Skip to content

Commit

Permalink
Merge branch 'dev'
Browse files Browse the repository at this point in the history
  • Loading branch information
@FTouzain
FTouzain committed Feb 4, 2025
2 parents e6c85c8 + 636d6ef commit ab43578
Show file tree
Hide file tree
Showing 4 changed files with 105 additions and 15 deletions.
8 changes: 5 additions & 3 deletions CHANGELOG
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,6 @@
0.2.3.5:
- bug correction: in convert_tbl2json.py, modif to take into account of vadr flu annotation (sig_peptide, note just after gene, etc)
- change version 0.2.3.4 -> 0.2.3.5
0.2.3.4:
- bug correction: in convert_tbl2json.py, handle case of ncRNA when gene is expected (for dengue example)
- correct a bug when gene displayed between product and protein_id
Expand All @@ -6,8 +9,8 @@
- change version 0.2.3.3 -> 0.2.3.4
0.2.3.3:
- in convert_tbl2json.py, now when no gene found in bed, deduce them from CDS and name them gene_1 .. gene_N (not ORFN
because some prot are named ORF2 prot in PCV2, for an ORF that is not the second one!). It avoids to get a bug
for PCV2 viruses for instance
because some prot are named ORF2 prot in PCV2, for an ORF that is not the second one!). It avoids to get a bug
for PCV2 viruses for instance
- in convert_vcffile_to_readablefile2.py, NOW handle genes in reverse orientation (did not display genes/prot labels previously)
- change version 0.2.3.2 -> 0.2.3.3
0.2.3.2:
Expand Down Expand Up @@ -63,6 +66,5 @@
- pyvcf replaced by pysam to improve compatibility / long term maintening
- consequence: PYTHON_SCRIPTS/convert_vcffile_to_readablefile.py replaced by PYTHON_SCRIPTS/convert_vcffile_to_readablefile2.py
- vvv2.py renamed vvv2_display.py (because this program replace only the visualization part of vvv)

0.1.0-alpha: first version

2 changes: 1 addition & 1 deletion setup.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@

setuptools.setup(
name="vvv2_display", # Required
version="0.2.3.4", # Required
version="0.2.3.5", # Required
description="Viral Variant Visualizer 2 display", # Optional
long_description=long_description,
long_description_content_type="text/markdown", # Optional (see note above)
Expand Down
106 changes: 97 additions & 9 deletions src/convert_tbl2json.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,8 @@

material_type_list = ['gene',
'misc_feature',
'mat_peptide']
'mat_peptide',
'sig_peptide']
material_type = '|'.join(material_type_list)

parser = argparse.ArgumentParser()
Expand Down Expand Up @@ -445,6 +446,26 @@ def indexlist(item2find, list_or_string):
gene_name = ''
continue

# added 2025 01 29 to handle sig_peptide of vadr flu annotation
elif line_fields[2] == 'sig_peptide':
if b_verbose:
print(' '.join(['sig_peptide',
gene_start,
gene_end,
gene_name])
)
b_next_is_gene = False
b_next_is_product = True

# ask to treat current mat_peptide info
cds_start = line_fields[0]
cds_end = line_fields[1]
cds_start = re.sub(non_alphanum, '', cds_start)
cds_end = re.sub(non_alphanum, '', cds_end)
curr_type = 'sig_peptide'
gene_name = ''
continue

# section added 2024 09 24, when 2 gene section are following each other
# without any other description
elif line_fields[2] == 'gene':
Expand Down Expand Up @@ -864,6 +885,37 @@ def indexlist(item2find, list_or_string):
b_next_is_gene = False
b_next_is_product = True
continue
elif (len(line_fields) == 3) and (line_fields[2] == 'mat_peptide'):
cds_start = line_fields[0]
cds_end = line_fields[1]
cds_start = re.sub(non_alphanum, '', cds_start)
cds_end = re.sub(non_alphanum, '', cds_end)
b_next_is_product = True
b_next_is_gene = False
curr_type = 'CDS'
if b_verbose:
print("\t".join([
"TMP_MAT_PEPTIDE:"+line_fields[2],
cds_start,
cds_end
]))
continue
# added 2025 01 29 to handle sig_peptide in vadr flu annotations
elif line_fields[2] == 'sig_peptide':
cds_start = line_fields[0]
cds_end = line_fields[1]
cds_start = re.sub(non_alphanum, '', cds_start)
cds_end = re.sub(non_alphanum, '', cds_end)
b_next_is_product = True
b_next_is_gene = False
curr_type = 'CDS'
if b_verbose:
print("\t".join([
"TMP_SIG_PEPTIDE:"+line_fields[2],
cds_start,
cds_end
]))
continue
else:
print("line_fields:"+str(line_fields)+", line "+ str(sys._getframe().f_lineno) )
sys.exit(prog_tag + "[Error] Case not encountered line "+ str(sys._getframe().f_lineno) )
Expand Down Expand Up @@ -956,8 +1008,28 @@ def indexlist(item2find, list_or_string):
b_next_is_protein_id = False
b_next_is_gene = True # added 2024 10 01
continue

if line_fields[0] == 'ncRNA_class':
# added 2025 01 29 to handle function provided in flu vadr annotations
elif line_fields[0] == 'function':
if b_verbose or b_check_gene_prot_rec:
print("\t".join([
prog_tag,
"function found:",
",".join(line_fields),
", line "+str(frame.f_lineno)
]))
continue
# added 2025 01 29 to handle note provided in flu vadr annotations just after gene
# do not bring usefull info
elif line_fields[0] == 'note':
if b_verbose or b_check_gene_prot_rec:
print("\t".join([
prog_tag,
"note found:",
",".join(line_fields),
", line "+str(frame.f_lineno)
]))
continue
elif line_fields[0] == 'ncRNA_class':
protein_id = line_fields[1]
tmp_name = protein_id
b_next_is_protein_id = False
Expand Down Expand Up @@ -1316,7 +1388,7 @@ def indexlist(item2find, list_or_string):

continue

elif line_fields[2] == 'gene':
elif (len(line_fields) == 3)and(line_fields[2] == 'gene'):
gene_start = line_fields[0]
gene_end = line_fields[1]
gene_start = re.sub(non_alphanum, '', gene_start)
Expand All @@ -1331,7 +1403,7 @@ def indexlist(item2find, list_or_string):
"for line "+str(line_fields)
]))

elif line_fields[2] == 'CDS':
elif (len(line_fields) == 3)and(line_fields[2] == 'CDS'):
cds_start = line_fields[0]
cds_end = line_fields[1]
cds_start = re.sub(non_alphanum, '', cds_start)
Expand All @@ -1346,7 +1418,7 @@ def indexlist(item2find, list_or_string):
cds_end
]))

elif line_fields[2] == 'ncRNA':
elif (len(line_fields) == 3)and(line_fields[2] == 'ncRNA'):
cds_start = line_fields[0]
cds_end = line_fields[1]
cds_start = re.sub(non_alphanum, '', cds_start)
Expand All @@ -1361,7 +1433,7 @@ def indexlist(item2find, list_or_string):
cds_end
]))

elif line_fields[2] == 'misc_feature':
elif (len(line_fields) == 3)and(line_fields[2] == 'misc_feature'):
misc_feature_start = line_fields[0]
misc_feature_end = line_fields[1]
misc_feature_start = re.sub(non_alphanum, '', misc_feature_start)
Expand All @@ -1375,7 +1447,7 @@ def indexlist(item2find, list_or_string):
misc_feature_end
]))

elif line_fields[2] == 'mat_peptide':
elif (len(line_fields) == 3)and(line_fields[2] == 'mat_peptide'):
cds_start = line_fields[0]
cds_end = line_fields[1]
cds_start = re.sub(non_alphanum, '', cds_start)
Expand All @@ -1390,7 +1462,23 @@ def indexlist(item2find, list_or_string):
cds_end
]))

elif line_fields[2] == 'stem_loop':
# added 2025 01 29 to handle sig_peptide in vadr flu annotations
elif (len(line_fields) == 3)and(line_fields[2] == 'sig_peptide'):
cds_start = line_fields[0]
cds_end = line_fields[1]
cds_start = re.sub(non_alphanum, '', cds_start)
cds_end = re.sub(non_alphanum, '', cds_end)
b_next_is_product = True
b_next_is_gene = False
curr_type = 'CDS'
if b_verbose:
print("\t".join([
"TMP_SIG_PEPTIDE:"+line_fields[2],
cds_start,
cds_end
]))

elif (len(line_fields) == 3)and(line_fields[2] == 'stem_loop'):
misc_feature_start = line_fields[0]
misc_feature_end = line_fields[1]
misc_feature_start = re.sub(non_alphanum, '', misc_feature_start)
Expand Down
4 changes: 2 additions & 2 deletions vvv2_display.xml
View file
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
<tool id="vvv2_display" name="vvv2_display: Display SNP proportions and CDS of an assembly in png image" version="0.2.3.4" python_template_version="3.9">
<tool id="vvv2_display" name="vvv2_display: Display SNP proportions and CDS of an assembly in png image" version="0.2.3.5" python_template_version="3.9">
<requirements>
<requirement type="package" version="0.2.3.4">vvv2_display</requirement>
<requirement type="package" version="0.2.3.5">vvv2_display</requirement>
</requirements>
<command detect_errors="exit_code"><![CDATA[
vvv2_display.py -f '$vadr_fail_annotation' -p '$vadr_pass_annotation' -s '$vadr_seqstat' -n '$vardict_vcf' -r '$snp_img' -w '$var_significant_thres' -o '$cov_depth' -e '$cov_depth_corr' -t '$snp_loc' -u '$snp_loc_summary' -j '$json_annot' -k '$bed_annot' -l '$correct_vcf' -m '$contig_limits' $cov_depth_scale
Expand Down

0 comments on commit ab43578

Please sign in to comment.