def read_insertions(telocate_out, sample_name, chromosomes, rp_threshold=0):
insertions = []
with open(telocate_out,"r") as raw:
for x, line in enumerate(raw):
if x > 1:
insert = output.Insertion(output.Telocate())
split_line = line.split("\t")
insert.chromosome = split_line[0]
insert.start = int(split_line[1])
te_name = split_line[3].split("/")[1]
insert.family = te_name
if "old" in split_line[15]:
insert.type = "reference"
insert.end = insert.start+int(split_line[2])
insert.name = te_name+"|reference|NA|"+sample_name+"|telocate|rp|"
else:
insert.type = "non-reference"
insert.end = insert.start
insert.name = te_name+"|non-reference|NA|"+sample_name+"|telocate|rp|"
if split_line[12] == "parallel":
insert.strand = "+"
elif split_line[12] == "uncertain":
insert.strand = "."
else:
insert.strand = "-"
insert.support_info.support['read_pair_support'].value = int(split_line[6])
if insert.support_info.support['read_pair_support'].value >= rp_threshold and insert.chromosome in chromosomes:
insertions.append(insert)
return insertions
def get_ref_tes(gff, taxon, chroms):
ref_inserts = []
te_family = {}
with open(taxon, "r") as t:
for line in t:
split_line = line.split("\t")
te_id = split_line[0]
family = split_line[1]
te_family[te_id] = family
with open(gff, "r") as g:
for line in g:
if "#" not in line:
split_line = line.split("\t")
insert = output.Insertion(output.Popoolationte2())
insert.type = "reference"
insert.chromosome = split_line[0]
insert.start = int(split_line[3])
insert.end = int(split_line[4])
insert.strand = split_line[6]
insert.family = te_family[split_line[2]]
if insert.chromosome in chroms:
ref_inserts.append(insert)
return ref_inserts
def read_insertions(bed,
te_to_family,
sample_name,
te_pos_to_family,
chromosomes,
reference=False):
inserts = []
with open(bed, "r") as b:
for line in b:
insert = output.Insertion(output.Tepid())
split_line = line.split("\t")
insert.chromosome = split_line[0]
if insert.chromosome in chromosomes:
insert.start = int(split_line[1])
insert.end = int(split_line[2])
if reference:
te_name = split_line[4].split(",")[0]
insert.family = te_to_family[te_name]
insert.strand = split_line[3]
insert.type = "reference"
insert.name = insert.family + "|reference|NA|" + sample_name + "|tepid|nonab|"
else:
te_chrom = split_line[3]
te_start = split_line[4]
te_end = split_line[5]
insert.family = te_pos_to_family[te_chrom + "_" +
te_start + "_" + te_end]
insert.type = "non-reference"
insert.name = insert.family + "|non-reference|NA|" + sample_name + "|tepid|sr|"
insert.support_info.id = split_line[-1].replace("\n", "")
inserts.append(insert)
return inserts
def get_non_absent_ref_tes(te_gff, absence_bed, sample, out, log):
insertions = []
tmp_gff = out + "/tmp.ref_nonabs.gff"
command = ["bedtools", "subtract", "-A", "-a", te_gff, "-b", absence_bed]
mccutils.run_command_stdout(command, tmp_gff, log=log)
with open(tmp_gff, "r") as gff:
for line in gff:
if "#" not in line:
line = line.replace(";", "\t")
split_line = line.split("\t")
insert = output.Insertion(output.Temp())
insert.chromosome = split_line[0]
insert.start = int(split_line[3])
insert.end = int(split_line[4])
insert.name = split_line[9].split(
"=")[1] + "|reference|NA|" + sample + "|temp|nonab|"
insert.strand = split_line[6]
insert.type = "reference"
insertions.append(insert)
mccutils.remove(tmp_gff)
return insertions
def read_insertions(insert_bed, sample_name, chromosomes, config):
insertions = []
with open(insert_bed, "r") as inf:
for x, line in enumerate(inf):
if x > 0:
insert = output.Insertion(output.Temp2())
split_line = line.split("\t")
if len(split_line) == 15:
insert.chromosome = split_line[0]
insert.start = int(split_line[1]) + 1
insert.end = int(split_line[2])
insert.family = split_line[3].split(":")[0]
insert.type = "non-reference"
insert.support_info.support["frequency"].value = float(
split_line[4])
insert.strand = split_line[5]
insert.support_info.support["class"].value = split_line[6]
insert.support_info.support["supportreads"].value = float(
split_line[7])
insert.support_info.support[
"referencereads"].value = float(split_line[8])
insert.support_info.support[
"fiveprimesupport"].value = float(split_line[9])
insert.support_info.support[
"threeprimesupport"].value = float(split_line[10])
insert.support_info.support["reliability"].value = float(
split_line[12].replace(
"%",
"")) # rare enties have a % sign for some reason
insert.support_info.support[
"fiveprimejunctionsupport"].value = float(
split_line[13])
insert.support_info.support[
"threeprimejunctionsupport"].value = float(
split_line[14])
insert.name = insert.family + "|non-reference|" + str(
insert.support_info.support['frequency'].value
) + "|" + sample_name + "|temp2|"
if insert.support_info.support[
"fiveprimejunctionsupport"].value > 0 and insert.support_info.support[
"threeprimejunctionsupport"].value > 0:
insert.name += "sr|"
else:
insert.name += "rp|"
if (insert.chromosome in chromosomes
and insert.support_info.support["frequency"].value
>= config.PARAMS["frequency_threshold"]
and insert.support_info.support["class"].value
in config.
