diff --git a/CHANGELOG.rst b/CHANGELOG.rst
index f339b4e614cdaad772c6256a8f87db11a4842178..a2a4a48dbd1849796c4f7fe0dda7182dce0018a8 100644
--- a/CHANGELOG.rst
+++ b/CHANGELOG.rst
@@ -1,6 +1,11 @@
=========
CHANGELOG
=========
+- 1.0.7
+ Adding choice for pKa values (option -p)
+
+ Fixing alphabetic order for enzymes
+
- 1.0.6
No default output file, only stdout
diff --git a/docs/conf.py b/docs/conf.py
index 6c548c4ab8751ef92dde0b5f67483d598d1493f0..7f9bc8e5f576e329e44771e3eb595fcbf9df2887 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -20,13 +20,13 @@ sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__),
# -- Project information -----------------------------------------------------
project = 'RapidPeptidesGenerator'
-copyright = '2018, Nicolas Maillet'
+copyright = '2019, Nicolas Maillet'
author = 'Nicolas Maillet'
# The short X.Y version
version = ''
# The full version, including alpha/beta/rc tags
-release = '1.0.6'
+release = '1.0.7'
# -- General configuration ---------------------------------------------------
diff --git a/docs/enzymes.rst b/docs/enzymes.rst
index 0d1e86e86750681016784c5679980674ead84cb2..7c345c9726bdad1b6fb85221071a44943ed20bbc 100644
--- a/docs/enzymes.rst
+++ b/docs/enzymes.rst
@@ -36,8 +36,8 @@ Available enzymes
28: :ref:`lysc` 29: :ref:`lysn` 30: :ref:`neut`
31: :ref:`ntcb` 32: :ref:`pap` 33: :ref:`peps13`
34: :ref:`peps2` 35: :ref:`prol` 36: :ref:`protk`
-37: :ref:`staphI` 38: :ref:`tev` 39: :ref:`therm`
-40: :ref:`throm` 41: :ref:`thromsg` 42: :ref:`tryps`
+37: :ref:`staphI` 38: :ref:`therm` 39: :ref:`throm`
+40: :ref:`thromsg` 41: :ref:`tev` 42: :ref:`tryps`
================== ================== ==================
.. _arg-c:
@@ -747,23 +747,6 @@ More information: https://web.expasy.org/peptide_cutter/peptidecutter_enzymes.ht
-.. _tev:
-
-Tobacco etch virus protease
-...........................
-
-Tobacco etch virus protease (TEV) preferentially cleaves after Q (`P1`) when followed by G or S in `P1'` and preceded by Y in `P3` and E in `P6`.
-
-**RPG definition:**
-
-cleaving rule:
-
-* ``(E)()()(Y)()(Q,)(G or S)``
-
-More information: https://web.expasy.org/peptide_cutter/peptidecutter_enzymes.html#TEV
-
-
-
.. _therm:
Thermolysin
@@ -836,6 +819,23 @@ More information: see thrombin cleavage kits of
+.. _tev:
+
+Tobacco etch virus protease
+...........................
+
+Tobacco etch virus protease (TEV) preferentially cleaves after Q (`P1`) when followed by G or S in `P1'` and preceded by Y in `P3` and E in `P6`.
+
+**RPG definition:**
+
+cleaving rule:
+
+* ``(E)()()(Y)()(Q,)(G or S)``
+
+More information: https://web.expasy.org/peptide_cutter/peptidecutter_enzymes.html#TEV
+
+
+
.. _tryps:
Trypsin
diff --git a/rpg/RapidPeptidesGenerator.py b/rpg/RapidPeptidesGenerator.py
index a8b1edc32bbaa083cfc65eba5a2c70d3ad4f5ce1..a6025668322e36472c39080378987beb6c043ddc 100644
--- a/rpg/RapidPeptidesGenerator.py
+++ b/rpg/RapidPeptidesGenerator.py
@@ -29,9 +29,9 @@
necessary functions
"""
-__version_info__ = ('1', '0', '6')
+__version_info__ = ('1', '0', '7')
__version__ = '.'.join(__version_info__)
-__revision_date__ = "2018-11-19"
+__revision_date__ = "2019-01-21"
__author__ = "Nicolas Maillet"
import argparse
@@ -275,6 +275,9 @@ def main():
"error(s) (--quiet enable, overwrite -v). If output "
"filename already exists, output file will be "
"overwritten.")
+ parser.add_argument("-p", "--pka", metavar="", choices=['ipc', 'stryer'],
+ default="ipc", help="Define pKa values. Either 'ipc' "
+ "or 'stryer (default: ipc)")
group_output = parser.add_mutually_exclusive_group()
group_output.add_argument("-o", "--outputfile", type=str, metavar="",
default="", help="Optional result file "
@@ -303,6 +306,11 @@ def main():
mode = "concurrent"
args.miscleavage = [] # No miscleavage on concurrent, infinite time
+ # --pka option
+ aa_pka = core.AA_PKA_IPC
+ if args.pka == "stryer":
+ aa_pka = core.AA_PKA_S
+
# --list option
if args.list:
list_enzyme()
@@ -371,7 +379,7 @@ def main():
# Make the actual digestion of input data
results_digestion = digest.digest_from_input(args.inputdata,
- enzymes_to_use, mode)
+ enzymes_to_use, mode, aa_pka)
# Output results
core.output_results(output_file, results_digestion, args.fmt, args.quiet,
diff --git a/rpg/core.py b/rpg/core.py
index 8c3b0ddba69fdc90846133df28f491e1c4d5671c..5d4f2ec428fb0834186272eb0fc04c63c860aac4 100644
--- a/rpg/core.py
+++ b/rpg/core.py
@@ -64,26 +64,27 @@ WATER_MASS = 18.01528
"""Mass of a water molecule."""
# Biochemistry Stryer 7th
-#AA_PKA = {"Nterm" : 8.0,
-# "C" : 8.3,
-# "D" : 4.1,
-# "E" : 4.1,
-# "H" : 6.0,
-# "K" : 10.8,
-# "R" : 12.5,
-# "Y" : 10.9,
-# "Cterm" : 3.1}
+AA_PKA_S = {"Nterm" : 8.0,
+ "C" : 8.3,
+ "D" : 4.1,
+ "E" : 4.1,
+ "H" : 6.0,
+ "K" : 10.8,
+ "R" : 12.5,
+ "Y" : 10.9,
+ "Cterm" : 3.1}
+"""pKa of important amino acid to compute pI (from Stryer)."""
# IPC_peptide
-AA_PKA = {"Nterm" : 9.564,
- "C" : 8.297,
- "D" : 3.887,
- "E" : 4.317,
- "H" : 6.018,
- "K" : 10.517,
- "R" : 12.503,
- "Y" : 10.071,
- "Cterm" : 2.383}
-"""pKa of important amino acid to compute pI."""
+AA_PKA_IPC = {"Nterm" : 9.564,
+ "C" : 8.297,
+ "D" : 3.887,
+ "E" : 4.317,
+ "H" : 6.018,
+ "K" : 10.517,
+ "R" : 12.503,
+ "Y" : 10.071,
+ "Cterm" : 2.383}
+"""pKa of important amino acid to compute pI (from IPC)."""
def handle_errors(message="", err=1, error_type=""):
"""Custom handling of errors and warnings.
diff --git a/rpg/digest.py b/rpg/digest.py
index 26d0068d7c299eb5cdeb9a5bd5decc28f4c4ab16..649ed3ec6a91bf7c65d05a5b80b19be713f81bfd 100644
--- a/rpg/digest.py
+++ b/rpg/digest.py
@@ -205,13 +205,15 @@ class ResultOneDigestion:
ret += "C terminal peptide: " + self.peptides[-1].sequence
return ret
-def one_digest(pep, enz):
+def one_digest(pep, enz, aa_pka):
"""Digest a peptide with an enzyme.
