Update app.py

app.py

@@ -13,10 +13,10 @@ import urllib.request
 import random
 import plotly.express as px
 
-st.set_page_config(page_title="Abstractalytics", page_icon=":microscope:", layout="wide",  # centered
+st.set_page_config(page_title="OncoDigger", page_icon=":microscope:", layout="wide",  # centered
                    initial_sidebar_state="auto",
-                   menu_items={'About': "Abstractalytics is a Natural Language Processing (NLP) that harnesses Word2Vec to mine"
-                         " insight from pubmed abstracts. Created by Jimmie E. Fata, PhD"})
+                   menu_items={'About': "OncoDigger is a Natural Language Processing (NLP) that harnesses Word2Vec to mine"
+                         " insight from pubmed abstracts. Created by Jimmie E. Fata, PhD, fata4science@gmail.com"})
 
 # Define the HTML and CSS styles
 st.markdown("""
@@ -41,25 +41,21 @@ st.markdown("""
     </style>
     """, unsafe_allow_html=True)
 
-st.header(":red[*Abstractalytics*]")
+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 Natural Language Processing (NLP) techniques.*")
+    "by Machine Learning and Natural Language Processing (NLP) algorithms.*")
 
 
 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("Welcome to our innovative web2vec app designed to unlock the wealth of knowledge and insights hidden "
-                 "within PubMed abstracts! To begin, simply select a corpus that interests you. Next, enter a single keyword "
-                 "you wish to explore within the corpus. Abstractalytics powerful Natural Language "
-                 "Processing (NLP) algorithms will analyze the chosen corpus and present you with a list of top words, "
+custom_subheader("To begin, simply select a 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. This advanced text-mining technique enables you to explore and understand complex "
-                 "relationships, uncovering new discoveries and connections in your field of research across a massive "
-                 "amount of abstracts. Dive in and enjoy the exploration! More oncology-related corpora comming soon.",
+                 "to your input. Dive in and enjoy the exploration!",
                  "unique-id", 18)
 
 st.markdown("---")
@@ -79,7 +75,8 @@ st.markdown("---")
 #
 # # If the password is correct, show the app content
 # if authenticate(password):
-opt = st.sidebar.radio("Select a PubMed Corpus", options=('Breast Cancer corpus', 'Lung Cancer corpus', 'Prostate Cancer corpus'))
+opt = st.sidebar.radio("Select a PubMed Corpus", options=('Breast Cancer corpus', 'Lung Cancer corpus',
+                                                          'Colorectal Cancer corpus', 'Prostate Cancer corpus'))
 # if opt == "Clotting corpus":
 #     model_used = ("pubmed_model_clotting")
 #     num_abstracts = 45493
@@ -100,9 +97,13 @@ 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
+    database_name = "Colorectal_cancer"
 if opt == "Prostate Cancer corpus":
     model_used = ("prostate_cancer_pubmed_model")
-    num_abstracts = 89000
+    num_abstracts = 89782
     database_name = "Prostate_cancer"
 
 st.header(f":blue[{database_name} Pubmed corpus.]")