frozenleaves/biopython
1
0
Fork 0
mirror of https://github.com/biopython/biopython.git synced 2025-10-20 21:53:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add a parser for Exonerate cigar and vulgar output to Bio.Align (#3943)

Browse Source 
* starting

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* bugfix

* black

* flake

* black

* bow suggestions
This commit is contained in:
mdehoon
2022-06-05 10:01:21 +09:00
committed by GitHub
parent b72e478a62
commit 918dda48ab
35 changed files with 4164 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Bio/Align/__init__.py
View File

@ -1788,7 +1788,7 @@ class Alignment:
if coordinates[0, 0] > coordinates[0, -1]: # mapped to reverse strand
coordinates = coordinates.copy()
coordinates[0, :] = n1 - coordinates[0, :]
seq2 = reverse_complement(seq2, inplace=False)
seq1 = reverse_complement(seq1, inplace=False)
if coordinates[1, 0] > coordinates[1, -1]: # mapped to reverse strand
coordinates = coordinates.copy()
coordinates[1, :] = n2 - coordinates[1, :]

649
Bio/Align/exonerate.py Normal file
View File

@ -0,0 +1,649 @@
# Copyright 2022 by Michiel de Hoon. All rights reserved.
#
# This file is part of the Biopython distribution and governed by your
# choice of the "Biopython License Agreement" or the "BSD 3-Clause License".
# Please see the LICENSE file that should have been included as part of this
# package.
"""Bio.Align support for Exonerate output format.
This module provides support for Exonerate outputs. Exonerate is a generic
tool for pairwise sequence comparison that allows you to align sequences using
several different models.
Bio.Align.exonerate was tested on the following Exonerate versions and models:
- version: 2.2
- models:
- affine:local - cdna2genome
- coding2coding - est2genome
- genome2genome - ner
- protein2dna - protein2genome
- ungapped - ungapped:translated
Although model testing were not exhaustive, ExonerateIO should be able to cope
with all Exonerate models. Please file a bug report if you stumble upon an
unparsable file.
More information on Exonerate is available on its home page at
www.ebi.ac.uk/~guy/exonerate/
You are expected to use this module via the Bio.Align functions.
"""
import numpy
from Bio.Align import Alignment
from Bio.Align import interfaces
from Bio.Seq import Seq
from Bio.SeqRecord import SeqRecord
from Bio import BiopythonExperimentalWarning
import warnings
warnings.warn(
"Bio.Align.exonerate is an experimental module which may undergo "
"significant changes prior to its future official release.",
BiopythonExperimentalWarning,
)
class AlignmentWriter(interfaces.AlignmentWriter):
"""Alignment file writer for the Exonerate cigar and vulgar file format."""
def __init__(self, target, fmt="vulgar"):
"""Create an AlignmentWriter object.
Arguments:
- target - output stream or file name
- fmt - write alignments in the vulgar (Verbose Useful Labelled
Gapped Alignment Report) format (fmt="vulgar") or in
the cigar (Compact Idiosyncratic Gapped Alignment Report)
format (fmt="cigar").
Default value is 'vulgar'.
"""
super().__init__(target, mode="w")
if fmt == "vulgar":
self.format_alignment = self._format_alignment_vulgar
elif fmt == "cigar":
self.format_alignment = self._format_alignment_cigar
else:
raise ValueError(
"argument fmt should be 'vulgar' or 'cigar' (received %s)" % fmt
)
def write_header(self, alignments):
"""Write the header."""
try:
commandline = alignments.commandline
except AttributeError:
commandline = ""
try:
hostname = alignments.hostname
except AttributeError:
hostname = ""
self.stream.write(f"Command line: [{commandline}]\n")
self.stream.write(f"Hostname: [{hostname}]\n")
def write_footer(self):
"""Write the footer."""
self.stream.write("-- completed exonerate analysis\n")
def _format_alignment_cigar(self, alignment):
"""Return a string with a single alignment formatted as a cigar line."""
if not isinstance(alignment, Alignment):
raise TypeError("Expected an Alignment object")
coordinates = alignment.coordinates
target_start = coordinates[0, 0]
target_end = coordinates[0, -1]
query_start = coordinates[1, 0]
query_end = coordinates[1, -1]
steps = coordinates[:, 1:] - coordinates[:, :-1]
query = alignment.query
target = alignment.target
try:
query_id = query.id
except AttributeError:
query_id = "query"
try:
target_id = target.id
except AttributeError:
target_id = "target"
try:
target_molecule_type = target.annotations["molecule_type"]
except (AttributeError, KeyError):
target_molecule_type = None
if target_molecule_type == "protein":
target_strand = "."
elif target_start <= target_end:
target_strand = "+"
elif target_start > target_end:
target_strand = "-"
steps[0, :] = -steps[0, :]
try:
query_molecule_type = query.annotations["molecule_type"]
except (AttributeError, KeyError):
query_molecule_type = None
if query_molecule_type == "protein":
query_strand = "."
elif query_start <= query_end:
query_strand = "+"
elif query_start > query_end:
query_strand = "-"
steps[1, :] = -steps[1, :]
score = alignment.score
words = [
"cigar:",
query_id,
str(query_start),
str(query_end),
query_strand,
target_id,
str(target_start),
str(target_end),
target_strand,
str(score),
]
try:
operations = alignment.operations
except AttributeError:
for step in steps.transpose():
target_step, query_step = step
if target_step == query_step:
operation = "M"
step = target_step
elif query_step == 0:
operation = "D" # Deletion
step = target_step
elif target_step == 0:
operation = "I" # Insertion
step = query_step
elif (
target_molecule_type != "protein"
and query_molecule_type == "protein"
):
operation = "M"
step = target_step
elif (
target_molecule_type == "protein"
and query_molecule_type != "protein"
):
operation = "M"
step = query_step
else:
raise ValueError(
"Unexpected step target %d, query %d for molecule type %s, %s"
% (
target_step,
query_step,
target_molecule_type,
query_molecule_type,
)
)
words.append(operation)
words.append(str(step))
else:
for step, operation in zip(steps.transpose(), operations.decode()):
target_step, query_step = step
if operation == "M":
if target_step == query_step:
step = target_step
elif target_step == 3 * query_step:
step = target_step
assert query_molecule_type == "protein"
assert target_molecule_type != "protein"
elif query_step == 3 * target_step:
step = query_step
assert query_molecule_type != "protein"
assert target_molecule_type == "protein"
else:
raise ValueError(
"Unexpected steps target %d, query %s for operation 'M'"
)
elif operation == "5": # 5' splice site
if query_step == 0:
step = target_step
operation = "D"
elif target_step == 0:
step = query_step
operation = "I"
else:
assert query_step == target_step
step = target_step
operation = "M"
elif operation == "N": # Intron
if query_step == 0:
step = target_step
operation = "D"
elif target_step == 0:
step = query_step
operation = "I"
else:
raise ValueError(
"Unexpected intron with steps target %d, query %d"
% (target_step, query_step)
)
elif operation == "3": # 3' splice site
if query_step == 0:
step = target_step
operation = "D"
elif target_step == 0:
step = query_step
operation = "I"
else:
assert query_step == target_step
step = target_step
operation = "M"
elif operation == "C": # Codon
assert target_step == query_step
step = target_step
operation = "M"
elif operation == "D": # Deletion
assert query_step == 0
step = target_step
operation = "D"
elif operation == "I": # Insertion
assert target_step == 0
step = query_step
elif operation == "U": # Non-equivalenced (unaligned) region
if target_step > 0:
operation = "D"
words.append(operation)
words.append(str(target_step))
if query_step > 0:
operation = "I"
words.append(operation)
words.append(str(query_step))
continue
elif operation == "S": # Split codon
if target_step > 0:
operation = "D"
words.append(operation)
words.append(str(target_step))
if query_step > 0:
operation = "I"
words.append(operation)
words.append(str(query_step))
continue
elif operation == "F": # Frame shift
if target_step == 0:
step = query_step
operation = "I"
elif query_step == 0:
step = target_step
operation = "D"
else:
raise ValueError("Expected target step or query step to be 0")
else:
raise ValueError("Unknown operation %s" % operation)
words.append(operation)
words.append(str(step))
line = " ".join(words) + "\n"
return line
def _format_alignment_vulgar(self, alignment):
"""Return a string with a single alignment formatted as one vulgar line."""
if not isinstance(alignment, Alignment):
raise TypeError("Expected an Alignment object")
coordinates = alignment.coordinates
target_start = coordinates[0, 0]
target_end = coordinates[0, -1]
query_start = coordinates[1, 0]
query_end = coordinates[1, -1]
steps = coordinates[:, 1:] - coordinates[:, :-1]
query = alignment.query
target = alignment.target
try:
query_id = query.id
except AttributeError:
query_id = "query"
try:
target_id = target.id
except AttributeError:
target_id = "target"
try:
target_molecule_type = target.annotations["molecule_type"]
except (AttributeError, KeyError):
target_molecule_type = None
if target_molecule_type == "protein":
target_strand = "."
elif target_start <= target_end:
target_strand = "+"
elif target_start > target_end:
target_strand = "-"
steps[0, :] = -steps[0, :]
try:
query_molecule_type = query.annotations["molecule_type"]
except (AttributeError, KeyError):
query_molecule_type = None
if query_molecule_type == "protein":
query_strand = "."
elif query_start <= query_end:
query_strand = "+"
elif query_start > query_end:
query_strand = "-"
steps[1, :] = -steps[1, :]
score = alignment.score
words = [
"vulgar:",
query_id,
str(query_start),
str(query_end),
query_strand,
target_id,
str(target_start),
str(target_end),
target_strand,
str(score),
]
try:
operations = alignment.operations
except AttributeError:
for step in steps.transpose():
target_step, query_step = step
if target_step == query_step:
operation = "M"
elif query_step == 0:
operation = "G" # Gap; exonerate definition
elif target_step == 0:
operation = "G" # Gap; exonerate definition
elif (
query_molecule_type == "protein"
and target_molecule_type != "protein"
):
operation = "M"
elif (
query_molecule_type != "protein"
and target_molecule_type == "protein"
):
operation = "M"
else:
raise ValueError("Both target and query step are zero")
words.append(operation)
words.append(str(query_step))
words.append(str(target_step))
else:
steps = steps.transpose()
operations = operations.decode()
n = len(operations)
i = 0
while i < n:
target_step, query_step = steps[i]
operation = operations[i]
if operation == "M":
if target_step == query_step:
pass
elif target_step == 3 * query_step:
assert query_molecule_type == "protein"
assert target_molecule_type != "protein"
elif query_step == 3 * target_step:
assert query_molecule_type != "protein"
assert target_molecule_type == "protein"
else:
raise ValueError(
"Unexpected steps target %d, query %s for operation 'M'"
)
elif operation == "5": # 5' splice site
assert target_step == 2 or query_step == 2
elif operation == "N": # Intron
operation = "I" # Intron; exonerate definition
assert query_step == 0 or target_step == 0
elif operation == "3": # 3' splice site
assert target_step == 2 or query_step == 2
elif operation == "C": # Codon
assert target_step == query_step
elif operation == "D": # Deletion
assert query_step == 0
operation = "G" # Gap; exonerate definition
elif operation == "I": # Insertion
assert target_step == 0
operation = "G" # Gap; exonerate definition
elif operation == "U": # Non-equivalenced (unaligned) region
if target_step == 0:
assert query_step > 0
i += 1
target_step, dummy = steps[i]
assert dummy == 0
if query_step == 0:
assert target_step > 0
i += 1
dummy, query_step = steps[i]
assert dummy == 0
operation = operations[i]
assert operation == "U"
operation = "N" # Non-equivalenced region; exonerate definition
elif operation == "S": # Split codon
step = target_step
elif operation == "F": # Frame shift
step = target_step
else:
raise ValueError("Unknown operation %s" % operation)
words.append(operation)
words.append(str(query_step))
words.append(str(target_step))
i += 1
line = " ".join(words) + "\n"
return line
class AlignmentIterator(interfaces.AlignmentIterator):
"""Alignment iterator for the Exonerate text, cigar, and vulgar formats.
Each line in the file contains one pairwise alignment, which are loaded
and returned incrementally. Alignment score information such as the number
of matches and mismatches are stored as attributes of each alignment.
"""
def __init__(self, source):
"""Create an AlignmentIterator object.
Arguments:
- source - input data or file name
"""
super().__init__(source, mode="t", fmt="PSL")
stream = self.stream
self.program = "exonerate"
line = next(stream)
prefix = "Command line: "
assert line.startswith(prefix)
commandline = line[len(prefix) :].strip()
assert commandline.startswith("[")
assert commandline.endswith("]")
self.commandline = commandline[1:-1]
line = next(stream)
prefix = "Hostname: "
assert line.startswith(prefix)
hostname = line[len(prefix) :].strip()
assert hostname.startswith("[")
assert hostname.endswith("]")
self.hostname = hostname[1:-1]
@staticmethod
def _parse_cigar(words):
query_id = words[0]
query_start = int(words[1])
query_end = int(words[2])
query_strand = words[3]
target_id = words[4]
target_start = int(words[5])
target_end = int(words[6])
target_strand = words[7]
score = int(words[8])
target_seq = Seq(None, length=target_end)
query_seq = Seq(None, length=query_end)
target = SeqRecord(target_seq, id=target_id)
query = SeqRecord(query_seq, id=query_id)
qs = 0
ts = 0
n = (len(words) - 8) // 2
coordinates = numpy.empty((2, n + 1), int)
coordinates[0, 0] = ts
coordinates[1, 0] = qs
for i, (operation, step) in enumerate(zip(words[9::2], words[10::2])):
step = int(step)
if operation == "M": # match or mismatch
ts += step
qs += step
elif operation == "I": # insertion
if query_strand == "." and target_strand != ".":
qs += step * 3
else:
qs += step
elif operation == "D": # deletion
if target_strand == "." and query_strand != ".":
ts += step * 3
else:
ts += step
else:
raise ValueError("Unknown operation %s in cigar string" % operation)
coordinates[0, i + 1] = ts
coordinates[1, i + 1] = qs
if target_strand == "+":
coordinates[0, :] += target_start
elif target_strand == "-":
coordinates[0, :] = target_start - coordinates[0, :]
elif target_strand == ".": # protein
if query_strand != ".":
# dna to protein alignment; integer division, but round up:
coordinates[0, :] = (coordinates[0, :] + 2) // 3
coordinates[0, :] += target_start
target.annotations["molecule_type"] = "protein"
if query_strand == "+":
coordinates[1, :] += query_start
elif query_strand == "-":
coordinates[1, :] = query_start - coordinates[1, :]
elif query_strand == ".": # protein
if target_strand != ".":
# protein to dna alignment; integer division, but round up:
coordinates[1, :] = (coordinates[1, :] + 2) // 3
coordinates[1, :] += query_start
query.annotations["molecule_type"] = "protein"
alignment = Alignment([target, query], coordinates)
alignment.score = score
return alignment
@staticmethod
def _parse_vulgar(words):
query_id = words[0]
query_start = int(words[1])
query_end = int(words[2])
query_strand = words[3]
target_id = words[4]
target_start = int(words[5])
target_end = int(words[6])
target_strand = words[7]
score = int(words[8])
target_seq = Seq(None, length=target_end)
query_seq = Seq(None, length=query_end)
target = SeqRecord(target_seq, id=target_id)
query = SeqRecord(query_seq, id=query_id)
ops = words[9::3]
qs = 0
ts = 0
n = (len(words) - 8) // 3 + ops.count("N")
coordinates = numpy.empty((2, n + 1), int)
coordinates[0, 0] = ts
coordinates[1, 0] = qs
operations = bytearray(n)
i = 0
for (operation, query_step, target_step) in zip(
ops, words[10::3], words[11::3]
):
query_step = int(query_step)
target_step = int(target_step)
if operation == "M": # Match
pass
elif operation == "5": # 5' splice site
assert target_step == 2 or query_step == 2
elif operation == "I": # Intron
# use SAM/BAM definitions of operations:
operation = "N"
elif operation == "3": # 3' splice site
assert target_step == 2 or query_step == 2
elif operation == "C": # Codon
assert target_step % 3 == 0
assert query_step % 3 == 0
elif operation == "G": # Gap
# use SAM/BAM definitions of operations:
if query_step == 0:
operation = "D" # Deletion
elif target_step == 0:
operation = "I" # Insertion
else:
raise ValueError(
"Unexpected gap operation with steps %d, %d in vulgar line"
% (query_step, target_step)
)
elif operation == "N": # Non-equivalenced (unaligned) region
operation = "U" # 'N' is alread used for introns in SAM/BAM
if target_step > 0:
ts += target_step
coordinates[0, i + 1] = ts
coordinates[1, i + 1] = qs
operations[i] = ord(operation)
i += 1
if query_step > 0:
qs += query_step
coordinates[0, i + 1] = ts
coordinates[1, i + 1] = qs
operations[i] = ord(operation)
i += 1
continue
elif operation == "S": # Split codon
pass
elif operation == "F": # Frame shift
pass
else:
raise ValueError("Unknown operation %s in vulgar string" % operation)
ts += target_step
qs += query_step
coordinates[0, i + 1] = ts
coordinates[1, i + 1] = qs
operations[i] = ord(operation)
i += 1
if target_strand == "+":
coordinates[0, :] += target_start
elif target_strand == "-":
coordinates[0, :] = target_start - coordinates[0, :]
elif target_strand == ".": # protein
coordinates[0, :] += target_start
target.annotations["molecule_type"] = "protein"
if query_strand == "+":
coordinates[1, :] += query_start
elif query_strand == "-":
coordinates[1, :] = query_start - coordinates[1, :]
elif query_strand == ".": # protein
coordinates[1, :] += query_start
query.annotations["molecule_type"] = "protein"
alignment = Alignment([target, query], coordinates)
alignment.operations = operations
alignment.score = score
return alignment
def parse(self, stream):
"""Parse the next alignment from the stream."""
if stream is None:
raise StopIteration
for line in stream:
line = line.strip()
if line == "-- completed exonerate analysis":
try:
next(stream)
except StopIteration:
return
raise ValueError(
"Found additional data after 'completed exonerate analysis'; corrupt file?"
)
elif line.startswith("vulgar: "):
words = line[8:].split()
alignment = self._parse_vulgar(words)
yield alignment
elif line.startswith("cigar: "):
words = line[7:].split()
alignment = self._parse_cigar(words)
yield alignment
raise ValueError(
"Failed to find 'completed exonerate analysis'; truncated file?"
)

