Update app.py

app.py

@@ -8,13 +8,9 @@ from rdkit.Chem import Draw
 import pandas as pd
 import matplotlib.pyplot as plt
 import seaborn as sns
-from fpdf import FPDF
-import tempfile
 import logging
-import os
-import plotly.graph_objects as go
-import networkx as nx
-from typing import Optional, Dict, List, Any, Tuple
+import re
+from typing import Optional, Dict, List, Any
 from openai import OpenAI
 
 # Configure advanced logging for full traceability and diagnostics
@@ -29,27 +25,10 @@ logger = logging.getLogger("PRIS")
 # GLOBAL CONSTANTS
 # -----------------------------
 API_ENDPOINTS = {
-    # Clinical Data Services
     "clinical_trials": "https://clinicaltrials.gov/api/v2/studies",
     "fda_drug_approval": "https://api.fda.gov/drug/label.json",
-    "faers_adverse_events": "https://api.fda.gov/drug/event.json",
-    
-    # Chemical & Biological Data
     "pubchem": "https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/name/{}/JSON",
-    "pubmed": "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi",
-    
-    # Pharmacogenomics Resources
-    "pharmgkb_variant_clinical_annotations": "https://api.pharmgkb.org/v1/data/variant/{}/clinicalAnnotations",
-    "pharmgkb_gene": "https://api.pharmgkb.org/v1/data/gene/{}",
-    "pharmgkb_gene_variants": "https://api.pharmgkb.org/v1/data/gene/{}/variants",
-    
-    # Semantic Medical Resources
-    "bioportal_search": "https://data.bioontology.org/search",
-    
-    # Drug Classification Systems
-    "rxnorm_rxcui": "https://rxnav.nlm.nih.gov/REST/rxcui.json",
-    "rxnorm_properties": "https://rxnav.nlm.nih.gov/REST/rxcui/{}/properties.json",
-    "rxclass_by_drug": "https://rxnav.nlm.nih.gov/REST/class/byDrugName.json"
+    # ... other endpoints omitted for brevity ...
 }
 
 DEFAULT_HEADERS = {
@@ -61,7 +40,7 @@ DEFAULT_HEADERS = {
 # SECRETS MANAGEMENT
 # -----------------------------
 class APIConfigurationError(Exception):
-    """Custom exception for missing API configurations in pharma research workflows."""
+    """Custom exception for missing API configurations."""
     pass
 
 try:
@@ -70,10 +49,8 @@ try:
     PUB_EMAIL = st.secrets["PUB_EMAIL"]
     OPENFDA_KEY = st.secrets["OPENFDA_KEY"]
     
-    # Validate that all essential API credentials are configured
     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:
     st.error(f"Critical configuration error: {str(e)}")
     st.stop()
@@ -82,7 +59,7 @@ except (KeyError, APIConfigurationError) as e:
 # CORE INFRASTRUCTURE
 # -----------------------------
 class PharmaResearchEngine:
-    """Core engine for integrating diverse pharmaceutical datasets and performing advanced analysis."""
+    """Core engine for data integration and advanced analysis."""
     
     def __init__(self):
         self.openai_client = OpenAI(api_key=OPENAI_API_KEY)
@@ -91,10 +68,7 @@ class PharmaResearchEngine:
     def api_request(endpoint: str, 
                     params: Optional[Dict] = None,
                     headers: Optional[Dict] = None) -> Optional[Dict]:
-        """
-        Enterprise-grade API request handler designed for robust and reproducible data acquisition.
-        Implements detailed error logging and user-friendly messaging.
-        """
+        """Robust API request handler with detailed error logging."""
         try:
             response = requests.get(
                 endpoint,
@@ -102,7 +76,7 @@ class PharmaResearchEngine:
                 headers={**DEFAULT_HEADERS, **(headers or {})},
                 timeout=(3.05, 15)
             )
-            response.raise_for_status()  # Raises HTTPError for bad responses (4xx, 5xx)
+            response.raise_for_status()
             return response.json()
         except requests.exceptions.HTTPError as e:
             logger.error(f"HTTP Error {e.response.status_code} for {endpoint} with params {params}")
@@ -113,15 +87,20 @@ class PharmaResearchEngine:
         return None
 
