def GetSequenceListAndPhycheValuePseknc(input_data, extra_phyche_index=None):
"""For PseDNC, PseKNC, make sequence_list and phyche_value.
:param input_data: file type or handle.
:param extra_phyche_index: dict, the key is the dinucleotide (string),
the value is its physicochemical property value (list).
It means the user-defined physicochemical indices.
"""
if extra_phyche_index is None:
extra_phyche_index = {}
original_phyche_value = {
'AA': [0.06, 0.5, 0.09, 1.59, 0.11, -0.11],
'AC': [1.5, 0.5, 1.19, 0.13, 1.29, 1.04],
'GT': [1.5, 0.5, 1.19, 0.13, 1.29, 1.04],
'AG': [0.78, 0.36, -0.28, 0.68, -0.24, -0.62],
'CC': [0.06, 1.08, -0.28, 0.56, -0.82, 0.24],
'CA': [-1.38, -1.36, -1.01, -0.86, -0.62, -1.25],
'CG': [-1.66, -1.22, -1.38, -0.82, -0.29, -1.39],
'TT': [0.06, 0.5, 0.09, 1.59, 0.11, -0.11],
'GG': [0.06, 1.08, -0.28, 0.56, -0.82, 0.24],
'GC': [-0.08, 0.22, 2.3, -0.35, 0.65, 1.59],
'AT': [1.07, 0.22, 0.83, -1.02, 2.51, 1.17],
'GA': [-0.08, 0.5, 0.09, 0.13, -0.39, 0.71],
'TG': [-1.38, -1.36, -1.01, -0.86, -0.62, -1.25],
'TA': [-1.23, -2.37, -1.38, -2.24, -1.51, -1.39],
'TC': [-0.08, 0.5, 0.09, 0.13, -0.39, 0.71],
'CT': [0.78, 0.36, -0.28, 0.68, -0.24, -0.62]
}
sequence_list = GetData(input_data)
phyche_value = ExtendPhycheIndex(original_phyche_value, extra_phyche_index)
return sequence_list, phyche_value
def GetSequenceListAndPhycheValuePsednc(input_data, extra_phyche_index=None):
"""For PseDNC, PseKNC, make sequence_list and phyche_value.
:param input_data: file type or handle.
:param extra_phyche_index: dict, the key is the dinucleotide (string),
the value is its physicochemical property value (list).
It means the user-defined physicochemical indices.
"""
if extra_phyche_index is None:
extra_phyche_index = {}
original_phyche_value = {
"AA": [0.06, 0.5, 0.27, 1.59, 0.11, -0.11],
"AC": [1.50, 0.50, 0.80, 0.13, 1.29, 1.04],
"AG": [0.78, 0.36, 0.09, 0.68, -0.24, -0.62],
"AT": [1.07, 0.22, 0.62, -1.02, 2.51, 1.17],
"CA": [-1.38, -1.36, -0.27, -0.86, -0.62, -1.25],
"CC": [0.06, 1.08, 0.09, 0.56, -0.82, 0.24],
"CG": [-1.66, -1.22, -0.44, -0.82, -0.29, -1.39],
"CT": [0.78, 0.36, 0.09, 0.68, -0.24, -0.62],
"GA": [-0.08, 0.5, 0.27, 0.13, -0.39, 0.71],
"GC": [-0.08, 0.22, 1.33, -0.35, 0.65, 1.59],
"GG": [0.06, 1.08, 0.09, 0.56, -0.82, 0.24],
"GT": [1.50, 0.50, 0.80, 0.13, 1.29, 1.04],
"TA": [-1.23, -2.37, -0.44, -2.24, -1.51, -1.39],
"TC": [-0.08, 0.5, 0.27, 0.13, -0.39, 0.71],
"TG": [-1.38, -1.36, -0.27, -0.86, -0.62, -1.25],
"TT": [0.06, 0.5, 0.27, 1.59, 0.11, -0.11],
}
sequence_list = GetData(input_data)
phyche_value = ExtendPhycheIndex(original_phyche_value, extra_phyche_index)
return sequence_list, phyche_value
def GeneratePhycheValue(k, phyche_index=None, all_property=False, extra_phyche_index=None):
"""
#################################################################
Combine the user selected phyche_list, is_all_property and
extra_phyche_index to a new standard phyche_value.
