def save_features(self, ask_filename=True):
features_filename = os.path.join(
self.host.settings.work_dir, self.host.get_project_name(),
"%s.features" % self.host.get_project_name())
if ask_filename:
features_filename = tkFileDialog.asksaveasfilename(
filetypes=(("Sequence features", "*.features"), ("All",
"*.*")))
Aln_basic.write_widget_into_file(self.features.text_widget,
features_filename, ask_filename)
def save_TMHMM(self, ask_filename=True):
TMHMM_filename = os.path.join(
self.host.settings.work_dir, self.host.get_project_name(),
"%s.TMHMM" % self.host.get_project_name())
if ask_filename:
TMHMM_filename = tkFileDialog.asksaveasfilename(
filetypes=(("Plain output of the TMHMM", "*.TMHMM"), ("All",
"*.*")))
Aln_basic.write_widget_into_file(self.TMHMM_results.text_widget,
TMHMM_filename, ask_filename)
def align(self):
if self.seq_input_frame.text_is_empty(): # No sequences were provided
self.host.set_status("No sequences were provided to align!", "#FF0000")
return
print (" Alignment construction started...")
(muscle_name, muscle_path) = Settings.get_program_name(self.host.settings.muscle_dir, "muscle")
unaligned_filename = os.path.join(self.host.settings.work_dir, "%s.fasta" % self.host.temp_name)
Aln_basic.write_widget_into_file(self.seq_input_frame.text_widget, unaligned_filename)
aligned_filename = os.path.join(self.host.settings.work_dir, "%s.aln" % self.host.temp_name)
self.host.set_status("Alignment")
maxiters_option = ""
if self.maxiters.get() != "":
try:
maxiters_option = "-maxiters %i" % int(self.maxiters.get())
except TypeError:
print ("Option -maxiters is not an integer and is ignored!")
gapopen_option = ""
if self.gapopen.get() != "":
if Aln_basic.is_negative_float(self.gapopen.get(), "-gapopen"):
gapopen_option = "-gapopen %s" % self.gapopen.get()
gapextend_option = ""
if self.gapextend.get() != "":
if Aln_basic.is_negative_float(self.gapextend.get(), "-gapextend"):
gapextend_option = "-gapextend %s" % self.gapextend.get()
muscle_command = "%s -in %s -out %s %s %s %s" % (muscle_path, unaligned_filename, aligned_filename, maxiters_option, gapopen_option, gapextend_option)
print ("Muscle command to be ran:")
print (muscle_command)
if self.host.verbose.get():
os.system(muscle_command)
else:
os.system("%s 1> nul 2> nul" % muscle_command)
Aln_basic.read_widget_from_file(self.aln_input_frame.text_widget, aligned_filename)
if self.insert_blocks.get(): # Empty sequence >BLOCKS should be added
curr_seqs = Aln_basic.read_fasta_from_strings(self.aln_input_frame.get_strings())
self.aln_input_frame.text_widget.delete(1.0, tkinter.END)
upd_aln_file = open(aligned_filename, "w")
upd_aln_file.write(">BLOCKS\n")
upd_aln_file.write("%s\n\n" % ("-" * len(curr_seqs[0].sequence)))
upd_aln_file.write(">SITE\n")
upd_aln_file.write("%s\n\n" % ("-" * len(curr_seqs[0].sequence)))
for s in curr_seqs:
s.print_fasta(upd_aln_file, 60)
upd_aln_file.close()
Aln_basic.read_widget_from_file(self.aln_input_frame.text_widget, aligned_filename)
self.host.set_status("Ready")
os.remove(unaligned_filename)
os.remove(aligned_filename)
print (" [..DONE..]")
def save_IDs(self, ask_filename = True):
ids_filename = os.path.join(self.host.settings.work_dir, self.host.get_project_name(), "%s.ids" % self.host.get_project_name())
if ask_filename:
ids_filename = tkFileDialog.asksaveasfilename(filetypes = (("List of protein IDs", "*.ids"), ("All", "*.*")))
curr_ID_save_mode = self.ID_save_mode.get()
curr_text = self.IDs.text_widget.get(1.0, tkinter.END).strip()
if curr_ID_save_mode != "No change":
print (" IDs will be converted before writing!")
