diff --git a/mutalyzer/describe.py b/mutalyzer/describe.py
index 44de257d0ab5d47fd1f01b2893e9cf76c89d5a13..555894661475b0ed114568f06dbf4d72b50e6c90 100644
--- a/mutalyzer/describe.py
+++ b/mutalyzer/describe.py
@@ -212,15 +212,14 @@ class Seq(object):
class SeqList(list):
def __str__(self):
- representation = ';'.join(map(str, self))
-
if len(self) > 1:
- return "[{}]".format(representation)
- return representation
+ return "[{}]".format(';'.join(map(str, self)))
+ return str(self[0])
#__str__
#SeqList
class HGVSVar(object):
+ # NOTE: This may be obsolete, but check the JSON generation.
def update(self):
self.hgvs = str(self)
self.hgvs_length = len(self)
@@ -321,6 +320,7 @@ class DNAVar(models.DNAVar, HGVSVar):
variant stored in this class.
:rtype: int
"""
+ # NOTE: Obsolete?
if self.type in ("none", "unknown"): # `=' or `?'
return 1
@@ -434,6 +434,7 @@ class ProteinVar(models.ProteinVar, HGVSVar):
variant stored in this class.
:rtype: int
"""
+ # NOTE: Obsolete?
if not self.start: # =
return 1
@@ -477,6 +478,7 @@ class Allele(list):
:rtype: int
"""
# NOTE: Do we need to count the ; and [] ?
+ # NOTE: Obsolete?
return sum(map(lambda x: x.hgvs_length, self))
#length
#Allele
@@ -571,7 +573,7 @@ def var_to_rawvar(s1, s2, var, seq_list=[], container=DNAVar):
sample_end=var.sample_end)
#var_to_rawvar
-def describe(s1, s2, dna=True):
+def describe_dna(s1, s2):
"""
Give an allele description of the change from {s1} to {s2}.
@@ -584,84 +586,91 @@ def describe(s1, s2, dna=True):
:rtype: list(RawVar)
"""
description = Allele()
+ in_transposition = 0
+
+ for variant in extractor.extract(str(s1), len(s1), str(s2), len(s2), 0):
+ print (variant.type, variant.reference_start,
+ variant.reference_end, variant.sample_start,
+ variant.sample_end, variant.transposition_start,
+ variant.transposition_end)
+ print (variant.type & extractor.TRANSPOSITION_OPEN, variant.type &
+ extractor.TRANSPOSITION_CLOSE)
+
+ if variant.type & extractor.TRANSPOSITION_OPEN:
+ if not in_transposition:
+ seq_list = SeqList()
+ in_transposition += 1
+ #if
- if not dna:
- fs1, fs2 = make_fs_tables(1)
- longest_fs_f = max(find_fs(s1, s2, fs1), find_fs(s1, s2, fs2))
- longest_fs_r = max(find_fs(s2, s1, fs1), find_fs(s2, s1, fs2))
-
- if longest_fs_f > longest_fs_r:
- print s1[:longest_fs_f[1]], s1[longest_fs_f[1]:]
- print s2[:len(s2) - longest_fs_f[0]], \
- s2[len(s2) - longest_fs_f[0]:]
- s1_part = s1[:longest_fs_f[1]]
- s2_part = s2[:len(s2) - longest_fs_f[0]]
- term = longest_fs_f[0]
+ if in_transposition:
+ if variant.type & extractor.IDENTITY:
+ seq_list.append(Seq(start=variant.transposition_start + 1,
+ end=variant.transposition_end, reverse=False))
+ elif variant.type & extractor.REVERSE_COMPLEMENT:
+ seq_list.append(Seq(start=variant.transposition_start + 1,
+ end=variant.transposition_end, reverse=True))
+ else:
+ seq_list.append(Seq(
+ sequence=s2[variant.sample_start:variant.sample_end]))
#if
- else:
- print s1[:len(s1) - longest_fs_r[0]], \
- s1[len(s1) - longest_fs_r[0]:]
- print s2[:longest_fs_r[1]], s2[longest_fs_r[1]:]
- s1_part = s1[:len(s1) - longest_fs_r[0]]
- s2_part = s2[:longest_fs_r[1]]
- term = len(s2) - longest_fs_r[1]
- #else
-
- s1_part = s1
- s2_part = s2
- for variant in extractor.extract(unicode(s1_part), len(s1_part),
- unicode(s2_part), len(s2_part), 1):
- description.append(var_to_rawvar(s1, s2, variant, container=ProteinVar))
-
- if description:
- description[-1].term = term + 2
- description[-1].update()
+ elif not (variant.type & extractor.IDENTITY):
+ description.append(var_to_rawvar(s1, s2, variant))
+
+ if variant.type & extractor.TRANSPOSITION_CLOSE:
+ in_transposition -= 1
+
+ if not in_transposition:
+ description.append(var_to_rawvar(s1, s2, variant, seq_list))
#if
+ #for
+
+ return description
+#describe_dna
+
+def describe_protein(s1, s2):
+ """
+ Give an allele description of the change from {s1} to {s2}.
+
+ :arg s1: Sequence 1.
