def protocol(self):
"""Main entrypoint for the protocol"""
#Create a output log file that we can append to
with open(self.directory + self.output_prefix + "_" + strftime("%m_%d_%Y") + "-" +
strftime("%H_%M_%S") + '_output.txt', 'w') as file_output:
file_output.write(self.pact_preamble + "\n")
"""
*****************************************
Pact Combine Section (Required)
*****************************************
"""
#Check to see if the section is there
if not self.obj_cfgparser.has_section('combinepact'):
print("[Protocols:Epitope Mapping Error] The combinepact config file is incorrect.")
print("[Protocols:Epitope Mapping Error] There is something wrong with the [combinepact] section.")
quit()
#Import our combinepact class
try:
from pact.analysis.combine_pact import combine_pact
except ImportError:
print("[Protocols:Epitope Mapping Error] combine_pact was not found.")
#Create the object then call the merger
obj_combine = combine_pact(self.obj_cfgparser, self.dict_programs, {})
#The dict will be like {'dataset name': {data...
dict_merged_datasets = obj_combine.combine_pact()
"""
*****************************************
PDB Import Section
*****************************************
"""
#Only import and run if selected
if self.dict_workflow['pdb_import']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('pdb_import'):
print("[Protocols:Epitope Mapping Error] The pdb_import config file is incorrect.")
print("[Protocols:Epitope Mapping Error] There is something wrong with the [pdb_import] section.")
quit()
#Import our combinepact class
try:
from pact.analysis.pdb_import import pdb_import
except ImportError:
print("[Protocols:Epitope Mapping Error] pdb_import was not found.")
#Create the object then call the merger
obj_pdb = pdb_import(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
#The dict will be like {'pdb name': {data...
dict_pdb = obj_pdb.pdb_import()
return
def protocol(self):
"""Provide a protocol that does general analyses that don't need a full protocol"""
#Create a output log file that we can append to
with open(self.directory + self.output_prefix + "_" + strftime("%m_%d_%Y") + "-" +
strftime("%H_%M_%S") + '_output.txt', 'w') as file_output:
file_output.write(self.pact_preamble + "\n")
"""
*****************************************
Pact Combine (Required)
*****************************************
"""
#Check to see if the section is there
if not self.obj_cfgparser.has_section('combinepact'):
print("[Protocols:Analysis Error] The combinepact config file is incorrect.")
print("[Protocols:Analysis Error] There is something wrong with the [combinepact] section.")
quit()
#Import our combinepact class
try:
from pact.analysis.combine_pact import combine_pact
except ImportError:
print("[Protocols:Analysis Error] combine_pact was not found.")
#Create the object then call the merger
obj_combine = combine_pact(self.obj_cfgparser, self.dict_programs, {})
#Print Section Progress
print("[Protocols:Analysis] Combine PACT")
#The dict will be like {'dataset name': {data...
dict_merged_datasets = obj_combine.combine_pact()
"""
*****************************************
PDB Import Section
*****************************************
"""
#Only import and run if selected
if self.dict_workflow['pdb_import']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('pdb_import'):
print("[Protocols:Analysis Error] The pdb_import config file is incorrect.")
print("[Protocols:Analysis Error] There is something wrong with the [pdb_import] section.")
quit()
#Import our combinepact class
try:
from pact.analysis.pdb_import import pdb_import
except ImportError:
print("[Protocols:Analysis Error] pdb_import was not found.")
#Create the object then call the merger
obj_pdb = pdb_import(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
#Print Section Progress
print("[Protocols:Analysis] PDB Import")
#The dict will be like {'pdb name': {data...
dict_pdb = obj_pdb.pdb_import()
"""
*****************************************
Assign colors to classifiers
*****************************************
"""
#Only import and run if selected
if self.dict_workflow['classifier_color']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('classifier_color'):
print("[Protocols:Analysis Error] The classifier_color config file is incorrect.")
print("[Protocols:Analysis Error] There is something wrong with the [classifier_color] section.")
quit()
#Import our combinepact class
try:
from pact.analysis.classifier_color import classifier_color
except ImportError:
print("[Protocols:Analysis Error] classifer_color was not found.")
#Create the object then call the merger
obj_classcolor = classifier_color(self.obj_cfgparser, self.dict_programs, {})
#Print Section Progress
print("[Protocols:Analysis] Classifier Color")
#This section returns a dict of [loc][mut] = "color"
if self.obj_cfgparser.get("classifier_color", "classifier").split(',')[0] == "pdb":
dict_custom_color = obj_classcolor.classifier_color(dict_merged_datasets, dict_pdb, "pdb")
"""
*****************************************
Set vs Set Section
*****************************************
"""
#Check to see if the section is there
if not self.obj_cfgparser.has_section('setvsset'):
print("[Protocols:Analysis Error] The setvsset config file is incorrect.")
print("[Protocols:Analysis Error] There is something wrong with the [setvsset] section.")
quit()
#Import our setvsset class
try:
from pact.analysis.set_vs_set import set_vs_set
except ImportError:
print("[Protocols:Analysis Error] set_vs_set was not found.")
#Create the object then call the merger
obj_svs = set_vs_set(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
#Do we have structural data?
if self.dict_workflow['classifier_color']:
print("[Protocols:Analysis] Dataset vs Dataset")
file_output.write(obj_svs.set_vs_set(dict_merged_datasets, dict_custom_color))
else:
print("[Protocols:Analysis] Dataset vs Dataset")
file_output.write(obj_svs.set_vs_set(dict_merged_datasets))
return
def protocol(self):
"""Main entrypoint for the protocol"""
#Create a output log file that we can append to
with open(
self.directory + self.output_prefix + "_" +
strftime("%m_%d_%Y") + "-" + strftime("%H_%M_%S") +
'_output.txt', 'w') as file_output:
file_output.write(self.pact_preamble + "\n")
#Import our class
try:
from pact.analysis.sequence.homology_pssm import homology_classifier
except ImportError:
print(
"[Protocols:Homology Error] pact.analysis.sequence.homology_pssm was not found."