:param pep: peptide to digest
:param enz: enzyme to digest with
+ :param aa_pka: pKa values (IPC / Stryer)
:type pep: :py:class:`~rpg.sequence.Peptide`
:type enz: :py:class:`~rpg.enzyme.Enzyme`
+ :type aa_pka: str
:return: result of the digestion
:rtype: :py:class:`ResultOneDigestion`
@@ -235,7 +237,7 @@ def one_digest(pep, enz):
after = False
tmp_seq = pep.sequence[previous_pos:pos]
tmp_peptide = sequence.Peptide(pep.header, tmp_seq, enzyme_name,
- cpt, pos + original_pos)
+ aa_pka, cpt, pos + original_pos)
ret.add_peptide(tmp_peptide)
cpt += 1
a_cut_occurs = True
@@ -272,7 +274,8 @@ def one_digest(pep, enz):
if previous_pos != pos:
tmp_seq = pep.sequence[previous_pos:pos]
tmp_peptide = sequence.Peptide(pep.header, tmp_seq,
- enzyme_name, cpt,
+ enzyme_name, aa_pka,
+ cpt,
pos + original_pos)
ret.add_peptide(tmp_peptide)
cpt += 1
@@ -291,45 +294,49 @@ def one_digest(pep, enz):
if a_cut_occurs:
tmp_pos = len(pep.sequence) # Last portion of protein
tmp_seq = pep.sequence[previous_pos:]
- tmp_peptide = sequence.Peptide(pep.header, tmp_seq, enzyme_name, cpt,
- tmp_pos + original_pos)
+ tmp_peptide = sequence.Peptide(pep.header, tmp_seq, enzyme_name,
+ aa_pka, cpt, tmp_pos + original_pos)
ret.add_peptide(tmp_peptide)
# Not cut, don't change the peptide
else:
ret.add_peptide(pep)
return ret
-def digest_one_sequence(seq, enz, mode):
+def digest_one_sequence(seq, enz, mode, aa_pka):
"""Launch a digest procedure on one sequence.
:param sequence: sequence to digest
:param enz: enzymes to digest with
:param mode: digestion mode (concurrent / sequential)
+ :param aa_pka: pKa values (IPC / Stryer)
:type sequence: :py:class:`~rpg.sequence.Sequence`
:type enz: list(:py:class:`~rpg.enzyme.Enzyme`)
:type mode: str
+ :type aa_pka: str
:return: result of the digestion
:rtype: list(:py:class:`ResultOneDigestion`)
"""
ret = None
if mode == "sequential":
- ret = sequential_digest(seq, enz)
+ ret = sequential_digest(seq, enz, aa_pka)
elif mode == "concurrent":
- ret = concurrent_digest(seq, enz)
+ ret = concurrent_digest(seq, enz, aa_pka)
else:
core.handle_errors("not able to understand digetion mode. Switching "
"to 'sequential'.")
- ret = sequential_digest(seq, enz)
+ ret = sequential_digest(seq, enz, aa_pka)
return ret
-def sequential_digest(seq, enz):
+def sequential_digest(seq, enz, aa_pka):
"""Sequentially digest a sequence with all Enzymes, **one by one**.
:param seq: sequence to digest
:param enz: enzymes to digest with
+ :param aa_pka: pKa values (IPC / Stryer)
:type seq: :py:class:`~rpg.sequence.Sequence`
:type enz: list(:py:class:`~rpg.enzyme.Enzyme`)
+ :type aa_pka: str
:return: result of the digestion
:rtype: list(:py:class:`ResultOneDigestion`)
@@ -338,19 +345,22 @@ def sequential_digest(seq, enz):
# Check each enzymes
for an_enz in enz:
# Create a fake peptide from input sequence
- fake_peptide = sequence.Peptide(seq.header, seq.sequence, an_enz.name)
+ fake_peptide = sequence.Peptide(seq.header, seq.sequence, an_enz.name,
+ aa_pka)
# Digest it
- ret.append(one_digest(fake_peptide, an_enz))
+ ret.append(one_digest(fake_peptide, an_enz, aa_pka))
return ret
-def concurrent_digest(seq, enz):
+def concurrent_digest(seq, enz, aa_pka):
"""Concurrently digest a sequence with all Enzymes **at the same
time**.
:param seq: sequence to digest
:param enz: enzymes to digest with
+ :param aa_pka: pKa values (IPC / Stryer)
:type seq: :py:class:`~rpg.sequence.Sequence`
:type enz: list(:py:class:`~rpg.enzyme.Enzyme`)
+ :type aa_pka: str
:return: result of the digestion
:rtype: list(:py:class:`ResultOneDigestion`)
@@ -363,7 +373,7 @@ def concurrent_digest(seq, enz):
enzymes_name_to_write = enzymes_name_to_write[:-1]
# First peptide is the sequence itself
fake_peptide = sequence.Peptide(seq.header, seq.sequence,
- enzymes_name_to_write)
+ enzymes_name_to_write, aa_pka)
# Result is currently just the sequence (list of one peptide)
result = ResultOneDigestion(enzymes_name_to_write, [fake_peptide])
# Do we digest as much as we can?
@@ -380,7 +390,8 @@ def concurrent_digest(seq, enz):
# remove them from the global result
for peptide in result.pop_peptides():
# Digest it, return a list of ResultOneDigestion
- all_res_digestion_tmp.append(one_digest(peptide, an_enz))
+ all_res_digestion_tmp.append(one_digest(peptide, an_enz,
+ aa_pka))
# Merge the result of digestion with previous result
for i in all_res_digestion_tmp:
result.merge(i)
@@ -398,16 +409,18 @@ def concurrent_digest(seq, enz):
# it will be one result by enzyme
return [result]
-def digest_from_input(input_data, enz, mode):
+def digest_from_input(input_data, enz, mode, aa_pka):
"""Digest all sequences of input data with
selected enzymes and mode.