to_gi = False
fix = False
if (curr_ID_save_mode == " -> gi ") or (curr_ID_save_mode == "fix & ->"):
to_gi = True
if (curr_ID_save_mode == "fix gi-gi") or (curr_ID_save_mode == "fix & ->"):
fix = True
locus_to_gi = dict()
id_to_gi = dict()
if to_gi:
self.host.set_status("Working")
import udav_soft
try: #FIX: (version 1.0) if <settings.table_filename> is not given, nothing bad will happen
(locus_to_gi, id_to_gi, a, b) = udav_soft.read_protein_table_info(self.host.settings.table_filename, True)
except AttributeError:
print (" [ERROR]: Table with assignment of GI to other types of IDs was not given to the script!")
print (" Please check 'table_filename' option in the <settings.ini> file")
except OSError:
print (" [ERROR]: Table with assignment of GI to other types of IDs '%s' not found!" % self.host.settings.table_filename)
del udav_soft
self.host.set_status("Ready")
strings = curr_text.split("\n")
i = 0
while i < len(strings):
curr_id = strings[i].strip()
if fix:
curr_id = curr_id.split("-", 1)[0]
new_id = curr_id
if to_gi:
if curr_id in locus_to_gi:
new_id = locus_to_gi[curr_id]
if curr_id in id_to_gi:
new_id = id_to_gi[curr_id]
strings[i] = new_id
i += 1
self.IDs.text_widget.delete(1.0, tkinter.END)
self.IDs.text_widget.insert(tkinter.END, "\n".join(strings).strip())
Aln_basic.write_widget_into_file(self.IDs.text_widget, ids_filename, ask_filename)
self.IDs.text_widget.delete(1.0, tkinter.END)
self.IDs.text_widget.insert(tkinter.END, curr_text)
def hmmsearch_profile_database(self, profile_database, database_type):
curr_project_dir = os.path.join(self.host.settings.work_dir, self.host.get_project_name())
if not os.path.isdir(curr_project_dir):
dir_answer = tkMessageBox.askyesno("Create directory and start analysis?", "This type of analysis cannot be done if the project directory is not created. Do you want to create the following directory and continue?\n%s" % curr_project_dir)
if dir_answer != True:
return
print (" Creating project directory de novo: '%s'" % curr_project_dir)
os.mkdir(curr_project_dir)
(hmmscan_name, hmmscan_path) = Settings.get_program_name(self.host.settings.hmmer_dir, "hmmscan")
pure_filename = os.path.join(self.host.settings.work_dir, self.host.get_project_name(), "%s.pure" % self.host.get_project_name())
Aln_basic.write_widget_into_file(self.pure.text_widget, pure_filename)
result_filename = os.path.join(self.host.settings.work_dir, self.host.get_project_name(), "%s.%s_out" % (self.host.get_project_name(), database_type))
table_filename = os.path.join(self.host.settings.work_dir, self.host.get_project_name(), "%s.%s_table" % (self.host.get_project_name(), database_type))
args = [hmmscan_path, "--domtblout", table_filename, "-o", result_filename, profile_database, pure_filename]
subprocess.Popen(args, stderr = subprocess.PIPE, stdout = subprocess.PIPE)
self.host.pending_filenames.append(result_filename)
self.host.pending_filenames.append(table_filename)
self.host.enable_check_button()
def obtain_features(self):
print(" Obtaining features...")
