Update app.py

app.py

@@ -63,7 +63,7 @@ st.header(f":blue[{database_name} Pubmed corpus.]")
 text_input_value = st.text_input(f"Enter one term to search within the {database_name} corpus")
 query = text_input_value
 query = query.lower()
-query = re.sub("[,.?!&*;:]", "", query)
+query = re.sub("[,.?!&*;: ]", "", query)
 matches = [" "]
 if any([x in query for x in matches]):
     st.write("Please only enter one term or a term without spaces")
@@ -171,9 +171,25 @@ if query:
     print()
     # df1.head(50).to_csv("clotting_sim2.csv", index=True, header=False)
     # time.sleep(2)
-
-
-    df10 = df1.head(10)
+    # Create the slider with increments of 5 up to 100
+
+    st.markdown(f"<b><p style='font-family: Arial; font-size: 20px;'>Populate a treemap with the slider below to visualize "
+                f"<span style='color:red; font-style: italic;'>genes</span> contextually "
+                f"and semantically similar to <span style='color:red; font-style: italic;'>{query}</span> "
+                f"within the <span style='color:red; font-style: italic;'>{database_name}</span> corpus.</p></b>",
+                    unsafe_allow_html=True)
+    value = st.slider("", 0, 100, step=5)
+    if value > 0:
+        # st.subheader(f"Top {value} genes closely related to {query}: "
+        #              f"Click on the Pubmed and NCBI links for more gene information")
+
+        st.markdown(
+            f"<b><p style='font-family: Arial; font-size: 20px; font-style: Bold;'>Top <span style='color:red; font-style: italic;'>{value} "
+            f"</span>genes similar to "
+            f"<span style='color:red; font-style: italic;'>{query}:</span> Click on the squares to expand and the Pubmed and NCBI links for more gene information</span></p></b>",
+            unsafe_allow_html=True)
+
+    df10 = df1.head(value)
     df10.index = (1 / df10.index)*10000
     sizes = df10.index.tolist()
 
@@ -191,51 +207,62 @@ if query:
     fig2.patch.set_facecolor('#CCFFFF')
     #
     df3 = df1.copy()
+    df3["SIMILARITY"] = 'Similarity Score ' + df3.head(value)["SIMILARITY"].round(2).astype(str)
     df3.reset_index(inplace=True)
     df3 = df3.rename(columns={'Human Gene': 'symbol2'})
     # Use df.query to get a subset of df1 based on ids in df2
-    subset = df3.head(10).query('symbol2 in @df2.symbol2')
+    subset = df3.head(value).query('symbol2 in @df2.symbol2')
     # Use merge to join the two DataFrames on id
     result = pd.merge(subset, df2, on='symbol2')
     # Show the result
     # print(result)
 
     df = df10
-
-    # Define the `text` column for labels and `href` column for links
-    df['text'] = df10.index
-    df['href'] = [f'https://pubmed.ncbi.nlm.nih.gov/?term={database_name}%5Bmh%5D+NOT+review%5Bpt%5D' \
+    try:
+        # Define the `text` column for labels and `href` column for links
+        df['text'] = df10.index
+        df['href'] = [f'https://pubmed.ncbi.nlm.nih.gov/?term={database_name}%5Bmh%5D+NOT+review%5Bpt%5D' \
                   '+AND+english%5Bla%5D+AND+hasabstract+AND+1990:2022%5Bdp%5D+AND+' + c for c in df10.index]
-    df['href2'] = [f'https://www.ncbi.nlm.nih.gov/gene/?term=' + c for c in df10.index]
-    df['name'] = [c for c in result['Approved name']]
-    df['database'] = database_name
-    # print(df['name'])
-
-    # Create the treemap using `px.treemap`
-    fig = px.treemap(df, path=[df10.index], values=sizes, hover_data=['SIMILARITY'],
-                     custom_data=['href', 'name', 'database', 'href2'])
-    # fig.update_traces(texttemplate="Gene: <b>%{label}</b><br>Gene "
-    #                                "name: %{customdata[1]}<br><a href='%{customdata[0]}'>PubMed Abstracts with %{label} "
-    #                                "in %{customdata[2]}</a><br><a href='%{customdata[3]}'>NCBI gene information for %{label} "
-    #                                "in %{customdata[2]}</a>")
-    fig.update(layout_coloraxis_showscale=False)
-    fig.update_layout(autosize=True, paper_bgcolor="#CCFFFF")
-    fig.update_annotations(visible=False)
-    fig.update_traces(marker=dict(cornerradius=5), root_color="#CCFFFF", hovertemplate=None,
+        df['href2'] = [f'https://www.ncbi.nlm.nih.gov/gene/?term=' + c for c in df10.index]
+
+        df['name'] = [c for c in result['Approved name']]
+
+        df['database'] = database_name
+
+        # print(df['name'])
+
+        # Create the treemap using `px.treemap`
+        fig = px.treemap(df, path=[df10.index], values=sizes,
+                     custom_data=['href', 'name', 'database', 'href2'], hover_name=(df3.head(value)['SIMILARITY']))
+
+        fig.update(layout_coloraxis_showscale=False)
+        fig.update_layout(autosize=True, paper_bgcolor="#CCFFFF", margin=dict(t=0, b=0, l=0, r=0))
+        fig.update_annotations(visible=False)
+        fig.update_traces(marker=dict(cornerradius=5), root_color="#CCFFFF", hovertemplate=None,
                       hoverlabel_bgcolor="lightblue", hoverlabel_bordercolor="#000000",
-                      texttemplate="<b>%{label}</b><br>%{customdata[1]}<br><a href='%{customdata[0]}'>PubMed"
+                      texttemplate="<b><span style='font-family: Arial; font-size: 20px;'>%{label}</span></b><br><span "
+                                   "style='font-family: Arial; font-size: 15px;'>%{customdata[1]}<br>"
+                                   "<a href='%{customdata[0]}'>PubMed"
                                    "</a><br><a href='%{customdata[3]}'>NCBI"
-                                   "</a>")
-    fig.update_layout(uniformtext=dict(minsize=10, mode='hide'), treemapcolorway=["lightblue"])
-    # # display the treemap in Streamlit
-    # with treemap2:
-    st.subheader(f"Top 10 Genes closely related to {query}")
+                                   "</span></a>")
+        fig.update_layout(uniformtext=dict(minsize=15), treemapcolorway=["lightblue"])
+        # # display the treemap in Streamlit
+        # with treemap2:
+
         # st.pyplot(fig2)
-    st.plotly_chart(fig, use_container_width=True)
+        st.plotly_chart(fig, use_container_width=True)
+
+        st.caption("Gene designation and database provided by HUGO Gene Nomenclature Committee (HGNC): https://www.genenames.org/")
+        st.caption("Gene designation add in exceptions [p21, p53, her2, her3]")
+
 
-    csv = df1.head(100).to_csv().encode('utf-8')
-    st.download_button(label="download top 100 genes (csv)", data=csv, file_name=f'{database_name}_genes.csv',
+
+        csv = df1.head(value).to_csv().encode('utf-8')
+        st.download_button(label=f"download top {value} genes (csv)", data=csv, file_name=f'{database_name}_genes.csv',
                        mime='text/csv')
+    except:
+        st.warning(
+            f"This selection exceeds the number of similar genes related to {query} within the {database_name} corpus")
     st.markdown("---")
     st.subheader("Cancer-related videos")
     if query: