add saturation kinetics curves

assets/assess_panel/assess_panel.py

@@ -9,7 +9,7 @@
 import click
 
 
-sys.path.append("../../bin")
+sys.path.append("../../bin/")
 
 from utils_context import triplet_context_iterator
 

bin/add_subgenicregions.py

@@ -68,7 +68,7 @@ def main(panel_file, autoexons, autodomains, custom, subgenic_regions_complement
 
             # If you reach ths point, ind_start is defined and valid
             # Search for END position starting from ind_start
-            search_end = chr_data.iloc[ind_start:,:]
+            search_end = chr_data.iloc[ind_start:]
             end_matches = np.where(search_end["POS"] == row["END"])[0]
 
             end_found = len(end_matches) > 0
@@ -117,7 +117,7 @@ def main(panel_file, autoexons, autodomains, custom, subgenic_regions_complement
             upd_end = ind_end
 
             # Extract subgenic data and modify gene names
-            subgenic_data = chr_data.iloc[upd_start: upd_end + 1, :].copy()
+            subgenic_data = chr_data.iloc[upd_start: upd_end + 1].copy()
             subgenic_data["GENE"] = region_name
 
             new_data = pd.concat((new_data, subgenic_data))

bin/annotate_omega_failing.py

@@ -18,7 +18,7 @@
 
 
 
-def load_flagged_tables(paths: List[Path]) -> Tuple[pd.DataFrame, pd.DataFrame]:
+def load_flagged_tables(paths: List[Path]) -> Tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame, pd.DataFrame]:
     """Read flagged files and return a normalized DataFrame with possible columns:
     SAMPLE, GENE, reason_exclusion
     """
@@ -30,7 +30,7 @@ def load_flagged_tables(paths: List[Path]) -> Tuple[pd.DataFrame, pd.DataFrame]:
         df = pd.read_csv(p, sep="\t", header=0, dtype=str)
         pieces.append(df)
     if not pieces:
-        return pd.DataFrame(columns=["sample", "gene", "reason_exclusion"]), pd.DataFrame(columns=["sample", "gene", "reason_exclusion"])
+        return pd.DataFrame(columns=["sample", "gene", "reason_exclusion"]), pd.DataFrame(columns=["sample", "gene", "reason_exclusion"]), pd.DataFrame(columns=["sample", "gene", "reason_exclusion"]), pd.DataFrame(columns=["sample", "gene", "reason_exclusion"])
 
     all_df = pd.concat(pieces, ignore_index=True, sort=False)
 

bin/check_samplesheet.py

@@ -211,7 +211,8 @@ def check_samplesheet(file_in, file_out, bam_required=False):
     with file_in.open(newline="") as in_handle:
         reader = csv.DictReader(in_handle, dialect=sniff_format(in_handle))
         # Validate the existence of the expected header columns.
-        if not required_columns.issubset(reader.fieldnames):
+        fieldnames = reader.fieldnames or []
+        if not required_columns.issubset(fieldnames):
             req_cols = ", ".join(required_columns)
             logger.critical(f"The sample sheet **must** contain these column headers: {req_cols}.")
             sys.exit(1)
@@ -224,7 +225,7 @@ def check_samplesheet(file_in, file_out, bam_required=False):
                 logger.critical(f"{str(error)} On line {i + 2}.")
                 sys.exit(1)
         checker.validate_unique_samples()
-    header = list(reader.fieldnames)
+    header = list(fieldnames)
     # See https://docs.python.org/3.9/library/csv.html#id3 to read up on `newline=""`.
     with file_out.open(mode="w", newline="") as out_handle:
         writer = csv.DictWriter(out_handle, header, delimiter=",")

bin/create_mask_matrix.py

@@ -63,7 +63,7 @@ def add_bed_positions(bed_df: pd.DataFrame,
     entries_added = 0
 
     for row in bed_df.itertuples():
-        for pos in range(row.START, row.END + 1):
+        for pos in range(int(row.START), int(row.END) + 1):
             key = (row.CHROM, pos, sample_name)
             if key not in masked_positions:
                 mask_data.append({

bin/filterbed.py

@@ -63,9 +63,9 @@ def main(sample_maf_file, bedfile, filtername, positive):
     positions_df = remove_non_canonical_chromosomes(positions_df)
 
     # adjust the CHROM field to adapt to the way it is being represented in the mutations list
-    if sample_maf.iloc[0,0].startswith("chr") and not positions_df.iloc[0,0].startswith("chr"):
+    if str(sample_maf.iloc[0,0]).startswith("chr") and not str(positions_df.iloc[0,0]).startswith("chr"):
         positions_df["CHROM"] = "chr" + positions_df["CHROM"]
-    elif not sample_maf.iloc[0,0].startswith("chr") and positions_df.iloc[0,0].startswith("chr"):
+    elif not str(sample_maf.iloc[0,0]).startswith("chr") and str(positions_df.iloc[0,0]).startswith("chr"):
         positions_df["CHROM"] = positions_df["CHROM"].str.replace("chr", "")
 
     filtered_maf = filter_panel(sample_maf, positions_df, filtername, positive = positive)