     def get_compound_profile(self, identifier: str) -> Optional[Dict]:
-        """
-        Retrieve a comprehensive chemical profile from PubChem for a given compound identifier.
-        Returns key molecular descriptors and structural data.
-        """
-        pubchem_data = self.api_request(API_ENDPOINTS["pubchem"].format(identifier))
+        """Retrieve comprehensive chemical profile data from PubChem."""
+        # Validate input using heuristic: check if input appears to be a compound or a disease
+        if not self._is_valid_compound_input(identifier):
+            msg = (f"The input '{identifier}' does not appear to be a valid chemical compound name or SMILES string. "
+                   "If you are searching for disease-related data, 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"):
             logger.warning(f"No compound data returned for identifier: {identifier}")
-            st.error("No compound data found. Please verify the input (e.g., drug name or SMILES).")
+            st.error("No compound data found. Please verify your input (e.g., check if it's a valid drug name or SMILES).")
             return None
             
         compound = pubchem_data["PC_Compounds"][0]
@@ -134,45 +113,50 @@ class PharmaResearchEngine:
         }
 
     def _extract_property(self, compound: Dict, prop_name: str) -> str:
-        """Helper function to extract a specified property from the PubChem compound data."""
+        """Helper function to extract a specified property from PubChem data."""
         for prop in compound.get("props", []):
             if prop.get("urn", {}).get("label") == prop_name:
                 return prop["value"].get("sval", "N/A")
         return "N/A"
 
+    @staticmethod
+    def _is_valid_compound_input(user_input: str) -> bool:
+        """
+        Basic heuristic to check if the user input is likely to be a compound.
+        Checks for presence of alphabetic chemical names or a valid SMILES pattern.
+        """
+        # A simplistic SMILES check: valid SMILES usually contain characters like "C", "O", "N", "=", "#", etc.
+        smiles_pattern = re.compile(r'^[BCNOFPSIbcnofpsi0-9@+\-\[\]\(\)=#$]+$')
+        if smiles_pattern.match(user_input.strip()):
+            return True
+        
+        # Alternatively, check if the input contains common compound words and is not a disease name.
+        disease_terms = ['diabetes', 'cancer', 'hypertension', 'asthma']
+        if any(term in user_input.lower() for term in disease_terms):
+            return False
+        
+        # Otherwise, assume a valid chemical name (could be improved with a dictionary lookup)
+        return True
+
 # -----------------------------
 # INTELLIGENCE MODULES
 # -----------------------------
 class ClinicalIntelligence:
-    """
-    Module for the analysis of clinical trial data and regulatory intelligence.
-    Provides real-time insights into trial landscapes and FDA approval statuses.
-    """
+    """Module for clinical trial and regulatory intelligence."""
     
     def __init__(self):
         self.engine = PharmaResearchEngine()
     
     def get_trial_landscape(self, query: str) -> List[Dict]:
-        """
-        Analyze the clinical trial landscape based on a user-defined query.
-        Returns a curated list of high-impact trials or an empty list if an error occurs.
-        """
         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:
             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 []
-        
-        # Safely extract studies, defaulting to an empty list if key is missing
         return trials.get("studies", [])[:5]
 
     def get_fda_approval(self, drug_name: str) -> Optional[Dict]:
-        """
-        Retrieve FDA approval information for a specified drug.
-        Integrates openFDA data to provide comprehensive regulatory insights.
-        """
         if not OPENFDA_KEY:
             st.error("OpenFDA API key not configured.")
             return None
@@ -182,29 +166,20 @@ class ClinicalIntelligence:
             "search": f'openfda.brand_name:"{drug_name}"',
             "limit": 1
         }
-        
         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 approval data found for drug: {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 strategic module for drug development.
-    Leverages advanced natural language processing to formulate comprehensive R&D blueprints.
-    """
+    """GPT-4 powered module for AI-driven drug development strategy."""
     
     def __init__(self):
         self.engine = PharmaResearchEngine()
         
     def generate_strategy(self, target: str, strategy: str) -> str:
-        """
-        Generate an AI-driven drug development strategy.
-        The output includes target validation, lead optimization, clinical trial design, regulatory analysis, and market assessment.
-        """
         prompt = f"""As the Chief Scientific Officer at a leading pharmaceutical company, please develop a {strategy} strategy for the target: {target}.
 Include the following sections:
 - **Target Validation Approach**
@@ -214,7 +189,6 @@ Include the following sections:
 - **Commercial Potential Assessment**
 