:param input_data: either a sequence or a file of sequence (fasta/fastq)
:param enz: enzymes to digest with
:param mode: digestion mode (concurrent / sequential)
+ :param aa_pka: pKa values (IPC / Stryer)
:type input_data: str
:type enz: list(:py:class:`~rpg.enzyme.Enzyme`)
:type mode: str
+ :type aa_pka: str
:return: result of digestions
:rtype: list(list(:py:class:`ResultOneDigestion`))
@@ -436,7 +449,7 @@ def digest_from_input(input_data, enz, mode):
sequence.check_sequence(seq))
# Digest sequence
results_digestion.append(digest_one_sequence
- (tmp_seq, enz, mode))
+ (tmp_seq, enz, mode, aa_pka))
seq = ""
header = tmp_line
tmp_line = in_file.readline().strip()
@@ -445,7 +458,7 @@ def digest_from_input(input_data, enz, mode):
sequence.check_sequence(seq))
# Digest it
results_digestion.append(digest_one_sequence(tmp_seq, enz,
- mode))
+ mode, aa_pka))
# Fastq file
elif header_first_car == "@":
header = in_file.readline().strip()
@@ -454,9 +467,8 @@ def digest_from_input(input_data, enz, mode):
tmp_seq = sequence.Sequence(header[1:],
sequence.check_sequence(seq))
# Digest sequence
- results_digestion.append(digest_one_sequence(tmp_seq,
- enz,
- mode))
+ results_digestion.append(digest_one_sequence(tmp_seq, enz,
+ mode, aa_pka))
in_file.readline()
in_file.readline()
header = in_file.readline().strip()
@@ -468,6 +480,7 @@ def digest_from_input(input_data, enz, mode):
tmp_seq = sequence.Sequence("Input",
sequence.check_sequence(input_data))
# Digest the sequence
- results_digestion.append(digest_one_sequence(tmp_seq, enz, mode))
+ results_digestion.append(digest_one_sequence(tmp_seq, enz, mode,
+ aa_pka))
# Return all peptides
return results_digestion
diff --git a/rpg/enzymes_definition.py b/rpg/enzymes_definition.py
index a7a27463add9425e08be05246f667984362c3da1..39e67f312209bf23531a4ba542f8f87ec2aac16f 100644
--- a/rpg/enzymes_definition.py
+++ b/rpg/enzymes_definition.py
@@ -931,7 +931,7 @@ ENZ.append(AFTER_G)
ENZ.append(AFTER_S)
ENZ.append(AFTER_E)
ENZ.append(AFTER_Y)
-ENZYME = enzyme.Enzyme(CPT_ENZ, "Papain", ENZ, 0)
+ENZYME = enzyme.Enzyme(CPT_ENZ, "Ficin", ENZ, 0)
# Add it to available enzymes
AVAILABLE_ENZYMES.append(ENZYME)
CPT_ENZ += 1
@@ -1398,42 +1398,6 @@ CPT_ENZ += 1
-# Tobacco etch virus protease
-# https://web.expasy.org/peptide_cutter/peptidecutter_enzymes.html#TEV
-# RULES: cleaves between Q (P1) and G or S in P1' when Y in P3 and E in P6.
-# RULES: cleaves after E-Xaa-Xaa-Y-Xaa-Q-(G/S)
-ENZ = []
-
-# Cutting rule
-AFTER_Q = rule.Rule(0, "Q", False, 1) # Never cleaves after Q, except...
-
-# Exceptions
-EXECPT_QG = rule.Rule(1, "G", False, -1) # Never cleaves after Q, followed by G
-EXECPT_QS = rule.Rule(1, "S", False, -1) # Never cleaves after Q, followed by S
-
-EXECPT_Y_Qx = rule.Rule(-2, "Y", False, -1) # Never cleaves after Q, followed by G/S, preceded by Y
-
-EXECPT_E__Y_Qx = rule.Rule(-5, "E", True, -1) # Always cleaves after Q, followed by G/S, preceded by Y and preceded by E
-
-# Add exception to cutting rules:
-EXECPT_Y_Qx.rules.append(EXECPT_E__Y_Qx)
-
-EXECPT_QG.rules.append(EXECPT_Y_Qx)
-EXECPT_QS.rules.append(EXECPT_Y_Qx)
-
-# Add exception to cutting rules
-AFTER_Q.rules.append(EXECPT_QG)
-AFTER_Q.rules.append(EXECPT_QS)
-
-# Add rules to enzyme
-ENZ.append(AFTER_Q)
-ENZYME = enzyme.Enzyme(CPT_ENZ, "Tobacco-Etch-Virus", ENZ, 0)
-# Add it to available enzymes
-AVAILABLE_ENZYMES.append(ENZYME)
-CPT_ENZ += 1
-
-
-
# Thermolysin
# https://web.expasy.org/peptide_cutter/peptidecutter_enzymes.html#Therm
# RULES: cleaves before A,F,I,L,M or V (P1') not preceded by D or E in P1 and not followed by P in P2'
@@ -1693,6 +1657,42 @@ CPT_ENZ += 1
+# Tobacco etch virus protease
+# https://web.expasy.org/peptide_cutter/peptidecutter_enzymes.html#TEV
+# RULES: cleaves between Q (P1) and G or S in P1' when Y in P3 and E in P6.
+# RULES: cleaves after E-Xaa-Xaa-Y-Xaa-Q-(G/S)
+ENZ = []
+
+# Cutting rule
+AFTER_Q = rule.Rule(0, "Q", False, 1) # Never cleaves after Q, except...
+
+# Exceptions
+EXECPT_QG = rule.Rule(1, "G", False, -1) # Never cleaves after Q, followed by G
+EXECPT_QS = rule.Rule(1, "S", False, -1) # Never cleaves after Q, followed by S
+
+EXECPT_Y_Qx = rule.Rule(-2, "Y", False, -1) # Never cleaves after Q, followed by G/S, preceded by Y
+
+EXECPT_E__Y_Qx = rule.Rule(-5, "E", True, -1) # Always cleaves after Q, followed by G/S, preceded by Y and preceded by E
+
+# Add exception to cutting rules:
+EXECPT_Y_Qx.rules.append(EXECPT_E__Y_Qx)
+
+EXECPT_QG.rules.append(EXECPT_Y_Qx)
+EXECPT_QS.rules.append(EXECPT_Y_Qx)
+
+# Add exception to cutting rules
+AFTER_Q.rules.append(EXECPT_QG)
+AFTER_Q.rules.append(EXECPT_QS)
+
+# Add rules to enzyme
+ENZ.append(AFTER_Q)
+ENZYME = enzyme.Enzyme(CPT_ENZ, "Tobacco-Etch-Virus", ENZ, 0)
+# Add it to available enzymes
+AVAILABLE_ENZYMES.append(ENZYME)
+CPT_ENZ += 1
+
+
+
# Trypsin
# https://web.expasy.org/peptide_cutter/peptidecutter_enzymes.html#Tryps
# RULES: after K except if next aa is P. This rule doesn't apply if W is before K
diff --git a/rpg/sequence.py b/rpg/sequence.py
index dfc389a5c6315acf8b0aa8e6f0752792d58f31db..3371ed0c1f4238c11243a7b87f48e1342c83fab8 100644
--- a/rpg/sequence.py
+++ b/rpg/sequence.py
@@ -33,11 +33,13 @@ class Peptide:
:param header: header of the peptide
:param sequence: sequence in amino acids