47
Tests/Exonerate/README.txt
View File

@ -8,31 +8,58 @@ Exonerate release version, from the most recent first.
Exonerate 2.4
-------------
exn_24_m_protein2genome_revcomp_fshifts.exn
exn_24_m_protein2genome_revcomp_fshifts_cigar.exn
exn_24_m_protein2genome_revcomp_fshifts_vulgar.exn
exn_24_m_protein2genome_met_intron.exn
exn_24_m_protein2genome_met_intron_cigar.exn
exn_24_m_protein2genome_met_intron_vulgar.exn
Exonerate 2.2
-------------
exn_22_m_affine_local.exn affine:local model alignment
exn_22_m_affine_local_cigar.exn affine:local model alignment, cigar lines
exn_22_m_affine_local_vulgar.exn affine:local model alignmen, vulgar lines
exn_22_m_cdna2genome.exn cdna2genome model alignment
exn_22_m_cdna2genome_cigar.exn cdna2genome model alignment, cigar lines
exn_22_m_cdna2genome_vulgar.exn cdna2genome model alignment, vulgar lines
exn_22_m_coding2coding.exn coding2coding model alignment
exn_22_m_coding2coding_cigar.exn coding2coding model alignment, cigar lines
exn_22_m_coding2coding_vulgar.exn coding2coding model alignment, vulgar lines
exn_22_m_coding2coding_fshifts.exn coding2coding model alignment, with frameshifts
exn_22_m_cigar_fshifts.exn coding2coding alignment with cigar lines only, frameshifts
exn_22_o_vulgar_fshifts.exn coding2coding alignment with vulgar lines only, frameshifts
exn_22_m_coding2genome.exn coding2genome model alignment
exn_22_m_coding2genome_cigar.exn coding2genome model alignment, cigar lines
exn_22_m_coding2genome_vulgar.exn coding2genome model alignment, vulgar lines
exn_22_m_dna2protein.exn dna2protein model alignment
exn_22_m_dna2protein_cigar.exn dna2protein model alignment, cigar lines
exn_22_m_dna2protein_vulgar.exn dna2protein model alignment, vulgar lines
exn_22_m_est2genome.exn est2genome model alignment
exn_22_m_est2genome_cigar.exn est2genome model alignment, cigar lines
exn_22_m_est2genome_vulgar.exn est2genome model alignment, vulgar lines
exn_22_m_genome2genome.exn genome2genome model alignment
exn_22_m_ner.exn ner model alignment
exn_22_m_protein2dna.exn protein2dna model alignment
exn_22_m_protein2dna_fshifts.exn protein2dna model alignment, with frameshifts
exn_22_m_protein2genome.exn protein2genome model alignment
exn_22_m_ungapped.exn ungapped model alignment (default)
exn_22_m_ungapped_trans.exn ungapped:translated model alignment
exn_22_o_vulgar_cigar.exn genome2genome alignment with vulgar and cigar lines only
exn_22_o_vulgar.exn genome2genome alignment with vulgar lines only
exn_22_o_vulgar_fshifts.exn coding2coding alignment with vulgar lines only, frameshifts
exn_22_m_ner.exn ner model alignment
exn_22_m_ner_cigar.exn ner model alignment, cigar lines
exn_22_m_ner_vulgar.exn ner model alignment, vulgar lines
exn_22_m_protein2dna.exn protein2dna model alignment
exn_22_m_protein2dna_cigar.exn protein2dna model alignment, cigar lines
exn_22_m_protein2dna_vulgar.exn protein2dna model alignment, vulgar lines
exn_22_m_protein2dna_fshifts.exn protein2dna model alignment, with frameshifts
exn_22_o_cigar_fshifts2.exn protein2dna alignment with cigar lines only, frameshifts
exn_22_o_vulgar_fshifts2.exn protein2dna alignment with vulgar lines only, frameshifts
exn_22_m_protein2genome.exn protein2genome model alignment
exn_22_m_protein2genome_cigar.exn protein2genome model alignment, cigar lines
exn_22_m_protein2genome_vulgar.exn protein2genome model alignment, vulgar lines
exn_22_m_ungapped.exn ungapped model alignment (default)
exn_22_m_ungapped_cigar.exn ungapped model alignment (default), cigar
exn_22_m_ungapped_vulgar.exn ungapped model alignment (default), vulgar
exn_22_m_ungapped_trans.exn ungapped:translated model alignment
exn_22_m_ungapped_trans_cigar.exn ungapped:translated model alignment, cigar
exn_22_m_ungapped_trans_vulgar.exn ungapped:translated model alignment, vulgar
exn_22_q_multiple.exn est2genome, multiple queries, multiple hits and hsps
exn_22_q_multiple_cigar.exn est2genome, multiple queries, multiple hits and hsps, cigar lines only
exn_22_q_multiple_vulgar.exn est2genome, multiple queries, multiple hits and hsps, vulgar lines only
exn_22_q_empty.exn est2genome, single query, no results
exn_22_q_none.exn est2genome, single query, no results

