Update app.py

app.py

@@ -24,18 +24,24 @@ logging.basicConfig(level=logging.ERROR)
 # API Endpoints (Centralized Configuration)
 # -----------------------------
 API_ENDPOINTS = {
-    "clinical_trials": "https://clinicaltrials.gov/api/v2/studies",
+    "clinical_trials": "https://clinicaltrials.gov/api/v2/studies",  # no email needed
     "pubchem": "https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/name/{}/JSON",
     "pubmed": "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi",
     "who_drugs": "https://health-products.canada.ca/api/drug/product",
     "fda_drug_approval": "https://api.fda.gov/drug/label.json",
     "faers_adverse_events": "https://api.fda.gov/drug/event.json",
-    # PharmGKB endpoints require a PharmGKB accession (e.g., PA1234)
+    # PharmGKB endpoints: these require a PharmGKB accession (e.g., PA1234)
     "pharmgkb_variant_clinical_annotations": "https://api.pharmgkb.org/v1/data/variant/{}/clinicalAnnotations",
-    "pharmgkb_gene": "https://api.pharmgkb.org/v1/data/gene/{}",  # expects PharmGKB accession
+    "pharmgkb_gene": "https://api.pharmgkb.org/v1/data/gene/{}",
     "pharmgkb_gene_variants": "https://api.pharmgkb.org/v1/data/gene/{}/variants",
     "bioportal_search": "https://data.bioontology.org/search",
+    # DailyMed: note the base URL now uses HTTPS and version v2
     "dailymed": "https://dailymed.nlm.nih.gov/dailymed/services/v2/spls.json",
+    # RxNorm endpoints (examples)
+    "rxnorm_rxcui": "https://rxnav.nlm.nih.gov/REST/rxcui.json",
+    "rxnorm_properties": "https://rxnav.nlm.nih.gov/REST/rxcui/{}/properties.json",
+    # RxClass endpoint example
+    "rxclass_by_drug": "https://rxnav.nlm.nih.gov/REST/class/byDrugName.json"
 }
 
 # -----------------------------------
@@ -43,7 +49,7 @@ API_ENDPOINTS = {
 # -----------------------------------
 OPENAI_API_KEY = st.secrets.get("OPENAI_API_KEY")
 BIOPORTAL_API_KEY = st.secrets.get("BIOPORTAL_API_KEY")
-PUB_EMAIL = st.secrets.get("PUB_EMAIL")  # Not used in clinical trials anymore.
+PUB_EMAIL = st.secrets.get("PUB_EMAIL")
 OPENFDA_KEY = st.secrets.get("OPENFDA_KEY")
 
 if not PUB_EMAIL:
@@ -62,7 +68,7 @@ from openai import OpenAI
 client = OpenAI(api_key=OPENAI_API_KEY)
 
 def generate_content(prompt: str) -> str:
-    """Generate content using GPT-4 via the latest OpenAI SDK."""
+    """Generate content using GPT‑4 via the new OpenAI SDK."""
     try:
         completion = client.chat.completions.create(
             model="gpt-4",
@@ -99,7 +105,7 @@ def _get_pubchem_smiles(drug_name: str) -> Optional[str]:
     """Retrieves a drug's SMILES string from PubChem."""
     url = API_ENDPOINTS["pubchem"].format(drug_name)
     data = _query_api(url)
-    if data and "PC_Compounds" in data and data["PC_Compounds"]:
+    if data and "PC_Compounds" in data and len(data["PC_Compounds"]) > 0:
         for prop in data["PC_Compounds"][0].get("props", []):
             if prop.get("name") == "Canonical SMILES":
                 return prop["value"]["sval"]
@@ -120,41 +126,37 @@ def _draw_molecule(smiles: str) -> Optional[Any]:
         return None
 
 def _get_clinical_trials(query: str) -> Optional[Dict]:
-    """Queries clinicaltrials.gov with a search term.
-       Note: the email parameter has been removed as it is not required."""
-    # Try using 'term' and if that fails, try 'query.term'
-    params = {"term": query, "retmax": 10, "retmode": "json"}
-    data = _query_api(API_ENDPOINTS["clinical_trials"], params)
-    if not data:
-        # Fallback to alternative parameter name:
+    """Queries ClinicalTrials.gov using the 'query.term' parameter (no email required)."""
+    if query.upper().startswith("NCT") and query[3:].isdigit():
+        params = {"id": query, "fmt": "json"}
+    else:
         params = {"query.term": query, "retmax": 10, "retmode": "json"}
-        data = _query_api(API_ENDPOINTS["clinical_trials"], params)
-    return data
+    return _query_api(API_ENDPOINTS["clinical_trials"], params)
 
 def _get_pubmed(query: str) -> Optional[Dict]:
     """Queries PubMed using E-utilities."""
     params = {"db": "pubmed", "term": query, "retmax": 10, "retmode": "json", "email": PUB_EMAIL}
     return _query_api(API_ENDPOINTS["pubmed"], params)
 
