Update app.py

app.py

@@ -10,11 +10,10 @@ import matplotlib.pyplot as plt
 import seaborn as sns
 import logging
 import re
-from io import BytesIO
-from typing import Optional, Dict, List
+from typing import Optional, Dict, List, Any
 from openai import OpenAI
 
-# Configure comprehensive logging for traceability and diagnostics
+# Configure advanced logging for full traceability and diagnostics
 logging.basicConfig(
     level=logging.INFO,
     format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
@@ -23,15 +22,17 @@ logging.basicConfig(
 logger = logging.getLogger("PRIS")
 
 # -----------------------------
-# GLOBAL CONSTANTS & ENDPOINTS
+# GLOBAL CONSTANTS
 # -----------------------------
 API_ENDPOINTS = {
     "clinical_trials": "https://clinicaltrials.gov/api/v2/studies",
     "fda_drug_approval": "https://api.fda.gov/drug/label.json",
-    "pubchem": "https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/name/{}/JSON"
+    "pubchem": "https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/name/{}/JSON",
+    # ... other endpoints omitted for brevity ...
 }
+
 DEFAULT_HEADERS = {
-    "User-Agent": "PharmaResearchIntelligenceSuite/2.0 (Advanced Research)",
+    "User-Agent": "PharmaResearchIntelligenceSuite/1.0 (Professional Use)",
     "Accept": "application/json"
 }
 
@@ -39,6 +40,7 @@ DEFAULT_HEADERS = {
 # SECRETS MANAGEMENT
 # -----------------------------
 class APIConfigurationError(Exception):
+    """Custom exception for missing API configurations."""
     pass
 
 try:
@@ -46,6 +48,7 @@ try:
     BIOPORTAL_API_KEY = st.secrets["BIOPORTAL_API_KEY"]
     PUB_EMAIL = st.secrets["PUB_EMAIL"]
     OPENFDA_KEY = st.secrets["OPENFDA_KEY"]
+    
     if not all([OPENAI_API_KEY, BIOPORTAL_API_KEY, PUB_EMAIL, OPENFDA_KEY]):
         raise APIConfigurationError("One or more required API credentials are missing.")
 except (KeyError, APIConfigurationError) as e:
@@ -56,16 +59,26 @@ except (KeyError, APIConfigurationError) as e:
 # CORE INFRASTRUCTURE
 # -----------------------------
 class PharmaResearchEngine:
-    """Core engine for data integration and advanced analysis in pharma research."""
+    """Core engine for integrating diverse pharmaceutical datasets and performing advanced analyses."""
+    
     def __init__(self):
         self.openai_client = OpenAI(api_key=OPENAI_API_KEY)
-    
+        
     @staticmethod
-    def api_request(endpoint: str, params: Optional[Dict] = None, headers: Optional[Dict] = None) -> Optional[Dict]:
-        """Robust API request handler with detailed logging and user feedback."""
+    def api_request(endpoint: str, 
+                    params: Optional[Dict] = None,
+                    headers: Optional[Dict] = None) -> Optional[Dict]:
+        """
+        Enterprise-grade API request handler with detailed error logging.
+        """
         try:
-            response = requests.get(endpoint, params=params, headers={**DEFAULT_HEADERS, **(headers or {})}, timeout=(3.05, 15))
-            response.raise_for_status()
+            response = requests.get(
+                endpoint,
+                params=params,
+                headers={**DEFAULT_HEADERS, **(headers or {})},
+                timeout=(3.05, 15)
+            )
+            response.raise_for_status()  # Raises HTTPError for 4xx/5xx responses
             return response.json()
         except requests.exceptions.HTTPError as e:
             logger.error(f"HTTP Error {e.response.status_code} for {endpoint} with params {params}")
@@ -77,49 +90,34 @@ class PharmaResearchEngine:
 
