Improved __repr__ for Insert class. Changed Insert.get behaviour.

src/plotting_on_genome/insert.py

@@ -64,9 +64,12 @@ class Insert(object):
         return (
             "Insert("
             f"seq_id={self.seq_id}, "
+            f"idx={self.idx}, "
             f"start={self.start}, "
             f"end={self.end}, "
-            f"hit_id={self.hit_id})"
+            f"hit_id={self.hit_id}, "
+            f"coverage={self.coverage:.2f}, "
+            f"matched={self.matched})"
         )
 
     def __len__(self):

src/plotting_on_genome/inserts_dict.py

@@ -287,11 +287,12 @@ class InsertsDict(object):
     def get(
         self,
         seq_id_or_idx=None,
-        insert_types="both",
+        insert_type="both",
         filter_threshold=None,
     ):
-        assert insert_types in ("matched", "unmatched", "both")
-        seq_id_or_idx = seq_id_or_idx or self.seq_ids
+        assert insert_type in ("matched", "unmatched", "both")
+        if seq_id_or_idx is None:
+            seq_id_or_idx = self.seq_ids
 
         inserts = self.__getitem__(seq_id_or_idx)
         # Apply the coverage filter
@@ -301,14 +302,14 @@ class InsertsDict(object):
 
             inserts = [x for x in inserts if x.coverage > filter_threshold]
 
-        if insert_types == "matched":
+        if insert_type == "matched":
             inserts = [x for x in inserts if x.matched]
-        elif insert_types == "unmatched":
+        elif insert_type == "unmatched":
             inserts = [x for x in inserts if not x.matched]
 
         return inserts
 
-    def to_dataframe(self, insert_types="both", filter_threshold=None):
+    def to_dataframe(self, insert_type="both", filter_threshold=None):
         return pd.DataFrame(
             [
                 (
@@ -322,7 +323,7 @@ class InsertsDict(object):
                     x.coverage,
                 )
                 for x in self.get(
-                    insert_types=insert_types, filter_threshold=filter_threshold
+                    insert_type=insert_type, filter_threshold=filter_threshold
                 )
             ],
             columns=(
@@ -340,11 +341,11 @@ class InsertsDict(object):
     def genes_to_dataframe(
         self,
         seq_id_or_idx=None,
-        insert_types="both",
+        insert_type="both",
         filter_threshold=None,
         buffer=4000,
     ):
-        inserts = self.get(seq_id_or_idx, insert_types, filter_threshold)
+        inserts = self.get(seq_id_or_idx, insert_type, filter_threshold)
 
         if len(inserts):
             df_genes = pd.concat(
@@ -415,7 +416,9 @@ class InsertsDict(object):
 
     def plot(
         self,
-        inserts=None,
+        seq_id_or_idxs=None,
+        insert_type="both",
+        filter_threshold=None,
         show_labels=True,
         col1="#8DDEF7",
         col2="#CFFCCC",
@@ -426,7 +429,7 @@ class InsertsDict(object):
         if "figsize" not in kwargs:
             kwargs["figsize"] = (10, 8)
 
-        inserts = inserts or []
+        inserts = self.get(seq_id_or_idxs, insert_type, filter_threshold)
         rec = self._get_graphic_records_genome(inserts, show_labels, col1, col2)
 
         if backend == "matplotlib":

streamlit_app.py

@@ -5,7 +5,6 @@ from pathlib import Path
 from tempfile import TemporaryDirectory
 
 import matplotlib.pyplot as plt
-import pandas as pd
 import streamlit as st
 
 import plotting_on_genome as pog
@@ -15,8 +14,8 @@ import plotting_on_genome as pog
 if "stage" not in st.session_state:
     st.session_state.stage = 0
 
-if "insert_types" not in st.session_state:
-    st.session_state.insert_types = "both"
+if "insert_type" not in st.session_state:
+    st.session_state.insert_type = "both"
 
 if "workdir" not in st.session_state:
     st.session_state.workdir = None
@@ -113,7 +112,7 @@ def get_main_inputs():
     fwd_suf = st.text_input("Forward suffix:", "_F", key="fwd_suf")
     rev_suf = st.text_input("Reverse suffix:", "_R", key="rev_suf")
 
-    st.session_state.insert_types = st.selectbox(
+    st.session_state.insert_type = st.selectbox(
         "insert types:", ["both", "matched", "unmatched"]
     )
 
@@ -143,7 +142,7 @@ def convert_df(df, **kwargs):
 
 def show_results():
     inserts_all = st.session_state.pipeline
-    insert_types = st.session_state.insert_types
+    insert_type = st.session_state.insert_type
 
     filter_threshold = st.slider("Filter threshold:", 0.0, 1.0, 0.7)
 
@@ -154,7 +153,7 @@ def show_results():
         value=4000,
         help="Number of bases either side of the insert",
     )
-    params = dict(insert_types=insert_types, filter_threshold=filter_threshold)
+    params = dict(insert_type=insert_type, filter_threshold=filter_threshold)
 
     df_inserts = inserts_all.to_dataframe(**params)
     df_genes = inserts_all.genes_to_dataframe(**params, buffer=buffer)
@@ -217,15 +216,14 @@ def show_results():
                 st.write(f"No inserts found for {seq_id}!")
 
         elif option == "plot genome":
-            labels = st.toggle("Labels")
-            inserts = []
-            if st.toggle("Plot inserts", True):
-                inserts = inserts_all.get(**params)
 
             st.write(df_inserts)
 
+            labels = st.toggle("Labels")
+            insert_idxs = None if st.toggle("Plot inserts", True) else []
+
             fig, ax = plt.subplots(figsize=(10, 10 * (1 + 2 * labels)))
-            ax = inserts_all.plot(inserts, show_labels=labels, ax=ax)
+            ax = inserts_all.plot(insert_idxs, show_labels=labels, ax=ax, **params)
             st.pyplot(fig, use_container_width=True)
             plt.close()