#################################################################
"""
if phyche_index is None:
phyche_index = []
if extra_phyche_index is None:
extra_phyche_index = {}
diphyche_list = ['Base stacking', 'Protein induced deformability', 'B-DNA twist', 'Dinucleotide GC Content',
'A-philicity', 'Propeller twist', 'Duplex stability:(freeenergy)',
'Duplex tability(disruptenergy)', 'DNA denaturation', 'Bending stiffness', 'Protein DNA twist',
'Stabilising energy of Z-DNA', 'Aida_BA_transition', 'Breslauer_dG', 'Breslauer_dH',
'Breslauer_dS', 'Electron_interaction', 'Hartman_trans_free_energy', 'Helix-Coil_transition',
'Ivanov_BA_transition', 'Lisser_BZ_transition', 'Polar_interaction', 'SantaLucia_dG',
'SantaLucia_dH', 'SantaLucia_dS', 'Sarai_flexibility', 'Stability', 'Stacking_energy',
'Sugimoto_dG', 'Sugimoto_dH', 'Sugimoto_dS', 'Watson-Crick_interaction', 'Twist', 'Tilt',
'Roll', 'Shift', 'Slide', 'Rise']
triphyche_list = ['Dnase I', 'Bendability (DNAse)', 'Bendability (consensus)', 'Trinucleotide GC Content',
'Nucleosome positioning', 'Consensus_roll', 'Consensus-Rigid', 'Dnase I-Rigid', 'MW-Daltons',
'MW-kg', 'Nucleosome', 'Nucleosome-Rigid']
# Set and check physicochemical properties.
if 2 == k:
if all_property is True:
phyche_index = diphyche_list
else:
for e in phyche_index:
if e not in diphyche_list:
error_info = 'Sorry, the physicochemical properties ' + e + ' is not exit.'
import sys
sys.stderr.write(error_info)
sys.exit(0)
elif 3 == k:
if all_property is True:
phyche_index = triphyche_list
else:
for e in phyche_index:
if e not in triphyche_list:
error_info = 'Sorry, the physicochemical properties ' + e + ' is not exit.'
import sys
sys.stderr.write(error_info)
sys.exit(0)
# Generate phyche_value.
from PyDNApsenacutil import GetPhycheIndex, ExtendPhycheIndex
return ExtendPhycheIndex(GetPhycheIndex(k, phyche_index), extra_phyche_index)
def GetSequenceListAndPhycheValue(input_data, k, phyche_index,
extra_phyche_index, all_property):
"""For PseKNC-general make sequence_list and phyche_value.
:param input_data: file type or handle.
:param k: int, the value of k-tuple.
:param k: physicochemical properties list.
:param extra_phyche_index: dict, the key is the dinucleotide (string),
the value is its physicochemical property value (list).
It means the user-defined physicochemical indices.
:param all_property: bool, choose all physicochemical properties or not.
"""
if phyche_index is None:
phyche_index = []
if extra_phyche_index is None:
extra_phyche_index = {}
diphyche_list = [
'Base stacking', 'Protein induced deformability', 'B-DNA twist',
'Dinucleotide GC Content', 'A-philicity', 'Propeller twist',
'Duplex stability:(freeenergy)', 'Duplex tability(disruptenergy)',
'DNA denaturation', 'Bending stiffness', 'Protein DNA twist',
'Stabilising energy of Z-DNA', 'Aida_BA_transition', 'Breslauer_dG',
'Breslauer_dH', 'Breslauer_dS', 'Electron_interaction',
'Hartman_trans_free_energy', 'Helix-Coil_transition',
'Ivanov_BA_transition', 'Lisser_BZ_transition', 'Polar_interaction',
'SantaLucia_dG', 'SantaLucia_dH', 'SantaLucia_dS', 'Sarai_flexibility',
'Stability', 'Stacking_energy', 'Sugimoto_dG', 'Sugimoto_dH',
'Sugimoto_dS', 'Watson-Crick_interaction', 'Twist', 'Tilt', 'Roll',
'Shift', 'Slide', 'Rise'
]
triphyche_list = [
'Dnase I', 'Bendability (DNAse)', 'Bendability (consensus)',
'Trinucleotide GC Content', 'Nucleosome positioning', 'Consensus_roll',
'Consensus-Rigid', 'Dnase I-Rigid', 'MW-Daltons', 'MW-kg',
'Nucleosome', 'Nucleosome-Rigid'
]
# Set and check physicochemical properties.
phyche_list = []
if k == 2:
phyche_list = diphyche_list
elif k == 3:
phyche_list = triphyche_list
try:
if all_property is True:
phyche_index = phyche_list
else:
for e in phyche_index:
if e not in phyche_list:
error_info = 'Sorry, the physicochemical properties ' + e + ' is not exit.'
raise NameError(error_info)
except NameError:
raise
# Generate phyche_value and sequence_list.
from PyDNApsenacutil import GetPhycheIndex
phyche_value = ExtendPhycheIndex(GetPhycheIndex(k, phyche_index),
extra_phyche_index)
sequence_list = GetData(input_data)
return sequence_list, phyche_value
def GetSequenceListAndPhycheValue(input_data, k, phyche_index,
extra_phyche_index, all_property):
"""For PseKNC-general make sequence_list and phyche_value.
:param input_data: file type or handle.
:param k: int, the value of k-tuple.
:param k: physicochemical properties list.
:param extra_phyche_index: dict, the key is the dinucleotide (string),
the value is its physicochemical property value (list).
It means the user-defined physicochemical indices.