:param enzyme_name: name of the enzyme used
+ :param aa_pka: pKa values (IPC / Stryer)
:param nb_peptide: number of this peptide (default: 0)
:param position: position of cleavage on the original sequence (default: 0)
:type header: str
:type sequence: str
:type enzyme_name: str
+ :type aa_pka: str
:type nb_peptide: int
:type position: int
@@ -48,10 +50,12 @@ class Peptide:
:vartype mass: float
:vartype p_i: float
"""
- def __init__(self, header, sequence, enzyme_name, nb_peptide=0, position=0):
+ def __init__(self, header, sequence, enzyme_name, aa_pka, nb_peptide=0,
+ position=0):
self.header = header # header of this peptide
self.sequence = sequence # peptide sequence
self.enzyme_name = enzyme_name # name of the enzyme used
+ self.aa_pka = aa_pka # pKa values for pI calculation
self.nb_peptide = nb_peptide # number of this peptide
self.position = position # position of cleavage
self.size = len(sequence) # size of the peptide
@@ -64,11 +68,15 @@ class Peptide:
# self representation for print
def __repr__(self):
+ pka = "IPC"
+ if self.aa_pka == core.AA_PKA_S:
+ pka = "Stryer"
return "Original header: " + self.header + "\nNo. peptide: " + \
str(self.nb_peptide) + "\nEnzyme: " + self.enzyme_name + \
"\nCleav. pos: " + str(self.position) + "\nPep. size: " + \
- str(self.size) + "\nPep. mass: " + str(self.mass) + "\nPep. pI: " \
- + str(self.p_i) + "\nSequence: " + self.sequence + "\n"
+ str(self.size) + "\nPep. mass: " + str(self.mass) + \
+ "\npKa values from: " + pka + "\nPep. pI: " + str(self.p_i) +\
+ "\nSequence: " + self.sequence + "\n"
# Equality between two Peptides
def __eq__(self, other):
@@ -117,22 +125,22 @@ class Peptide:
# While we are not precise enough
while (ph_val-ph_min > precision) or (ph_max-ph_val > precision):
# Compute the pI
- qn1 = -1.0 / (1.0 + pow(10, (core.AA_PKA["Cterm"] - ph_val)))
- qn2 = -self.sequence.count('D') / (1.0 + pow(10, (core.AA_PKA["D"]-
+ qn1 = -1.0 / (1.0 + pow(10, (self.aa_pka["Cterm"] - ph_val)))
+ qn2 = -self.sequence.count('D') / (1.0 + pow(10, (self.aa_pka["D"]-
ph_val)))
- qn3 = -self.sequence.count('E') / (1.0 + pow(10, (core.AA_PKA["E"]-
+ qn3 = -self.sequence.count('E') / (1.0 + pow(10, (self.aa_pka["E"]-
ph_val)))
- qn4 = -self.sequence.count('C') / (1.0 + pow(10, (core.AA_PKA["C"]-
+ qn4 = -self.sequence.count('C') / (1.0 + pow(10, (self.aa_pka["C"]-
ph_val)))
- qn5 = -self.sequence.count('Y') / (1.0 + pow(10, (core.AA_PKA["Y"]-
+ qn5 = -self.sequence.count('Y') / (1.0 + pow(10, (self.aa_pka["Y"]-
ph_val)))
qp1 = self.sequence.count('H') / (1.0 + pow(10, (ph_val -
- core.AA_PKA["H"])))
- qp2 = 1.0 / (1.0 + pow(10, (ph_val - core.AA_PKA["Nterm"])))
+ self.aa_pka["H"])))
+ qp2 = 1.0 / (1.0 + pow(10, (ph_val - self.aa_pka["Nterm"])))
qp3 = self.sequence.count('K') / (1.0 + pow(10, (ph_val -
- core.AA_PKA["K"])))
+ self.aa_pka["K"])))
qp4 = self.sequence.count('R') / (1.0 + pow(10, (ph_val -
- core.AA_PKA["R"])))
+ self.aa_pka["R"])))
nq_final = qn1 + qn2 + qn3 + qn4 + qn5 + qp1 + qp2 + qp3 + qp4
# We are below solution, good pH value must be smaller
if nq_final < 0.0:
diff --git a/setup.py b/setup.py
index ec9795783162e92b307e92d481b85c3b70e4ea88..b5f3e20da0405dd3619abb7aedbf238f2f9b8c16 100644
--- a/setup.py
+++ b/setup.py
@@ -4,7 +4,7 @@ from setuptools import setup, find_packages
_MAJOR = 1
_MINOR = 0
-_MICRO = 6
+_MICRO = 7
version = '%d.%d.%d' % (_MAJOR, _MINOR, _MICRO)
release = '%d.%d' % (_MAJOR, _MINOR)
diff --git a/tests/test_RapidPeptidesGenerator.py b/tests/test_RapidPeptidesGenerator.py
index df7ef32b0ba2b91520b039bd34236fd4c4002274..1f1cbf5484e7dc625ea41d03217f39abb8280a5e 100644
--- a/tests/test_RapidPeptidesGenerator.py
+++ b/tests/test_RapidPeptidesGenerator.py
@@ -49,17 +49,15 @@ def test_list_enzyme(capsys):
RapidPeptidesGenerator.list_enzyme()
out, _ = capsys.readouterr()
assert out == "1: Arg-C\n2: Asp-N\n3: BNPS-Skatole\n4: Bromelain\n5: Casp"\
- "ase-1\n6: Caspase-2\n7: Caspase-3\n8: Caspase-4\n9: Caspas"\
- "e-5\n10: Caspase-6\n11: Caspase-7\n12: Caspase-8\n13: Casp"\
- "ase-9\n14: Caspase-10\n15: Chymotrypsin-high\n16: Chymotry"\
- "psin-low\n17: Clostripain\n18: CNBr\n19: Enterokinase\n20:"\
- " Factor-Xa\n21: Papain\n22: Formic-acid\n23: Glu-C\n24: Gl"\
- "utamyl-endopeptidase\n25: Granzyme-B\n26: Hydroxylamine\n2"\
- "7: Iodosobenzoic-acid\n28: Lys-C\n29: Lys-N\n30: Neutrophi"\
- "l-elastase\n31: NTCB\n32: Papain\n33: Pepsin-pH1.3\n34: Pe"\
- "psin-pH>=2\n35: Proline-endopeptidase\n36: Proteinase-K\n3"\
- "7: Staphylococcal-peptidase-I\n38: Tobacco-Etch-Virus\n39:"\
- " Thermolysin\n40: Thrombin\n41: Thrombin-SG\n42: Trypsin\n"
+ "ase-1\n6: Caspase-2\n7: Caspase-3\n8: Caspase-4\n9: Caspase-5\n10: Caspa"\
+ "se-6\n11: Caspase-7\n12: Caspase-8\n13: Caspase-9\n14: Caspase-10\n15: C"\
+ "hymotrypsin-high\n16: Chymotrypsin-low\n17: Clostripain\n18: CNBr\n19: E"\
+ "nterokinase\n20: Factor-Xa\n21: Ficin\n22: Formic-acid\n23: Glu-C\n24: G"\
+ "lutamyl-endopeptidase\n25: Granzyme-B\n26: Hydroxylamine\n27: Iodosobenz"\
+ "oic-acid\n28: Lys-C\n29: Lys-N\n30: Neutrophil-elastase\n31: NTCB\n32: P"\
+ "apain\n33: Pepsin-pH1.3\n34: Pepsin-pH>=2\n35: Proline-endopeptidase\n36"\
+ ": Proteinase-K\n37: Staphylococcal-peptidase-I\n38: Thermolysin\n39: Thr"\
+ "ombin\n40: Thrombin-SG\n41: Tobacco-Etch-Virus\n42: Trypsin\n"
def test_create_enzymes_to_use(capsys):