PARAMS["acceptable_insertion_support_classes"]):
insertions.append(insert)
return insertions
def read_insertions(tebreak_out, sample_name, chromosomes, config):
insertions = []
header = {}
with open(tebreak_out, "r") as inf:
for ln,line in enumerate(inf):
line = line.replace("\n","")
split_line = line.split("\t")
if ln == 0:
for x,val in enumerate(split_line):
header[val] = x
else:
insert = output.Insertion(output.Tebreak())
insert.chromosome = split_line[header['Chromosome']]
insert.start = int(split_line[header['3_Prime_End']])+1
insert.end = int(split_line[header['5_Prime_End']])
insert.family = split_line[header['Superfamily']]
insert.type = "non-reference"
if split_line[header['Orient_5p']] == split_line[header['Orient_3p']]:
insert.strand = split_line[header['Orient_5p']]
else:
insert.strand = "."
if insert.strand == "-":
tmp = insert.start
insert.start = insert.end
insert.end = tmp
insert.support_info.support["five_p_elt_match"].value = float(split_line[header['5p_Elt_Match']])
insert.support_info.support["three_p_elt_match"].value = float(split_line[header['3p_Elt_Match']])
insert.support_info.support["five_p_genome_match"].value = float(split_line[header['5p_Genome_Match']])
insert.support_info.support["three_p_genome_match"].value = float(split_line[header['3p_Genome_Match']])
insert.support_info.support["split_reads_5prime"].value = float(split_line[header['Split_reads_5prime']])
insert.support_info.support["split_reads_3prime"].value = float(split_line[header['Split_reads_3prime']])
insert.support_info.support["remapped_discordant"].value = float(split_line[header['Remapped_Discordant']])
insert.support_info.support["remap_disc_fraction"].value = float(split_line[header['Remap_Disc_Fraction']])
insert.support_info.support["remapped_splitreads"].value = float(split_line[header['Remapped_Splitreads']])
insert.support_info.support["remap_split_fraction"].value = float(split_line[header['Remap_Split_Fraction']])
insert.name = insert.family+"|non-reference|NA|"+sample_name+"|tebreak|sr|"
if (
insert.chromosome in chromosomes and
insert.support_info.support["five_p_elt_match"].value >= config.MIN_5P_ELT_MATCH and
insert.support_info.support["three_p_elt_match"].value >= config.MIN_3P_ELT_MATCH and
insert.support_info.support["five_p_genome_match"].value >= config.MIN_5P_GENOME_MATCH and
insert.support_info.support["three_p_genome_match"].value >= config.MIN_3P_GENOME_MATCH and
insert.support_info.support["split_reads_5prime"].value >= config.MIN_SPLIT_READS_5P and
insert.support_info.support["split_reads_3prime"].value >= config.MIN_SPLIT_READS_3P and
insert.support_info.support["remapped_discordant"].value >= config.MIN_REMAPPED_DISCORDANT and
insert.support_info.support["remap_disc_fraction"].value >= config.MIN_REMAP_DISC_FRACTION and
insert.support_info.support["remapped_splitreads"].value >= config.MIN_REMAPPED_SPLITREADS and
insert.support_info.support["remap_split_fraction"].value >= config.MIN_REMAP_SPLIT_FRACTION
):
insertions.append(insert)
return insertions
def read_insertions(predictions,
ref_tes,
chroms,
sample,
both_end_support_needed=True,
support_threshold=0.1):
insertions = []
with open(predictions, "r") as tsv:
for line in tsv:
split_line = line.split("\t")
insert = output.Insertion(output.Popoolationte2())
insert.chromosome = split_line[1]
insert.start = int(split_line[2])
insert.end = int(split_line[2])
insert.strand = split_line[3]
insert.family = split_line[4]
insert.support_info.support['flanks_supported'].value = split_line[
6]
insert.support_info.support['frequency'].value = float(
split_line[8])
if (insert.support_info.support['flanks_supported'].value == "FR"
or not both_end_support_needed
) and insert.support_info.support[
'frequency'].value > support_threshold:
# determine if insert is a ref insert
for x in range(0, len(ref_tes)):
if ref_tes[
x].start <= insert.start and insert.start <= ref_tes[