     def get_compound_profile(self, identifier: str) -> Optional[Dict]:
         """
-        Retrieve comprehensive chemical profile from PubChem.
-        Uses advanced input validation and fallback mechanisms.
+        Retrieve comprehensive chemical profile data from PubChem for a given compound.
+        Accepts both common compound names and SMILES strings.
         """
         if not self._is_valid_compound_input(identifier):
-            msg = (f"Input '{identifier}' does not appear to be a valid compound name or SMILES. "
-                   "If you are seeking disease-related information, please try the Clinical Trial Analytics module.")
+            msg = (f"The input '{identifier}' appears to reference a disease term rather than a chemical compound. "
+                   "For disease-related inquiries, please use the Clinical Trial Analytics module.")
             logger.warning(msg)
             st.error(msg)
             return None
-        
+
         pubchem_url = API_ENDPOINTS["pubchem"].format(identifier)
         pubchem_data = self.api_request(pubchem_url)
         if not pubchem_data or not pubchem_data.get("PC_Compounds"):
-            msg = f"No compound data returned for '{identifier}'. Please verify your input."
-            logger.warning(msg)
-            st.error(msg)
+            logger.warning(f"No compound data returned for identifier: {identifier}")
+            st.error("No compound data found. Please verify your input (e.g., check for typos or use a recognized compound name).")
             return None
-
+            
         compound = pubchem_data["PC_Compounds"][0]
-        profile = {
+        return {
             'molecular_formula': self._extract_property(compound, 'Molecular Formula'),
             'iupac_name': self._extract_property(compound, 'IUPAC Name'),
             'canonical_smiles': self._extract_property(compound, 'Canonical SMILES'),
             'molecular_weight': self._extract_property(compound, 'Molecular Weight'),
             'logp': self._extract_property(compound, 'LogP')
         }
-        # Validate that we have a plausible SMILES; if not, attempt a fallback search
-        if profile['canonical_smiles'] in ["N/A", ""]:
-            logger.warning("Canonical SMILES is missing, attempting fallback retrieval.")
-            profile['canonical_smiles'] = self._fallback_smiles(compound)
-        return profile
-
-    def _fallback_smiles(self, compound: Dict) -> str:
-        """Fallback routine to extract a valid SMILES string from alternative PubChem data fields."""
-        # Sometimes the data may be nested in a different property.
-        for prop in compound.get("props", []):
-            val = prop.get("value", {}).get("sval")
-            if val and any(char in val for char in "CNOPS"):
-                return val
-        return "N/A"
 
     def _extract_property(self, compound: Dict, prop_name: str) -> str:
-        """Helper to extract a property value from PubChem compound data."""
+        """Helper to extract a specific property from PubChem compound data."""
         for prop in compound.get("props", []):
             if prop.get("urn", {}).get("label") == prop_name:
                 return prop["value"].get("sval", "N/A")
@@ -128,25 +126,35 @@ class PharmaResearchEngine:
     @staticmethod
     def _is_valid_compound_input(user_input: str) -> bool:
         """
-        Use regex and keyword heuristics to check if input is a valid compound name or SMILES.
-        Reject common disease terms.
+        Determines whether the user input is a valid chemical compound identifier.
+        Accepts both conventional compound names and SMILES strings.
+        Rejects inputs containing known disease terms.
         """
-        # Check for a valid SMILES-like string (simple heuristic)
-        smiles_pattern = re.compile(r'^[BCNOFPSIbcnofpsi0-9@+\-\[\]\(\)=#$]+$')
-        if smiles_pattern.fullmatch(user_input.strip()):
-            return True
-        # Block disease terms
+        input_lower = user_input.lower().strip()
+        # Known disease terms that should not be processed as compounds
         disease_terms = ['diabetes', 'cancer', 'hypertension', 'asthma']
-        if any(term in user_input.lower() for term in disease_terms):
+        if any(term in input_lower for term in disease_terms):
             return False
-        # Assume other alphabetic strings may be valid chemical names
-        return True
+        
+        # If the input contains characters common in SMILES (e.g., '=', '(', ')', '#'), treat as SMILES.
+        if re.search(r"[=\(\)#]", user_input):
+            return True
+        
+        # Otherwise, if input is alphanumeric with spaces or hyphens, assume it's a valid compound name.
+        if re.match(r'^[A-Za-z0-9\s\-]+$', user_input):
+            return True
+        
+        return False
 
 # -----------------------------
 # INTELLIGENCE MODULES
 # -----------------------------
 class ClinicalIntelligence:
-    """Module for clinical trial and regulatory intelligence."""
+    """
+    Module for clinical trial and regulatory intelligence.
+    Provides deep insights into trial landscapes and FDA approval data.
+    """
+    
     def __init__(self):
         self.engine = PharmaResearchEngine()
     
@@ -154,9 +162,8 @@ class ClinicalIntelligence:
         params = {"query.term": query, "retmax": 10} if not query.startswith("NCT") else {"id": query}
         trials = self.engine.api_request(API_ENDPOINTS["clinical_trials"], params=params)
         if trials is None:
-            msg = f"Clinical trial data could not be retrieved for '{query}'."
-            logger.error(msg)
-            st.error(msg)
+            logger.error(f"Clinical trial API returned no data for query: {query}")
+            st.error("Failed to retrieve clinical trials. Please try a different query or check your network connection.")
             return []
         return trials.get("studies", [])[:5]
 