:param all_property: bool, choose all physicochemical properties or not.
"""
if phyche_index is None:
phyche_index = []
if extra_phyche_index is None:
extra_phyche_index = {}
diphyche_list = [
"Base stacking",
"Protein induced deformability",
"B-DNA twist",
"Dinucleotide GC Content",
"A-philicity",
"Propeller twist",
"Duplex stability:(freeenergy)",
"Duplex tability(disruptenergy)",
"DNA denaturation",
"Bending stiffness",
"Protein DNA twist",
"Stabilising energy of Z-DNA",
"Aida_BA_transition",
"Breslauer_dG",
"Breslauer_dH",
"Breslauer_dS",
"Electron_interaction",
"Hartman_trans_free_energy",
"Helix-Coil_transition",
"Ivanov_BA_transition",
"Lisser_BZ_transition",
"Polar_interaction",
"SantaLucia_dG",
"SantaLucia_dH",
"SantaLucia_dS",
"Sarai_flexibility",
"Stability",
"Stacking_energy",
"Sugimoto_dG",
"Sugimoto_dH",
"Sugimoto_dS",
"Watson-Crick_interaction",
"Twist",
"Tilt",
"Roll",
"Shift",
"Slide",
"Rise",
]
triphyche_list = [
"Dnase I",
"Bendability (DNAse)",
"Bendability (consensus)",
"Trinucleotide GC Content",
"Nucleosome positioning",
"Consensus_roll",
"Consensus-Rigid",
"Dnase I-Rigid",
"MW-Daltons",
"MW-kg",
"Nucleosome",
"Nucleosome-Rigid",
]
# Set and check physicochemical properties.
phyche_list = []
if k == 2:
phyche_list = diphyche_list
elif k == 3:
phyche_list = triphyche_list
try:
if all_property is True:
phyche_index = phyche_list
else:
for e in phyche_index:
if e not in phyche_list:
error_info = ("Sorry, the physicochemical properties " +
e + " is not exit.")
raise NameError(error_info)
except NameError:
raise
# Generate phyche_value and sequence_list.
from PyDNApsenacutil import GetPhycheIndex
phyche_value = ExtendPhycheIndex(GetPhycheIndex(k, phyche_index),
extra_phyche_index)
sequence_list = GetData(input_data)
return sequence_list, phyche_value
def GeneratePhycheValue(k,
phyche_index=None,
all_property=False,
extra_phyche_index=None):
"""
#################################################################
Combine the user selected phyche_list, is_all_property and
extra_phyche_index to a new standard phyche_value.
#################################################################
"""
if phyche_index is None:
phyche_index = []
if extra_phyche_index is None:
extra_phyche_index = {}
diphyche_list = [
"Base stacking",
"Protein induced deformability",
"B-DNA twist",
"Dinucleotide GC Content",
"A-philicity",
"Propeller twist",
"Duplex stability:(freeenergy)",
"Duplex tability(disruptenergy)",
"DNA denaturation",
"Bending stiffness",
"Protein DNA twist",
"Stabilising energy of Z-DNA",
"Aida_BA_transition",
"Breslauer_dG",
"Breslauer_dH",
"Breslauer_dS",
"Electron_interaction",
"Hartman_trans_free_energy",
"Helix-Coil_transition",
"Ivanov_BA_transition",
"Lisser_BZ_transition",
"Polar_interaction",
"SantaLucia_dG",
"SantaLucia_dH",
"SantaLucia_dS",
"Sarai_flexibility",
"Stability",
"Stacking_energy",
"Sugimoto_dG",
"Sugimoto_dH",
"Sugimoto_dS",
"Watson-Crick_interaction",
"Twist",
"Tilt",
"Roll",
"Shift",
"Slide",
"Rise",
]
triphyche_list = [
"Dnase I",
"Bendability (DNAse)",
"Bendability (consensus)",
"Trinucleotide GC Content",
"Nucleosome positioning",
"Consensus_roll",
"Consensus-Rigid",
"Dnase I-Rigid",
"MW-Daltons",
"MW-kg",
"Nucleosome",
"Nucleosome-Rigid",
]
# Set and check physicochemical properties.
if 2 == k:
if all_property is True:
phyche_index = diphyche_list
else:
for e in phyche_index:
if e not in diphyche_list:
error_info = ("Sorry, the physicochemical properties " +
e + " is not exit.")
import sys
sys.stderr.write(error_info)
sys.exit(0)
elif 3 == k:
if all_property is True:
phyche_index = triphyche_list
else:
for e in phyche_index:
if e not in triphyche_list:
error_info = ("Sorry, the physicochemical properties " +
e + " is not exit.")
import sys
sys.stderr.write(error_info)
sys.exit(0)
# Generate phyche_value.
from PyDNApsenacutil import GetPhycheIndex, ExtendPhycheIndex
return ExtendPhycheIndex(GetPhycheIndex(k, phyche_index),
extra_phyche_index)