x].end:
insert.family = ref_tes[x].family
insert.support_info.added = ref_tes[
x].support_info.added
if not ref_tes[x].support_info.added:
ref_tes[x].support_info.added = True
insert.type = "reference"
insert.start = ref_tes[x].start
insert.end = ref_tes[x].end
insert.strand = ref_tes[x].strand
if insert.type == "reference":
insert.name = insert.family + "|reference|" + str(
insert.support_info.support['frequency'].value
) + "|" + sample + "|popoolationte2|rp|"
else:
insert.type = "non-reference"
insert.name = insert.family + "|non-reference|" + str(
insert.support_info.support['frequency'].value
) + "|" + sample + "|popoolationte2|rp|"
if not insert.support_info.added:
insertions.append(insert)
return insertions
def read_insertions(ref_bed, nonref_bed, chromosomes, sample_name, out_dir):
insertions = []
with open(ref_bed, "r") as inbed:
for line in inbed:
line = line.replace("\n", "")
insert = output.Insertion(output.Ngs_te_mapper2())
split_line = line.split("\t")
insert.chromosome = split_line[0]
insert.start = int(split_line[1]) + 1
insert.end = int(split_line[2])
insert.type = "reference"
insert.strand = split_line[5]
insert.family = split_line[3]
insert.name = insert.family + "|" + insert.type + "|NA|" + sample_name + "|ngs_te_mapper2|sr|"
if insert.chromosome in chromosomes:
insertions.append(insert)
with open(nonref_bed, "r") as inbed:
for line in inbed:
line = line.replace("\n", "")
insert = output.Insertion(output.Ngs_te_mapper2())
split_line = line.split("\t")
insert.chromosome = split_line[0]
insert.start = int(split_line[1]) + 1
insert.end = int(split_line[2])
insert.type = "non-reference"
insert.strand = split_line[5]
insert.family = split_line[3].split("|")[0]
insert.support_info.support['frequency'].value = float(
split_line[3].split("|")[2])
insert.support_info.support['three_prime_support'].value = int(
split_line[3].split("|")[3])
insert.support_info.support['five_prime_support'].value = int(
split_line[3].split("|")[4])
insert.support_info.support['reference_reads'].value = int(
split_line[3].split("|")[5])
insert.name = insert.family + "|" + insert.type + "|" + str(
insert.support_info.support['frequency'].value
) + "|" + sample_name + "|ngs_te_mapper2|sr|"
if insert.chromosome in chromosomes:
insertions.append(insert)
return insertions
def get_insertions(gff, sample_name, chromosomes, ref_l_threshold=0, ref_r_threshold=0, nonref_l_threshold=0, nonref_r_threshold=0):
insertions = []
with open(gff, "r") as ingff:
for line in ingff:
if "#" not in line:
split_line = line.split("\t")
feats = split_line[8].split(";")
insert = output.Insertion(output.Relocate())
insert.chromosome = split_line[0]
insert.start = int(split_line[3])
insert.end = int(split_line[4])
insert.strand = split_line[6]
feat_id = ""
feat_te_name = ""
for feat in feats:
if "ID=" in feat:
feat_id = feat.split("=")[1]
elif "TE_Name=" in feat:
feat_te_name = feat.split("=")[1]
elif "Note=" in feat:
if "Shared" in feat:
insert.type = "reference"
elif "Non-reference" in feat:
insert.type = "non-reference"
else:
insert.type = "missing"
elif "left_flanking_read_count=" in feat:
insert.support_info.support['left_flanking_reads'].value = int(feat.split("=")[1])
elif "right_flanking_read_count=" in feat:
insert.support_info.support['right_flanking_reads'].value = int(feat.split("=")[1])
if insert.type == "reference":
insert.family = feat_te_name
insert.name = feat_te_name+"|reference|NA|"+sample_name+"|relocate|sr|"
elif insert.type == "non-reference":
feat_te_name = feat_id.split(".")[0]
insert.family = feat_te_name
insert.name = feat_te_name+"|non-reference|NA|"+sample_name+"|relocate|sr|"
if insert.type == "reference" and insert.support_info.support['left_flanking_reads'].value >= ref_l_threshold and insert.support_info.support['right_flanking_reads'].value >= ref_r_threshold and insert.chromosome in chromosomes:
insertions.append(insert)
elif insert.type == "non-reference" and insert.support_info.support['left_flanking_reads'].value >= nonref_l_threshold and insert.support_info.support['right_flanking_reads'].value >= nonref_r_threshold and insert.chromosome in chromosomes:
insertions.append(insert)
return insertions
def read_insertions(retroseq_vcf,
sample_name,
chromosomes,
support_threshold=0,
breakpoint_threshold=6):
insertions = []
with open(retroseq_vcf, "r") as vcf:
for line in vcf:
if "#" not in line:
insert = output.Insertion(output.Retroseq())
line = line.replace("\n", "")
split_line = line.split("\t")
insert.chromosome = split_line[0]
info = {}
split_info = split_line[7].split(";")
for i in split_info:
if "=" in i:
info[i.split("=")[0]] = i.split("=")[1]
insert.family = (info['MEINFO'].split(",")[0]).split("-")[0]
insert.start = int(info['MEINFO'].split(",")[1])
insert.end = int(info['MEINFO'].split(",")[2])
format_keys = split_line[8].split(":")
format_vals = split_line[9].split(":")
form = {}
for x, key in enumerate(format_keys):
form[key] = format_vals[x]
insert.support_info.support['read_pair_support'].value = int(
form['SP'])
insert.support_info.support['clip3'].value = int(form['CLIP3'])
insert.support_info.support['clip5'].value = int(form['CLIP5'])
insert.support_info.support['call_status'].value = int(
form['FL'])
insert.type = "non-reference"
insert.name = insert.family + "|non-reference|NA|" + sample_name + "|retroseq|rp|"
if insert.support_info.support[
'read_pair_support'].value >= support_threshold and insert.support_info.support[
'call_status'].value >= breakpoint_threshold and insert.chromosome in chromosomes:
insertions.append(insert)
return insertions
def get_non_absent_ref_tes(deletions, te_gff, te_to_family, sample_name):
ref_tes = []
with open(te_gff, "r") as gff:
for line in gff:
ref_te = output.Insertion(output.Tepid())
split_line = line.split("\t")
ref_te.chromosome = split_line[0]
ref_te.start = int(split_line[3])
ref_te.end = int(split_line[4])
ref_te.strand = split_line[6]
feats = split_line[8]
split_feats = feats.split(";")
te_id = ""
for f in split_feats:
if "ID=" in f:
te_id = f.split("=")[1]
ref_te.family = te_to_family[te_id]
ref_te.type = "reference"
ref_te.name = ref_te.family + "|reference|NA|" + sample_name + "|tepid|nonab|"
ref_tes.append(ref_te)
absent = []
for deletion in deletions:
key = "_".join([
deletion.chromosome,
str(deletion.start),
str(deletion.end), deletion.strand, deletion.family
])
absent.append(key)
non_absent = []
for te in ref_tes:
key = "_".join(
[te.chromosome,
str(te.start),
str(te.end), te.strand, te.family])
if key not in absent:
non_absent.append(te)
return non_absent
def read_insertions(bed, chromosomes, sample_name, out_dir, min_read_cutoff=0):
insertions = []
with open(bed, "r") as inbed:
for line in inbed:
insert = output.Insertion(output.Ngs_te_mapper())
line = line.replace(";", "\t")
split_line = line.split("\t")
insert.chromosome = split_line[0]
insert.start = int(split_line[1]) + 1
insert.end = int(split_line[2])
insert.type = split_line[8].replace("\n", "")
insert.strand = split_line[4]
insert.family = split_line[5]
insert.name = insert.family + "|" + insert.type + "|NA|" + sample_name + "|ngs_te_mapper|sr|"
insert.support_info.support['supportingreads'].value = int(
split_line[7])
if insert.support_info.support[
'supportingreads'].value > min_read_cutoff and insert.chromosome in chromosomes:
insertions.append(insert)
return insertions
def get_insertions(gff,
sample_name,
chromosomes,
l_support_threshold=0,
r_support_threshold=0,
l_junction_threshold=0,
r_junction_threshold=0,
insert_type="ref"):
insertions = []
with open(gff, "r") as ingff:
for line in ingff:
if "#" not in line:
line = line.replace(";", "\t")
split_line = line.split("\t")
insert = output.Insertion(output.Relocate2())
insert.chromosome = split_line[0]
insert.start = int(split_line[3])