@@ -164,6 +171,7 @@ class ClinicalIntelligence:
         if not OPENFDA_KEY:
             st.error("OpenFDA API key not configured.")
             return None
+        
         params = {
             "api_key": OPENFDA_KEY,
             "search": f'openfda.brand_name:"{drug_name}"',
@@ -172,54 +180,53 @@ class ClinicalIntelligence:
         data = self.engine.api_request(API_ENDPOINTS["fda_drug_approval"], params=params)
         if data and data.get("results"):
             return data["results"][0]
-        logger.warning(f"No FDA data found for '{drug_name}'.")
+        logger.warning(f"No FDA data found for drug: {drug_name}")
         st.error("No FDA regulatory data found for the specified drug.")
         return None
 
 class AIDrugInnovator:
-    """GPT-4 powered module for generating cutting-edge drug development strategies."""
+    """
+    GPT-4 powered module for generating advanced, cutting-edge drug development strategies.
+    """
+    
     def __init__(self):
         self.engine = PharmaResearchEngine()
-    
+        
     def generate_strategy(self, target: str, strategy: str) -> str:
-        prompt = f"""# First-In-Class Strategy for {target.capitalize()}
+        prompt = f"""As the Chief Scientific Officer at a leading pharmaceutical company, please develop a {strategy} strategy for the target: {target}.
         
 **Target Validation Approach**  
-Our target validation will involve:
-- A comprehensive literature review to understand disease pathophysiology.
-- Pre-clinical in vitro and in vivo studies to validate target functionality.
-- Genomic and proteomic analyses to confirm the role of the target.
-- Collaborative efforts with leading academic and clinical research institutions.
+- Perform an exhaustive literature review to understand the molecular basis of the disease.  
+- Validate targets using in vitro and in vivo models.  
+- Integrate genomic and proteomic data to identify actionable targets.  
+- Collaborate with top-tier academic and clinical institutions.
 
 **Lead Optimization Tactics**  
-Post validation, we will:
-- Employ chemical modification and high-throughput screening to optimize lead compounds.
-- Run extensive biological assays to fine-tune efficacy and safety.
-- Utilize in vivo studies to assess pharmacokinetics and toxicity.
-- Regularly review patent landscapes to ensure novelty.
+- Conduct chemical optimization to improve potency, selectivity, and pharmacokinetic properties.  
+- Utilize high-throughput screening and biological assays for iterative lead refinement.  
+- Perform rigorous in vivo efficacy and safety evaluations.  
+- Secure intellectual property through comprehensive patent landscaping.
 
 **Clinical Trial Design**  
-Our patient-centric clinical trial phases will include:
-- **Phase I:** Safety and dosage optimization.
-- **Phase II:** Efficacy and side-effect profiling.
-- **Phase III:** Large-scale comparative trials.
-- **Phase IV:** Post-marketing surveillance for long-term outcomes.  
-We may also incorporate adaptive trial designs to expedite development.
+- Initiate Phase I trials focused on safety and dosage determination.  
+- Scale to Phase II for efficacy and side-effect profiling in a broader patient cohort.  
+- Execute large-scale Phase III trials to validate clinical benefits against current standards of care.  
+- Plan for Phase IV post-marketing surveillance for long-term outcome assessment.  
+- Incorporate adaptive trial designs to enhance responsiveness and efficiency.
 
 **Regulatory Pathway Analysis**  
-Key regulatory steps:
-- Early pre-IND consultations with regulatory agencies.
-- Compilation of robust pre-clinical data for IND submission.
-- Continuous dialogue with regulators during clinical phases.
-- Exploring expedited pathways like Fast Track or Breakthrough Therapy designations.
+- Engage in early pre-IND consultations with regulatory authorities.  
+- Prepare robust IND submissions incorporating comprehensive preclinical data.  
+- Maintain continuous dialogue with regulators throughout clinical development.  
+- Strategize for expedited review pathways (e.g., Fast Track, Breakthrough Therapy).
 
 **Commercial Potential Assessment**  
-We will conduct:
-- In-depth market research to understand competitive landscapes.
-- Patient segmentation analyses to tailor our therapy.
-- Pricing, reimbursement, and go-to-market strategy development to maximize impact.
+- Conduct detailed market research to understand the competitive landscape and unmet needs.  
+- Segment patient populations to tailor therapeutic approaches.  
+- Devise dynamic pricing and reimbursement strategies aligned with payer requirements.  
+- Formulate a comprehensive go-to-market plan leveraging multi-channel marketing strategies.
 
