def __init__(self, inputFileName):
# variables used in this class
self.multiSum = 0 # multitargetting sum taken from the previous version of make_graphs
self.multiCount = 0 # multitargetting count taken from the previous version of make_graphs
self.seqTrans = SeqTranslate(
) # SeqTranslate variable. for decrompressing the data
self.chromesomeList = list(
) # list of a list for the chromesomes. As it currently stands, this variable is used in both read_chromesomes and in read_targets
self.karystatsList = list(
) # list of (ints) of the karyStats (whatever those are) to be used for the get_chrom_length function
self.genome = "" # genome name
self.misc = "" # anything from the misc line
self.repeats = {
} # dictionary of the number of repeats. See the read_repeats function for more info
self.seeds = {
} # dictionary of which chromesomes are repeats. See the read_repeats function for more info
self.dec_tup_data = {}
self.chromesomesSelectedList = list()
# data for population analysis
# dict:
# key = the seed
# value = tuple (org name, chom #, location, sequence, pam, score, strand, endo)
self.popData = {}
# file path variable
self.fileName = inputFileName
def __init__(self, casper_seq_file, output_file_path, ofa):
self.csffile = casper_seq_file
self.ST = SeqTranslate()
self.allTargets = {}
self.location = tuple()
self.output = output_file_path
self.off_target_all = ofa
def __init__(self):
# qt stuff
super(genLibrary, self).__init__()
uic.loadUi('library_prompt.ui', self)
self.setWindowTitle('Generate Library')
self.setWindowIcon(Qt.QIcon('cas9image.png'))
# button connections
self.cancel_button.clicked.connect(self.cancel_function)
self.BrowseButton.clicked.connect(self.browse_function)
self.submit_button.clicked.connect(self.submit_data)
self.progressBar.setValue(0)
# variables
self.anno_data = dict()
self.cspr_file = ''
self.parser = CSPRparser('')
self.kegg_nonKegg = ''
self.gen_lib_dict = dict()
self.S = SeqTranslate()
self.cspr_data = dict()
self.Output = dict()
self.off_tol = .05
self.off_max_misMatch = 4
self.off_target_running = False
# set the numbers for the num genes combo box item
for i in range(10):
self.numGenescomboBox.addItem(str(i + 1))
# set the numbers for the minOn combo box
for i in range(19, 70):
self.minON_comboBox.addItem(str(i + 1))
def __init__(self, parent=None):
super(Multitargeting, self).__init__()
uic.loadUi('multitargetingwindow.ui', self)
self.setWindowIcon(QtGui.QIcon("cas9image.png"))
# Storage containers for the repeats and seed sequences
self.sq = SeqTranslate() # SeqTranslate object used in class
# Initializes the three graphs
self.chart_view_chro_bar = QChartView()
self.chart_view_repeat_bar = QChartView()
self.chart_view_repeat_line = QChartView()
self.data = ""
self.shortHand = ""
self.chromo_length = list()
# Listeners for changing the seed sequence or the .cspr file
self.max_chromo.currentIndexChanged.connect(self.fill_seed_id_chrom)
self.min_chromo.currentIndexChanged.connect(self.fill_seed_id_chrom)
self.chromo_seed.currentIndexChanged.connect(self.chro_bar_data)
self.Analyze_Button.clicked.connect(self.make_graphs)
#go back to main button
self.back_button.clicked.connect(self.go_back)
#Tool Bar options
self.actionCASPER.triggered.connect(self.changeto_main)
# Statistics storage variables
self.max_repeats = 1
self.average = 0
self.median = 0
self.mode = 0
self.average_unique = 0
self.average_rep = 0
self.bar_coords = []
self.seed_id_seq_pair = {}
self.positions = []
#parser object
self.parser = CSPRparser("")
self.ready_chromo_min_max = True
self.ready_chromo_make_graph = True
self.directory = 'Cspr files'
self.info_path = os.getcwd()
##################################
self.scene = QtWidgets.QGraphicsScene()
self.graphicsView.setScene(self.scene)
self.scene2 = QtWidgets.QGraphicsScene()
self.graphicsView_2.setScene(self.scene2)
self.graphicsView.viewport().installEventFilter(self)
def decode_targets(self):
f = open(self.filename)
# make sure to recognize chromosome number
data = f.readline()[:-1]
while data != "REPEATS":
data = f.readline()[:-1]
# parse location and sequence
midpoint = data.find(',')
location = data[:midpoint]
sequence = data[midpoint + 1:]
# decompress the location and sequence information
s = SeqTranslate()
location = s.decompress64(location, toseq=False)
sequence = s.decompress64(sequence, toseq=True)
# add location to storage vector
self.targets.append((location, sequence))
def __init__(self, info_path):
super(NewGenome, self).__init__()
uic.loadUi('NewGenome.ui', self)
self.setWindowTitle('New Genome')
self.k = KEGG()
self.info_path = info_path
#---Button Modifications---#
self.setWindowIcon(Qt.QIcon("cas9image.png"))
self.whatsthisButton.clicked.connect(self.whatsthisclicked)
self.KeggSearchButton.clicked.connect(self.updatekegglist)
self.resetButton.clicked.connect(self.reset)
self.submitButton.clicked.connect(self.submit)
self.browseForFile.clicked.connect(self.selectFasta)
self.NCBI_File_Search.clicked.connect(self.prep_ncbi_search)
self.JobsQueueBox.setReadOnly(True)
self.output_browser.setText("Waiting for program initiation...")