)
quit()
#Create our object
obj_homology = homology_classifier(self.obj_cfgparser,
self.dict_programs,
{'directory': self.directory})
"""
*****************************************
DNA Filtering/Alignment Section
*****************************************
"""
if self.dict_workflow['blastp_align_filter']:
#Convert our XML file
print("[Protocols:Homology] xml_to_fasta")
file_output.write("[Protocols:Homology] xml_to_fasta\n")
obj_homology.xml_to_fasta()
#Run CD-HIT on our new fasta file
print("[Protocols:Homology] cdhit")
file_output.write("[Protocols:Homology] cdhit\n")
#Check to see if the number of processes is logical
self.processes = self.obj_cfgparser.get(
"blastp_align_filter", "processes")
if int(self.processes) <= 0:
self.processes = "2"
check_output([
self.dict_programs['cdhit'], "-i",
self.directory + self.output_prefix + ".fa", "-o",
self.directory + self.output_prefix + ".afa", "-c",
str(
self.obj_cfgparser.get("blastp_align_filter",
"cdhit_clustering_threshold")),
"-M", "40000", "-T",
str(self.processes)
])
#Check to see if we have WT in our cdhit output
print("[Protocols:Homology] cdhit_wtcheck")
file_output.write("[Protocols:Homology] cdhit_wtcheck\n")
obj_homology.cdhit_wt_check()
#Run MUSCLE on our new fasta file
print("[Protocols:Homology] muscle")
file_output.write("[Protocols:Homology] muscle\n")
check_output([
self.dict_programs['muscle'], "-in",
self.directory + self.output_prefix + ".afa", "-out",
self.directory + self.output_prefix + ".msa"
])
#Process our MSA (needs to be on for PSIBlast)
print("[Protocols:Homology] processmsa")
file_output.write("[Protocols:Homology] processmsa\n")
list_msa = obj_homology.process_msa()
#Save our list
print("[Protocols:Homology] Saving our MSA")
file_output.write("[Protocols:Homology] Saving our MSA\n")
save_pact_file(
list_msa,
self.directory + self.output_prefix + '_' + "list_msa")
"""
*****************************************
PSSM Section
*****************************************
"""
if self.dict_workflow['pssm']:
#Open our list
print("[Protocols:Homology] Opening our MSA")
file_output.write("[Protocols:Homology] Opening our MSA\n")
list_msa = open_pact_file(self.directory + self.output_prefix +
'_' + "list_msa")
#Split our msa for PSIBlast (needs to be on for PSIBlast)
print("[Protocols:Homology] msa_split")
file_output.write("[Protocols:Homology] msa_split\n")
list_pbcmds = obj_homology.msa_split(list_msa)
#Run PSIBlast
print("[Protocols:Homology] psiblast")
file_output.write("[Protocols:Homology] psiblast\n")
for command in list_pbcmds:
check_output([self.dict_programs['psiblast'], *command])
#Import our PSSM data
print("[Protocols:Homology] pssm_file_import")
file_output.write("[Protocols:Homology] pssm_file_import\n")
dict_pssm = obj_homology.pssm_file_import()
#Save our heatmap
print("[Protocols:Homology] Saving a PSSM .csv heatmap")
file_output.write(
obj_homology.pssm_output_heat(dict_pssm) + "\n")
#Save our csv
print("[Protocols:Homology] Saving a PSSM .csv column data")
file_output.write(
obj_homology.pssm_output_csv(dict_pssm) + "\n")
#Save our PACT File
print("[Protocols:Homology] Saving a PSSM .pact file")
file_output.write(
save_pact_file(
dict_pssm, self.directory + self.output_prefix + '_' +
"PSSM") + "\n")
"""
*****************************************
Sitewise Frequency Section
*****************************************
"""
if self.dict_workflow['site_frequencies']:
#Open our list
print("[Protocols:Homology] Opening our MSA")
file_output.write("[Protocols:Homology] Opening our MSA\n")
list_msa = open_pact_file(self.directory + self.output_prefix +
'_' + "list_msa")
#Calculate our frequencies
print("[Protocols:Homology] Calculate our frequencies")
file_output.write(
"[Protocols:Homology] Calculate our frequencies\n")
dict_freq = obj_homology.msa_freq(list_msa)
#Save our CSV heatmap
print("[Protocols:Homology] Saving the frequencies heatmap")
file_output.write(
"[Protocols:Homology] Saving the frequencies heatmap\n")
obj_homology.freq_output_heat(dict_freq)
#Save our PACT File
print("[Protocols:Homology] Saving a Freq .pact file")
file_output.write(
save_pact_file(
dict_freq, self.directory + self.output_prefix + '_' +
"freq") + "\n")
"""
*****************************************
Read stored .pact files
*****************************************
"""
if self.dict_workflow['pssm_reader']:
#Open our PACT File
print("[Protocols:" + str_protocol_name +
"] Opening a PSSM .pact file")
dict_pssm = open_pact_file(self.directory +
self.output_prefix + '_' + "PSSM")
#Count our classifiers
print("[Protocols:" + str_protocol_name +
"] PSSM Classifier Count")
file_output.write("[Protocols:" + str_protocol_name +
"] PSSM Classifier Count")
"""
*****************************************
Pact Combine Section
*****************************************
"""
if self.dict_workflow['combinepact']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('combinepact'):
print(
"[Protocols:Homology Error] The combinepact config file is incorrect."
)
print(
"[Protocols:Homology Error] There is something wrong with the [combinepact] section."
)
quit()
#Import our combinepact class
try:
from pact.analysis.combine_pact import combine_pact
except ImportError:
print(
"[Protocols:Homology Error] combine_pact was not found."
)
#Create the object then call the merger
obj_combine = combine_pact(self.obj_cfgparser,
self.dict_programs, {})
#The dict will be like {'dataset name': {data...
dict_merged_datasets = obj_combine.combine_pact()
"""
*****************************************
Analysis Section
*****************************************
"""
if self.dict_workflow['analysis_sitefitness_homology']:
#Which dataset do we want?
if self.obj_cfgparser.get('analysis_sitefitness_homology',
'dataset_x') == "site_frequencies":
file_name = "freq"
else:
file_name = "pssm"
#Open our dict
print("[Protocols:Homology] Opening our homology data")
file_output.write(
"[Protocols:Homology] Opening our site freqs\n")
dict_homology = open_pact_file(self.directory +
self.output_prefix + '_' +
file_name)
#Plot our data
if self.obj_cfgparser.get('analysis_sitefitness_homology',
'scatter') == "True":
print("[Protocols:Homology] Plotting the figure")
file_output.write(
"[Protocols:Homology] Plotting the figure\n")
obj_homology.analysis_site_fit_homology_plot(
dict_homology, dict_merged_datasets, file_name)
#Plot our data
print("[Protocols:Homology] Making our classifier table")
file_output.write(
"[Protocols:Homology] Making our classifier table\n")
obj_homology.analysis_site_fit_homology_classifier(
dict_homology, dict_merged_datasets, file_name)
return
def protocol(self):
"""Main entrypoint for the protocol"""
#Create a output log file that we can append to
with open(self.directory + self.output_prefix + "_" + strftime("%m_%d_%Y") + "-" +
strftime("%H_%M_%S") + '_output.txt', 'w') as file_output:
file_output.write(self.pact_preamble + "\n")
"""
*****************************************
Pact Combine (Required)
*****************************************
"""
#Check to see if the section is there
if not self.obj_cfgparser.has_section('combinepact'):
print("[Protocols:" + str_protocol_name + " Error] The combinepact config file is incorrect.")
print("[Protocols:" + str_protocol_name + " Error] There is something wrong with the [combinepact] section.")
quit()
#Import our combinepact class
try:
from pact.analysis.combine_pact import combine_pact
except ImportError:
print("[Protocols:" + str_protocol_name + " Error] combine_pact was not found.")
#Create the object then call the merger
obj_combine = combine_pact(self.obj_cfgparser, self.dict_programs, {})
#The dict will be like {'dataset name': {data...
dict_merged_datasets = obj_combine.combine_pact()
"""
*****************************************
Classify our mutations
*****************************************
"""
#Build a dict_classified with [location][mutation] = "DEL/NEU/BEN/NONE"
#Get the config file elements
try:
class_column = self.obj_cfgparser.get("variant_classification", "class_column").lower()
class_threshold = float(self.obj_cfgparser.get("variant_classification", "class_threshold"))
except NoOptionError:
print("[Protocols:" + str_protocol_name + " Error] Missing [variant_classification] config file elements.")
quit()
except ValueError:
print("[Protocols:" + str_protocol_name + " Error] Incorrect [variant_classification] config file elements.")
quit()
except TypeError:
print("[Protocols:" + str_protocol_name + " Error] Incorrect [variant_classification] config file elements.")
quit()
#Make a dict to add our classifications into
dict_classified = {}
#Classify each dataset
for dataset in dict_merged_datasets:
#Add if not existing
if dataset not in dict_classified:
dict_classified[dataset] = {}
#Loop the locations
for loc in dict_merged_datasets[dataset]:
#Add a new location if not in the dict
if loc not in dict_classified[dataset]:
dict_classified[dataset][loc] = {}
#Loop the muts
for mut in dict_merged_datasets[dataset][loc]:
#Skip WT, stop, and NaN
if (mut == dict_merged_datasets[dataset][loc][mut]['wt_residue'] or
mut == "*" or
dict_merged_datasets[dataset][loc][mut][class_column] == "NaN"):
dict_classified[dataset][loc][mut] = "UNCLASSIFIED"
continue
#Get the fitness value from the dataset
mut_value = float(dict_merged_datasets[dataset][loc][mut][class_column])
#Assign a classification of deleterious, slightly deleterious, or neutral
if mut_value <= (-1 * class_threshold):
dict_classified[dataset][loc][mut] = "DEL"
elif (mut_value > (-1 * class_threshold) and mut_value < class_threshold):
dict_classified[dataset][loc][mut] = "NEU"
elif mut_value >= class_threshold:
dict_classified[dataset][loc][mut] = "BEN"
"""
*****************************************
Count the basal classifiers
*****************************************
"""
if self.dict_workflow['basal_count']:
#Import our class
try:
from pact.analysis.basal_count import basal_count
except ImportError:
print("[Protocols:" + str_protocol_name + " Error] pact.analysis.basal_count was not found.")