-Please note: This strategy is generated by an AI system leveraging state-of-the-art insights and is intended to support, not replace, expert human judgment."""
+Please format your response in Markdown with clear section headers."""
         try:
             response = self.engine.openai_client.chat.completions.create(
                 model="gpt-4",
@@ -237,7 +244,11 @@ Please note: This strategy is generated by an AI system leveraging state-of-the-
 # STREAMLIT INTERFACE
 # -----------------------------
 class PharmaResearchInterface:
-    """Next-generation Streamlit interface for PRIS with enhanced UI/UX."""
+    """
+    Next-generation Streamlit interface for the Pharma Research Intelligence Suite.
+    Provides an integrated, intuitive dashboard for advanced pharmaceutical data analytics and AI-driven strategy generation.
+    """
+    
     def __init__(self):
         self.clinical_intel = ClinicalIntelligence()
         self.ai_innovator = AIDrugInnovator()
@@ -251,15 +262,16 @@ class PharmaResearchInterface:
         )
         st.markdown("""
             <style>
-            .main {background-color: #f0f2f6; font-family: 'Helvetica Neue', Arial, sans-serif;}
-            .stAlert {padding: 20px; font-size: 1.1em;}
+            .main {background-color: #f0f2f6;}
+            .stAlert {padding: 20px;}
+            .reportview-container .markdown-text-container {font-family: 'Helvetica Neue', Arial, sans-serif}
             </style>
             """, unsafe_allow_html=True)
 
     def render(self):
         st.title("Next-Generation Pharmaceutical Research Intelligence Suite")
         self._render_navigation()
-
+        
     def _render_navigation(self):
         tabs = st.tabs([
             "🚀 Drug Innovation",
@@ -325,7 +337,7 @@ class PharmaResearchInterface:
 
     def _compound_profiler(self):
         st.header("Advanced Multi-Omics Compound Profiler")
-        compound = st.text_input("Analyze Compound:", placeholder="Enter drug name or SMILES (e.g., Aspirin, C1=CC=CC=C1O)")
+        compound = st.text_input("Analyze Compound:", placeholder="Enter drug name or SMILES (e.g., Aspirin, CC(=O)OC1=CC=CC=C1C(=O)O)")
         if st.button("Profile Compound"):
             with st.spinner("Decoding molecular profile..."):
                 profile = PharmaResearchEngine().get_compound_profile(compound)
@@ -334,30 +346,20 @@ class PharmaResearchInterface:
                     with col1:
                         st.subheader("Structural Insights")
                         smiles = profile.get('canonical_smiles', '')
-                        if smiles != "N/A":
-                            try:
-                                mol = Chem.MolFromSmiles(smiles)
-                                if mol:
-                                    # Convert RDKit image to a stream for better handling
-                                    img = Draw.MolToImage(mol, size=(400, 300))
-                                    buf = BytesIO()
-                                    img.save(buf, format="PNG")
-                                    st.image(buf.getvalue(), caption="2D Molecular Structure")
-                                else:
-                                    st.error("Generated SMILES appears invalid. Please verify the compound input.")
-                            except Exception as ex:
-                                logger.error(f"Error generating molecular image: {ex}")
-                                st.error("Error generating molecular structure image. Verify the SMILES string.")
+                        mol = Chem.MolFromSmiles(smiles) if smiles != "N/A" else None
+                        if mol:
+                            img = Draw.MolToImage(mol, size=(400, 300))
+                            st.image(img, caption="2D Molecular Structure")
                         else:
-                            st.error("No valid SMILES available. The compound profile may be incomplete.")
+                            st.error("Could not generate molecular structure image. Verify the SMILES string or compound name.")
                     with col2:
                         st.subheader("Physicochemical Profile")
-                        st.metric("Molecular Weight", profile.get('molecular_weight', 'N/A'))
-                        st.metric("LogP", profile.get('logp', 'N/A'))
-                        st.metric("IUPAC Name", profile.get('iupac_name', 'N/A'))
+                        st.metric("Molecular Weight", profile.get('molecular_weight', "N/A"))
+                        st.metric("LogP", profile.get('logp', "N/A"))
+                        st.metric("IUPAC Name", profile.get('iupac_name', "N/A"))
                         st.code(f"SMILES: {profile.get('canonical_smiles', 'N/A')}")
                 else:
-                    st.warning("Compound profiling failed. Ensure that you have entered a valid chemical compound.")
+                    st.warning("Compound profiling failed. Please ensure you have entered a valid chemical compound.")
 
     def _regulatory_hub(self):
         st.header("Regulatory Intelligence Hub")
@@ -375,7 +377,7 @@ class PharmaResearchInterface:
     def _ai_strategist(self):
         st.header("AI Drug Development Strategist")
         st.write("Leverage GPT-4 to generate cutting-edge drug development strategies.")
-        target = st.text_input("Enter Target Disease or Pathway:", placeholder="e.g., Diabetics")
+        target = st.text_input("Enter Target Disease or Pathway:", placeholder="e.g., KRAS G12C mutation")
         if st.button("Generate AI Strategy"):
             with st.spinner("Generating AI-driven strategy..."):
                 strategy = self.ai_innovator.generate_strategy(target, "First-in-class")