6
Tests/Exonerate/exn_22_m_affine_local_cigar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m affine:local ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar yes --showvulgar no]
Hostname: [Michiels-MacBook-Pro.local]
cigar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 6150 M 1230
cigar: gi|296143771|ref|NM_001180731.1| 83 552 + gi|330443688|ref|NC_001145.3| 253990 254474 + 359 M 34 D 1 M 6 D 2 M 101 D 2 M 6 I 2 M 3 I 1 M 12 D 1 M 9 I 1 M 26 D 1 M 34 D 5 M 13 D 2 M 7 D 1 M 10 D 1 M 14 D 3 M 9 D 1 M 20 D 2 M 2 D 1 M 7 D 1 M 2 D 1 M 6 D 1 M 3 I 1 M 2 I 3 M 10 D 1 M 2 D 3 M 9 I 2 M 9 I 3 M 7 D 1 M 6 I 2 M 8 D 1 M 32 I 2 M 9 I 2 M 9 D 2 M 23
cigar: gi|296143771|ref|NM_001180731.1| 60 517 + gi|330443715|ref|NC_001146.8| 454073 454531 + 219 M 14 I 1 M 7 I 1 M 3 I 1 M 12 D 1 M 23 D 1 M 16 I 2 M 17 D 2 M 6 D 1 M 7 D 1 M 8 I 1 M 12 D 1 M 3 D 1 M 14 D 1 M 10 D 1 M 20 D 1 M 19 D 2 M 9 I 5 M 8 I 1 M 41 I 3 M 42 D 1 M 8 D 3 M 1 D 1 M 26 I 2 M 11 I 3 M 12 D 1 M 18 D 1 M 18 D 1 M 14 D 1 M 30 I 1 M 7
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_affine_local_vulgar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m affine:local ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar no --showvulgar yes]
Hostname: [blackbriar]
vulgar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 6150 M 1230 1230
vulgar: gi|296143771|ref|NM_001180731.1| 83 552 + gi|330443688|ref|NC_001145.3| 253990 254474 + 359 M 34 34 G 0 1 M 6 6 G 0 2 M 101 101 G 0 2 M 6 6 G 2 0 M 3 3 G 1 0 M 12 12 G 0 1 M 9 9 G 1 0 M 26 26 G 0 1 M 34 34 G 0 5 M 13 13 G 0 2 M 7 7 G 0 1 M 10 10 G 0 1 M 14 14 G 0 3 M 9 9 G 0 1 M 20 20 G 0 2 M 2 2 G 0 1 M 7 7 G 0 1 M 2 2 G 0 1 M 6 6 G 0 1 M 3 3 G 1 0 M 2 2 G 3 0 M 10 10 G 0 1 M 2 2 G 0 3 M 9 9 G 2 0 M 9 9 G 3 0 M 7 7 G 0 1 M 6 6 G 2 0 M 8 8 G 0 1 M 32 32 G 2 0 M 9 9 G 2 0 M 9 9 G 0 2 M 23 23
vulgar: gi|296143771|ref|NM_001180731.1| 60 517 + gi|330443715|ref|NC_001146.8| 454073 454531 + 219 M 14 14 G 1 0 M 7 7 G 1 0 M 3 3 G 1 0 M 12 12 G 0 1 M 23 23 G 0 1 M 16 16 G 2 0 M 17 17 G 0 2 M 6 6 G 0 1 M 7 7 G 0 1 M 8 8 G 1 0 M 12 12 G 0 1 M 3 3 G 0 1 M 14 14 G 0 1 M 10 10 G 0 1 M 20 20 G 0 1 M 19 19 G 0 2 M 9 9 G 5 0 M 8 8 G 1 0 M 41 41 G 3 0 M 42 42 G 0 1 M 8 8 G 0 3 M 1 1 G 0 1 M 26 26 G 2 0 M 11 11 G 3 0 M 12 12 G 0 1 M 18 18 G 0 1 M 18 18 G 0 1 M 14 14 G 0 1 M 30 30 G 1 0 M 7 7
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_cdna2genome_cigar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m cdna2genome ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar yes --showvulgar no]
Hostname: [blackbriar]
cigar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 6146 M 1 M 3 M 1226
cigar: gi|296143771|ref|NM_001180731.1| 1230 0 - gi|330443520|ref|NC_001136.10| 1318045 1319275 + 6146 M 129 M 3 M 1098
cigar: gi|296143771|ref|NM_001180731.1| 0 516 + gi|330443688|ref|NC_001145.3| 85010 667216 + 518 M 11 I 1 M 15 I 2 M 4 I 1 M 1 I 1 M 8 I 4 M 17 D 168908 M 4 D 1 M 8 I 2 M 3 I 1 M 33 D 2 M 7 D 1 M 102 D 96824 M 14 D 2 M 10 I 2 M 5 D 2 M 10 I 2 M 4 D 1 M 20 I 1 M 15 D 1 M 5 I 3 M 4 D 122118 M 20 D 5 M 6 D 193839 M 12 D 2 M 5 I 1 M 7 D 2 M 1 D 1 M 12 M 75 M 6 I 1 M 4 D 1 M 2 D 1 M 3 D 1 M 41
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_cdna2genome_vulgar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m cdna2genome ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar no --showvulgar yes]
Hostname: [blackbriar]
vulgar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 6146 M 1 1 C 3 3 M 1226 1226
vulgar: gi|296143771|ref|NM_001180731.1| 1230 0 - gi|330443520|ref|NC_001136.10| 1318045 1319275 + 6146 M 129 129 C 3 3 M 1098 1098
vulgar: gi|296143771|ref|NM_001180731.1| 0 516 + gi|330443688|ref|NC_001145.3| 85010 667216 + 518 M 11 11 G 1 0 M 15 15 G 2 0 M 4 4 G 1 0 M 1 1 G 1 0 M 8 8 G 4 0 M 17 17 5 0 2 I 0 168904 3 0 2 M 4 4 G 0 1 M 8 8 G 2 0 M 3 3 G 1 0 M 33 33 G 0 2 M 7 7 G 0 1 M 102 102 5 0 2 I 0 96820 3 0 2 M 14 14 G 0 2 M 10 10 G 2 0 M 5 5 G 0 2 M 10 10 G 2 0 M 4 4 G 0 1 M 20 20 G 1 0 M 15 15 G 0 1 M 5 5 G 3 0 M 4 4 5 0 2 I 0 122114 3 0 2 M 20 20 G 0 5 M 6 6 5 0 2 I 0 193835 3 0 2 M 12 12 G 0 2 M 5 5 G 1 0 M 7 7 G 0 2 M 1 1 G 0 1 M 12 12 C 75 75 M 6 6 G 1 0 M 4 4 G 0 1 M 2 2 G 0 1 M 3 3 G 0 1 M 41 41
-- completed exonerate analysis

5
Tests/Exonerate/exn_22_m_cigar_fshifts.exn Normal file
View File

@ -0,0 +1,5 @@
Command line: [exonerate -m coding2coding c2c_frameshift2.fa scer_cad1.fa --showcigar yes --showvulgar no --showalignment no --bestn 3]
Hostname: [blackbriar]
cigar: gi|296143771|ref|NM_001180731.1| 0 160 + gi|296143771|ref|NM_001180731.1| 465 630 + 213 M 93 I 1 M 33 D 2 M 12 D 4 M 21
cigar: gi|296143771|ref|NM_001180731.1| 158 1 - gi|296143771|ref|NM_001180731.1| 628 466 - 201 M 24 D 6 M 39 I 1 M 93
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_coding2coding_cigar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m coding2coding ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar yes --showvulgar no]
Hostname: [blackbriar]
cigar: gi|296143771|ref|NM_001180731.1| 1228 1 - gi|330443520|ref|NC_001136.10| 1318047 1319274 + 2151 M 1227
cigar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 2106 M 1230
cigar: gi|296143771|ref|NM_001180731.1| 1065 1224 + gi|330443688|ref|NC_001145.3| 255638 255794 + 116 M 105 I 3 M 51
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_coding2coding_vulgar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m coding2coding ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar no --showvulgar yes]
Hostname: [blackbriar]
vulgar: gi|296143771|ref|NM_001180731.1| 1228 1 - gi|330443520|ref|NC_001136.10| 1318047 1319274 + 2151 C 1227 1227
vulgar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 2106 C 1230 1230
vulgar: gi|296143771|ref|NM_001180731.1| 1065 1224 + gi|330443688|ref|NC_001145.3| 255638 255794 + 116 C 105 105 G 3 0 C 51 51
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_coding2genome_cigar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m coding2genome ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar yes --showvulgar no]
Hostname: [blackbriar]
cigar: gi|296143771|ref|NM_001180731.1| 1228 1 - gi|330443520|ref|NC_001136.10| 1318047 1319274 + 2151 M 1227
cigar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 2106 M 1230
cigar: gi|296143771|ref|NM_001180731.1| 1065 1224 + gi|330443688|ref|NC_001145.3| 255638 255794 + 116 M 105 I 3 M 51
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_coding2genome_vulgar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m coding2genome ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar no --showvulgar yes]
Hostname: [blackbriar]
vulgar: gi|296143771|ref|NM_001180731.1| 1228 1 - gi|330443520|ref|NC_001136.10| 1318047 1319274 + 2151 C 1227 1227
vulgar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 2106 C 1230 1230
vulgar: gi|296143771|ref|NM_001180731.1| 1065 1224 + gi|330443688|ref|NC_001145.3| 255638 255794 + 116 C 105 105 G 3 0 C 51 51
-- completed exonerate analysis

4
Tests/Exonerate/exn_22_m_dna2protein_cigar.exn Normal file
View File

@ -0,0 +1,4 @@
Command line: [exonerate --showcigar yes --showvulgar no --showalignment no nuc2.fa pro.fa]
Hostname: [blackbriar]
cigar: dna 0 93 + protein 313 344 . 105 M 93
-- completed exonerate analysis