curr_mode = self.feature_mode.get()
domain_filename = os.path.join(self.host.settings.work_dir,
"%s.domain_table" % self.host.temp_name)
domain_not_empty = None
if curr_mode == "COG":
domain_not_empty = Aln_basic.write_widget_into_file(
self.hmmresults_COG.text_widget, domain_filename)
else:
domain_not_empty = Aln_basic.write_widget_into_file(
self.hmmresults_Pfam.text_widget, domain_filename)
fixed_filename = os.path.join(self.host.settings.work_dir,
"%s.fixed" % self.host.temp_name)
dom_filename = "%s.domain_info" % self.host.temp_name
Aln_basic.write_widget_into_file(self.host.parse_tab.fixed.text_widget,
fixed_filename)
obtain_features_path = os.path.join(self.host.settings.script_dir,
"obtain_features.py")
data_for_features = ""
if domain_not_empty:
data_for_features += "-p %s" % os.path.basename(domain_filename)
if not self.TMHMM_results.text_is_empty():
TM_filename = os.path.join(self.host.settings.work_dir,
"%s.TMHMM" % self.host.temp_name)
Aln_basic.write_widget_into_file(self.TMHMM_results.text_widget,
TM_filename)
data_for_features += " -t %s" % os.path.basename(TM_filename)
self.host.set_status("Working")
if self.host.verbose.get():
os.system("%s -i %s -w %s -o %s %s -e %s -f %s -d %s" %
(obtain_features_path, os.path.basename(fixed_filename),
self.host.settings.work_dir,
"%s.features" % self.host.temp_name, data_for_features,
self.evalue_threshold.get(),
self.overlap_threshold.get(), dom_filename))
else:
os.system(
"%s -i %s -w %s -o %s %s -e %s -f %s -d %s 1> nul 2> nul" %
(obtain_features_path, os.path.basename(fixed_filename),
self.host.settings.work_dir,
"%s.features" % self.host.temp_name, data_for_features,
self.evalue_threshold.get(), self.overlap_threshold.get(),
dom_filename))
self.host.set_status("Ready")
Aln_basic.read_widget_from_file(
self.features.text_widget,
os.path.join(self.host.settings.work_dir,
"%s.features" % self.host.temp_name))
dom_filename_full = os.path.join(self.host.settings.work_dir,
dom_filename)
if os.path.isfile(
dom_filename_full): # File was created (non-empty domains)
domain_dict = Aln_basic.read_domain_info_file(dom_filename_full)
self.host.load_domain_info(
domain_dict) # Loading domain info into the info tab
print(" [..DONE..]")
def check_input(self):
print (" Checking input alignment...")
if self.aln_input_frame.text_is_empty(): # No alignment is provided
self.host.set_status("No alignment is provided!", "#FF0000")
else:
aligned_filename = os.path.join(self.host.settings.work_dir, "%s.aln" % self.host.temp_name)
Aln_basic.write_widget_into_file(self.aln_input_frame.text_widget, aligned_filename)
import udav_base
try:
seq_list = udav_base.read_alignment(aligned_filename)
if type(seq_list) == type(""): # This means that at least one sequence in alignment differs in length from other
self.host.set_status(seq_list, "#FF0000")
else:
status_OK = True
id_to_name = dict()
for s in seq_list:
s.remove_limits(False, False)
if s.ID in id_to_name: # Identical protein IDs detected
status_OK = False
print (" [..WARNING..] Identical protein ID detected: '%s'" % s.ID)
id_to_name[s.ID] = s.name
my_format = re.match("^[^\|]+\|[^\|]+\|[^\|]+$", s.name)
my_format_simple = re.match("^[^\|]+\|[^\|]+$", s.name)
if not (my_format or my_format_simple) and not ((s.name == "BLOCKS") or (s.name == "SITE")):
status_OK = False
print (" [..WARNING..] This name can fail a purification step. Consider 'My' format instead")
print (" Current name: '%s'" % s.name)
print (" 'My' format example: 'ID|smth|organism' or 'ID|organism'")
if status_OK:
self.host.set_status("OK")
else:
self.host.set_status("Alignment has problems with names format, check console for details", "#888800")
except IndexError:
self.host.set_status("Alignment is corrupted; check that it is in FASTA format!", "#888800")
del udav_base
os.remove(aligned_filename)
print (" [..DONE..]")
