Merge pull request #225 from bioinfo-chru-strasbourg/fix_from_annovar

fix from annovar tool #224

howard/functions/commons.py

@@ -10,6 +10,7 @@
 import sys
 from tempfile import NamedTemporaryFile
 import tempfile
+import typing
 import duckdb
 import json
 import argparse
@@ -3467,3 +3468,46 @@ def transcripts_file_to_df(transcripts_file: str) -> pd.DataFrame:
 
  # Return
  return transcripts_dataframe
+
+
+def identical(
+ vcf_list: typing.List[str], begin: str = "##", line_strip: bool = True
+) -> bool:
+ """
+ The `identical` function compares the contents of multiple VCF files to determine if they are
+ identical.
+
+ :param vcf_list: The `vcf_list` parameter is a list of file paths to VCF (Variant Call Format) files
+ that you want to compare for identity. The function reads the contents of these files and checks if
+ they are identical based on the specified conditions
+ :type vcf_list: typing.List[str]
+ :param begin: The `begin` parameter in the `identical` function is used to specify a string that
+ indicates the beginning of a line in the input files. If a line in the input file starts with the
+ specified `begin` string, it will be skipped and not included in the comparison process. By default,
+ defaults to ##
+ :type begin: str (optional)
+ :param line_strip: The `line_strip` parameter in the `identical` function is a boolean flag that
+ determines whether each line read from the input files should be stripped of leading and trailing
+ whitespaces before being compared. If `line_strip` is set to `True`, each line will be stripped
+ using the `strip, defaults to True
+ :type line_strip: bool (optional)
+ :return: The function `identical` is returning a boolean value. It returns `True` if all the lines
+ in the VCF files provided in the `vcf_list` are identical, and `False` otherwise.
+ """
+
+ vcfs_lines = []
+ k = 0
+ for vcf in vcf_list:
+ vcfs_lines.append([])
+ with open(vcf, "r") as f:
+ for l in f:
+ if not l.startswith(begin) or begin == "":
+ if line_strip:
+ l = l.strip()
+ vcfs_lines[k].append(l)
+ k += 1
+
+ for i in range(len(vcf_list) - 1):
+ if vcfs_lines[i] != vcfs_lines[i + 1]:
+ return False
+ return True

howard/functions/from_annovar.py

@@ -307,13 +307,15 @@ def annovar_to_vcf(
  else:
 
  with open(input_file, "r") as f:
+
  for line in f:
  if str(line).startswith("##"):
  continue
  elif len(line.strip().split("\t")) < 5:
  header_ok = False
  elif str(line).startswith("#"):
  log.debug("Found header")
+ header_ok = True
  header = line.strip().split("\t")
  if "#CHROM" not in header:
  chrom_list_for_header = [
@@ -388,7 +390,10 @@ def annovar_to_vcf(
  break
  f.close()
 
- if not header_ok:
+ if not header_ok and (
+ set(["#CHROM", "POS", "REF", "ALT"]).issubset(set(header))
+ or set(["#CHROM", "START", "END"]).issubset(set(header))
+ ):
  raise ValueError("Error in header")
 
  # protect info tag from unauthorized characters
@@ -413,7 +418,6 @@ def annovar_to_vcf(
 
  # Clean nb header and skip line
  nb_skip_line = nb_header_line
- nb_header_line -= 1
  if nb_header_line <= 0:
  nb_header_line = None
 
@@ -429,9 +433,10 @@ def annovar_to_vcf(
  dtype[h] = column_type
 
  # Check format VCF readable
- # nrows = 100000
  log.debug("Check input file struct...")
  nrows_sampling = 1000000
+ log.debug(f"nrows_sampling={nrows_sampling}")
+ log.debug(f"nb_header_line={nb_header_line}")
  try:
  df = pd.read_csv(
  input_file,