 Format your response in Markdown with clear and concise sections."""
-        
         try:
             response = self.engine.openai_client.chat.completions.create(
                 model="gpt-4",
@@ -232,10 +206,7 @@ Format your response in Markdown with clear and concise sections."""
 # STREAMLIT INTERFACE
 # -----------------------------
 class PharmaResearchInterface:
-    """
-    User interface for PRIS built with Streamlit.
-    Provides researchers with an intuitive dashboard for accessing multi-modal pharmaceutical data and AI-driven insights.
-    """
+    """Next-generation Streamlit interface for PRIS."""
     
     def __init__(self):
         self.clinical_intel = ClinicalIntelligence()
@@ -243,27 +214,24 @@ class PharmaResearchInterface:
         self._configure_page()
 
     def _configure_page(self):
-        """Setup the Streamlit page configuration with a focus on clarity and ease-of-use."""
         st.set_page_config(
-            page_title="PRIS - Pharmaceutical Research Intelligence Suite",
+            page_title="PRIS - Next-Generation Pharmaceutical Research Suite",
             layout="wide",
             initial_sidebar_state="expanded"
         )
         st.markdown("""
             <style>
-            .main {background-color: #f9f9f9;}
+            .main {background-color: #f0f2f6;}
             .stAlert {padding: 20px;}
-            .reportview-container .markdown-text-container {font-family: 'Arial'}
+            .reportview-container .markdown-text-container {font-family: 'Helvetica Neue', Arial, sans-serif}
             </style>
             """, unsafe_allow_html=True)
 
     def render(self):
-        """Render the main application interface."""
-        st.title("Pharmaceutical Research Intelligence Suite")
+        st.title("Next-Generation Pharmaceutical Research Intelligence Suite")
         self._render_navigation()
         
     def _render_navigation(self):
-        """Dynamic tab-based navigation to access different research modules."""
         tabs = st.tabs([
             "🚀 Drug Innovation",
             "📈 Trial Analytics",
@@ -271,7 +239,6 @@ class PharmaResearchInterface:
             "📜 Regulatory Hub",
             "🤖 AI Strategist"
         ])
-        
         with tabs[0]:
             self._drug_innovation()
         with tabs[1]:
@@ -284,33 +251,27 @@ class PharmaResearchInterface:
             self._ai_strategist()
 
     def _drug_innovation(self):
-        """Interface for AI-driven drug development strategies."""
         st.header("AI-Powered Drug Innovation Engine")
         col1, col2 = st.columns([1, 3])
-        
         with col1:
             target = st.text_input("Target Pathobiology:", placeholder="e.g., EGFR mutant NSCLC")
             strategy = st.selectbox("Development Paradigm:", 
-                                  ["First-in-class", "Fast-follower", "Biologic", "ADC", "Gene Therapy"])
+                                     ["First-in-class", "Fast-follower", "Biologic", "ADC", "Gene Therapy"])
             if st.button("Generate Development Blueprint"):
                 with st.spinner("Formulating strategic plan..."):
                     blueprint = self.ai_innovator.generate_strategy(target, strategy)
                     st.markdown(blueprint, unsafe_allow_html=True)
 
     def _trial_analytics(self):
-        """Interface for clinical trial landscape analytics."""
         st.header("Clinical Trial Landscape Analysis")
         trial_query = st.text_input("Search Clinical Trials:", placeholder="Enter condition, intervention, or NCT number")
-        
         if st.button("Analyze Trial Landscape"):
             with st.spinner("Fetching trial data..."):
                 trials = self.clinical_intel.get_trial_landscape(trial_query)
-                
                 if trials:
                     st.subheader("Top 5 Clinical Trials")
                     trial_data = []
                     for study in trials:
-                        # Use .get() safely and log missing keys if necessary
                         title = study.get("protocolSection", {}).get("identificationModule", {}).get("briefTitle", "N/A")
                         status = study.get("protocolSection", {}).get("statusModule", {}).get("overallStatus", "N/A")
                         phase = study.get("protocolSection", {}).get("designModule", {}).get("phases", ["N/A"])[0]
@@ -321,12 +282,8 @@ class PharmaResearchInterface:
                             "Phase": phase,
                             "Enrollment": enrollment
                         })
-                    
-                    # Display as a DataFrame
                     df = pd.DataFrame(trial_data)
                     st.dataframe(df)
-                    
-                    # Visualization: Trial Phase Distribution
                     st.subheader("Trial Phase Distribution")
                     phase_counts = df["Phase"].value_counts()
                     fig, ax = plt.subplots()
@@ -338,40 +295,34 @@ class PharmaResearchInterface:
                     st.warning("No clinical trials found for the provided query.")
 