def save_sequence_sample(self):
sequence_filename = os.path.join(self.host.settings.work_dir, self.host.get_project_name(), "%s.sample" % self.host.get_project_name())
Aln_basic.write_widget_into_file(self.seq_input_frame.text_widget, sequence_filename, False)
def save_alignment(self):
aligned_filename = os.path.join(self.host.settings.work_dir, self.host.get_project_name(), "%s.aln" % self.host.get_project_name())
Aln_basic.write_widget_into_file(self.aln_input_frame.text_widget, aligned_filename, False)
def save_pure(self, ask_filename = True):
pure_filename = os.path.join(self.host.settings.work_dir, self.host.get_project_name(), "%s.pure" % self.host.get_project_name())
if ask_filename:
pure_filename = tkFileDialog.asksaveasfilename(filetypes = (("Non-aligned sequences with pure names (fasta)", "*.pure"), ("All", "*.*")))
Aln_basic.write_widget_into_file(self.pure.text_widget, pure_filename, ask_filename)
def parse(self):
aligned_filename = os.path.join(self.settings.work_dir,
"%s.aln" % self.temp_name)
Aln_basic.write_widget_into_file(
self.input_tab.aln_input_frame.text_widget, aligned_filename)
remove_seq_limits_path = os.path.join(self.settings.script_dir,
"remove_seq_limits.py")
self.set_status("Working")
if self.verbose.get():
os.system("%s -i %s -w %s -o %s -d -x" %
(remove_seq_limits_path, "%s.aln" % self.temp_name,
self.settings.work_dir, self.temp_name))
else:
os.system("%s -i %s -w %s -o %s -d -x 1> nul 2> nul" %
(remove_seq_limits_path, "%s.aln" % self.temp_name,
self.settings.work_dir, self.temp_name))
self.set_status("Ready")
try:
os.remove(
os.path.join(self.settings.work_dir,
"%s.aln" % self.temp_name))
os.remove(
os.path.join(self.settings.work_dir,
"%s.blocks" % self.temp_name))
os.remove(
os.path.join(self.settings.work_dir,
"%s.motif" % self.temp_name))
os.remove(
os.path.join(self.settings.work_dir,
"%s.motif_var" % self.temp_name))
os.remove(
os.path.join(self.settings.work_dir,
"%s.orgs" % self.temp_name))
os.remove(
os.path.join(self.settings.work_dir,
"%s.pure.correspond" % self.temp_name))
except OSError:
pass
fixed_filename = os.path.join(self.settings.work_dir,
"%s.fixed" % self.temp_name)
Aln_basic.read_widget_from_file(self.parse_tab.fixed.text_widget,
fixed_filename)
os.remove(fixed_filename)
pure_filename = os.path.join(self.settings.work_dir,
"%s.pure" % self.temp_name)
Aln_basic.read_widget_from_file(self.parse_tab.pure.text_widget,
pure_filename)
self.parse_tab.enable_pure_analysis()
os.remove(pure_filename)
blocks_filename = os.path.join(self.settings.work_dir,
"%s.blocks_regions" % self.temp_name)
if os.path.isfile(blocks_filename):
Aln_basic.read_widget_from_file(self.parse_tab.blocks.text_widget,
blocks_filename)
os.remove(blocks_filename)
ids_filename = os.path.join(self.settings.work_dir,
"%s.ids" % self.temp_name)
Aln_basic.read_widget_from_file(self.parse_tab.IDs.text_widget,
ids_filename)
os.remove(ids_filename)
self.parse_tab.check_numbers()
def save_logs(self, ask_if_exists = True):
auto_filename = os.path.join(self.host.settings.work_dir, self.host.get_project_name(), "%s.auto_log" % self.host.get_project_name())
Aln_basic.write_widget_into_file(self.auto_log.text_widget, auto_filename, ask_if_exists, True)
man_filename = os.path.join(self.host.settings.work_dir, self.host.get_project_name(), "%s.man_log" % self.host.get_project_name())
Aln_basic.write_widget_into_file(self.manual_log.text_widget, man_filename, ask_if_exists, True)