quit()
#Create our object
obj_basal = basal_count(self.obj_cfgparser, self.dict_programs, {})
#Count our basal rates
for dataset in dict_classified:
print("[Protocols:" + str_protocol_name + "] Basal Fitness Counts for dataset: " + dataset)
file_output.write("[Protocols:" + str_protocol_name + "] Basal Fitness Counts for dataset: " + dataset)
file_output.write(obj_basal.basal_count(dict_classified[dataset]) + "\n")
"""
*****************************************
DNA Filtering/Alignment or PSSM Object
*****************************************
"""
if (self.dict_workflow['blastp_align_filter'] or
self.dict_workflow['pssm'] or
self.dict_workflow['pssm_reader']):
#Import Check Output
from subprocess import check_output
#Import our class
try:
from pact.analysis.sequence.homology_pssm import homology_classifier
except ImportError:
print("[Protocols:" + str_protocol_name + " Error] pact.analysis.sequence.homology_pssm was not found.")
quit()
#Create our object
obj_homology = homology_classifier(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
#Count our classifiers
print("[Protocols:" + str_protocol_name + "] Homology PSSM")
file_output.write("[Protocols:" + str_protocol_name + "] Homology PSSM")
"""
*****************************************
DNA Filtering/Alignment
*****************************************
"""
if self.dict_workflow['blastp_align_filter']:
#Convert our XML file
print("[Protocols:" + str_protocol_name + "] xml_to_fasta")
file_output.write("[Protocols:" + str_protocol_name + "] xml_to_fasta\n")
obj_homology.xml_to_fasta()
#Run CD-HIT on our new fasta file
print("[Protocols:" + str_protocol_name + "] cdhit")
file_output.write("[Protocols:" + str_protocol_name + "] cdhit\n")
#Check to see if the number of processes is logical
self.processes = self.obj_cfgparser.get("blastp_align_filter", "processes")
if int(self.processes) <= 0:
self.processes = "2"
check_output([self.dict_programs['cdhit'],
"-i",
self.directory + self.output_prefix + ".fa",
"-o",
self.directory + self.output_prefix + ".afa",
"-c",
str(self.obj_cfgparser.get("blastp_align_filter", "cdhit_clustering_threshold")),
"-M",
"40000",
"-T",
str(self.processes)])
#Check to see if we have WT in our cdhit output
print("[Protocols:" + str_protocol_name + "] cdhit_wtcheck")
file_output.write("[Protocols:" + str_protocol_name + "] cdhit_wtcheck\n")
obj_homology.cdhit_wt_check()
#Run MUSCLE on our new fasta file
print("[Protocols:" + str_protocol_name + "] muscle")
file_output.write("[Protocols:" + str_protocol_name + "] muscle\n")
check_output([self.dict_programs['muscle'],
"-in",
self.directory + self.output_prefix + ".afa",
"-out",
self.directory + self.output_prefix + ".msa"])
#Process our MSA (needs to be on for PSIBlast)
print("[Protocols:" + str_protocol_name + "] processmsa")
file_output.write("[Protocols:" + str_protocol_name + "] processmsa\n")
list_msa = obj_homology.process_msa()
#Save our list
print("[Protocols:" + str_protocol_name + "] Saving our MSA")
file_output.write("[Protocols:" + str_protocol_name + "] Saving our MSA\n")
save_pact_file(list_msa, self.directory + self.output_prefix + '_' + "list_msa")
"""
*****************************************
PSSM
*****************************************
"""
if self.dict_workflow['pssm']:
#Open our list
print("[Protocols:" + str_protocol_name + "] Opening our MSA")
file_output.write("[Protocols:" + str_protocol_name + "] Opening our MSA\n")
list_msa = open_pact_file(self.directory + self.output_prefix + '_' + "list_msa")
#Split our msa for PSIBlast (needs to be on for PSIBlast)
print("[Protocols:" + str_protocol_name + "] msa_split")
file_output.write("[Protocols:" + str_protocol_name + "] msa_split\n")
list_pbcmds = obj_homology.msa_split(list_msa)
#Run PSIBlast
print("[Protocols:" + str_protocol_name + "] psiblast")
file_output.write("[Protocols:" + str_protocol_name + "] psiblast\n")
for command in list_pbcmds:
check_output([self.dict_programs['psiblast'], *command])
#Import our PSSM data
print("[Protocols:" + str_protocol_name + "] pssm_file_import")
file_output.write("[Protocols:" + str_protocol_name + "] pssm_file_import\n")
dict_pssm = obj_homology.pssm_file_import()
#Save our heatmap
print("[Protocols:" + str_protocol_name + "] Saving a PSSM .csv heatmap")
file_output.write(obj_homology.pssm_output_heat(dict_pssm) + "\n")
#Save our csv
print("[Protocols:" + str_protocol_name + "] Saving a PSSM .csv column data")
file_output.write(obj_homology.pssm_output_csv(dict_pssm) + "\n")
#Save our PACT File
print("[Protocols:" + str_protocol_name + "] Saving a PSSM .pact file")
file_output.write(save_pact_file(dict_pssm, self.directory + self.output_prefix + '_' + "PSSM") + "\n")
"""
*****************************************
Read stored PSSM files
*****************************************
"""
if self.dict_workflow['pssm_reader'] or self.dict_workflow['wt_consensus']:
#Open our PACT File
print("[Protocols:" + str_protocol_name + "] Opening a PSSM .pact file")
dict_pssm = open_pact_file(self.directory + self.output_prefix + '_' + "PSSM")
#Count our classifiers
print("[Protocols:" + str_protocol_name + "] PSSM Classifier Count")
file_output.write("[Protocols:" + str_protocol_name + "] PSSM Classifier Count")
for dataset in dict_classified:
print("[Protocols:" + str_protocol_name + "] PSSM Fitness Rates for dataset: " + dataset)
file_output.write("[Protocols:" + str_protocol_name + "] PSSM Fitness Rates for dataset: " + dataset)
file_output.write(obj_homology.classified_count_pssm(dict_pssm, dict_classified[dataset]) + "\n")
print("[Protocols:" + str_protocol_name + "] Wrote CSV of fitness values categorized by PSSM group and mutation type for dataset: " + dataset)
file_output.write("[Protocols:" + str_protocol_name + "] PSSM Fitness Rates for dataset: " + dataset)
file_output.write(obj_homology.classified_count_pssm_csv(dict_pssm, dict_classified[dataset],
dict_merged_datasets, dataset, class_column) + "\n")
"""
*****************************************
PDB Import Section
*****************************************
"""
#Only import and run if selected
if self.dict_workflow['pdb_import']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('pdb_import'):
print("[Protocols:" + str_protocol_name + " Error] The pdb_import config file is incorrect.")
print("[Protocols:" + str_protocol_name + " Error] There is something wrong with the [pdb_import] section.")
quit()
#Import our combinepact class
try:
from pact.analysis.pdb_import import pdb_import
except ImportError:
print("[Protocols:" + str_protocol_name + " Error] pdb_import was not found.")
