = '%s' % p[3]
    output.write(qid + "\t" + hit + "\t" + ev + '\t' + per + "\n")
output.close()