4
Tests/Exonerate/exn_22_m_dna2protein_vulgar.exn Normal file
View File

@ -0,0 +1,4 @@
Command line: [exonerate --showcigar no --showvulgar yes --showalignment no nuc2.fa pro.fa]
Hostname: [blackbriar]
vulgar: dna 0 93 + protein 313 344 . 105 M 93 31
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_est2genome_cigar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m est2genome ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar yes --showvulgar no]
Hostname: [blackbriar]
cigar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 6150 M 1230
cigar: gi|296143771|ref|NM_001180731.1| 0 346 + gi|330443688|ref|NC_001145.3| 85010 473201 + 439 M 11 I 1 M 15 I 2 M 4 I 1 M 1 I 1 M 8 I 4 M 17 D 168908 M 4 D 1 M 8 I 1 M 3 I 2 M 33 D 1 M 7 D 2 M 102 D 96824 M 14 D 2 M 10 I 2 M 5 D 2 M 10 I 2 M 4 D 1 M 20 I 1 M 15 D 1 M 5 I 3 M 4 D 122118 M 20 D 5 M 6
cigar: gi|296143771|ref|NM_001180731.1| 25 406 + gi|330443688|ref|NC_001145.3| 130198 11338 - 263 M 14 D 1 M 4 I 2 M 25 D 1 M 9 D 6 M 42 I 2 M 16 D 2 M 7 D 1 M 3 I 2 M 23 I 3 M 6 D 9357 M 1 I 1 M 11 D 1 M 12 I 1 M 9 D 1 M 10 I 1 M 18 D 1 M 5 D 109125 M 16 I 4 M 4 I 1 M 11 I 5 M 8 I 1 M 22 D 2 M 4 D 2 M 34 D 1 M 3 D 1 M 41
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_est2genome_vulgar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m est2genome ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar no --showvulgar yes]
Hostname: [blackbriar]
vulgar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 6150 M 1230 1230
vulgar: gi|296143771|ref|NM_001180731.1| 0 346 + gi|330443688|ref|NC_001145.3| 85010 473201 + 439 M 11 11 G 1 0 M 15 15 G 2 0 M 4 4 G 1 0 M 1 1 G 1 0 M 8 8 G 4 0 M 17 17 5 0 2 I 0 168904 3 0 2 M 4 4 G 0 1 M 8 8 G 1 0 M 3 3 G 2 0 M 33 33 G 0 1 M 7 7 G 0 2 M 102 102 5 0 2 I 0 96820 3 0 2 M 14 14 G 0 2 M 10 10 G 2 0 M 5 5 G 0 2 M 10 10 G 2 0 M 4 4 G 0 1 M 20 20 G 1 0 M 15 15 G 0 1 M 5 5 G 3 0 M 4 4 5 0 2 I 0 122114 3 0 2 M 20 20 G 0 5 M 6 6
vulgar: gi|296143771|ref|NM_001180731.1| 25 406 + gi|330443688|ref|NC_001145.3| 130198 11338 - 263 M 14 14 G 0 1 M 4 4 G 2 0 M 25 25 G 0 1 M 9 9 G 0 6 M 42 42 G 2 0 M 16 16 G 0 2 M 7 7 G 0 1 M 3 3 G 2 0 M 23 23 G 3 0 M 6 6 3 0 2 I 0 9353 5 0 2 M 1 1 G 1 0 M 11 11 G 0 1 M 12 12 G 1 0 M 9 9 G 0 1 M 10 10 G 1 0 M 18 18 G 0 1 M 5 5 3 0 2 I 0 109121 5 0 2 M 16 16 G 4 0 M 4 4 G 1 0 M 11 11 G 5 0 M 8 8 G 1 0 M 22 22 G 0 2 M 4 4 G 0 2 M 34 34 G 0 1 M 3 3 G 0 1 M 41 41
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_ner_cigar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m ner ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar yes --showvulgar no]
Hostname: [blackbriar]
cigar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 6150 M 1230
cigar: gi|296143771|ref|NM_001180731.1| 110 1230 + gi|330443681|ref|NC_001144.5| 297910 318994 + 502 M 8 D 28 I 30 M 12 D 12 I 9 M 14 D 8 I 1 M 5 I 1 M 8 D 11 I 29 D 3 M 4 D 1 M 7 D 1 M 7 D 10 I 10 M 7 D 9 I 4 M 19 D 11 I 11 M 13 D 9 M 6 I 1 M 10 D 2 M 4 D 1 M 10 I 368 D 20287 M 9 D 6 I 11 D 2 M 7 D 15 I 9 M 12 I 2 M 10 D 5 I 10 M 20 I 1 M 6 D 3 I 1 D 19 I 1 D 7 I 1 D 1 I 1 D 1 I 3 D 2 I 1 D 1 I 1 D 1 I 1 D 1 I 1 M 6 D 40 I 10 M 14 D 5 I 43 M 8 D 1 I 18 M 7 I 1 M 9 D 4 I 8 M 7 D 15 I 6 M 7 D 3 M 9 D 8 I 10 M 5 I 1 M 9 D 3 I 12 M 10 D 7 M 7 D 6 I 1 M 11 D 1 M 6 D 14 I 6 M 6 I 1 M 15 I 1 M 14 D 12 I 8 M 6 D 11 I 1 M 20 D 18 I 2 M 4 I 1 M 5 D 15 I 2 M 7 D 2 I 16 D 2 M 10 D 10 I 1 M 11 D 4 I 9 M 14 D 1 I 9 M 20
cigar: gi|296143771|ref|NM_001180731.1| 509 1192 + gi|330443520|ref|NC_001136.10| 183946 184603 + 440 M 6 D 8 I 22 D 17 M 11 D 7 I 19 D 7 M 29 D 8 I 11 D 5 M 11 D 4 I 1 D 1 I 2 D 3 I 2 D 1 I 3 D 2 I 10 M 15 D 2 I 16 D 9 M 16 D 3 M 7 D 1 M 6 D 1 M 6 I 1 M 16 D 21 I 18 M 10 D 11 I 1 M 4 D 2 M 4 I 1 M 10 D 1 I 10 M 3 I 1 M 11 D 14 I 5 M 13 D 19 I 5 M 9 I 1 M 9 D 10 I 9 M 6 D 6 I 3 D 3 I 1 D 1 I 8 M 22 D 2 I 19 D 7 M 19 D 1 I 6 M 12 D 12 I 18 D 3 M 6 I 1 M 11 D 1 M 4 D 2 M 11 I 1 M 5 D 6 I 14 M 11 D 13 I 1 M 10 D 7 I 2 D 1 I 1 D 2 I 2 D 1 I 2 D 1 I 11 M 10 I 1 M 19 D 1 I 19 M 10 D 14 I 1 D 2 I 2 D 1 I 10 M 10 D 2 M 9 D 2 I 6 M 8 D 3 I 12 D 2 M 25
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_ner_vulgar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m ner ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar no --showvulgar yes]
Hostname: [blackbriar]
vulgar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 6150 M 1230 1230
vulgar: gi|296143771|ref|NM_001180731.1| 110 1230 + gi|330443681|ref|NC_001144.5| 297910 318994 + 502 M 7 7 N 31 29 M 11 11 N 10 13 M 13 13 N 2 9 M 5 5 G 1 0 M 7 7 N 30 15 M 4 4 G 0 1 M 7 7 G 0 1 M 6 6 N 11 11 M 6 6 N 5 10 M 18 18 N 12 12 M 12 12 N 1 10 M 6 6 G 1 0 M 10 10 G 0 2 M 4 4 G 0 1 M 9 9 N 369 20288 M 8 8 N 12 9 M 6 6 N 10 16 M 12 12 G 2 0 M 9 9 N 11 6 M 20 20 G 1 0 M 5 5 N 12 37 M 5 5 N 11 41 M 13 13 N 44 6 M 7 7 N 19 2 M 7 7 G 1 0 M 8 8 N 9 5 M 6 6 N 7 16 M 6 6 N 1 4 M 8 8 N 11 9 M 5 5 G 1 0 M 8 8 N 13 4 M 9 9 N 1 8 M 6 6 N 2 7 M 11 11 G 0 1 M 5 5 N 7 15 M 6 6 G 1 0 M 15 15 G 1 0 M 13 13 N 9 13 M 5 5 N 2 12 M 19 19 N 3 19 M 4 4 G 1 0 M 4 4 N 3 16 M 6 6 N 17 5 M 9 9 N 2 11 M 10 10 N 10 5 M 13 13 N 10 2 M 20 20
vulgar: gi|296143771|ref|NM_001180731.1| 509 1192 + gi|330443520|ref|NC_001136.10| 183946 184603 + 440 M 5 5 N 23 26 M 10 10 N 20 15 M 28 28 N 12 14 M 10 10 N 19 12 M 14 14 N 17 12 M 15 15 N 1 4 M 7 7 G 0 1 M 6 6 G 0 1 M 6 6 G 1 0 M 15 15 N 19 22 M 9 9 N 2 12 M 4 4 G 0 2 M 4 4 G 1 0 M 9 9 N 11 2 M 3 3 G 1 0 M 10 10 N 6 15 M 12 12 N 6 20 M 9 9 G 1 0 M 8 8 N 10 11 M 5 5 N 13 11 M 21 21 N 20 10 M 18 18 N 7 2 M 11 11 N 19 16 M 6 6 G 1 0 M 11 11 G 0 1 M 4 4 G 0 2 M 11 11 G 1 0 M 4 4 N 15 7 M 10 10 N 2 14 M 9 9 N 19 13 M 10 10 G 1 0 M 18 18 N 20 2 M 9 9 N 14 18 M 10 10 G 0 2 M 8 8 N 7 3 M 7 7 N 13 6 M 25 25
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_protein2dna_cigar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m protein2dna ../scer_cad1_prot.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar yes --showvulgar no]
Hostname: [blackbriar]
cigar: sp|P24813|YAP2_YEAST 0 409 . gi|330443520|ref|NC_001136.10| 1319275 1318048 - 2105 M 1227
cigar: sp|P24813|YAP2_YEAST 28 120 . gi|330443688|ref|NC_001145.3| 253991 254270 + 205 M 36 D 3 M 240
cigar: sp|P24813|YAP2_YEAST 355 408 . gi|330443688|ref|NC_001145.3| 255638 255794 + 116 M 105 I 1 M 51
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_protein2dna_vulgar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m protein2dna ../scer_cad1_prot.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar no --showvulgar yes]
Hostname: [blackbriar]
vulgar: sp|P24813|YAP2_YEAST 0 409 . gi|330443520|ref|NC_001136.10| 1319275 1318048 - 2105 M 409 1227
vulgar: sp|P24813|YAP2_YEAST 28 120 . gi|330443688|ref|NC_001145.3| 253991 254270 + 205 M 12 36 G 0 3 M 80 240
vulgar: sp|P24813|YAP2_YEAST 355 408 . gi|330443688|ref|NC_001145.3| 255638 255794 + 116 M 35 105 G 1 0 M 17 51
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_protein2genome_cigar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m protein2genome ../scer_cad1_prot.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar yes --showvulgar no]
Hostname: [blackbriar]
cigar: sp|P24813|YAP2_YEAST 0 409 . gi|330443520|ref|NC_001136.10| 1319275 1318048 - 2105 M 1227
cigar: sp|P24813|YAP2_YEAST 28 120 . gi|330443688|ref|NC_001145.3| 253991 254270 + 205 M 36 D 3 M 240
cigar: sp|P24813|YAP2_YEAST 37 125 . gi|330443590|ref|NC_001140.6| 84646 68450 - 122 M 111 D 15934 M 151
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_protein2genome_vulgar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m protein2genome ../scer_cad1_prot.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar no --showvulgar yes]
Hostname: [blackbriar]
vulgar: sp|P24813|YAP2_YEAST 0 409 . gi|330443520|ref|NC_001136.10| 1319275 1318048 - 2105 M 409 1227
vulgar: sp|P24813|YAP2_YEAST 28 120 . gi|330443688|ref|NC_001145.3| 253991 254270 + 205 M 12 36 G 0 3 M 80 240
vulgar: sp|P24813|YAP2_YEAST 37 125 . gi|330443590|ref|NC_001140.6| 84646 68450 - 122 M 37 111 S 0 2 5 0 2 I 0 15928 3 0 2 S 1 1 M 50 150
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_ungapped_cigar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m ungapped ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar yes --showvulgar no]
Hostname: [blackbriar]
cigar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 6150 M 1230
cigar: gi|296143771|ref|NM_001180731.1| 121 236 + gi|330443688|ref|NC_001145.3| 254031 254146 + 233 M 115
cigar: gi|296143771|ref|NM_001180731.1| 1098 1166 + gi|330443688|ref|NC_001145.3| 255671 255739 + 151 M 68
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_ungapped_trans_cigar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m ungapped:trans ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar yes --showvulgar no]
Hostname: [blackbriar]
cigar: gi|296143771|ref|NM_001180731.1| 1228 1 - gi|330443520|ref|NC_001136.10| 1318047 1319274 + 2151 M 1227
cigar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 2106 M 1230
cigar: gi|296143771|ref|NM_001180731.1| 1230 0 - gi|330443520|ref|NC_001136.10| 1318045 1319275 + 2072 M 1230
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_ungapped_trans_vulgar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m ungapped:trans ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar no --showvulgar yes]
Hostname: [blackbriar]
vulgar: gi|296143771|ref|NM_001180731.1| 1228 1 - gi|330443520|ref|NC_001136.10| 1318047 1319274 + 2151 C 1227 1227
vulgar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 2106 C 1230 1230
vulgar: gi|296143771|ref|NM_001180731.1| 1230 0 - gi|330443520|ref|NC_001136.10| 1318045 1319275 + 2072 C 1230 1230
-- completed exonerate analysis