#Create the object then call the merger
obj_pdb = pdb_import(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
#The dict will be like {'pdb name': {data...
dict_pdb = obj_pdb.pdb_import()
"""
*****************************************
Back to Consensus Analyses
*****************************************
"""
if self.dict_workflow['consensus']:
#Import our class
try:
from pact.analysis.sequence.consensus import consensus
except ImportError:
print("[Protocols:" + str_protocol_name + "] pact.analysis.basal_count was not found.")
quit()
#Create our object
obj_consensus = consensus(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
#Get the wild-type sequence information
dict_wtcons = obj_consensus.wt_consensus(dict_pssm)
#Get the prob of finding a classified mutation
for dataset in dict_classified:
print("[Protocols:" + str_protocol_name + "] Mut Classification vs WT Cons for dataset: " + dataset)
obj_consensus.wtcons_count_class(dict_wtcons, dict_classified[dataset], dataset)
#Get the prob of finding a classified mutation
for dataset in dict_classified:
print("[Protocols:" + str_protocol_name + "] Mutating a non-conserved site to a conserved site: " + dataset)
file_output.write(obj_consensus.nonconserved_sites(dict_wtcons, dict_pssm, dict_classified[dataset], dataset))
#Get the prob of finding a classified mutation
for dataset in dict_classified:
print("[Protocols:" + str_protocol_name + "] Mutating a non-conserved site to a non-conserved mutation: " + dataset)
file_output.write(obj_consensus.nonconserved_mutations(dict_wtcons, dict_pssm, dict_classified[dataset], dataset))
#Get the cross set distribution
obj_consensus.cons_count_setvset(dict_wtcons, dict_pssm, dict_classified)
if self.dict_workflow['pdb_import']:
for dataset in dict_classified:
print("[Protocols:" + str_protocol_name +
"] Mutating a non-conserved site to a conserved site (Buried Residues Only): " + dataset)
file_output.write(obj_consensus.nonconserved_sites_burial(
dict_wtcons, dict_pssm, dict_classified[dataset], dataset, dict_pdb, "<"))
for dataset in dict_classified:
print("[Protocols:" + str_protocol_name +
"] Mutating a non-conserved site to a conserved site (Surface Residues Only): " + dataset)
file_output.write(obj_consensus.nonconserved_sites_burial(
dict_wtcons, dict_pssm, dict_classified[dataset], dataset, dict_pdb, ">="))
return
def protocol(self):
"""Main entrypoint for the protocol"""
#Create a output log file that we can append to
with open(
self.directory + self.output_prefix + "_" +
strftime("%m_%d_%Y") + "-" + strftime("%H_%M_%S") +
'_output.txt', 'w') as file_output:
file_output.write(self.pact_preamble + "\n")
"""
*****************************************
Pact Combine (Required)
*****************************************
"""
#Check to see if the section is there
if not self.obj_cfgparser.has_section('combinepact'):
print(
"[Protocols:Shannon Entropy Error] The combinepact config file is incorrect."
)
print(
"[Protocols:Shannon Entropy Error] There is something wrong with the [combinepact] section."
)
quit()
#Import our combinepact class
try:
from pact.analysis.combine_pact import combine_pact
except ImportError:
print(
"[Protocols:Shannon Entropy Error] combine_pact was not found."
)
#Create the object then call the merger
obj_combine = combine_pact(self.obj_cfgparser, self.dict_programs,
{})
#The dict will be like {'dataset name': {data...
dict_merged_datasets = obj_combine.combine_pact()
"""
*****************************************
Shannon Class Import
*****************************************
"""
#Check to see if the section is there
if not self.obj_cfgparser.has_section('shannon_entropy'):
print(
"[Protocols:Shannon Entropy Error] The combinepact config file is incorrect."
)
print(
"[Protocols:Shannon Entropy Error] There is something wrong with the [combinepact] section."
)
quit()
#Import our SE class
try:
from pact.analysis.sequence.shannon_entropy import shannon_entropy_classifier
except ImportError:
print(
"[Protocols:Shannon Entropy Error] Cannot load pact.analysis.sequence.shannon_entropy"
)
quit()
#Create our object
obj_se = shannon_entropy_classifier(self.obj_cfgparser,
self.dict_programs,
{'directory': self.directory})
#Run our object
dict_entropy = obj_se.shannon_entropy(dict_merged_datasets)
return
def protocol(self):
"""Main entrypoint for the protocol"""
#Create a output log file that we can append to
with open(self.directory + self.output_prefix + "_" + strftime("%m_%d_%Y") + "-" +
strftime("%H_%M_%S") + '_output.txt', 'w') as file_output:
file_output.write(self.pact_preamble + "\n")
"""
*****************************************
Pact Combine
*****************************************
"""
if self.dict_workflow['combinepact']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('combinepact'):
print("[Protocols:" + str_protocol_name + " Error] The combinepact config file is incorrect.")
print("[Protocols:" + str_protocol_name + " Error] There is something wrong with the [combinepact] section.")
quit()
#Import our combinepact class
try:
from pact.analysis.combine_pact import combine_pact
except ImportError:
print("[Protocols:" + str_protocol_name + " Error] combine_pact was not found.")
#Create the object then call the merger
obj_combine = combine_pact(self.obj_cfgparser, self.dict_programs, {})
#The dict will be like {'dataset name': {data...
dict_merged_datasets = obj_combine.combine_pact()
"""
*****************************************
Classify our mutations
*****************************************
"""
#Build a dict_classified with [location][mutation] = "DEL/NEU/BEN/NONE"
#Get the config file elements
try:
class_column = self.obj_cfgparser.get("variant_classification", "class_column").lower()
class_threshold = float(self.obj_cfgparser.get("variant_classification", "class_threshold"))
except NoOptionError:
print("[Protocols:" + str_protocol_name + " Error] Missing [variant_classification] config file elements.")
quit()
except ValueError:
print("[Protocols:" + str_protocol_name + " Error] Incorrect [variant_classification] config file elements.")
quit()
except TypeError:
print("[Protocols:" + str_protocol_name + " Error] Incorrect [variant_classification] config file elements.")
quit()
#Make a dict to add our classifications into
dict_classified = {}
#Classify each dataset
for dataset in dict_merged_datasets:
#Add if not existing
if dataset not in dict_classified:
dict_classified[dataset] = {}
#Loop the locations
for loc in dict_merged_datasets[dataset]:
#Add a new location if not in the dict
if loc not in dict_classified[dataset]:
dict_classified[dataset][loc] = {}
#Loop the muts
for mut in dict_merged_datasets[dataset][loc]:
#Skip WT, stop, and NaN
if (mut == dict_merged_datasets[dataset][loc][mut]['wt_residue'] or
mut == "*" or
dict_merged_datasets[dataset][loc][mut][class_column] == "NaN"):
dict_classified[dataset][loc][mut] = "UNCLASSIFIED"
continue
#Get the fitness value from the dataset
mut_value = float(dict_merged_datasets[dataset][loc][mut][class_column])
#Assign a classification of deleterious, slightly deleterious, or neutral
if mut_value <= (-1 * class_threshold):
dict_classified[dataset][loc][mut] = "DEL"
elif (mut_value > (-1 * class_threshold) and mut_value < class_threshold):
dict_classified[dataset][loc][mut] = "NEU"
elif mut_value >= class_threshold:
dict_classified[dataset][loc][mut] = "BEN"
#if mut_value < -1:
# dict_classified[dataset][loc][mut] = "DEL"
#elif mut_value >= -1 and mut_value < -0.3:
# dict_classified[dataset][loc][mut] = "NEU"
#elif mut_value >= -0.3:
# dict_classified[dataset][loc][mut] = "BEN"
"""
*****************************************
Count the basal classifiers
*****************************************
"""
if self.dict_workflow['basal_count']:
#Import our class
try:
from pact.analysis.basal_count import basal_count
except ImportError:
print("[Protocols:" + str_protocol_name + " Error] pact.analysis.basal_count was not found.")
quit()
#Create our object
obj_basal = basal_count(self.obj_cfgparser, self.dict_programs, {})
#Count our basal rates
for dataset in dict_classified:
print("[Protocols:" + str_protocol_name + "] Basal Fitness Counts for dataset: " + dataset)
file_output.write("[Protocols:" + str_protocol_name + "] Basal Fitness Counts for dataset: " + dataset)
file_output.write(obj_basal.basal_count(dict_classified[dataset]) + "\n")
"""
*****************************************
DNA Filtering/Alignment or PSSM Object
*****************************************
"""
if (self.dict_workflow['blastp_align_filter'] or
self.dict_workflow['pssm'] or
self.dict_workflow['pssm_reader']):
#Import Check Output
from subprocess import check_output
#Import our class
try:
from pact.analysis.sequence.homology_pssm import homology_classifier
except ImportError:
print("[Protocols:" + str_protocol_name + " Error] pact.analysis.sequence.homology_pssm was not found.")