self.CompletedJobs.setText(" ")
self.contButton.clicked.connect(self.continue_to_main)
self.comboBoxEndo.currentIndexChanged.connect(self.endo_settings)
self.runButton.clicked.connect(self.run_jobs)
self.clearButton.clicked.connect(self.clear_job_queue)
self.viewStatButton.setEnabled(False)
self.JobsQueue = [] # holds Job classes.
self.Endos = dict()
self.file = ""
self.process = QtCore.QProcess()
self.process.setProcessChannelMode(QtCore.QProcess.MergedChannels)
self.process.finished.connect(self.upon_process_finishing)
self.seqTrans = SeqTranslate()
self.first = False
#show functionalities on window
self.fillEndo()
#self.show()
self.num_chromo_next = False
def __init__(self, output_path, base_org_path, base_org, endo, other_genomes, csize):
# initialize SeqTranslate object
self.ST = SeqTranslate()
self.output_path = output_path
# my_orgs contains just the
self.organisms = other_genomes
self.organisms.append(base_org)
self.organisms = sorted(self.organisms)
self.db_path = base_org_path
# This sets the size of the subsets. NOTE: DO NOT SET THIS TO A LARGE NUMBER IF THERE ARE A LOT OF ORGANISMS
self.combo_size = csize
# Dictionary of dictionaries. Key1: generic total sequence Key2: org Value: position
self.searchableseqs = {}
# Container that stores all the sequences seen the combination of organisms defined by the key
# An example key would be (sce, yli) for the shared sequences between S.cerevisiae and Y.lipolytica
self.buckets = {}
# Intitialize the self.buckets container to contain the tuple of every organism subset
for i in range(2, csize+1):
for subset in itertools.combinations(self.organisms, i):
self.buckets[subset] = []
print(subset)
self.endo = endo
# The object that is iterated over to decompress the output into readable form
self.compressed_output = {}
# Generates the sequence lists
for org in self.organisms:
print(org)
self.make_lists(org)
# Runs the comparison
self.create_comparison()
self.write_to_file()
def get_instances(self):
ST = SeqTranslate()
os.chdir(path)
f = open(self.file_name, 'r')
while True:
x = f.readline()
if x == 'REPEATS\n':
print("reached repeat sequences")
break
while True:
t = f.readline()
if t == 'END_OF_FILE':
print("reached end of repeat sequences")
break
ukey = t[:-1] # takes away the "\n" in the string
key = ST.decompress64(ukey, slength=20, toseq=True)
key = ST.fill_As(key, 16)
self.BAD_instances[key] = list()
# Add sequences and locations to the list
v = f.readline().split('\t')[:-1]
for item in v:
loctup = item.split(',')
chrom = loctup[0]
location = ST.decompress64(loctup[1])
seq = ST.decompress64(loctup[2][1:], slength=20, toseq=True)
seq = ST.fill_As(
seq, 4
) # when A's get lost in the compression this fills them back in
mytup = (chrom, location, seq)
self.BAD_instances[key].append(mytup)
f.close()
print("currently sorting")
for key in self.BAD_instances:
size = len(self.BAD_instances[key])
newtuple = (key, self.BAD_instances[key], size
) # sequence, location, size
self.sorted_instances.append(newtuple)
def __init__(self, threshold, endo, base_org, csf_file, other_orgs,
casperofflist, output_path):
self.ST = SeqTranslate()
self.rSequences = []
self.get_rseqs(casperofflist)
self.mypath = csf_file[:csf_file.find(base_org)]
self.ref_genomes = [base_org]
self.ref_genomes += other_orgs
self.endo = endo
self.threshold = threshold
self.dSequence = str(
) # global to class so that all scoring functions can use it