6
Tests/Exonerate/exn_22_m_ungapped_vulgar.exn Normal file
View File

@ -0,0 +1,6 @@
Command line: [exonerate -m ungapped ../scer_cad1.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar no --showvulgar yes]
Hostname: [blackbriar]
vulgar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 6150 M 1230 1230
vulgar: gi|296143771|ref|NM_001180731.1| 121 236 + gi|330443688|ref|NC_001145.3| 254031 254146 + 233 M 115 115
vulgar: gi|296143771|ref|NM_001180731.1| 1098 1166 + gi|330443688|ref|NC_001145.3| 255671 255739 + 151 M 68 68
-- completed exonerate analysis

5
Tests/Exonerate/exn_22_o_cigar_fshifts2.exn Normal file
View File

@ -0,0 +1,5 @@
Command line: [exonerate -m protein2dna scer_cad1_prot.fa scer_cad1frameshift.fa --showcigar yes --showvulgar no --showalignment no --bestn 3]
Hostname: [blackbriar]
cigar: sp|P24813|YAP2_YEAST 330 409 . gi|296143771|ref|NM_001180731.1| 216 455 + 367 M 129 D 2 M 108
cigar: sp|P24813|YAP2_YEAST 6 70 . gi|296143771|ref|NM_001180731.1| 16 208 + 322 M 192
-- completed exonerate analysis