quit()
#Create our object
obj_homology = homology_classifier(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
#Count our classifiers
print("[Protocols:" + str_protocol_name + "] Homology PSSM")
file_output.write("[Protocols:" + str_protocol_name + "] Homology PSSM")
"""
*****************************************
DNA Filtering/Alignment
*****************************************
"""
if self.dict_workflow['blastp_align_filter']:
#Convert our XML file
print("[Protocols:" + str_protocol_name + "] xml_to_fasta")
file_output.write("[Protocols:" + str_protocol_name + "] xml_to_fasta\n")
obj_homology.xml_to_fasta()
#Run CD-HIT on our new fasta file
print("[Protocols:" + str_protocol_name + "] cdhit")
file_output.write("[Protocols:" + str_protocol_name + "] cdhit\n")
#Check to see if the number of processes is logical
self.processes = self.obj_cfgparser.get("blastp_align_filter", "processes")
if int(self.processes) <= 0:
self.processes = "2"
check_output([self.dict_programs['cdhit'],
"-i",
self.directory + self.output_prefix + ".fa",
"-o",
self.directory + self.output_prefix + ".afa",
"-c",
str(self.obj_cfgparser.get("blastp_align_filter", "cdhit_clustering_threshold")),
"-M",
"40000",
"-T",
str(self.processes)])
#Check to see if we have WT in our cdhit output
print("[Protocols:" + str_protocol_name + "] cdhit_wtcheck")
file_output.write("[Protocols:" + str_protocol_name + "] cdhit_wtcheck\n")
obj_homology.cdhit_wt_check()
#Run MUSCLE on our new fasta file
print("[Protocols:" + str_protocol_name + "] muscle")
file_output.write("[Protocols:" + str_protocol_name + "] muscle\n")
check_output([self.dict_programs['muscle'],
"-in",
self.directory + self.output_prefix + ".afa",
"-out",
self.directory + self.output_prefix + ".msa"])
#Process our MSA (needs to be on for PSIBlast)
print("[Protocols:" + str_protocol_name + "] processmsa")
file_output.write("[Protocols:" + str_protocol_name + "] processmsa\n")
list_msa = obj_homology.process_msa()
#Save our list
print("[Protocols:" + str_protocol_name + "] Saving our MSA")
file_output.write("[Protocols:" + str_protocol_name + "] Saving our MSA\n")
save_pact_file(list_msa, self.directory + self.output_prefix + '_' + "list_msa")
"""
*****************************************
PSSM
*****************************************
"""
if self.dict_workflow['pssm']:
#Open our list
print("[Protocols:" + str_protocol_name + "] Opening our MSA")
file_output.write("[Protocols:" + str_protocol_name + "] Opening our MSA\n")
list_msa = open_pact_file(self.directory + self.output_prefix + '_' + "list_msa")
#Split our msa for PSIBlast (needs to be on for PSIBlast)
print("[Protocols:" + str_protocol_name + "] msa_split")
file_output.write("[Protocols:" + str_protocol_name + "] msa_split\n")
list_pbcmds = obj_homology.msa_split(list_msa)
#Run PSIBlast
print("[Protocols:" + str_protocol_name + "] psiblast")
file_output.write("[Protocols:" + str_protocol_name + "] psiblast\n")
for command in list_pbcmds:
check_output([self.dict_programs['psiblast'], *command])
#Import our PSSM data
print("[Protocols:" + str_protocol_name + "] pssm_file_import")
file_output.write("[Protocols:" + str_protocol_name + "] pssm_file_import\n")
dict_pssm = obj_homology.pssm_file_import()
#Save our heatmap
print("[Protocols:" + str_protocol_name + "] Saving a PSSM .csv heatmap")
file_output.write(obj_homology.pssm_output_heat(dict_pssm) + "\n")
#Save our csv
print("[Protocols:" + str_protocol_name + "] Saving a PSSM .csv column data")
file_output.write(obj_homology.pssm_output_csv(dict_pssm) + "\n")
#Save our PACT File
print("[Protocols:" + str_protocol_name + "] Saving a PSSM .pact file")
file_output.write(save_pact_file(dict_pssm, self.directory + self.output_prefix + '_' + "PSSM") + "\n")
"""
*****************************************
Read stored PSSM files
*****************************************
"""
if (self.dict_workflow['pssm_reader'] or self.dict_workflow['consensus']):
#Open our PACT File
print("[Protocols:" + str_protocol_name + "] Opening a PSSM .pact file")
dict_pssm = open_pact_file(self.directory + self.output_prefix + '_' + "PSSM")
"""
*****************************************
PDB Import Section
*****************************************
"""
#Only import and run if selected
if self.dict_workflow['pdb_import']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('pdb_import'):
print("[Protocols:" + str_protocol_name + " Error] The pdb_import config file is incorrect.")
print("[Protocols:" + str_protocol_name + " Error] There is something wrong with the [pdb_import] section.")
quit()
#Import our class
try:
from pact.analysis.pdb_import import pdb_import
except ImportError:
print("[Protocols:" + str_protocol_name + " Error] pdb_import was not found.")
#Create the object then call the merger
obj_pdb = pdb_import(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
#The dict will be like {'pdb name': {data...
dict_pdb = obj_pdb.pdb_import()
"""
*****************************************
Back to Consensus Analyses
*****************************************
"""
if self.dict_workflow['consensus']:
#Import our class
try:
from pact.analysis.sequence.consensus import consensus
except ImportError:
print("[Protocols:" + str_protocol_name + "] pact.analysis.basal_count was not found.")
quit()
#Create our object
obj_consensus = consensus(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
#Get the wild-type sequence information
dict_wtcons = obj_consensus.wt_consensus(dict_pssm)
"""
*****************************************
Residue Chemical/Size
*****************************************
"""
if self.dict_workflow['residue_chemical_size']:
#Import our residue_chemical_size class
try:
from pact.analysis.sequence.residue_chemical_size import residue_chemical_size
except ImportError:
print("[Protocols:Enzyme Solubility Error] residue_chemical_size was not found.")
#Create the object then call the merger
obj_rcs = residue_chemical_size(self.obj_cfgparser, self.dict_programs, {})
"""
*****************************************
Distance to Active Site
*****************************************
"""
#Only import and run if selected
if self.dict_workflow['distance_to_active']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('distance_to_active'):
print("[Protocols:Enzyme Solubility Error] The distance_to_active config file is incorrect.")
print("[Protocols:Enzyme Solubility Error] There is something wrong with the [distance_to_active] section.")
quit()
#Import our class
try:
from pact.analysis.structure.dist_to_active import dist_to_active
except ImportError:
print("[Protocols:Enzyme Solubility] pact.analysis.structure.dist_to_active was not found.")
quit()
#Create our object
obj_dtoa = dist_to_active(self.obj_cfgparser, self.dict_programs, {})
#Calculate the distance
dict_dtoa_dist = obj_dtoa.dta_dist(dict_pdb)
"""
*****************************************
Contact Number
*****************************************
"""
#Only import and run if selected
if self.dict_workflow['contact_number']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('contact_number'):
print("[Protocols:Enzyme Solubility Error] The contact_number config file is incorrect.")
print("[Protocols:Enzyme Solubility Error] There is something wrong with the [contact_number] section.")
quit()
#Import our class
try:
from pact.analysis.structure.contact_number import contact_number
except ImportError:
print("[Protocols:Enzyme Solubility] pact.analysis.structure.contact_number was not found.")