"""Test function 'create_enzymes_to_use(enzymes, miscleavage)'"""
diff --git a/tests/test_core.py b/tests/test_core.py
index e5cb68ad10343cc4e0d72b984d5dc6a9ce01801b..75a3720dd9ccc2076eaed46a65c8ab161fb7083c 100644
--- a/tests/test_core.py
+++ b/tests/test_core.py
@@ -75,7 +75,8 @@ def test_output_results(capsys, tmpdir):
# CSV output
seq = "WQSDESDFZQSDESDF"
- all_seq_digested = digest.digest_from_input(seq, enzymes, mode)
+ aa_pka = core.AA_PKA_IPC
+ all_seq_digested = digest.digest_from_input(seq, enzymes, mode, aa_pka)
output_file = tmpdir.join("test_result.csv")
fmt = "csv"
quiet = False
@@ -127,7 +128,7 @@ def test_output_results(capsys, tmpdir):
# CSV output in quiet
seq = "WQSDESDFZQSDESDF"
- all_seq_digested = digest.digest_from_input(seq, enzymes, mode)
+ all_seq_digested = digest.digest_from_input(seq, enzymes, mode, aa_pka)
output_file = tmpdir.join("test_result.csv")
fmt = "csv"
quiet = True
@@ -148,7 +149,7 @@ def test_output_results(capsys, tmpdir):
# CSV output in verbose > 2
seq = "WQSDESDFZQSDESDF"
- all_seq_digested = digest.digest_from_input(seq, enzymes, mode)
+ all_seq_digested = digest.digest_from_input(seq, enzymes, mode, aa_pka)
output_file = tmpdir.join("test_result.csv")
fmt = "csv"
quiet = False
@@ -176,23 +177,25 @@ def test_peptide():
header = "Test"
seq = "QWSDESDF"
enz_name = "fake_enzyme"
- pep0 = sequence.Peptide(header, seq, enz_name, 1, 3)
+ aa_pka = core.AA_PKA_IPC
+ pep0 = sequence.Peptide(header, seq, enz_name, aa_pka, 1, 3)
# Test function '__repr__()'
print_res = pep0.__repr__()
assert print_res == "Original header: Test\nNo. peptide: 1\nEnzyme: fake_"\
"enzyme\nCleav. pos: 3\nPep. size: 8\nPep. mass: 1012"\
- ".98488\nPep. pI: 2.91\nSequence: QWSDESDF\n"
+ ".98488\npKa values from: IPC\nPep. pI: 2.91\nSequenc"\
+ "e: QWSDESDF\n"
# Test function '__eq__()'
- pep1 = sequence.Peptide(header, seq, enz_name, 1, 3)
+ pep1 = sequence.Peptide(header, seq, enz_name, aa_pka, 1, 3)
assert pep0 == pep1
# Test function '__ne__()'
- pep2 = sequence.Peptide(header, seq, enz_name, 1, 2)
- pep3 = sequence.Peptide(header, seq, enz_name, 2, 3)
- pep4 = sequence.Peptide(header, seq, enz_name + "A", 1, 3)
- pep5 = sequence.Peptide(header, seq + "A", enz_name, 1, 3)
- pep6 = sequence.Peptide(header + "A", seq, enz_name, 1, 3)
+ pep2 = sequence.Peptide(header, seq, enz_name, aa_pka, 1, 2)
+ pep3 = sequence.Peptide(header, seq, enz_name, aa_pka, 2, 3)
+ pep4 = sequence.Peptide(header, seq, enz_name + "A", aa_pka, 1, 3)
+ pep5 = sequence.Peptide(header, seq + "A", enz_name, aa_pka, 1, 3)
+ pep6 = sequence.Peptide(header + "A", seq, enz_name, aa_pka, 1, 3)
assert pep0 != pep2
assert pep0 != pep3
assert pep0 != pep4
diff --git a/tests/test_digest.py b/tests/test_digest.py
index 49667d198320b6b1cbdc45a8983de900543f25c2..9735df5cce6059196c38f84d7eb3beede73a6053 100644
--- a/tests/test_digest.py
+++ b/tests/test_digest.py
@@ -5,6 +5,7 @@ from .context import rpg
from rpg import digest
from rpg import enzyme
from rpg import rule
+from rpg import core
from sequence import Peptide, Sequence
def test_resultonedigestion():
@@ -12,8 +13,9 @@ def test_resultonedigestion():
header = "Test"
seq = "QWSDESDF"
enz_name = "fake_enzyme"
- pep0 = Peptide(header, seq, enz_name, 0, 3)
- pep1 = Peptide(header, seq, enz_name, 1, 4)
+ aa_pka = core.AA_PKA_IPC
+ pep0 = Peptide(header, seq, enz_name, aa_pka, 0, 3)
+ pep1 = Peptide(header, seq, enz_name, aa_pka, 1, 4)
peptides = [pep0, pep1]
nb_cleav = 1
pos_mc = [2, 3]
@@ -26,11 +28,12 @@ def test_resultonedigestion():
"66\nPeptides: [Original header: Test\nNo. "\
"peptide: 0\nEnzyme: fake_enzyme\nCleav. po"\
"s: 3\nPep. size: 8\nPep. mass: 1012.98488"\
- "\nPep. pI: 2.91\nSequence: QWSDESDF\n, Ori"\
- "ginal header: Test\nNo. peptide: 1\nEnzyme"\
- ": fake_enzyme\nCleav. pos: 4\nPep. size: 8"\
- "\nPep. mass: 1012.98488\nPep. pI: 2.91\nSe"\
- "quence: QWSDESDF\n]\n"
+ "\npKa values from: IPC\nPep. pI: 2.91\nSeq"\
+ "uence: QWSDESDF\n, Original header: Test\n"\
+ "No. peptide: 1\nEnzyme: fake_enzyme\nCleav"\
+ ". pos: 4\nPep. size: 8\nPep. mass: 1012.98"\
+ "488\npKa values from: IPC\nPep. pI: 2.91\n"\
+ "Sequence: QWSDESDF\n]\n"
# Test function '__eq__()'
res_dig1 = digest.ResultOneDigestion(enz_name, peptides, nb_cleav, pos_mc)
@@ -130,23 +133,24 @@ def test_one_digest():
rule_dict[rule_exc] = False
all_rules = rule.create_rules(rule_dict)
enz = enzyme.Enzyme(-1, "fake_enzyme", all_rules)
+ aa_pka = core.AA_PKA_IPC
# Input sequence
- pep = Peptide("Test", "WASD", enz.name)
+ pep = Peptide("Test", "WASD", enz.name, aa_pka)
# Results, two peptides: 'WAS' and 'D'
- res_pep0 = Peptide("Test", "WAS", enz.name, 0, 3)
- res_pep1 = Peptide("Test", "D", enz.name, 1, 4)
+ res_pep0 = Peptide("Test", "WAS", enz.name, aa_pka, 0, 3)
+ res_pep1 = Peptide("Test", "D", enz.name, aa_pka, 1, 4)
# Test it!
- res = digest.one_digest(pep, enz)
+ res = digest.one_digest(pep, enz, aa_pka)
assert res.enzyme_name == "fake_enzyme"
assert res.peptides[0].__repr__() == res_pep0.__repr__()
assert res.peptides[1].__repr__() == res_pep1.__repr__()
# Input sequence
- pep = Peptide("Test", "WADSD", enz.name)
+ pep = Peptide("Test", "WADSD", enz.name, aa_pka)
# Results, no cut
- res_pep1 = Peptide("Test", "WADSD", enz.name, 0, 0)
+ res_pep1 = Peptide("Test", "WADSD", enz.name, aa_pka, 0, 0)