9
Tests/Exonerate/exn_22_q_multiple_cigar.exn Normal file
View File

@ -0,0 +1,9 @@
Command line: [exonerate -m est2genome comb.fa /media/Waterloo/Downloads/genomes/scer_s288c/scer_s288c.fa --bestn 3 --showalignment no --showcigar yes --showvulgar no]
Hostname: [blackbriar]
cigar: gi|296142823|ref|NM_001178508.1| 0 897 + gi|330443482|ref|NC_001134.8| 560077 560974 + 4485 M 897
cigar: gi|296142823|ref|NM_001178508.1| 2 896 + gi|330443753|ref|NC_001148.4| 492933 492033 - 941 M 4 I 2 M 21 I 1 M 51 I 2 M 6 I 3 M 11 I 3 M 1 I 1 M 26 I 3 M 102 I 1 M 1 I 1 M 1 I 1 M 55 D 3 M 5 I 2 M 7 D 1 M 4 D 1 M 9 I 1 M 3 D 1 M 2 D 2 M 2 D 3 M 3 D 1 M 22 D 1 M 9 I 1 M 68 D 1 M 3 I 1 M 174 I 1 M 8 D 1 M 154 D 3 M 8 D 1 M 4 D 2 M 9 D 2 M 1 D 1 M 5 D 6 M 53 D 1 M 14 I 1 M 23
cigar: gi|296142823|ref|NM_001178508.1| 34 721 + gi|330443520|ref|NC_001136.10| 267809 300717 + 651 M 34 I 1 M 8 I 1 M 1 I 2 M 7 D 4 M 4 I 2 M 3 I 3 M 10 I 3 M 28 I 1 M 34 I 1 M 6 D 2 M 10 D 1 M 14 D 1 M 15 I 1 M 12 I 1 M 1 I 1 M 3 I 3 M 28 I 8 M 3 I 2 M 21 I 2 M 7 D 4 M 2 D 2 M 6 D 3 M 13 D 2 M 4 D 1 M 11 I 5 M 6 I 2 M 12 D 1 M 52 I 1 M 7 D 1 M 55 D 1 M 7 I 3 M 13 D 2 M 100 D 1 M 6 I 1 M 40 I 2 M 6 D 2 M 22 D 32238 M 12 D 1 M 18
cigar: gi|296143771|ref|NM_001180731.1| 0 1230 + gi|330443520|ref|NC_001136.10| 1319275 1318045 - 6150 M 1230
cigar: gi|296143771|ref|NM_001180731.1| 0 346 + gi|330443688|ref|NC_001145.3| 85010 473201 + 439 M 11 I 1 M 15 I 2 M 4 I 1 M 1 I 1 M 8 I 4 M 17 D 168908 M 4 D 1 M 8 I 1 M 3 I 2 M 33 D 1 M 7 D 2 M 102 D 96824 M 14 D 2 M 10 I 2 M 5 D 2 M 10 I 2 M 4 D 1 M 20 I 1 M 15 D 1 M 5 I 3 M 4 D 122118 M 20 D 5 M 6
cigar: gi|296143771|ref|NM_001180731.1| 25 406 + gi|330443688|ref|NC_001145.3| 130198 11338 - 263 M 14 D 1 M 4 I 2 M 25 D 1 M 9 D 6 M 42 I 2 M 16 D 2 M 7 D 1 M 3 I 2 M 23 I 3 M 6 D 9357 M 1 I 1 M 11 D 1 M 12 I 1 M 9 D 1 M 10 I 1 M 18 D 1 M 5 D 109125 M 16 I 4 M 4 I 1 M 11 I 5 M 8 I 1 M 22 D 2 M 4 D 2 M 34 D 1 M 3 D 1 M 41
-- completed exonerate analysis

4
Tests/Exonerate/exn_24_m_protein2genome_met_intron.exn
View File

@ -1,12 +1,12 @@
Command line: [exonerate -m protein2genome gene001_baits.fasta gene001_contigs.fasta --showcigar no --showvulgar no --bestn 1 --refine full]
Hostname: [RBGs-MacBook-Air.local]
Hostname: [Michiels-MacBook-Pro.local]
C4 Alignment:
------------
Query: Morus-gene001
Target: NODE_1_length_2817_cov_100.387732 SPAdes contig NODE_1:[revcomp]
Model: protein2genome:local
Raw score: 1958
Raw score: 1978
Query range: 48 -> 482
Target range: 2392 -> 388

4
Tests/Exonerate/exn_24_m_protein2genome_met_intron_cigar.exn Normal file
View File

@ -0,0 +1,4 @@
Command line: [exonerate -m protein2genome gene001_baits.fasta gene001_contigs.fasta --showalignment no --showcigar yes --showvulgar no --bestn 1 --refine full]
Hostname: [Michiels-MacBook-Pro.local]
cigar: Morus-gene001 48 482 . NODE_1_length_2817_cov_100.387732 2392 388 - 1978 M 111 D 152 M 99 D 109 M 111 D 86 M 303 D 223 M 140 D 133 M 537
-- completed exonerate analysis

4
Tests/Exonerate/exn_24_m_protein2genome_met_intron_vulgar.exn Normal file
View File

@ -0,0 +1,4 @@
Command line: [exonerate -m protein2genome gene001_baits.fasta gene001_contigs.fasta --showalignment no --showcigar no --showvulgar yes --bestn 1 --refine full]
Hostname: [Michiels-MacBook-Pro.local]
vulgar: Morus-gene001 48 482 . NODE_1_length_2817_cov_100.387732 2392 388 - 1978 M 37 111 5 0 2 I 0 148 3 0 2 M 33 99 5 0 2 I 0 105 3 0 2 M 37 111 5 0 2 I 0 82 3 0 2 M 101 303 S 0 1 5 0 2 I 0 218 3 0 2 S 1 2 M 46 138 5 0 2 I 0 129 3 0 2 M 179 537
-- completed exonerate analysis

4
Tests/Exonerate/exn_24_m_protein2genome_revcomp_fshifts_cigar.exn Normal file
View File

@ -0,0 +1,4 @@
Command line: [exonerate -m protein2genome gene026_baits.fasta gene026_contigs.fasta --showalignment no --showcigar yes --showvulgar no --bestn 2 --refine full]
Hostname: [Michiels-MacBook-Pro.local]
cigar: Morus-gene026 69 441 . NODE_2_length_1708_cov_48.590765 1416 331 - 1308 M 36 D 6 M 249 I 5 M 78 I 1 M 303 I 3 M 294 I 4 D 2 M 117
-- completed exonerate analysis

4
Tests/Exonerate/exn_24_m_protein2genome_revcomp_fshifts_vulgar.exn Normal file
View File

@ -0,0 +1,4 @@
Command line: [exonerate -m protein2genome gene026_baits.fasta gene026_contigs.fasta --showalignment no --showcigar no --showvulgar yes --bestn 2 --refine full]
Hostname: [Michiels-MacBook-Pro.local]
vulgar: Morus-gene026 69 441 . NODE_2_length_1708_cov_48.590765 1416 331 - 1308 M 12 36 G 0 6 M 83 249 G 5 0 M 26 78 G 1 0 M 101 303 G 3 0 M 98 294 G 4 0 F 0 2 M 39 117
-- completed exonerate analysis

3311
Tests/test_Align_exonerate.py Normal file
View File

File diff suppressed because it is too large Load Diff

2
Tests/test_SearchIO_exonerate.py
View File

@ -2346,7 +2346,7 @@ class ExonerateTextCases(unittest.TestCase):
self.assertEqual("SPAdes contig NODE_1", hit.description)
self.assertEqual(1, len(hit))
# first hit, first hsp
self.assertEqual(1958, hsp.score)
self.assertEqual(1978, hsp.score)
self.assertEqual([0, 0, 0, 0, 0, 0], hsp.query_strand_all)
self.assertEqual([-1, -1, -1, -1, -1, -1], hsp.hit_strand_all)
self.assertEqual(48, hsp.query_start)