Merge pull request #37 from stjude/fix

Fix
stjude · Apr 18, 2023 · 797fff3 · 797fff3
2 parents fdbf1d8 + 426ef91
commit 797fff3
Show file tree

Hide file tree

Showing 3 changed files with 26 additions and 25 deletions.
diff --git a/rnaindel/analysis/postprocessor.py b/rnaindel/analysis/postprocessor.py
@@ -26,6 +26,8 @@ def postprocess(df, data_dir, perform_outlier_analysis, pon):
 
     df = df[df["keep_this"]]
 
+    df.reset_index(drop=True, inplace=True)
+
     return sort_positionally(df)
 
 
@@ -61,7 +63,6 @@ def is_rescurable_homopolymer(row):
 
 
 def filter_str(row, non_somatic_db, pon, mapping_thresh):
-
     pred = row["predicted_class"]
 
     if pred == "somatic":
@@ -79,7 +80,6 @@ def filter_str(row, non_somatic_db, pon, mapping_thresh):
 
 
 def filter_by_db(row, non_somatic_db, pon):
-
     non_somatic_hits = row["indel"].query_vcf(non_somatic_db)
 
     if non_somatic_hits:
@@ -126,16 +126,12 @@ def reclassify_by_knowledge(row, cosmic):
 
 
 def sort_positionally(df):
-    df["chrom"] = df.apply(lambda x: x["chrom"].replace("chr", ""), axis=1)
-    df["chrom"] = df.apply(lambda x: 23 if x["chrom"] == "X" else x["chrom"], axis=1)
-    df["chrom"] = df.apply(lambda x: 24 if x["chrom"] == "Y" else x["chrom"], axis=1)
-    df["chrom"] = df.apply(lambda x: int(x["chrom"]), axis=1)
-
-    df.sort_values(["chrom", "cpos"], inplace=True)
+    df["_chrom"] = df.apply(lambda x: x["chrom"].replace("chr", ""), axis=1)
+    df["_chrom"] = df.apply(lambda x: 23 if x["chrom"] == "X" else x["_chrom"], axis=1)
+    df["_chrom"] = df.apply(lambda x: 24 if x["chrom"] == "Y" else x["_chrom"], axis=1)
+    df["_chrom"] = df.apply(lambda x: int(x["_chrom"]), axis=1)
 
-    df["chrom"] = df.apply(lambda x: "Y" if x["chrom"] == 24 else x["chrom"], axis=1)
-    df["chrom"] = df.apply(lambda x: "X" if x["chrom"] == 23 else x["chrom"], axis=1)
-    df["chrom"] = df.apply(lambda x: "chr" + str(x["chrom"]), axis=1)
+    df.sort_values(["_chrom", "cpos"], inplace=True)
 
     return df
 

diff --git a/rnaindel/analysis/vcf_writer.py b/rnaindel/analysis/vcf_writer.py
@@ -5,7 +5,6 @@
 
 
 def write_vcf(df, version, arguments, tdna, ndna):
-
     header = (
         header_1(version, arguments.reference)
         + filter_fields()
@@ -17,7 +16,14 @@ def write_vcf(df, version, arguments, tdna, ndna):
         + bottom_header(arguments.bam)
     )
 
-    f = open(arguments.output_vcf, "w")
+    _out_vcf = arguments.output_vcf
+    if _out_vcf.endswith(".vcf.gz"):
+        _out_vcf = _out_vcf[:-3]
+
+    if not _out_vcf.endswith(".vcf"):
+        _out_vcf = _out_vcf + ".vcf"
+
+    f = open(_out_vcf, "w")
 
     f.write("\n".join(header))
 
@@ -27,9 +33,7 @@ def write_vcf(df, version, arguments, tdna, ndna):
 
     f.close()
 
-    pysam.tabix_index(
-        arguments.output_vcf, preset="vcf", force=True, keep_original=False
-    )
+    pysam.tabix_index(_out_vcf, preset="vcf", force=True, keep_original=False)
 
 
 def header_1(version, fasta):
@@ -230,13 +234,15 @@ def parse_row_to_vcf_record(row):
 
 
 def generate_info_str(row):
-    info_str = "predicted_class={};probabilities={},{},{};annotation={};cosmic_cnt={};".format(
-        row["predicted_class"],
-        row["prob_s"],
-        row["prob_g"],
-        row["prob_a"],
-        row["annotation"],
-        row["cosmic_cnt"],
+    info_str = (
+        "predicted_class={};probabilities={},{},{};annotation={};cosmic_cnt={};".format(
+            row["predicted_class"],
+            row["prob_s"],
+            row["prob_g"],
+            row["prob_a"],
+            row["annotation"],
+            row["cosmic_cnt"],
+        )
     )
 
     if row["pop_freq"] > 0:

diff --git a/rnaindel/version.py b/rnaindel/version.py
@@ -1,2 +1 @@
-__version__ = "3.2.3"
-
+__version__ = "3.2.4"