# Test it!
- res = digest.one_digest(pep, enz)
+ res = digest.one_digest(pep, enz, aa_pka)
assert res.enzyme_name == "fake_enzyme"
assert res.peptides[0].__repr__() == res_pep1.__repr__()
@@ -157,12 +161,12 @@ def test_one_digest():
all_rules = rule.create_rules(rule_dict)
enz = enzyme.Enzyme(-1, "fake_enzyme", all_rules)
# Input sequence
- pep = Peptide("Test", "WADS", enz.name)
+ pep = Peptide("Test", "WADS", enz.name, aa_pka)
# Results, two peptides: 'WAS' and 'D'
- res_pep0 = Peptide("Test", "WAD", enz.name, 0, 3)
- res_pep1 = Peptide("Test", "S", enz.name, 1, 4)
+ res_pep0 = Peptide("Test", "WAD", enz.name, aa_pka, 0, 3)
+ res_pep1 = Peptide("Test", "S", enz.name, aa_pka, 1, 4)
# Test it!
- res = digest.one_digest(pep, enz)
+ res = digest.one_digest(pep, enz, aa_pka)
assert res.enzyme_name == "fake_enzyme"
assert res.peptides[0].__repr__() == res_pep0.__repr__()
assert res.peptides[1].__repr__() == res_pep1.__repr__()
@@ -179,6 +183,7 @@ def test_digest_one_sequence():
all_rules = rule.create_rules(rule_dict)
enz1 = enzyme.Enzyme(-1, "fake_enzyme1", all_rules)
enzymes.append(enz1)
+ aa_pka = core.AA_PKA_IPC
# Second enzyme: cut after S
rule_dict = {}
@@ -194,13 +199,13 @@ def test_digest_one_sequence():
# Sequential, only one enzyme will cut
mode = "sequential"
# Enz1 will not cut
- res_pep0 = Peptide("Test", "WASDESDF", enzymes[0].name, 0, 0)
+ res_pep0 = Peptide("Test", "WASDESDF", enzymes[0].name, aa_pka, 0, 0)
# Enz2 will cut, three peptides: 'WAS', 'DES' and 'DF'
- res_pep1 = Peptide("Test", "WAS", enzymes[1].name, 0, 3)
- res_pep2 = Peptide("Test", "DES", enzymes[1].name, 1, 6)
- res_pep3 = Peptide("Test", "DF", enzymes[1].name, 2, 8)
+ res_pep1 = Peptide("Test", "WAS", enzymes[1].name, aa_pka, 0, 3)
+ res_pep2 = Peptide("Test", "DES", enzymes[1].name, aa_pka, 1, 6)
+ res_pep3 = Peptide("Test", "DF", enzymes[1].name, aa_pka, 2, 8)
# Test it!
- res = digest.digest_one_sequence(seq, enzymes, mode)
+ res = digest.digest_one_sequence(seq, enzymes, mode, aa_pka)
assert res[0].enzyme_name == "fake_enzyme1"
assert res[0].peptides[0].__repr__() == res_pep0.__repr__()
assert res[1].enzyme_name == "fake_enzyme2"
@@ -212,13 +217,13 @@ def test_digest_one_sequence():
mode = "concurrent"
enzs_name = enzymes[0].name + "-" + enzymes[1].name
# Results, five peptides: 'WAS', 'D', ES', 'D', and 'F'
- res_pep0 = Peptide("Test", "WAS", enzs_name, 0, 3)
- res_pep1 = Peptide("Test", "D", enzs_name, 1, 4)
- res_pep2 = Peptide("Test", "ES", enzs_name, 2, 6)
- res_pep3 = Peptide("Test", "D", enzs_name, 3, 7)
- res_pep4 = Peptide("Test", "F", enzs_name, 4, 8)
+ res_pep0 = Peptide("Test", "WAS", enzs_name, aa_pka, 0, 3)
+ res_pep1 = Peptide("Test", "D", enzs_name, aa_pka, 1, 4)
+ res_pep2 = Peptide("Test", "ES", enzs_name, aa_pka, 2, 6)
+ res_pep3 = Peptide("Test", "D", enzs_name, aa_pka, 3, 7)
+ res_pep4 = Peptide("Test", "F", enzs_name, aa_pka, 4, 8)
# Test it!
- res = digest.digest_one_sequence(seq, enzymes, mode)
+ res = digest.digest_one_sequence(seq, enzymes, mode, aa_pka)
assert res[0].enzyme_name == enzs_name
assert res[0].peptides[0].__repr__() == res_pep0.__repr__()
assert res[0].peptides[1].__repr__() == res_pep1.__repr__()
@@ -229,13 +234,13 @@ def test_digest_one_sequence():
# Error, so sequential, only one enzyme will cut
mode = "pwet"
# Enz1 will not cut
- res_pep0 = Peptide("Test", "WASDESDF", enzymes[0].name, 0, 0)
+ res_pep0 = Peptide("Test", "WASDESDF", enzymes[0].name, aa_pka, 0, 0)
# Enz2 will cut, three peptides: 'WAS', 'DES' and 'DF'
- res_pep1 = Peptide("Test", "WAS", enzymes[1].name, 0, 3)
- res_pep2 = Peptide("Test", "DES", enzymes[1].name, 1, 6)
- res_pep3 = Peptide("Test", "DF", enzymes[1].name, 2, 8)
+ res_pep1 = Peptide("Test", "WAS", enzymes[1].name, aa_pka, 0, 3)
+ res_pep2 = Peptide("Test", "DES", enzymes[1].name, aa_pka, 1, 6)
+ res_pep3 = Peptide("Test", "DF", enzymes[1].name, aa_pka, 2, 8)
# Test it!
- res = digest.digest_one_sequence(seq, enzymes, mode)
+ res = digest.digest_one_sequence(seq, enzymes, mode, aa_pka)
assert res[0].enzyme_name == "fake_enzyme1"
assert res[0].peptides[0].__repr__() == res_pep0.__repr__()
assert res[1].enzyme_name == "fake_enzyme2"
@@ -253,6 +258,7 @@ def test_sequential_digest():
all_rules = rule.create_rules(rule_dict)
enz1 = enzyme.Enzyme(-1, "fake_enzyme1", all_rules)
enzymes.append(enz1)
+ aa_pka = core.AA_PKA_IPC
# Second enzyme: cut after S
rule_dict = {}
@@ -266,15 +272,15 @@ def test_sequential_digest():
seq = Sequence("Test", "WASDESDF")
# Enz1 will cut
- res_pep0 = Peptide("Test", "WASD", enzymes[0].name, 0, 4)
- res_pep1 = Peptide("Test", "ESD", enzymes[0].name, 1, 7)
- res_pep2 = Peptide("Test", "F", enzymes[0].name, 2, 8)
+ res_pep0 = Peptide("Test", "WASD", enzymes[0].name, aa_pka, 0, 4)
+ res_pep1 = Peptide("Test", "ESD", enzymes[0].name, aa_pka, 1, 7)
+ res_pep2 = Peptide("Test", "F", enzymes[0].name, aa_pka, 2, 8)
# Enz2 will cut, three peptides: 'WAS', 'DES' and 'DF'
- res_pep3 = Peptide("Test", "WAS", enzymes[1].name, 0, 3)
- res_pep4 = Peptide("Test", "DES", enzymes[1].name, 1, 6)
- res_pep5 = Peptide("Test", "DF", enzymes[1].name, 2, 8)
+ res_pep3 = Peptide("Test", "WAS", enzymes[1].name, aa_pka, 0, 3)
+ res_pep4 = Peptide("Test", "DES", enzymes[1].name, aa_pka, 1, 6)
+ res_pep5 = Peptide("Test", "DF", enzymes[1].name, aa_pka, 2, 8)