-def _get_fda_approval(drug_name: str, api_key: Optional[str] = OPENFDA_KEY) -> Optional[Dict]:
+def _get_fda_approval(drug_name: str) -> Optional[Dict]:
     """Retrieves FDA drug label approval info."""
-    if not api_key:
+    if not OPENFDA_KEY:
         st.error("OpenFDA API key not configured.")
         return None
     query = f'openfda.brand_name:"{drug_name}"'
-    params = {"api_key": api_key, "search": query, "limit": 1}
+    params = {"api_key": OPENFDA_KEY, "search": query, "limit": 1}
     data = _query_api(API_ENDPOINTS["fda_drug_approval"], params)
     if data and data.get("results"):
         return data["results"][0]
     return None
 
-def _analyze_adverse_events(drug_name: str, api_key: Optional[str] = OPENFDA_KEY, limit: int = 5) -> Optional[Dict]:
+def _analyze_adverse_events(drug_name: str, limit: int = 5) -> Optional[Dict]:
     """Fetches adverse event reports from FAERS."""
-    if not api_key:
+    if not OPENFDA_KEY:
         st.error("OpenFDA API key not configured.")
         return None
     query = f'patient.drug.medicinalproduct:"{drug_name}"'
-    params = {"api_key": api_key, "search": query, "limit": limit}
+    params = {"api_key": OPENFDA_KEY, "search": query, "limit": limit}
     return _query_api(API_ENDPOINTS["faers_adverse_events"], params)
 
 def _get_pharmgkb_clinical_annotations(variant_id: str) -> Optional[Dict]:
@@ -169,10 +171,10 @@ def _get_pharmgkb_clinical_annotations(variant_id: str) -> Optional[Dict]:
 def _get_pharmgkb_variants_for_gene(pharmgkb_gene_id: str) -> Optional[List[str]]:
     """
     Retrieves variant IDs for a gene using its PharmGKB accession.
-    If an invalid accession is provided (not starting with "PA"), a warning is issued.
+    If the accession does not start with "PA", warn the user.
     """
     if not pharmgkb_gene_id.startswith("PA"):
-        st.warning("Please provide a valid PharmGKB accession ID for the gene (e.g., PA1234).")
+        st.warning("Please provide a valid PharmGKB accession ID (e.g., PA1234).")
         return None
     endpoint = API_ENDPOINTS["pharmgkb_gene_variants"].format(pharmgkb_gene_id)
     data = _query_api(endpoint)
@@ -182,7 +184,9 @@ def _get_pharmgkb_variants_for_gene(pharmgkb_gene_id: str) -> Optional[List[str]
     return None
 
 def get_pharmgkb_gene_data(pharmgkb_gene_id: str) -> Optional[Dict]:
-    """Retrieves PharmGKB gene data using a PharmGKB accession."""
+    """
+    Retrieves PharmGKB gene data using a PharmGKB accession.
+    """
     if not pharmgkb_gene_id.startswith("PA"):
         st.warning("Please enter a valid PharmGKB gene accession ID (e.g., PA1234).")
         return None
@@ -194,7 +198,7 @@ def get_pharmgkb_gene_data(pharmgkb_gene_id: str) -> Optional[Dict]:
     return None
 
 def scrape_ema_drug_info(drug_name: str) -> Optional[Dict]:
-    """Scrapes the EMA website for drug information using a browser-like header."""
+    """Scrapes EMA website for drug information using browser-like headers."""
     try:
         search_url = f"https://www.ema.europa.eu/en/search?text={drug_name.replace(' ', '+')}&type=Product"
         headers = {
@@ -229,7 +233,7 @@ def scrape_ema_drug_info(drug_name: str) -> Optional[Dict]:
         return None
 
 def _get_dailymed_label(drug_name: str) -> Optional[Dict]:
-    """Retrieves DailyMed label info; if URL is missing, returns None."""
+    """Retrieves DailyMed label info using the v2 API (returns JSON)."""
     try:
         params = {"drug_name": drug_name, "page": 1, "pagesize": 1}
         data = _query_api(API_ENDPOINTS["dailymed"], params)
@@ -346,18 +350,39 @@ def _create_variant_network(gene: str, variants: List[str], annotations: Dict) -
     return fig
 
