added back number_of_contigs

metagenlab · Oct 11, 2024 · 72dfab8 · 72dfab8
1 parent e9ab869
commit 72dfab8
Showing 1 changed file with 8 additions and 5 deletions.
diff --git a/mess/workflow/scripts/calculate_cov.py b/mess/workflow/scripts/calculate_cov.py
@@ -93,7 +93,7 @@ def get_even_dist(table):
     df["tax_abundance"] = df["proportion"] / df["count"]
     df["genome_bases"] = df["total_sequence_length"] * df["tax_abundance"]
     df["sum_genome_bases"] = df.groupby("samplename")["genome_bases"].transform("sum")
-    df["cov_obtained"] = bases / (df["sum_genome_bases"] * p)
+    df["cov_obtained"] = bases / df["sum_genome_bases"] 
     df["cov_sim"] = df["tax_abundance"] * df["cov_obtained"]
     df["sum_cov"] = df.groupby("samplename")["cov_sim"].transform("sum")
     df["bases"] = df["cov_sim"] * df["total_sequence_length"]
@@ -117,7 +117,7 @@ def get_even_dist(table):
         df["sum_genome_bases"] = df.groupby("samplename")["genome_bases"].transform(
             "sum"
         )
-        df["cov_obtained"] = bases / (df["sum_genome_bases"] * p)
+        df["cov_obtained"] = bases / df["sum_genome_bases"] 
         df["cov_sim"] = df["tax_abundance"] * df["cov_obtained"]
         df["sum_cov"] = df.groupby("samplename")["cov_sim"].transform("sum")
         df["bases"] = df["cov_sim"] * df["total_sequence_length"]
@@ -133,7 +133,7 @@ def get_even_dist(table):
         df["tax_abundance"] = df["cov_sim"] / df["sum_cov"]
 
     if "reads" in entry_df.columns:
-        df["bases"] = df["reads"] * (snakemake.params.read_len * p)
+        df["bases"] = df["reads"] * snakemake.params.read_len * p
         df["sum_bases"] = df.groupby("samplename")["bases"].transform("sum")
         df["seq_abundance"] = df["bases"] / df["sum_bases"]
         df["cov_sim"] = df["bases"] / df["total_sequence_length"]
@@ -165,6 +165,7 @@ def get_even_dist(table):
     "path",
     "tax_id",
     "total_sequence_length",
+    "number_of_contigs",
     "reads",
     "bases",
     "seq_abundance",
@@ -178,5 +179,7 @@ def get_even_dist(table):
 df["tax_abundance"] = df["tax_abundance"].apply(lambda x: round(x, 3))
 df["seq_abundance"] = df["seq_abundance"].apply(lambda x: round(x, 3))
 
-df = df.astype({"seed": int, "tax_id": int, "total_sequence_length": int})
-df[cols].set_index(["samplename", "fasta"]).to_csv(snakemake.output[0], sep="\t")  # type: ignore
+df = df.astype(
+    {"seed": int, "tax_id": int, "total_sequence_length": int, "number_of_contigs": int}
+)
+df[cols].set_index(["samplename", "fasta"]).to_csv(snakemake.output[0], sep="\t")  # type: ignore