# This is for autofilling the HsuMatrix
self.matrixKeys = [
"GT", "AC", "GG", "TG", "TT", "CA", "CT", "GA", "AA", "AG", "TC",
"CC"
]
self.matrix = {}
self.fill_matrix()
# This is where the data is stored before it is written
self.output_data = dict()
for myseq in self.rSequences:
self.output_data[myseq[0]] = list()
# BEGIN RUNNING THROUGH SEQUENCES
for sequence in self.rSequences:
print(sequence)
for genome in self.ref_genomes:
f = open(self.mypath + genome + self.endo + ".cspr", 'r')
while True:
line = f.readline()
if line.find("CHROMOSOME") != -1:
curchrom = line[line.find("#") + 1:-1]
print("Finished checking " + curchrom)
else:
if line[0:-1] == "REPEATS":
break
# Checks for a signifcant number of mismatches:
#locseq = line[:-1].split(",")
if self.critical_similarity(
sequence[0],
self.ST.decompress_csf_tuple(line)[1]):
# This is where the real fun begins: off target analysis
print('found a similarity')
seqscore = self.get_scores(
sequence[1],
self.ST.decompress_csf_tuple(line)[1])
if seqscore > self.threshold:
self.output_data[sequence[0]].append(
(str(curchrom),
self.ST.decompress_csf_tuple(line[:-1]),
int(seqscore * 100), genome))
# END SEQUENCES RUN
# Output the data acquired:
out = open(
output_path + "off_results" + str(datetime.datetime.now().time()) +
'.txt', 'w')
out.write(
"Off-target sequences identified. Scores are between O and 1. A higher value indicates greater"
"probability of off-target activity at that location.\n")
for sequence in self.output_data:
out.write(sequence + "\n")
for off_target in self.output_data[sequence]:
outloc = off_target[0] + "," + str(
off_target[1][0]) + "," + off_target[1][1]
out.write(off_target[3] + "," + outloc + "\t" +
str(off_target[2] / 100) + '\n')
out.close()
def __init__(self, parent=None):
super(Multitargeting, self).__init__()
uic.loadUi(GlobalSettings.appdir + 'multitargetingwindow.ui', self)
self.setWindowIcon(QtGui.QIcon(GlobalSettings.appdir +
"cas9image.png"))
self.sq = SeqTranslate() # SeqTranslate object used in class
# Initializes the three graphs
self.chart_view_chro_bar = QChartView()
self.chart_view_repeat_bar = QChartView()
self.chart_view_repeat_line = QChartView()
self.data = ""
self.shortHand = ""
self.chromo_length = list()
# Listeners for changing the seed sequence or the .cspr file
self.chromo_seed.currentIndexChanged.connect(self.seed_chromo_changed)
self.update_min_max.clicked.connect(self.update)
self.Analyze_Button.clicked.connect(self.make_graphs)
# go back to main button
self.back_button.clicked.connect(self.go_back)
# Tool Bar options
self.actionCASPER.triggered.connect(self.changeto_main)
# Statistics storage variables
self.max_repeats = 1
self.average = 0
self.median = 0
self.mode = 0
self.average_unique = 0
self.average_rep = 0
self.bar_coords = []
self.seed_id_seq_pair = {}
# parser object
self.parser = CSPRparser("")
self.ready_chromo_min_max = True
self.ready_chromo_make_graph = True
self.directory = 'Cspr files'
self.info_path = os.getcwd()
##################################
self.scene = QtWidgets.QGraphicsScene()
self.graphicsView.setScene(self.scene)
self.scene2 = QtWidgets.QGraphicsScene()
self.graphicsView_2.setScene(self.scene2)
self.graphicsView.viewport().installEventFilter(self)
self.loading_window = loading_window()
screen = QtGui.QGuiApplication.screenAt(QtGui.QCursor().pos())
self.mwfg = self.frameGeometry() ##Center window