tests/databases/others/hg19_dbnsfp42a.txt

@@ -0,0 +1,10 @@
+#Chr Start End Ref Alt SIFT_score SIFT_converted_rankscore SIFT_pred SIFT4G_score SIFT4G_converted_rankscore SIFT4G_pred Polyphen2_HDIV_score Polyphen2_HDIV_rankscore Polyphen2_HDIV_pred Polyphen2_HVAR_score Polyphen2_HVAR_rankscore Polyphen2_HVAR_pred LRT_score LRT_converted_rankscore LRT_pred MutationTaster_score MutationTaster_converted_rankscore MutationTaster_pred MutationAssessor_score MutationAssessor_rankscore MutationAssessor_pred FATHMM_score FATHMM_converted_rankscore FATHMM_pred PROVEAN_score PROVEAN_converted_rankscore PROVEAN_pred VEST4_score VEST4_rankscore MetaSVM_score MetaSVM_rankscore MetaSVM_pred MetaLR_score MetaLR_rankscore MetaLR_pred MetaRNN_score MetaRNN_rankscore MetaRNN_pred M-CAP_score M-CAP_rankscore M-CAP_pred REVEL_score REVEL_rankscore MutPred_score MutPred_rankscore MVP_score MVP_rankscore MPC_score MPC_rankscore PrimateAI_score PrimateAI_rankscore PrimateAI_pred DEOGEN2_score DEOGEN2_rankscore DEOGEN2_pred BayesDel_addAF_score BayesDel_addAF_rankscore BayesDel_addAF_pred BayesDel_noAF_score BayesDel_noAF_rankscore BayesDel_noAF_pred ClinPred_score ClinPred_rankscore ClinPred_pred LIST-S2_score LIST-S2_rankscore LIST-S2_pred Aloft_pred Aloft_Confidence CADD_raw CADD_raw_rankscore CADD_phred DANN_score DANN_rankscore fathmm-MKL_coding_score fathmm-MKL_coding_rankscore fathmm-MKL_coding_pred fathmm-XF_coding_score fathmm-XF_coding_rankscore fathmm-XF_coding_pred Eigen-raw_coding Eigen-raw_coding_rankscore Eigen-PC-raw_coding Eigen-PC-raw_coding_rankscore GenoCanyon_score GenoCanyon_rankscore integrated_fitCons_score integrated_fitCons_rankscore integrated_confidence_value LINSIGHT LINSIGHT_rankscore GERP++_NR GERP++_RS GERP++_RS_rankscore phyloP100way_vertebrate phyloP100way_vertebrate_rankscore phyloP30way_mammalian phyloP30way_mammalian_rankscore phastCons100way_vertebrate phastCons100way_vertebrate_rankscore phastCons30way_mammalian phastCons30way_mammalian_rankscore SiPhy_29way_logOdds SiPhy_29way_logOdds_rankscore Interpro_domain GTEx_V8_gene GTEx_V8_tissue 
+1 65565 65565 A C . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 0.317 0.491 T . . . . . . . . . . . . . . . . . . . . . . . . . . 0.9 0.651 D .; .; 1.166 0.191 14.46 0.703 0.092 0.567 0.302 D . . . . . . . 0.000 0.029 0.061 0.011 0 0.207 0.308 2.73 2.73 0.313 2.589 0.458 1.152 0.705 0.993 0.379 1.000 0.863 4.611 0.118 . . .
+1 65565 65565 A G . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 0.318 0.492 T . . . . . . . . . . . . . . . . . . . . . . . . . . 0.9 0.651 D .; .; 1.189 0.194 14.59 0.739 0.105 0.286 0.236 N . . . . . . . 0.000 0.029 0.061 0.011 0 0.207 0.308 2.73 2.73 0.313 2.589 0.458 1.152 0.705 0.993 0.379 1.000 0.863 4.611 0.118 . . .
+1 65565 65565 A T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 0.316 0.491 T . . . . . . . . . . . . . . . . . . . . . . . . . . 0.9 0.651 D .; .; 1.173 0.192 14.50 0.689 0.088 0.551 0.298 D . . . . . . . 0.000 0.029 0.061 0.011 0 0.207 0.308 2.73 2.73 0.313 2.589 0.458 1.152 0.705 0.993 0.379 1.000 0.863 4.611 0.118 . . .
+1 65566 65566 T A . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 0.343 0.514 T . . . . . . . . . . . . . . . . . . . . . . . . . . 0.9 0.651 D .; .; 1.257 0.203 14.96 0.710 0.095 0.441 0.272 N . . . . . . . 0.000 0.058 0.061 0.011 0 0.692 0.427 2.73 2.73 0.313 2.158 0.420 1.002 0.370 1.000 0.716 1.000 0.863 9.273 0.368 . . .
+1 65566 65566 T C . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 0.346 0.516 T . . . . . . . . . . . . . . . . . . . . . . . . . . 0.9 0.651 D .; .; 1.273 0.206 15.05 0.782 0.122 0.594 0.309 D . . . . . . . 0.000 0.058 0.061 0.011 0 0.692 0.427 2.73 2.73 0.313 2.158 0.420 1.002 0.370 1.000 0.716 1.000 0.863 9.273 0.368 . . .
+1 65566 65566 T G . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 0.344 0.514 T . . . . . . . . . . . . . . . . . . . . . . . . . . 0.9 0.651 D .; .; 1.249 0.202 14.92 0.753 0.110 0.620 0.316 D . . . . . . . 0.000 0.058 0.061 0.011 0 0.692 0.427 2.73 2.73 0.313 2.158 0.420 1.002 0.370 1.000 0.716 1.000 0.863 9.273 0.368 . . .
+1 65567 65567 G A . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 0.350 0.519 T . . . . . . . . . . . . . . . . . . . . . . . . . . 0.9 0.651 D .; .; 1.142 0.188 14.32 0.541 0.051 0.575 0.304 D . . . . . . . 0.000 0.029 0.061 0.011 0 0.207 0.308 2.73 2.73 0.313 2.639 0.462 1.034 0.512 1.000 0.716 0.999 0.704 7.790 0.283 . . .
+1 65567 65567 G C . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 0.348 0.517 T . . . . . . . . . . . . . . . . . . . . . . . . . . 0.9 0.651 D .; .; 1.082 0.180 13.96 0.609 0.066 0.564 0.301 D . . . . . . . 0.000 0.029 0.061 0.011 0 0.207 0.308 2.73 2.73 0.313 2.639 0.462 1.034 0.512 1.000 0.716 0.999 0.704 7.790 0.283 . . .
+1 65567 65567 G T . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 0.347 0.516 T . . . . . . . . . . . . . . . . . . . . . . . . . . 0.9 0.651 D .; .; 1.092 0.181 14.03 0.540 0.051 0.462 0.277 N . . . . . . . 0.000 0.029 0.061 0.011 0 0.207 0.308 2.73 2.73 0.313 2.639 0.462 1.034 0.512 1.000 0.716 0.999 0.704 7.790 0.283 . . .