# Test it!
- res = digest.sequential_digest(seq, enzymes)
+ res = digest.sequential_digest(seq, enzymes, aa_pka)
assert res[0].enzyme_name == "fake_enzyme1"
assert res[0].peptides[0].__repr__() == res_pep0.__repr__()
assert res[0].peptides[1].__repr__() == res_pep1.__repr__()
@@ -294,6 +300,7 @@ def test_concurrent_digest():
all_rules = rule.create_rules(rule_dict)
enz1 = enzyme.Enzyme(-1, "fake_enzyme1", all_rules)
enzymes.append(enz1)
+ aa_pka = core.AA_PKA_S
# Second enzyme: cut after S
rule_dict = {}
@@ -307,14 +314,14 @@ def test_concurrent_digest():
seq = Sequence("Test", "WASDESDF")
enzs_name = enzymes[0].name + "-" + enzymes[1].name
# Results
- res_pep0 = Peptide("Test", "WAS", enzs_name, 0, 3)
- res_pep1 = Peptide("Test", "D", enzs_name, 1, 4)
- res_pep2 = Peptide("Test", "ES", enzs_name, 2, 6)
- res_pep3 = Peptide("Test", "D", enzs_name, 3, 7)
- res_pep4 = Peptide("Test", "F", enzs_name, 4, 8)
+ res_pep0 = Peptide("Test", "WAS", enzs_name, aa_pka, 0, 3)
+ res_pep1 = Peptide("Test", "D", enzs_name, aa_pka, 1, 4)
+ res_pep2 = Peptide("Test", "ES", enzs_name, aa_pka, 2, 6)
+ res_pep3 = Peptide("Test", "D", enzs_name, aa_pka, 3, 7)
+ res_pep4 = Peptide("Test", "F", enzs_name, aa_pka, 4, 8)
# Test it!
- res = digest.concurrent_digest(seq, enzymes)
+ res = digest.concurrent_digest(seq, enzymes, aa_pka)
assert res[0].enzyme_name == enzs_name
assert res[0].peptides[0].__repr__() == res_pep0.__repr__()
assert res[0].peptides[1].__repr__() == res_pep1.__repr__()
@@ -331,11 +338,12 @@ def test_digest_from_input(capsys, tmpdir):
enz1 = enzyme.Enzyme(-1, "fake_enzyme1", all_rules)
enzymes = [enz1]
mode = "sequential"
+ aa_pka = core.AA_PKA_IPC
# Test wrong file
with pytest.raises(SystemExit) as pytest_wrapped_e:
digest.digest_from_input(str(Path.home()) + "/rpg_user.py",
- enzymes, mode)
+ enzymes, mode, aa_pka)
_, err = capsys.readouterr()
assert err == "Input Error: input file format not recognized (f).\n"
assert pytest_wrapped_e.type == SystemExit
@@ -343,92 +351,103 @@ def test_digest_from_input(capsys, tmpdir):
# Test input data
seq = "WQSDESDFZQSDESDF"
- res = digest.digest_from_input(seq, enzymes, mode)
+ res = digest.digest_from_input(seq, enzymes, mode, aa_pka)
assert res[0][0].__repr__() == "Number of cleavage: 4\nNumber of miscle"\
"avage: 0\nPositions of miscleavage: []"\
"\nRatio of miscleavage: 0.0\nPeptides: "\
"[Original header: Input\nNo. peptide: 0"\
"\nEnzyme: fake_enzyme1\nCleav. pos: 4\nPe"\
- "p. size: 4\nPep. mass: 534.52598\nPep. pI"\
- ": 3.14\nSequence: WQSD\n, Original header:"\
- " Input\nNo. peptide: 1\nEnzyme: fake_enzy"\
- "me1\nCleav. pos: 7\nPep. size: 3\nPep. ma"\
- "ss: 349.29758\nPep. pI: 3.04\nSequence: ES"\
- "D\n, Original header: Input\nNo. peptide:"\
- " 2\nEnzyme: fake_enzyme1\nCleav. pos: 12"\
- "\nPep. size: 5\nPep. mass: 495.48938\nPep"\
- ". pI: 3.14\nSequence: FZQSD\n, Original he"\
- "ader: Input\nNo. peptide: 3\nEnzyme: fake"\
- "_enzyme1\nCleav. pos: 15\nPep. size: 3\nP"\
- "ep. mass: 349.29758\nPep. pI: 3.04\nSequen"\
- "ce: ESD\n, Original header: Input\nNo. pe"\
- "ptide: 4\nEnzyme: fake_enzyme1\nCleav. po"\
- "s: 16\nPep. size: 1\nPep. mass: 165.19188"\
- "\nPep. pI: 5.97\nSequence: F\n]\n"
+ "p. size: 4\nPep. mass: 534.52598\npKa val"\
+ "ues from: IPC\nPep. pI: 3.14\nSequence: W"\
+ "QSD\n, Original header: Input\nNo. peptid"\
+ "e: 1\nEnzyme: fake_enzyme1\nCleav. pos: 7"\
+ "\nPep. size: 3\nPep. mass: 349.29758\npKa"\
+ " values from: IPC\nPep. pI: 3.04\nSequenc"\
+ "e: ESD\n, Original header: Input\nNo. pep"\
+ "tide: 2\nEnzyme: fake_enzyme1\nCleav. pos"\
+ ": 12\nPep. size: 5\nPep. mass: 495.48938"\
+ "\npKa values from: IPC\nPep. pI: 3.14\nSe"\
+ "quence: FZQSD\n, Original header: Input\n"\
+ "No. peptide: 3\nEnzyme: fake_enzyme1\nCle"\
+ "av. pos: 15\nPep. size: 3\nPep. mass: 349"\
+ ".29758\npKa values from: IPC\nPep. pI: 3."\
+ "04\nSequence: ESD\n, Original header: Inp"\
+ "ut\nNo. peptide: 4\nEnzyme: fake_enzyme1"\
+ "\nCleav. pos: 16\nPep. size: 1\nPep. mass"\
+ ": 165.19188\npKa values from: IPC\nPep. p"\
+ "I: 5.97\nSequence: F\n]\n"
# Test fasta file
fasta_file = tmpdir.join("test.fasta")
fasta_file.write(">Fake1\nWQSDESDFZQS\nDESDF\n>Fake2\nNPHARDORCOMPLET")
- res = digest.digest_from_input(str(fasta_file), enzymes, mode)
+ res = digest.digest_from_input(str(fasta_file), enzymes, mode, aa_pka)
assert res[0][0].__repr__() == "Number of cleavage: 4\nNumber of miscle"\
"avage: 0\nPositions of miscleavage: []"\
"\nRatio of miscleavage: 0.0\nPeptides: "\
"[Original header: Fake1\nNo. peptide: 0\n"\
"Enzyme: fake_enzyme1\nCleav. pos: 4\nPep."\
- " size: 4\nPep. mass: 534.52598\nPep. pI: "\
- "3.14\nSequence: WQSD\n, Original header: F"\
- "ake1\nNo. peptide: 1\nEnzyme: fake_enzyme"\
- "1\nCleav. pos: 7\nPep. size: 3\nPep. mass"\