+ :type s1: str
+ :arg s2: Sequence 2.
+ :type s2: str
+
+ :returns: A list of RawVar objects, representing the allele.
+ :rtype: list(RawVar)
+ """
+ description = Allele()
+
+ fs1, fs2 = make_fs_tables(1)
+ longest_fs_f = max(find_fs(s1, s2, fs1), find_fs(s1, s2, fs2))
+ longest_fs_r = max(find_fs(s2, s1, fs1), find_fs(s2, s1, fs2))
+
+ if longest_fs_f > longest_fs_r:
+ print s1[:longest_fs_f[1]], s1[longest_fs_f[1]:]
+ print s2[:len(s2) - longest_fs_f[0]], s2[len(s2) - longest_fs_f[0]:]
+ s1_part = s1[:longest_fs_f[1]]
+ s2_part = s2[:len(s2) - longest_fs_f[0]]
+ term = longest_fs_f[0]
#if
- else: # DNA description extraction, the only thing that `works'.
- in_transposition = 0
-
- for variant in extractor.extract(unicode(s1), len(s1), unicode(s2), len(s2),
- 0):
- print variant.type, variant.reference_start, variant.reference_end, variant.sample_start, variant.sample_end, variant.transposition_start, variant.transposition_end
- print variant.type & extractor.TRANSPOSITION_OPEN, variant.type & extractor.TRANSPOSITION_CLOSE
-
- if variant.type & extractor.TRANSPOSITION_OPEN:
- if not in_transposition:
- seq_list = SeqList()
- in_transposition += 1
- #if
-
- if in_transposition:
- if variant.type & extractor.IDENTITY:
- seq_list.append(Seq(#reference=s1,
- start=variant.transposition_start + 1,
- end=variant.transposition_end, reverse=False))
- elif variant.type & extractor.REVERSE_COMPLEMENT:
- seq_list.append(Seq(#reference=s1,
- start=variant.transposition_start + 1,
- end=variant.transposition_end, reverse=True))
- else:
- seq_list.append(Seq(
- sequence=s2[variant.sample_start:variant.sample_end]))
- #if
- elif not (variant.type & extractor.IDENTITY):
- description.append(var_to_rawvar(s1, s2, variant))
-
- if variant.type & extractor.TRANSPOSITION_CLOSE:
- in_transposition -= 1
-
- if not in_transposition:
- description.append(var_to_rawvar(s1, s2, variant, seq_list))
- #for i in seq_list:
- # print i.dump()
- #if
- #for
+ else:
+ print s1[:len(s1) - longest_fs_r[0]], s1[len(s1) - longest_fs_r[0]:]
+ print s2[:longest_fs_r[1]], s2[longest_fs_r[1]:]
+ s1_part = s1[:len(s1) - longest_fs_r[0]]
+ s2_part = s2[:longest_fs_r[1]]
+ term = len(s2) - longest_fs_r[1]
#else
- # Nothing happened.
- if not description:
- return Allele(RawVar())
+ s1_part = s1
+ s2_part = s2
+ for variant in extractor.extract(str(s1_part), len(s1_part),
+ str(s2_part), len(s2_part), 1):
+ description.append(var_to_rawvar(s1, s2, variant,
+ container=ProteinVar))
+
+ if description:
+ description[-1].term = term + 2
+ description[-1].update()
+ #if
return description
-#describe
+#describe_protein
diff --git a/mutalyzer/entrypoints/mutalyzer.py b/mutalyzer/entrypoints/mutalyzer.py
index f2a4b10de57f038cd2f6342b6067a1ecbbc4db69..dc1ea00880440ac85000a77d20481fd5acbcf3bd 100644
--- a/mutalyzer/entrypoints/mutalyzer.py
+++ b/mutalyzer/entrypoints/mutalyzer.py
@@ -100,28 +100,28 @@ def check_name(description):
reference_sequence = O.getIndexedOutput("original", 0)
sample_sequence = O.getIndexedOutput("mutated", 0)
- extracted_allele = describe.describe(reference_sequence,
+ described_allele = describe.describe_dna(reference_sequence,
sample_sequence)
- #extracted_protein_allele = describe.describe(
+ #described_protein_allele = describe.describe(
# O.getIndexedOutput("oldprotein", 0),
# O.getIndexedOutput("newprotein", 0, default=""),
# DNA=False)
- extracted_protein_allele = ""
+ described_protein_allele = ""
- extracted = extracted_protein = '(skipped)'
+ described = described_protein = '(skipped)'
- if extracted_allele:
- extracted = extracted_allele
- if extracted_protein_allele:
- extracted_protein = extracted_protein_allele
+ if described_allele:
+ described = described_allele
+ if described_protein_allele:
+ described_protein = described_protein_allele
print "\nExperimental services:"
- print extracted
- print extracted_protein
+ print described
+ print described_protein
#print "+++ %s" % O.getOutput("myTranscriptDescription")
print json.dumps({"reference_sequence": reference_sequence,
"sample_sequence": sample_sequence, "allele_description":
- extracted_allele}, cls=MyEncoder)
+ described_allele}, cls=MyEncoder)
def main():