self.cp = QtWidgets.QDesktopWidget().availableGeometry().center(
) ##Center window
self.mwfg.moveCenter(self.cp) ##Center window
self.move(self.mwfg.topLeft()) ##Center window
self.hide()
def __init__(self, info_path):
super(NewGenome, self).__init__()
uic.loadUi(GlobalSettings.appdir + 'NewGenome.ui', self)
self.setWindowTitle('New Genome')
self.setWindowTitle('New Genome')
self.info_path = info_path
#---Style Modifications---#
groupbox_style = """
QGroupBox:title{subcontrol-origin: margin;
left: 10px;
padding: 0 5px 0 5px;}
QGroupBox#Step1{border: 2px solid rgb(111,181,110);
border-radius: 9px;
font: 15pt "Arial";
font: bold;
margin-top: 10px;}"""
self.Step1.setStyleSheet(groupbox_style)
self.Step2.setStyleSheet(groupbox_style.replace("Step1", "Step2"))
self.Step3.setStyleSheet(groupbox_style.replace("Step1", "Step3"))
#---Button Modifications---#
self.setWindowIcon(Qt.QIcon(GlobalSettings.appdir + "cas9image.png"))
self.resetButton.clicked.connect(self.reset)
self.submitButton.clicked.connect(self.submit)
self.browseForFile.clicked.connect(self.selectFasta)
self.remove_job.clicked.connect(self.remove_from_queue)
self.output_browser.setText("Waiting for program initiation...")
self.contButton.clicked.connect(self.continue_to_main)
self.comboBoxEndo.currentIndexChanged.connect(self.endo_settings)
self.runButton.clicked.connect(self.run_jobs_wrapper)
self.clearButton.clicked.connect(self.clear_job_queue)
self.JobsQueue = [] # holds Job classes.
self.Endos = dict()
self.file = ""
self.process = QtCore.QProcess()
self.process.setProcessChannelMode(QtCore.QProcess.MergedChannels)
self.process.finished.connect(self.upon_process_finishing)
self.seqTrans = SeqTranslate()
self.exit = False
self.first = False
#show functionalities on window
self.fillEndo()
#self.show()
self.num_chromo_next = False
#Jobs Table
#self.job_Table.setColumnCount(3)
self.job_Table.setShowGrid(False)
#self.job_Table.setHorizontalHeaderLabels(["Job Queue","Job in Progress", "Completed Jobs"])
self.job_Table.horizontalHeader().setSectionsClickable(True)
#self.job_Table.horizontalHeader().setSectionResizeMode(QHeaderView.ResizeToContents)
#self.job_Table.horizontalHeader().setSectionResizeMode(2, QHeaderView.Stretch)
self.job_Table.setSelectionBehavior(
QtWidgets.QAbstractItemView.SelectRows)
self.job_Table.setEditTriggers(
QtWidgets.QAbstractItemView.NoEditTriggers)
self.job_Table.setSelectionMode(
QtWidgets.QAbstractItemView.MultiSelection)
self.job_Table.setSizeAdjustPolicy(
QtWidgets.QAbstractScrollArea.AdjustToContents)
self.fin_index = 0
self.mwfg = self.frameGeometry() ##Center window
self.cp = QtWidgets.QDesktopWidget().availableGeometry().center(
) ##Center window
self.total_chrom_count = 0
self.perc_increase = 0
self.progress = 0
#toolbar button actions
self.visit_repo.triggered.connect(self.visit_repo_func)
self.go_ncbi.triggered.connect(self.open_ncbi_web_page)
self.comboBoxEndo.currentIndexChanged.connect(self.changeEndos)
#ncbi tool
self.NCBI_File_Search.clicked.connect(self.open_ncbi_tool)
self.seed_length.setEnabled(False)
self.five_length.setEnabled(False)
self.three_length.setEnabled(False)
self.repeats_box.setEnabled(False)
#user prompt class
self.goToPrompt = goToPrompt()
self.goToPrompt.goToMain.clicked.connect(self.continue_to_main)
self.goToPrompt.goToMT.clicked.connect(self.continue_to_MT)
self.goToPrompt.goToPop.clicked.connect(self.continue_to_pop)