Update app.py

app.py

@@ -67,18 +67,18 @@ st.markdown("""
 st.header(":red[*O*]nco:red[*D*]igger")
 
 st.subheader(
-    "*A web app designed to explore :red[*PubMed abstracts*] for deeper understanding and fresh insights, driven "
-    "by Machine Learning and Natural Language Processing (NLP) algorithms.*")
+    "A web app designed to explore massive amounts of :red[*PubMed abstracts*] for a deeper understanding of your research. Results are driven "
+    "by Machine Learning and Natural Language Processing algorithms, which allow you to scan and mine information from hundreds of thousands of abstracts in seconds.")
 
 
 def custom_subheader(text, identifier, font_size):
     st.markdown(f"<h3 id='{identifier}' style='font-size: {font_size}px;'>{text}</h3>", unsafe_allow_html=True)
 
 
-custom_subheader("To begin, simply select a corpus from the left sidebar and enter a keyword "
+custom_subheader("To begin, simply select a cancer corpus from the left sidebar and enter a keyword "
                  "you wish to explore within the corpus. OncoDigger will determine the top words, "
                  "genes, drugs, phytochemicals, and compounds that are contextually and semantically related "
-                 "to your input. Dive in and enjoy the exploration!",
+                 "to your input, both directly and indirectly. Dive in and enjoy the exploration!",
                  "unique-id", 18)
 
 st.markdown("---")
@@ -117,10 +117,6 @@ if opt == "Lung Cancer corpus":
     model_used = ("lung_cancer_pubmed_model")
     num_abstracts = 143886
     database_name = "Lung_cancer"
-if opt == "Breast Cancer corpus":
-    model_used = ("pubmed_model_breast_cancer2")
-    num_abstracts = 204381
-    database_name = "Breast_cancer"
 if opt == "Colorectal Cancer corpus":
     model_used = ("colorectal_cancer_pubmed_model")
     num_abstracts = 140000
@@ -164,6 +160,11 @@ if query:
         # print(model.wv.similar_by_word('bfgf', topn=50, restrict_vocab=None))
         df = pd.DataFrame(X)
 
+        if 'melanin' in model.wv.key_to_index:
+            print("The term 'melanin' is present in the model.")
+        else:
+            print("The term 'melanin' is not present in the model.")
+
         def get_compound_ids(compound_names):
             with concurrent.futures.ThreadPoolExecutor() as executor:
                 compound_ids = list(executor.map(get_compound_id, compound_names))