quit()
#Create our object
obj_contact = contact_number(self.obj_cfgparser, self.dict_programs, {})
#Calculate the distance
dict_contact = obj_contact.contact_number(dict_pdb)
"""
*****************************************
Output CSV and .pact
*****************************************
"""
quit()
aa_table = 'ACDEFGHIKLMNPQRSTVWY'
wtaa = self.obj_cfgparser.get('global', 'wtaa').upper()
if self.dict_workflow['pdb_import']:
chain = self.obj_cfgparser.get('classification_analysis', 'chain').upper()
pdb_file = self.obj_cfgparser.get('classification_analysis', 'pdb_file')
list_pdb_sites = sorted([x for x in dict_pdb[pdb_file]['dssp'][chain]])
#Make a dict to work into
dict_output = {}
#Get the dataset name in order
if self.obj_cfgparser.has_section("combinepact"):
num_datasets = int(self.obj_cfgparser.get('combinepact', 'numdatasets'))
list_datasets = [self.obj_cfgparser.get('combinepact', 'dataset_' + str(int_dataset))
for int_dataset in range(1, num_datasets + 1)]
else:
list_datasets = []
#Get the header
str_output = ','.join([
"Location",
"Mutation",
','.join([dataset + "_fitness" for dataset in list_datasets]),
','.join([dataset + "_sd_from_wt" for dataset in list_datasets]),
','.join([dataset + "_classified" for dataset in list_datasets]),
"wt_resi",
"wt_pssm",
"wt_percent",
"max_pssm",
"max_percent",
"pssm_cons_count",
"percent_cons_count",
"wt_max_pssm",
"wt_max_percent",
"mut_pssm",
"mut_percent",
"frac_burial",
"polarity",
"aromatics",
"philic_phobic",
"size",
"hydropathy",
"dist_to_active",
"contact_number"
]) + "\n"
#Loop the locations
for loc in range(1, len(wtaa) + 1):
#Add to dict if not already added
if loc not in dict_output:
dict_output[loc] = {}
#Loop the mutations
for mut in aa_table:
#Add to dict if not already added
if mut not in dict_output[loc]:
dict_output[loc][mut] = {}
#Get the location
str_output = str_output + str(loc) + ','
#Get the mutation
str_output = str_output + mut + ','
#Get the datasets, test if loc is in there
str_output = str_output + ','.join([str(dict_merged_datasets[dataset][loc][mut]['fitness'])
if loc in dict_merged_datasets[dataset] else " "
for dataset in list_datasets
]) + ','
str_output = str_output + ','.join([str(dict_merged_datasets[dataset][loc][mut]['sd_from_wt'])
if loc in dict_merged_datasets[dataset] else " "
for dataset in list_datasets
]) + ','
#Get the classified
str_output = str_output + ','.join([str(dict_classified[dataset][loc][mut])
if loc in dict_classified[dataset] else " "
for dataset in list_datasets
]) + ','
#Get the WT Consensus Data
if self.dict_workflow['consensus']:
str_output = str_output + ','.join(map(str, [
dict_wtcons[loc]['wt_resi'],
dict_wtcons[loc]['wt_pssm'],
dict_wtcons[loc]['wt_percent'],
dict_wtcons[loc]['max_pssm'],
dict_wtcons[loc]['max_percent'],
dict_wtcons[loc]['pssm_cons_count'],
dict_wtcons[loc]['percent_cons_count'],
dict_wtcons[loc]['wt_max_pssm'],
dict_wtcons[loc]['wt_max_percent'],
])) + ','
else:
str_output = str_output + "NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,"
#Get the PSSM data
if self.dict_workflow['pssm_reader']:
str_output = str_output + dict_pssm[loc][mut][0] + ","
str_output = str_output + dict_pssm[loc][mut][1] + ","
else:
str_output = str_output + "NaN,NaN,"
#Get the fraction burial
if self.dict_workflow['pdb_import']:
if loc in list_pdb_sites:
str_output = str_output + str(dict_pdb[pdb_file]['dssp'][chain][loc]['frac_burial']) + ","
else:
str_output = str_output + "NaN,"
else:
str_output = str_output + "NaN,"
#To/From Proline
if self.dict_workflow['residue_chemical_size']:
dict_rcs_mut = obj_rcs.mut_info(wtaa[loc - 1], mut)
str_output = str_output + ','.join([dict_rcs_mut['polarity'],
dict_rcs_mut['aromatics'],
dict_rcs_mut['philic_phobic'],
dict_rcs_mut['size'],
str(dict_rcs_mut['hydropathy']),
]) + ','
else:
str_output = str_output + "NaN,NaN,NaN,NaN,NaN,"
#Dist to active site
if self.dict_workflow['distance_to_active']:
str_output = str_output + str(min(dict_dtoa_dist[chain][loc])) + ','
else:
str_output = str_output + "NaN,"
#Contact number
if self.dict_workflow['contact_number']:
str_output = str_output + str(len(dict_contact[chain][loc])) + ','
else:
str_output = str_output + "NaN,"
#Newline
str_output = str_output + '\n'
#Output a csv file
with open(self.directory + self.output_prefix + '_dataset.csv', 'w') as file_output:
file_output.write(str_output)
#At this point it's easier to backcalculate the csv file
list_output = str_output.splitlines()
list_keys = list_output[0].rstrip('\n').split(',')
columns = len(list_keys)
#Parse the lines
for line in list_output[1:]:
#Split the line
splitline = line.split(',')
#Parse each column
for i in range(2, columns):
dict_output[int(splitline[0])][splitline[1]][list_keys[i]] = splitline[i]
#Output a pact file
print(save_pact_file(dict_output, self.directory + self.output_prefix + '_dataset'))
return
def protocol(self):
"""Provide a protocol that does general analyses that don't need a full protocol"""
#Create a output log file that we can append to
with open(self.directory + self.output_prefix + "_" + strftime("%m_%d_%Y") + "-" +
strftime("%H_%M_%S") + '_output.txt', 'w') as file_output:
file_output.write(self.pact_preamble + "\n")
"""
*****************************************
Pact Combine (Required)
*****************************************
"""
#Check to see if the section is there
if not self.obj_cfgparser.has_section('combinepact'):
print("[Protocols:Analysis Error] The combinepact config file is incorrect.")
print("[Protocols:Analysis Error] There is something wrong with the [combinepact] section.")
quit()
#Import our combinepact class
try:
from pact.analysis.combine_pact import combine_pact
except ImportError:
print("[Protocols:Analysis Error] combine_pact was not found.")
#Create the object then call the merger
obj_combine = combine_pact(self.obj_cfgparser, self.dict_programs, {})
#Print Section Progress
print("[Protocols:Analysis] Combine PACT")
#The dict will be like {'dataset name': {data...
dict_merged_datasets = obj_combine.combine_pact()
"""
*****************************************
T-Test of Two Groups
*****************************************
"""
if self.dict_workflow['aa_compare_ttest']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('aa_compare_ttest'):
print("[Protocols:Analysis Error] The aa_compare_ttest config file is incorrect.")
print("[Protocols:Analysis Error] There is something wrong with the [aa_compare_ttest] section.")
quit()
#Import our class
try:
from pact.analysis.sequence.aa_fitmet_compare import aa_fitmet_compare
except ImportError:
print("[Protocols:Analysis Error] aa_fitmet_compare was not found.")
#Create the object then call the merger
obj_aac = aa_fitmet_compare(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
#Run the main routine
print("[Protocols:Analysis] T-Test of amino acid groups")
file_output.write(obj_aac.aa_fitmet_compare(dict_merged_datasets))
"""
*****************************************
Count our mutations
*****************************************
"""
if self.dict_workflow['threshold_count']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('threshold_count'):
print("[Protocols:Analysis Error] The threshold_count config file is incorrect.")
print("[Protocols:Analysis Error] There is something wrong with the [threshold_count] section.")
quit()
#Create our object
try:
from pact.analysis.sequence.threshold_count import threshold_count
except ImportError:
print("[Protocols:Analysis Error] threshold_count was not found.")
#Create the object then call the analysis
obj_tc = threshold_count(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
#Count them
print("[Protocols:Analysis] Count of mutations above and below a cutoff")
file_output.write(obj_tc.threshold_count(dict_merged_datasets))
return
def protocol(self):
"""Main entrypoint for the protocol"""
#Create a output log file that we can append to
with open(self.directory + self.output_prefix + "_" + strftime("%m_%d_%Y") + "-" +
strftime("%H_%M_%S") + '_output.txt', 'w') as file_output:
file_output.write(self.pact_preamble + "\n")
"""
*****************************************
Pact Combine (Required)
*****************************************
"""
#Check to see if the section is there
if not self.obj_cfgparser.has_section('combinepact'):
print("[Protocols:Enzyme Solubility Error] The combinepact config file is incorrect.")
print("[Protocols:Enzyme Solubility Error] There is something wrong with the [combinepact] section.")
quit()
#Import our combinepact class
try:
from pact.analysis.combine_pact import combine_pact
except ImportError:
print("[Protocols:Enzyme Solubility Error] combine_pact was not found.")
#Create the object then call the merger
obj_combine = combine_pact(self.obj_cfgparser, self.dict_programs, {})
#The dict will be like {'dataset name': {data...
dict_merged_datasets = obj_combine.combine_pact()
"""
*****************************************
Classify our mutations
*****************************************
"""
#Build a dict_classified with [location][mutation] = "DEL/SLIGHTDEL/NEU/NONE"
#0.15 in GFP, 80% of WT = neutral, 50% of WT = slightly, <50% of WT = deleterious
#Get the config file elements
try:
screen_dataset = self.obj_cfgparser.get("enzyme_solubility", "dataset_screen")
screen_threshold = float(self.obj_cfgparser.get("enzyme_solubility", "screen_threshold"))
fitness_dataset = self.obj_cfgparser.get("enzyme_solubility", "dataset_fitness")
fitness_neutral = float(self.obj_cfgparser.get("enzyme_solubility", "fitness_neu"))
fitness_slightdel = float(self.obj_cfgparser.get("enzyme_solubility", "fitness_slightdel"))
except NoOptionError:
print("[Enzyme Solubility Error] Missing [enzyme_solubility] config file elements.")
quit()
except ValueError:
print("[Enzyme Solubility Error] Incorrect [enzyme_solubility] config file elements.")
quit()
except TypeError:
print("[Enzyme Solubility Error] Incorrect [enzyme_solubility] config file elements.")
quit()
#Make a dict to add our classifications into
dict_classified = {}
dict_basal = {}
#Loop the locations
for loc in dict_merged_datasets[screen_dataset]:
#Add a new location if not in the dict
if loc not in dict_classified:
dict_classified[loc] = {}
#Add a new location if not in the dict
if loc not in dict_basal:
dict_basal[loc] = {}
#Loop the muts
for mut in dict_merged_datasets[screen_dataset][loc]:
#Skip WT, stop, and NaN
if (mut == dict_merged_datasets[fitness_dataset][loc][mut]['wt_residue'] or
mut == "*" or
dict_merged_datasets[fitness_dataset][loc][mut]['fitness'] == "NaN"):
dict_basal[loc][mut] = "UNCLASSIFIED"
continue
#Get the fitness value from the fitness dataset
fitness_value = float(dict_merged_datasets[fitness_dataset][loc][mut]['fitness'])
#For the basal screen fitness
#Assign a classification of deleterious, slightly deleterious, or neutral
if fitness_value < fitness_slightdel:
dict_basal[loc][mut] = "DEL"
elif (fitness_value >= fitness_slightdel and fitness_value < fitness_neutral):
dict_basal[loc][mut] = "SLIGHTDEL"
elif fitness_value >= fitness_neutral:
dict_basal[loc][mut] = "NEU"
#Skip WT, stop, and NaN
if (mut == dict_merged_datasets[screen_dataset][loc][mut]['wt_residue'] or
mut == "*" or
dict_merged_datasets[screen_dataset][loc][mut]['fitness'] == "NaN"):
dict_classified[loc][mut] = "UNCLASSIFIED"
continue
#Are we are enriched in the screen dataset?
if float(dict_merged_datasets[screen_dataset][loc][mut]['fitness']) < screen_threshold:
dict_classified[loc][mut] = "UNCLASSIFIED"
continue
#Assign a classification of deleterious, slightly deleterious, or neutral
if fitness_value < fitness_slightdel:
dict_classified[loc][mut] = "DEL"
elif (fitness_value >= fitness_slightdel and fitness_value < fitness_neutral):
dict_classified[loc][mut] = "SLIGHTDEL"
elif fitness_value >= fitness_neutral:
dict_classified[loc][mut] = "NEU"
"""
*****************************************
Count the basal classifiers
*****************************************
"""
if self.dict_workflow['basal_count']:
#Import our class
try:
from pact.analysis.basal_count import basal_count
except ImportError:
print("[Protocols:Enzyme Solubility] pact.analysis.basal_count was not found.")
quit()
#Create our object
obj_basal = basal_count(self.obj_cfgparser, self.dict_programs, {})
#Count our basal rates
print("[Protocols:Enzyme Solubility] Basal Screen Counts")
file_output.write("[Protocols:Enzyme Solubility] Basal Screen Counts")
file_output.write(obj_basal.basal_count(dict_basal) + "\n")
print("[Protocols:Enzyme Solubility] Basal Fitness Counts")
file_output.write("[Protocols:Enzyme Solubility] Basal Fitness Counts")
file_output.write(obj_basal.basal_count(dict_classified) + "\n")
"""
*****************************************
DNA Filtering/Alignment or PSSM Object
*****************************************
"""
if self.dict_workflow['blastp_align_filter'] or self.dict_workflow['pssm']:
#Import Check Output
from subprocess import check_output
#Import our class
try:
from pact.analysis.sequence.homology_pssm import homology_classifier
except ImportError:
print("[Protocols:Enzyme Solubility] pact.analysis.sequence.homology_pssm was not found.")
quit()
#Create our object
obj_homology = homology_classifier(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
"""
*****************************************
DNA Filtering/Alignment
*****************************************
"""
if self.dict_workflow['blastp_align_filter']:
#Convert our XML file
print("[Protocols:Enzyme Solubility] xml_to_fasta")
file_output.write("[Protocols:Enzyme Solubility] xml_to_fasta\n")
obj_homology.xml_to_fasta()
#Run CD-HIT on our new fasta file
print("[Protocols:Enzyme Solubility] cdhit")
file_output.write("[Protocols:Enzyme Solubility] cdhit\n")
#Check to see if the number of processes is logical
self.processes = self.obj_cfgparser.get("blastp_align_filter", "processes")
if int(self.processes) <= 0:
self.processes = "2"
check_output([self.dict_programs['cdhit'],
"-i",
self.directory + self.output_prefix + ".fa",
"-o",
self.directory + self.output_prefix + ".afa",
"-c",
str(self.obj_cfgparser.get("blastp_align_filter", "cdhit_clustering_threshold")),
"-M",
"40000",
"-T",
str(self.processes)])
#Check to see if we have WT in our cdhit output
print("[Protocols:Enzyme Solubility] cdhit_wtcheck")
file_output.write("[Protocols:Enzyme Solubility] cdhit_wtcheck\n")
obj_homology.cdhit_wt_check()
#Run MUSCLE on our new fasta file
print("[Protocols:Enzyme Solubility] muscle")
file_output.write("[Protocols:Enzyme Solubility] muscle\n")
check_output([self.dict_programs['muscle'],
"-in",
self.directory + self.output_prefix + ".afa",
"-out",
self.directory + self.output_prefix + ".msa"])
#Process our MSA (needs to be on for PSIBlast)
print("[Protocols:Enzyme Solubility] processmsa")
file_output.write("[Protocols:Enzyme Solubility] processmsa\n")
list_msa = obj_homology.process_msa()
#Save our list
print("[Protocols:Enzyme Solubility] Saving our MSA")
file_output.write("[Protocols:Enzyme Solubility] Saving our MSA\n")
obj_homology.save_data_structure(list_msa, "list_msa")
"""
*****************************************
PSSM
*****************************************
"""
if self.dict_workflow['pssm'] or self.dict_workflow['strict_filter']:
#Open our list
print("[Protocols:Enzyme Solubility] Opening our MSA")
file_output.write("[Protocols:Enzyme Solubility] Opening our MSA\n")
list_msa = obj_homology.open_data_structure("list_msa")
#Split our msa for PSIBlast (needs to be on for PSIBlast)
print("[Protocols:Enzyme Solubility] msa_split")
file_output.write("[Protocols:Enzyme Solubility] msa_split\n")
list_pbcmds = obj_homology.msa_split(list_msa)
#Run PSIBlast
print("[Protocols:Enzyme Solubility] psiblast")
file_output.write("[Protocols:Enzyme Solubility] psiblast\n")
for command in list_pbcmds:
check_output([self.dict_programs['psiblast'], *command])
#Import our PSSM data
print("[Protocols:Enzyme Solubility] pssm_file_import")
file_output.write("[Protocols:Enzyme Solubility] pssm_file_import\n")
dict_pssm = obj_homology.pssm_file_import()
#Save our heatmap
print("[Protocols:Enzyme Solubility] Saving a PSSM .csv heatmap")
file_output.write(obj_homology.pssm_output_heat(dict_pssm) + "\n")
#Save our csv
print("[Protocols:Enzyme Solubility] Saving a PSSM .csv column data")
file_output.write(obj_homology.pssm_output_csv(dict_pssm) + "\n")
#Save our PACT File
print("[Protocols:Enzyme Solubility] Saving a PSSM .pact file")
file_output.write(obj_homology.save_data_structure(dict_pssm, "PSSM") + "\n")
#Count our classifiers
print("[Protocols:Enzyme Solubility] PSSM")
file_output.write("[Protocols:Enzyme Solubility] PSSM")
print("Fitness Rates:")
file_output.write("Fitness Rates:")
file_output.write(obj_homology.classified_count_pssm(dict_pssm, dict_basal) + "\n")
print("\nScreen Rates:")
file_output.write("\nScreen Rates:")
file_output.write(obj_homology.classified_count_pssm(dict_pssm, dict_classified) + "\n")
"""
*****************************************
Residue Chemical/Size
*****************************************
"""
if self.dict_workflow['residue_chemical_size']:
#Import our residue_chemical_size class
try:
from pact.analysis.sequence.residue_chemical_size import residue_chemical_size
except ImportError:
print("[Protocols:Enzyme Solubility Error] residue_chemical_size was not found.")
