def load_gene_list(self,
file_name,
filter_havana=True,
protein_coding=False,
known_only=False):
"""Reads gene annotation in gtf (gencode) format. It populates self.gene_list with such entries.
*Keyword arguments:*
- file_name -- The gencode .gtf file name.
"""
# Opening GTF file
try:
gtf_file = open(file_name, "r")
except Exception:
print("Error: Cannot find the annotation file: " + file_name)
print("Please check the path in ~/rgtdata/data.config")
sys.exit(1)
# Reading GTF file
for line in gtf_file:
# Processing line
line = line.strip()
if line[0] == "#": continue
line_list = line.split("\t")
try:
if filter_havana and line_list[1] == "HAVANA": continue
except:
pass
addt_list = line_list[8].split(";")
addt_list = [_f for _f in addt_list if _f]
# Processing additional list of options
addt_dict = dict()
for addt_element in addt_list:
addt_element_list = addt_element.split(" ")
addt_element_list = [_f for _f in addt_element_list if _f]
# Removing " symbol from string options
addt_element_list[1] = addt_element_list[1].replace("\"", "")
addt_dict[addt_element_list[0]] = addt_element_list[1]
# filter non-protein-coding sequences, if required
if protein_coding:
if "gene_type" not in addt_dict or addt_dict[
"gene_type"] != "protein_coding":
continue
if "transcript_type" in addt_dict and addt_dict[
"transcript_type"] != "protein_coding":
continue
# filter unknown sequences, if required
if known_only:
if "gene_status" not in addt_dict or addt_dict[
"gene_status"] != "KNOWN":
continue
if "transcript_status" in addt_dict and addt_dict[
"transcript_status"] != "KNOWN":
continue
# Removing dot from IDs
addt_dict["gene_id"] = addt_dict["gene_id"].split(".")[0]
try:
addt_dict["transcript_id"] = addt_dict["transcript_id"].split(
".")[0]
except:
pass
# Creating final version of additional arguments
final_addt_list = []
for addt_key in [
"gene_id", "transcript_id", "gene_type", "gene_status",
"gene_name", "transcript_type", "transcript_status",
"transcript_name", "level"
]:
try:
final_addt_list.append(addt_dict[addt_key])
except Exception:
final_addt_list.append(None)
# Handling score
current_score = 0
if AuxiliaryFunctions.string_is_int(line_list[5]):
current_score = AuxiliaryFunctions.correct_standard_bed_score(
line_list[5])
# Creating GenomicRegion
genomic_region = GenomicRegion(chrom=line_list[0],
initial=int(line_list[3]) - 1,
final=int(line_list[4]),
orientation=line_list[6],
data=current_score)
# Creating final vector
extra_index_elements = [
[], []
] # One list for each: EXACT_GENE_MATCHES, INEXACT_GENE_MATCHES
final_vector = [
genomic_region, line_list[1], line_list[2], line_list[7]
] + final_addt_list + extra_index_elements
self.gene_list.append(final_vector)
# Termination
gtf_file.close()
def load_gene_list(self, file_name, filter_havana=True):
"""
Reads gene annotation in gtf (gencode) format. It populates self.gene_list with such entries.
Keyword arguments:
file_name -- The gencode .gtf file name.
Return: void.
"""
# Opening GTF file
try:
gtf_file = open(file_name, "r")
except Exception:
pass # TODO
# Reading GTF file
for line in gtf_file:
# Processing line
line = line.strip()
if (line[0] == "#"): continue
line_list = line.split("\t")
if (filter_havana and line_list[1] == "HAVANA"): continue
addt_list = line_list[8].split(";")
addt_list = filter(None, addt_list)
# Processing additional list of options
addt_dict = dict()
for addt_element in addt_list:
addt_element_list = addt_element.split(" ")
addt_element_list = filter(None, addt_element_list)
addt_element_list[1] = addt_element_list[1].replace(
"\"", "") # Removing " symbol from string options
addt_dict[addt_element_list[0]] = addt_element_list[1]
# Removing dot from IDs
addt_dict["gene_id"] = addt_dict["gene_id"].split(".")[0]
addt_dict["transcript_id"] = addt_dict["transcript_id"].split(
".")[0]
# Creating final version of additional arguments
final_addt_list = []
for addt_key in [
"gene_id", "transcript_id", "gene_type", "gene_status",
"gene_name", "transcript_type", "transcript_status",
"transcript_name", "level"
]:
try:
final_addt_list.append(addt_dict[addt_key])
except Exception:
final_addt_list.append(None)
# Handling score
current_score = 0
if (AuxiliaryFunctions.string_is_int(line_list[5])):
current_score = AuxiliaryFunctions.correct_standard_bed_score(
line_list[5])
# Creating GenomicRegion
genomic_region = GenomicRegion(chrom=line_list[0],
initial=int(line_list[3]) - 1,
final=int(line_list[4]),
orientation=line_list[6],
data=current_score)
# Creating final vector
extra_index_elements = [
[], []
] # One list for each: EXACT_GENE_MATCHES, INEXACT_GENE_MATCHES
final_vector = [
genomic_region, line_list[1], line_list[2], line_list[7]
] + final_addt_list + extra_index_elements
self.gene_list.append(final_vector)
# Termination
gtf_file.close()
def load_gene_list(self, file_name, filter_havana=True, protein_coding=False, known_only=False):
"""Reads gene annotation in gtf (gencode) format. It populates self.gene_list with such entries.