     def _compound_profiler(self):
-        """Interface for advanced multi-omics compound profiling."""
-        st.header("Multi-Omics Compound Profiler")
-        compound = st.text_input("Analyze Compound:", placeholder="Enter drug name or SMILES")
-        
-        if compound:
+        st.header("Advanced Multi-Omics Compound Profiler")
+        compound = st.text_input("Analyze Compound:", placeholder="Enter drug name or SMILES (e.g., Metformin, C(C(=O)O)N)")
+        if st.button("Profile Compound"):
             with st.spinner("Decoding molecular profile..."):
                 profile = PharmaResearchEngine().get_compound_profile(compound)
-                
-            if profile:
-                col1, col2 = st.columns(2)
-                with col1:
-                    st.subheader("Structural Insights")
-                    mol = Chem.MolFromSmiles(profile['canonical_smiles'])
-                    if mol:
-                        img = Draw.MolToImage(mol, size=(400, 300))
-                        st.image(img, caption="2D Molecular Structure")
-                    else:
-                        st.error("Failed to generate molecular structure image. Check the SMILES string.")
-                
-                with col2:
-                    st.subheader("Physicochemical Profile")
-                    st.metric("Molecular Weight", profile['molecular_weight'])
-                    st.metric("LogP", profile['logp'])
-                    st.metric("IUPAC Name", profile['iupac_name'])
-                    st.code(f"SMILES: {profile['canonical_smiles']}")
-            else:
-                st.warning("Compound profile could not be generated. Please try again with a valid input.")
+                if profile:
+                    col1, col2 = st.columns(2)
+                    with col1:
+                        st.subheader("Structural Insights")
+                        mol = Chem.MolFromSmiles(profile['canonical_smiles'])
+                        if mol:
+                            img = Draw.MolToImage(mol, size=(400, 300))
+                            st.image(img, caption="2D Molecular Structure")
+                        else:
+                            st.error("Could not generate molecular structure image. Verify the SMILES string.")
+                    with col2:
+                        st.subheader("Physicochemical Profile")
+                        st.metric("Molecular Weight", profile['molecular_weight'])
+                        st.metric("LogP", profile['logp'])
+                        st.metric("IUPAC Name", profile['iupac_name'])
+                        st.code(f"SMILES: {profile['canonical_smiles']}")
+                else:
+                    st.warning("Compound profiling failed. Ensure that you have entered a valid chemical compound.")
 
     def _regulatory_hub(self):
-        """Interface for accessing regulatory intelligence and FDA approval data."""
         st.header("Regulatory Intelligence Hub")
-        st.write("This section provides insights into FDA approvals and regulatory pathways.")
-        drug_name = st.text_input("Enter Drug Name for Regulatory Analysis:", placeholder="e.g., aspirin")
-        
+        st.write("Gain insights into FDA approvals and regulatory pathways.")
+        drug_name = st.text_input("Enter Drug Name for Regulatory Analysis:", placeholder="e.g., Aspirin")
         if st.button("Fetch Regulatory Data"):
             with st.spinner("Retrieving regulatory information..."):
                 fda_data = self.clinical_intel.get_fda_approval(drug_name)
@@ -382,11 +333,9 @@ class PharmaResearchInterface:
                     st.warning("No FDA regulatory data found for the specified drug.")
 
     def _ai_strategist(self):
-        """Interface for AI-driven strategic drug development."""
         st.header("AI Drug Development Strategist")
-        st.write("Leverage GPT-4 to generate innovative drug development strategies.")
+        st.write("Leverage GPT-4 to generate cutting-edge drug development strategies.")
         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")