#Create the object then call the merger
obj_rcs = residue_chemical_size(self.obj_cfgparser, self.dict_programs, {})
#Return the process dict {1: {'A': {''
dict_rcs = obj_rcs.process_dataset(dict_merged_datasets)
#Count our classifiers
print("[Protocols:Enzyme Solubility] Residue Chemical/Size")
file_output.write("[Protocols:Enzyme Solubility] Residue Chemical/Size")
print("Fitness Rates:")
file_output.write("Fitness Rates:")
file_output.write(obj_rcs.classified_count(dict_rcs, fitness_dataset, dict_basal) + "\n")
print("\nScreen Rates:")
file_output.write("\nScreen Rates:")
file_output.write(obj_rcs.classified_count(dict_rcs, screen_dataset, dict_classified) + "\n")
"""
*****************************************
PDB Import Section
*****************************************
"""
#Only import and run if selected
if (self.dict_workflow['pdb_import'] or
self.dict_workflow['distance_to_active'] or
self.dict_workflow['contact_number'] or
self.dict_workflow['strict_filter']):
#Check to see if the section is there
if not self.obj_cfgparser.has_section('pdb_import'):
print("[Protocols:Enzyme Solubility Error] The pdb_import config file is incorrect.")
print("[Protocols:Enzyme Solubility Error] There is something wrong with the [pdb_import] section.")
quit()
#Import our combinepact class
try:
from pact.analysis.pdb_import import pdb_import
except ImportError:
print("[Protocols:Enzyme Solubility Error] pdb_import was not found.")
#Create the object then call the merger
obj_pdb = pdb_import(self.obj_cfgparser, self.dict_programs, {'directory':self.directory})
#The dict will be like {'pdb name': {data...
dict_pdb = obj_pdb.pdb_import()
"""
*****************************************
Distance to Active Site
*****************************************
"""
#Only import and run if selected
if self.dict_workflow['distance_to_active'] or self.dict_workflow['strict_filter']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('distance_to_active'):
print("[Protocols:Enzyme Solubility Error] The distance_to_active config file is incorrect.")
print("[Protocols:Enzyme Solubility Error] There is something wrong with the [distance_to_active] section.")
quit()
#Import our class
try:
from pact.analysis.structure.dist_to_active import dist_to_active
except ImportError:
print("[Protocols:Enzyme Solubility] pact.analysis.structure.dist_to_active was not found.")
quit()
#Create our object
obj_dtoa = dist_to_active(self.obj_cfgparser, self.dict_programs, {})
#Calculate the distance
dict_dtoa_dist = obj_dtoa.dta_dist(dict_pdb)
#Count our classifiers
print("[Protocols:Enzyme Solubility] Distance to Active Site")
file_output.write("[Protocols:Enzyme Solubility] Distance to Active Site")
print("Fitness Rates:")
file_output.write("Fitness Rates:")
file_output.write(obj_dtoa.classified_count(dict_dtoa_dist, dict_basal) + "\n")
print("\nScreen Rates:")
file_output.write("\nScreen Rates:")
file_output.write(obj_dtoa.classified_count(dict_dtoa_dist, dict_classified) + "\n")
"""
*****************************************
Contact Number
*****************************************
"""
#Only import and run if selected
if self.dict_workflow['contact_number'] or self.dict_workflow['strict_filter']:
#Check to see if the section is there
if not self.obj_cfgparser.has_section('contact_number'):
print("[Protocols:Enzyme Solubility Error] The contact_number config file is incorrect.")
print("[Protocols:Enzyme Solubility Error] There is something wrong with the [contact_number] section.")
quit()
#Import our class
try:
from pact.analysis.structure.contact_number import contact_number
except ImportError:
print("[Protocols:Enzyme Solubility] pact.analysis.structure.contact_number was not found.")
quit()
#Create our object
obj_contact = contact_number(self.obj_cfgparser, self.dict_programs, {})
#Calculate the distance
dict_contact = obj_contact.contact_number(dict_pdb)
#Count our classifiers
print("[Protocols:Enzyme Solubility] Contact Number")
file_output.write("[Protocols:Enzyme Solubility] Contact Number")
print("Fitness Rates:")
file_output.write("Fitness Rates:")
file_output.write(obj_contact.classified_count(dict_contact, dict_basal) + "\n")
print("\nScreen Rates:")
file_output.write("\nScreen Rates:")
file_output.write(obj_contact.classified_count(dict_contact, dict_classified) + "\n")
"""
*****************************************
Strict Enzyme Filter
*****************************************
"""
#Only import and run if selected
if self.dict_workflow['strict_filter']:
print("[Protocols:Enzyme Solubility] Strict Enzyme Filter")
file_output.write("[Protocols:Enzyme Solubility] Strict Enzyme Filter")
#Check if the dicts exist
if 'dict_pssm' not in locals():
print("[Protocols:Enzyme Solubility] Missing PSSM Data")
file_output.write("[Protocols:Enzyme Solubility] Missing PSSM Data")
quit()
if 'dict_contact' not in locals():
print("[Protocols:Enzyme Solubility] Missing Contact Number Data")
file_output.write("[Protocols:Enzyme Solubility] Missing Contact Number Data")
quit()
if 'dict_dtoa_dist' not in locals():
print("[Protocols:Enzyme Solubility] Missing Active Site Distance Data")
file_output.write("[Protocols:Enzyme Solubility] Missing Active Site Distance Data")
quit()
#Implement a filter that
#PSSM >= 0
#Distance to Active >= 15A
#Contact Number <= 16
#No proline mutations
#Create a list to work into
list_strictfilter = []
#Loop the locations
for loc in dict_classified:
#Loop the mutations
for mut in dict_classified[loc]:
#Skip PRO, and Stop
if (mut == "P" or
mut == "*" or
dict_merged_datasets[screen_dataset][loc][mut]['wt_residue'] == "P"):
continue
#Check if PSSM is less than 0
if int(dict_pssm[loc][mut][0]) < 0:
continue
#Skip residues without location data
if loc not in dict_contact or loc not in dict_dtoa_dist:
continue
#Check if Distance to Active is less than 15A
if min(dict_dtoa_dist[loc]) < 15:
continue
#Check if the contact number is greater than 16
if len(dict_contact[loc]) > 16:
continue
#Otherwise, add to our list
list_strictfilter.append(dict_classified[loc][mut])
#Report
str_return = '\n'.join(map(str, [
"Enzyme Strict Filter",
pretty_counter_dicts(dict(Counter(list_strictfilter)))
]))
print(str_return)
file_output.write(str_return)
return