More potential selection criteria for genes.

libcodonusage/libcodonusage.py

@@ -122,6 +122,7 @@ def detect_fishy_genes(codon_counts):
     start_upstream_met_start_col = start_upstream_col & ~no_met_start_col
     start_upstream_met_start_nostops_col = (
         start_upstream_met_start_col & ~has_stops_col)
+    good_met_start_col = (~start_upstream_col & ~no_met_start_col)
     has_stops_good_met_start_col = (
         has_stops_col & ~no_met_start_col
         & ~start_upstream_met_start_col)
@@ -137,8 +138,9 @@ def detect_fishy_genes(codon_counts):
         "start_upstream_met_start": start_upstream_met_start_col,
         "start_upstream_met_start_nostops": (
             start_upstream_met_start_nostops_col),
+        "good_met_start": good_met_start_col,
         "has_stops_good_met_start": has_stops_good_met_start_col})
-    render_md("Number of genes in potentially fishy categories:\n\n")
+    render_md("Number of genes fitting various selection criteria:\n\n")
     display(criteria.agg(sum))
     render_md("Upset plot of the non-empty categories:\n\n")
     fig = plt.figure()
@@ -157,6 +159,7 @@ def detect_fishy_genes(codon_counts):
         criteria[start_upstream_met_start_col].index)
     start_upstream_met_start_nostops = set(
         criteria[start_upstream_met_start_nostops_col].index)
+    good_met_start = set(criteria[good_met_start_col].index)
     has_stops_good_met_start = set(
         criteria[has_stops_good_met_start_col].index)
     no_stop_good_met_start = set(criteria[no_stop_good_met_start_col].index)
@@ -206,6 +209,9 @@ def detect_fishy_genes(codon_counts):
         " but have a well defined start position with 'M'.")
     if len(has_stops_good_met_start) <= 10:
         display(has_stops_good_met_start)
+    render_md(
+        f"{len(good_met_start)} genes have a well defined "
+        "start position with 'M'.")
     render_md(
         """If genes that have stop readthrough are a known phenomenon,
         only those among them that do not have a valid start codon