insert.end = int(split_line[4])
insert.strand = split_line[6]
insert.type = insert_type
insert.name = split_line[8].split("=")[1]
te_name = ""
if insert_type == "ref":
insert.type = "reference"
insert.support_info.support[
'right_junction_reads'].value = int(
split_line[11].split(":")[1])
insert.support_info.support[
'left_junction_reads'].value = int(
split_line[12].split(":")[1])
insert.support_info.support[
'right_support_reads'].value = int(
split_line[13].split(":")[1])
insert.support_info.support[
'left_support_reads'].value = int(
split_line[14].split(":")[1])
else:
insert.type = "non-reference"
te_name = split_line[9].split("=")[1]
te_name = te_name.split("/")[0]
insert.family = te_name
insert.name = te_name + "|non-reference|NA|" + sample_name + "|relocate2|sr|"
insert.support_info.support[
'right_junction_reads'].value = int(
split_line[12].split("=")[1])
insert.support_info.support[
'left_junction_reads'].value = int(
split_line[13].split("=")[1])
insert.support_info.support[
'right_support_reads'].value = int(
split_line[14].split("=")[1])
insert.support_info.support[
'left_support_reads'].value = int(
split_line[15].split("=")[1])
if (insert.support_info.support['right_junction_reads'].value
>= r_junction_threshold
and insert.support_info.support['left_junction_reads'].
value >= l_junction_threshold
and insert.support_info.support['right_support_reads'].
value >= r_support_threshold and
insert.support_info.support['left_support_reads'].value
>= l_support_threshold
and insert.chromosome in chromosomes
and te_name != "repeat_name"):
insertions.append(insert)
return insertions
def read_insertions(predictions,
chroms,
sample,
ref_tes,
min_presence=3,
max_absence=None,
min_presence_fraction=0.1,
require_tsd=False,
require_both_breakpoints=False):
insertions = []
with open(predictions, "r") as tsv:
for line in tsv:
split_line = line.split("\t")
insert = output.Insertion(output.Teflon())
insert.chromosome = split_line[0]
both_ends = False
tsd = False
if insert.chromosome in chroms:
if split_line[1] != "-" and split_line[2] != "-":
left = int(split_line[1])
right = int(split_line[2])
both_ends = True
elif split_line[1] == "-":
left = int(split_line[2])
right = int(split_line[2])
else:
left = int(split_line[1])
right = int(split_line[1])
if left > right:
tsd = True
tmp = right
right = left
left = tmp
elif left == right:
tsd = True
right += 1
insert.start = left - 1
insert.end = right
insert.family = split_line[3]
insert.strand = split_line[5]
# if reference prediction, uses ref TE coordinates
if split_line[6] != "-":
tsd = True
both_ends = True
insert.type = "reference"
te_names = split_line[6].split(",")
te_name = ""
for name in te_names:
if name in ref_tes.keys():
if te_name == "":
te_name = name
if te_name == "":
sys.exit("TEFLON ERROR: can't find:" + split_line[6] +
" in reference TEs...\n")
insert.chromosome = ref_tes[te_name][0]
insert.start = ref_tes[te_name][1]
insert.end = ref_tes[te_name][2]
else:
insert.type = "non-reference"
insert.support_info.support[
'five_prime_supported'].value = split_line[7]
insert.support_info.support[
'three_prime_supported'].value = split_line[7]
insert.support_info.support['presence_reads'].value = int(
split_line[9])
insert.support_info.support['absence_reads'].value = int(
split_line[10])
insert.support_info.support['ambiguous_reads'].value = int(
split_line[11])
insert.support_info.support['frequency'].value = float(
split_line[12])
insert.name = insert.family + "|" + insert.type + "|" + str(
insert.support_info.support['frequency'].value
) + "|" + sample + "|teflon|rp|"
if ((insert.support_info.support['presence_reads'].value >=
min_presence) and
(max_absence is None
or insert.support_info.support['absence_reads'].value <=
max_absence)
and (insert.support_info.support['frequency'].value >=
min_presence_fraction)
and ((tsd or not require_tsd) and