- ": 349.29758\nPep. pI: 3.04\nSequence: ESD"\
- "\n, Original header: Fake1\nNo. peptide: "\
- "2\nEnzyme: fake_enzyme1\nCleav. pos: 12\n"\
- "Pep. size: 5\nPep. mass: 495.48938\nPep. "\
- "pI: 3.14\nSequence: FZQSD\n, Original head"\
- "er: Fake1\nNo. peptide: 3\nEnzyme: fake_e"\
- "nzyme1\nCleav. pos: 15\nPep. size: 3\nPep"\
- ". mass: 349.29758\nPep. pI: 3.04\nSequence"\
- ": ESD\n, Original header: Fake1\nNo. pept"\
- "ide: 4\nEnzyme: fake_enzyme1\nCleav. pos:"\
- " 16\nPep. size: 1\nPep. mass: 165.19188\n"\
- "Pep. pI: 5.97\nSequence: F\n]\n"
- assert res[1][0].__repr__() == "Number of cleavage: 0\nNumber of miscle"\
- "avage: 0\nPositions of miscleavage: []"\
- "\nRatio of miscleavage: 0\nPeptides: [O"\
- "riginal header: Fake2\nNo. peptide: 0\nEn"\
- "zyme: fake_enzyme1\nCleav. pos: 0\nPep. s"\
- "ize: 15\nPep. mass: 2014.35098\nPep. pI: "\
- "7.16\nSequence: NPHARDORCOMPLET\n]\n"
+ " size: 4\nPep. mass: 534.52598\npKa value"\
+ "s from: IPC\nPep. pI: 3.14\nSequence: WQS"\
+ "D\n, Original header: Fake1\nNo. peptide:"\
+ " 1\nEnzyme: fake_enzyme1\nCleav. pos: 7\n"\
+ "Pep. size: 3\nPep. mass: 349.29758\npKa v"\
+ "alues from: IPC\nPep. pI: 3.04\nSequence:"\
+ " ESD\n, Original header: Fake1\nNo. pepti"\
+ "de: 2\nEnzyme: fake_enzyme1\nCleav. pos: "\
+ "12\nPep. size: 5\nPep. mass: 495.48938\np"\
+ "Ka values from: IPC\nPep. pI: 3.14\nSeque"\
+ "nce: FZQSD\n, Original header: Fake1\nNo."\
+ " peptide: 3\nEnzyme: fake_enzyme1\nCleav."\
+ " pos: 15\nPep. size: 3\nPep. mass: 349.29"\
+ "758\npKa values from: IPC\nPep. pI: 3.04"\
+ "\nSequence: ESD\n, Original header: Fake1"\
+ "\nNo. peptide: 4\nEnzyme: fake_enzyme1\nC"\
+ "leav. pos: 16\nPep. size: 1\nPep. mass: 1"\
+ "65.19188\npKa values from: IPC\nPep. pI: "\
+ "5.97\nSequence: F\n]\n"
+ assert res[1][0].__repr__() == "Number of cleavage: 0\nNumber of miscleav"\
+ "age: 0\nPositions of miscleavage: []\nRat"\
+ "io of miscleavage: 0\nPeptides: [Original"\
+ " header: Fake2\nNo. peptide: 0\nEnzyme: f"\
+ "ake_enzyme1\nCleav. pos: 0\nPep. size: 15"\
+ "\nPep. mass: 2014.35098\npKa values from:"\
+ " IPC\nPep. pI: 7.16\nSequence: NPHARDORCO"\
+ "MPLET\n]\n"
# Test fastq file (same result)
fastq_file = tmpdir.join("test.fastq")
fastq_file.write("@Fake1\nWQSDESDFZQSDESDF\n+Fake1\nnWQSDESDFZQSDESDF\n@Fa"\
"ke2\nNPHARDORCOMPLET\n+Fake2\nnNPHARDORCOMPLET\n")
- res = digest.digest_from_input(str(fastq_file), enzymes, mode)
+ res = digest.digest_from_input(str(fastq_file), enzymes, mode, aa_pka)
assert res[0][0].__repr__() == "Number of cleavage: 4\nNumber of miscle"\
"avage: 0\nPositions of miscleavage: []"\
"\nRatio of miscleavage: 0.0\nPeptides: "\
"[Original header: Fake1\nNo. peptide: 0\n"\
"Enzyme: fake_enzyme1\nCleav. pos: 4\nPep."\
- " size: 4\nPep. mass: 534.52598\nPep. pI: "\
- "3.14\nSequence: WQSD\n, Original header: F"\
- "ake1\nNo. peptide: 1\nEnzyme: fake_enzyme"\
- "1\nCleav. pos: 7\nPep. size: 3\nPep. mass"\
- ": 349.29758\nPep. pI: 3.04\nSequence: ESD"\
- "\n, Original header: Fake1\nNo. peptide: "\
- "2\nEnzyme: fake_enzyme1\nCleav. pos: 12\n"\
- "Pep. size: 5\nPep. mass: 495.48938\nPep. "\
- "pI: 3.14\nSequence: FZQSD\n, Original head"\
- "er: Fake1\nNo. peptide: 3\nEnzyme: fake_e"\
- "nzyme1\nCleav. pos: 15\nPep. size: 3\nPep"\
- ". mass: 349.29758\nPep. pI: 3.04\nSequence"\
- ": ESD\n, Original header: Fake1\nNo. pept"\
- "ide: 4\nEnzyme: fake_enzyme1\nCleav. pos:"\
- " 16\nPep. size: 1\nPep. mass: 165.19188\n"\
- "Pep. pI: 5.97\nSequence: F\n]\n"
+ " size: 4\nPep. mass: 534.52598\npKa value"\
+ "s from: IPC\nPep. pI: 3.14\nSequence: WQS"\
+ "D\n, Original header: Fake1\nNo. peptide:"\
+ " 1\nEnzyme: fake_enzyme1\nCleav. pos: 7\n"\
+ "Pep. size: 3\nPep. mass: 349.29758\npKa v"\
+ "alues from: IPC\nPep. pI: 3.04\nSequence:"\
+ " ESD\n, Original header: Fake1\nNo. pepti"\
+ "de: 2\nEnzyme: fake_enzyme1\nCleav. pos: "\
+ "12\nPep. size: 5\nPep. mass: 495.48938\np"\
+ "Ka values from: IPC\nPep. pI: 3.14\nSeque"\
+ "nce: FZQSD\n, Original header: Fake1\nNo."\
+ " peptide: 3\nEnzyme: fake_enzyme1\nCleav."\
+ " pos: 15\nPep. size: 3\nPep. mass: 349.29"\
+ "758\npKa values from: IPC\nPep. pI: 3.04"\
+ "\nSequence: ESD\n, Original header: Fake1"\
+ "\nNo. peptide: 4\nEnzyme: fake_enzyme1\nC"\
+ "leav. pos: 16\nPep. size: 1\nPep. mass: 1"\
+ "65.19188\npKa values from: IPC\nPep. pI: "\
+ "5.97\nSequence: F\n]\n"
assert res[1][0].__repr__() == "Number of cleavage: 0\nNumber of miscle"\
"avage: 0\nPositions of miscleavage: []"\
"\nRatio of miscleavage: 0\nPeptides: [O"\
"riginal header: Fake2\nNo. peptide: 0\nEn"\
"zyme: fake_enzyme1\nCleav. pos: 0\nPep. s"\
- "ize: 15\nPep. mass: 2014.35098\nPep. pI: "\
- "7.16\nSequence: NPHARDORCOMPLET\n]\n"
+ "ize: 15\nPep. mass: 2014.35098\npKa value"\
+ "s from: IPC\nPep. pI: 7.16\nSequence: NPH"\
+ "ARDORCOMPLET\n]\n"