*Keyword arguments:*
- file_name -- The gencode .gtf file name.
"""
# Opening GTF file
try: gtf_file = open(file_name, "r")
except Exception:
print("Error: Cannot find the annotation file: "+file_name)
print("Please check the path in ~/rgtdata/data.config")
sys.exit(1)
# Reading GTF file
for line in gtf_file:
# Processing line
line = line.strip()
if line[0] == "#": continue
line_list = line.split("\t")
try:
if filter_havana and line_list[1] == "HAVANA": continue
except: pass
addt_list = line_list[8].split(";")
addt_list = filter(None, addt_list)
# Processing additional list of options
addt_dict = dict()
for addt_element in addt_list:
addt_element_list = addt_element.split(" ")
addt_element_list = filter(None, addt_element_list)
# Removing " symbol from string options
addt_element_list[1] = addt_element_list[1].replace("\"", "")
addt_dict[addt_element_list[0]] = addt_element_list[1]
# filter non-protein-coding sequences, if required
if protein_coding:
if "gene_type" not in addt_dict or addt_dict["gene_type"] != "protein_coding":
continue
if "transcript_type" in addt_dict and addt_dict["transcript_type"] != "protein_coding":
continue
# filter unknown sequences, if required
if known_only:
if "gene_status" not in addt_dict or addt_dict["gene_status"] != "KNOWN":
continue
if "transcript_status" in addt_dict and addt_dict["transcript_status"] != "KNOWN":
continue
# Removing dot from IDs
addt_dict["gene_id"] = addt_dict["gene_id"].split(".")[0]
try: addt_dict["transcript_id"] = addt_dict["transcript_id"].split(".")[0]
except: pass
# Creating final version of additional arguments
final_addt_list = []
for addt_key in ["gene_id", "transcript_id", "gene_type", "gene_status", "gene_name",
"transcript_type", "transcript_status", "transcript_name", "level"]:
try:
final_addt_list.append(addt_dict[addt_key])
except Exception:
final_addt_list.append(None)
# Handling score
current_score = 0
if AuxiliaryFunctions.string_is_int(line_list[5]):
current_score = AuxiliaryFunctions.correct_standard_bed_score(line_list[5])
# Creating GenomicRegion
genomic_region = GenomicRegion(chrom=line_list[0],
initial=int(line_list[3])-1,
final=int(line_list[4]),
orientation=line_list[6],
data=current_score)
# Creating final vector
extra_index_elements = [[],[]] # One list for each: EXACT_GENE_MATCHES, INEXACT_GENE_MATCHES
final_vector = [genomic_region,line_list[1],line_list[2],line_list[7]] + final_addt_list + extra_index_elements
self.gene_list.append(final_vector)
# Termination
gtf_file.close()
def load_gene_list(self, file_name, filter_havana=True, protein_coding=False, known_only=False):
"""
Reads gene annotation in gtf (gencode) format. It populates self.gene_list with such entries.
Keyword arguments:
file_name -- The gencode .gtf file name.
Return: void.
"""
# Opening GTF file
try: gtf_file = open(file_name,"r")
except Exception: pass # TODO
# Reading GTF file
for line in gtf_file:
# Processing line
line = line.strip()
if(line[0] == "#"): continue
line_list = line.split("\t")
if(filter_havana and line_list[1] == "HAVANA"): continue
addt_list = line_list[8].split(";")
if(protein_coding and "protein_coding" not in addt_list[2] ): continue
if(known_only and "KNOWN" not in addt_list[3] ): continue
if(protein_coding and "protein_coding" not in addt_list[5] ): continue
if(known_only and "KNOWN" not in addt_list[6] ): continue
addt_list = filter(None,addt_list)
# Processing additional list of options
addt_dict = dict()
for addt_element in addt_list:
addt_element_list = addt_element.split(" ")
addt_element_list = filter(None,addt_element_list)
addt_element_list[1] = addt_element_list[1].replace("\"","") # Removing " symbol from string options
addt_dict[addt_element_list[0]] = addt_element_list[1]
# Removing dot from IDs
addt_dict["gene_id"] = addt_dict["gene_id"].split(".")[0]
addt_dict["transcript_id"] = addt_dict["transcript_id"].split(".")[0]
# Creating final version of additional arguments
final_addt_list = []
for addt_key in ["gene_id", "transcript_id", "gene_type", "gene_status", "gene_name",
"transcript_type", "transcript_status", "transcript_name", "level"]:
try: final_addt_list.append(addt_dict[addt_key])
except Exception: final_addt_list.append(None)
# Handling score
current_score = 0
if(AuxiliaryFunctions.string_is_int(line_list[5])):
current_score = AuxiliaryFunctions.correct_standard_bed_score(line_list[5])
# Creating GenomicRegion
genomic_region = GenomicRegion(chrom = line_list[0],
initial = int(line_list[3])-1,
final = int(line_list[4]),
orientation = line_list[6],
data = current_score)
# Creating final vector
extra_index_elements = [[],[]] # One list for each: EXACT_GENE_MATCHES, INEXACT_GENE_MATCHES
final_vector = [genomic_region,line_list[1],line_list[2],line_list[7]] + final_addt_list + extra_index_elements
self.gene_list.append(final_vector)
# Termination
gtf_file.close()