(both_ends or not require_both_breakpoints))):
insertions.append(insert)
return insertions
def read_insertions(popoolationte,
sample_name,
chromosomes,
require_both_end_support=True,
percent_read_support_threshold=0.1):
insertions = []
with open(popoolationte, "r") as tsv:
for line in tsv:
insert = output.Insertion(output.Popoolationte())
split_line = line.split("\t")
insert.chromosome = split_line[0]
pos_in_reference_seq = to_number(split_line[1])
insert.support_info.support["flanks_supported"].value = split_line[
2]
insert.family = split_line[3]
insert.support_info.support["frequency"].value = to_number(
split_line[4], to_float=True)
ref_te_id = split_line[6]
insert.support_info.support[
"forward_insert_start"].value = to_number(split_line[8])
insert.support_info.support[
"forward_insert_end"].value = to_number(split_line[9])
insert.support_info.support[
"forward_insert_freq"].value = to_number(split_line[10],
to_float=True)
insert.support_info.support[
"forward_insert_cov"].value = to_number(split_line[11])
insert.support_info.support[
"forward_presence_reads"].value = to_number(split_line[12])
insert.support_info.support[
"forward_absence_reads"].value = to_number(split_line[13])
insert.support_info.support[
"reverse_insert_start"].value = to_number(split_line[15])
insert.support_info.support[
"reverse_insert_end"].value = to_number(split_line[16])
insert.support_info.support[
"reverse_insert_freq"].value = to_number(split_line[17],
to_float=True)
insert.support_info.support[
"reverse_insert_cov"].value = to_number(split_line[18])
insert.support_info.support[
"reverse_presence_reads"].value = to_number(split_line[19])
insert.support_info.support[
"reverse_absence_reads"].value = to_number(split_line[20])
if insert.support_info.support["forward_insert_start"].value == 0:
insert.start = pos_in_reference_seq
insert.end = insert.support_info.support[
"reverse_insert_start"].value
elif insert.support_info.support[
"reverse_insert_start"].value == 0:
insert.start = insert.support_info.support[
"forward_insert_end"].value
insert.end = pos_in_reference_seq
else:
insert.start = insert.support_info.support[
"forward_insert_end"].value
insert.end = insert.support_info.support[
"reverse_insert_start"].value
if "-" == ref_te_id:
insert.type = "non-reference"
insert.name = insert.family + "|non-reference|" + str(
insert.support_info.support["frequency"].value
) + "|" + sample_name + "|popoolationte|rp|"
else:
insert.type = "reference"
insert.name = insert.family + "|reference|" + str(
insert.support_info.support["frequency"].value
) + "|" + sample_name + "|popoolationte|rp|"
if not require_both_end_support:
if ("FR" in
insert.support_info.support["flanks_supported"].value
and (insert.support_info.support["frequency"].value >=
percent_read_support_threshold)
and insert.chromosome in chromosomes):
insertions.append(insert)
elif ("F"
in insert.support_info.support["flanks_supported"].value
and
(insert.support_info.support["forward_insert_freq"].value
>= percent_read_support_threshold)
and insert.chromosome in chromosomes):
insertions.append(insert)
elif ((insert.support_info.support["reverse_insert_freq"].value
>= percent_read_support_threshold)
and insert.chromosome in chromosomes):
insertions.append(insert)
else:
if ("FR" in
insert.support_info.support["flanks_supported"].value
and
(insert.support_info.support["forward_insert_freq"].value
>= percent_read_support_threshold or
insert.support_info.support["reverse_insert_freq"].value
>= percent_read_support_threshold)
and insert.chromosome in chromosomes):
insertions.append(insert)
return insertions
def read_insertions(jitterbug_gff,
taxonomy,
chroms,
sample_name,
min_fwd_read_support=0,
min_rev_read_support=0,
min_sr_support=0,
min_zygosity=0.0):
insertions = []
te_family = {}
with open(taxonomy, "r") as tsv:
for line in tsv:
line = line.replace("\n", "")
split_line = line.split("\t")