 # -----------------------------
-# Streamlit App Layout and Tabs
+# New Functions: RxNorm and RxClass Integration
 # -----------------------------
-st.title("🔬 Pharma Research Expert Platform")
-st.markdown("An integrated platform for drug discovery, clinical research, and regulatory affairs.")
+def get_rxnorm_rxcui(drug_name: str) -> Optional[str]:
+    """Retrieves the RxNorm Concept Unique Identifier (RxCUI) for a drug name."""
+    url = f"{API_ENDPOINTS['rxnorm_rxcui']}?name={drug_name}"
+    data = _query_api(url)
+    if data and "idGroup" in data and data["idGroup"].get("rxnormId"):
+        return data["idGroup"]["rxnormId"][0]
+    st.warning(f"No RxCUI found for {drug_name}.")
+    return None
+
+def get_rxnorm_properties(rxcui: str) -> Optional[Dict]:
+    """Retrieves RxNorm properties for a given RxCUI."""
+    url = API_ENDPOINTS["rxnorm_properties"].format(rxcui)
+    return _query_api(url)
+
+def get_rxclass_by_drug_name(drug_name: str) -> Optional[Dict]:
+    """Retrieves RxClass information for a drug by name."""
+    url = f"{API_ENDPOINTS['rxclass_by_drug']}?drugName={drug_name}"
+    return _query_api(url)
 
+# -----------------------------
+# Streamlit App Layout and Tabs
+# -----------------------------
+# Add a new tab "🧪 Drug Data Integration" to bring together various drug APIs.
 tabs = st.tabs([
     "💊 Drug Development",
     "📊 Trial Analytics",
     "🧬 Molecular Profiling",
     "📜 Regulatory Intelligence",
     "📚 Literature Search",
-    "📈 Dashboard"
+    "📈 Dashboard",
+    "🧪 Drug Data Integration"
 ])
 
 # -----------------------------
@@ -469,7 +494,7 @@ with tabs[2]:
     if st.button("Analyze Compound"):
         with st.spinner("Querying PubChem..."):
             smiles = None
-            # If the input is already a valid SMILES string, use it; otherwise, query PubChem.
+            # If input is a valid SMILES, use it; otherwise attempt to retrieve from PubChem.
             if Chem.MolFromSmiles(compound_input):
                 smiles = compound_input
             else:
@@ -510,7 +535,7 @@ with tabs[3]:
             ema_info = scrape_ema_drug_info(drug_name)
             ema_status = ema_info.get("EMA Approval Status") if ema_info else "Not Available"
             
-            # WHO Data from Health Canada API – fallback if not found
+            # WHO Data (Health Canada API)
             who = _query_api(API_ENDPOINTS["who_drugs"], params={"name": drug_name})
             who_status = "Yes" if who else "No"
             
@@ -637,3 +662,60 @@ with tabs[5]:
     except Exception as e:
         st.error(f"Error generating network graph: {e}")
 
+# -----------------------------
+# Tab 7: Drug Data Integration
+# -----------------------------
+with tabs[6]:
+    st.header("🧪 Drug Data Integration")
+    drug_query = st.text_input("Enter Drug Name for API Integration:", placeholder="e.g., aspirin")
+    
+    if st.button("Retrieve Drug Data"):
+        with st.spinner("Fetching drug data from multiple sources..."):
+            # DailyMed – using our existing DailyMed label function
+            dailymed_label = _get_dailymed_label(drug_query)
+            if dailymed_label:
+                dm_label = dailymed_label.get("Label URL", "Not Available")
+            else:
+                dm_label = "Not Available"
+            
+            # RxNorm – Get RxCUI and then properties
+            rxnorm_id = get_rxnorm_rxcui(drug_query)
+            if rxnorm_id:
+                rx_properties = get_rxnorm_properties(rxnorm_id)
+            else:
+                rx_properties = None
+            
+            # RxClass – Get classes related to the drug
+            rxclass_data = get_rxclass_by_drug_name(drug_query)
+            
+            st.subheader("DailyMed Label")
+            st.write(f"DailyMed Label URL: {dm_label}")
+            
+            st.subheader("RxNorm Data")
+            if rxnorm_id:
+                st.write(f"RxCUI for {drug_query}: {rxnorm_id}")
+                if rx_properties:
+                    st.json(rx_properties)
+                else:
+                    st.write("No RxNorm properties found.")
+            else:
+                st.write("No RxCUI found for the given drug name.")
+            
+            st.subheader("RxClass Information")
+            if rxclass_data:
+                st.json(rxclass_data)
+            else:
+                st.write("No RxClass data found for the given drug.")
+
+# -----------------------------
+# Sidebar Information
+# -----------------------------
+st.sidebar.header("About")
+st.sidebar.info("""
+**Pharma Research Expert Platform**
+
+An integrated tool for drug discovery, clinical research, and regulatory affairs.
+
+**Developed by:** Your Name  
+**Contact:** [[email protected]](mailto:[email protected])
+""")