te_family[split_line[0]] = split_line[1]
with open(jitterbug_gff, "r") as gff:
for line in gff:
line = line.replace("\n", "")
split_line = line.split("\t")
if len(split_line) == 9:
# insert = mccutils.Insertion()
insert = output.Insertion(output.Jitterbug())
insert.chromosome = split_line[0]
if insert.chromosome in chroms:
insert.start = int(split_line[3])
insert.end = int(split_line[4])
insert.type = "non-reference"
feats = split_line[8]
feats = feats.replace(" ", "")
feats = feats.split(";")
supporting_families = []
sr = False
family = "NONE"
for feat in feats:
if "softclipped_pos" in feat:
pos = feat.split("=")[1]
pos = pos.replace("(", "")
pos = pos.replace(")", "")
pos = pos.split(",")
start = int(pos[0]) - 1
end = int(pos[1])
if start > -1 and end > -1:
insert.start = start
insert.end = end
sr = True
if "predicted_superfam" in feat:
te = feat.split("=")[1]
family = te_family[te]
insert.family = family
if "supporting_fwd_reads" in feat:
insert.support_info.support[
'supporting_fwd_reads'].value = int(
feat.split("=")[1])
if "supporting_rev_reads" in feat:
insert.support_info.support[
'supporting_rev_reads'].value = int(
feat.split("=")[1])
if "softclipped_support" in feat:
insert.support_info.support[
'softclipped_support'].value = int(
feat.split("=")[1])
if "zygosity" in feat:
insert.support_info.support[
'zygosity'].value = float(feat.split("=")[1])
insert.name = family + "|non-reference|" + str(
insert.support_info.support['zygosity'].value
) + "|" + sample_name + "|jitterbug|"
if sr:
insert.name += "sr|"
else:
insert.name = "rp|"
if ((insert.support_info.support['supporting_fwd_reads'].
value >= min_fwd_read_support) and
(insert.support_info.support['supporting_rev_reads'].
value >= min_rev_read_support) and
(insert.support_info.support['softclipped_support'].
value >= min_sr_support)
and (insert.support_info.support['zygosity'].value
>= min_zygosity)):
insertions.append(insert)
return insertions
def read_insertion_summary(infile, sample):
insertions = []
with open(infile, "r") as inf:
for x, line in enumerate(inf):
if x > 0:
insert = output.Insertion(output.Temp())
split_line = line.split("\t")
if len(split_line) == 14:
insert.chromosome = split_line[0]
insert.start = int(split_line[1]) - 1
insert.end = int(split_line[2])
insert.family = split_line[3]
insert.name = insert.family + "|non-reference|" + split_line[
7] + "|" + sample + "|temp|"
if "antisense" in split_line[4]:
insert.strand = "-"
else:
insert.strand = "+"
insert.support_info.support['class'].value = split_line[5]
insert.support_info.support['variantsupport'].value = int(
float(split_line[6]))
insert.support_info.support['frequency'].value = float(
split_line[7])
insert.support_info.support['junction1'].value = int(
split_line[8])
insert.support_info.support[
'junction1support'].value = int(split_line[9])
insert.support_info.support['junction2'].value = int(
split_line[10])
insert.support_info.support[
'junction2support'].value = int(split_line[11])
insert.support_info.support[
'fiveprimesupport'].value = int(float(split_line[12]))
insert.support_info.support[
'threeprimesupport'].value = int(
float(split_line[13].replace("\n", "")))
insert.type = "non-reference"
if insert.end >= insert.start and insert.end > 0 and insert.start > -1:
# if split read, use junction positions as start and end
if insert.support_info.support[
'junction1support'].value > 0 and insert.support_info.support[
'junction2support'].value > 0:
insert.start = insert.support_info.support[
'junction1'].value
insert.end = insert.support_info.support[
'junction2'].value
insert.name = insert.name + "sr|"
# read pair
else:
insert.name = insert.name + "rp|"
insertions.append(insert)
else:
print(
"<TEMP POST> Omitting malformed line from insertion summary results:",
line)
else:
print(
"<TEMP POST> Omitting malformed line from insertion summary results:",
line)
return insertions
