Update genesis/pipeline.py

genesis/pipeline.py

@@ -1,78 +1,170 @@
 # genesis/pipeline.py
 import os
+import json
+import re
 from datetime import datetime
-from typing import Dict, Any, List
+from typing import Dict, Any, List, Optional
 
-from genesis.ontology import expand_terms_with_ontology
-from genesis.structures import fetch_structures_for_terms
-from genesis.narration import narrate_text
-from genesis.graphdb import write_topic_and_papers
+# API client imports
+from genesis.api_clients.pubmed_api import search_pubmed_literature
+from genesis.api_clients.bioportal_api import expand_with_bioportal
+from genesis.api_clients.umls_api import expand_with_umls
+from genesis.api_clients.chembl_api import get_molecule_data
+from genesis.api_clients.ncbi_api import fetch_ncbi_structure
+
+# Core logic
 from genesis.providers import (
-    run_pubmed_literature,
     run_deepseek_summary,
-    run_gemini_polish,
-    run_image_generation
+    run_gemini_summary,
+    run_openai_summary,
+    run_gemini_image,
+    run_openai_image,
+    run_hf_image,
+    narrate_text_elevenlabs
 )
+from genesis.utils.pdf_export import export_report_to_pdf
+from genesis.visualization import generate_pathway_graph, generate_funding_network
+from genesis.funding import fetch_funding_data
+from genesis.trials import fetch_clinical_trials
+from genesis.biosecurity import analyze_biosecurity_risks
+from genesis.regulation import fetch_regulatory_info
+from genesis.safety import analyze_safety_concerns
+from genesis.structures import fetch_structures_for_terms
+from genesis.ontology import merge_ontology_terms
 
-UMLS_API_KEY = os.getenv("UMLS_API_KEY")
-BIOPORTAL_API_KEY = os.getenv("BIOPORTAL_API_KEY")
-NCBI_API_KEY = os.getenv("NCBI_API_KEY")
-NCBI_EMAIL = os.getenv("NCBI_EMAIL")
-NEO4J_URI = os.getenv("NEO4J_URI")
+from genesis.graph_tools import write_topic_and_papers
+
+# Environment vars
 ELEVEN_LABS_API_KEY = os.getenv("ELEVEN_LABS_API_KEY")
+NEO4J_URI = os.getenv("NEO4J_URI")
+NEO4J_USER = os.getenv("NEO4J_USER")
+NEO4J_PASSWORD = os.getenv("NEO4J_PASSWORD")
 
-SYNBIO_MODE = True
+SYNBIO_MODE = True  # always bias to synthetic biology domain
 
+# Preloaded demo queries
 DEMO_QUERIES = [
-    "Map all CRISPR-based living therapeutics in clinical trials since 2020",
-    "Graph metabolic engineering pathways for bio-based drug production",
-    "Synthetic biology startups developing oncolytic viruses — funding + trials",
-    "3D bioprinting advances for organ transplantation with regulatory analysis",
-    "AI-driven biosensor design for early cancer detection"
+    "CRISPR living therapeutics in clinical trials since 2020",
+    "AI-designed enzymes for plastic degradation — literature + pathways",
+    "Synthetic biology startups in oncology — funding map",
+    "Metabolic pathway for artemisinin biosynthesis in yeast",
+    "Oncolytic virus engineering — biosecurity risk analysis"
 ]
 
-def synthetic_biology_prompt_inject(query: str, expanded_terms: List[str]) -> str:
-    """Bias toward synthetic biology."""
+
+def extract_citations(text: str) -> List[Dict[str, str]]:
+    """Extract citations (DOI, PMID, URLs) from text."""
+    citations = []
+    doi_pattern = r"(10\.\d{4,9}/[-._;()/:A-Z0-9]+)"
+    pmid_pattern = r"PMID:\s*(\d+)"
+    url_pattern = r"(https?://[^\s)]+)"
+
+    for match in re.finditer(doi_pattern, text, re.IGNORECASE):
+        citations.append({"type": "DOI", "id": match.group(1), "url": f"https://doi.org/{match.group(1)}"})
+    for match in re.finditer(pmid_pattern, text, re.IGNORECASE):
+        citations.append({"type": "PMID", "id": match.group(1), "url": f"https://pubmed.ncbi.nlm.nih.gov/{match.group(1)}/"})
+    for match in re.finditer(url_pattern, text, re.IGNORECASE):
+        if not any(c["url"] == match.group(1) for c in citations):
+            citations.append({"type": "URL", "id": "", "url": match.group(1)})
+
+    return citations
+
+
+def inject_synbio_context(query: str, expanded_terms: List[str]) -> str:
+    """Injects synthetic biology expertise into the prompt."""
     context = (
-        "You are an expert synthetic biologist and AI researcher. "
-        "Focus on CRISPR, metabolic engineering, living therapeutics, protein design, "
-        "biosensors, and biosecurity. Integrate literature, molecular structures, market trends, "
-        "and policy/regulatory outlook. Produce a structured, citation-rich report."
+        "You are an expert in synthetic biology, biosecurity, and regulatory affairs. "
+        "Provide literature review, molecular insights, market trends, and policy implications. "
+        "Focus on CRISPR, metabolic engineering, living therapeutics, protein design, biosensors, and biosecurity. "
+        "Be concise, factual, and provide citations."
     )
     return f"{context}\n\nQuery: {query}\nExpanded terms: {', '.join(expanded_terms)}"
 
-def research_once(query: str, graph_preview: bool = True, narration: bool = True) -> Dict[str, Any]:
-    """Main research pipeline."""
-    expanded_terms = expand_terms_with_ontology(query, UMLS_API_KEY, BIOPORTAL_API_KEY)
-    enriched_query = synthetic_biology_prompt_inject(query, expanded_terms) if SYNBIO_MODE else query
 
-    # Summarize with DeepSeek
-    raw_summary = run_deepseek_summary(enriched_query) or "Summary unavailable."
-    polished_summary = run_gemini_polish(raw_summary)
+def multimodal_research(query: str, narration: bool = False, generate_pdf: bool = False) -> Dict[str, Any]:
+    """Main multi-modal synthetic biology pipeline."""
+    # 1 — Expand query with ontology
+    expanded_terms = merge_ontology_terms(
+        query,
+        expand_with_umls(query),
+        expand_with_bioportal(query)
+    )
+
+    # 2 — Inject domain-specific context
+    enriched_query = inject_synbio_context(query, expanded_terms) if SYNBIO_MODE else query
+
+    # 3 — Summarization with fallback
+    summary = None
+    for summarizer in [run_deepseek_summary, run_gemini_summary, run_openai_summary]:
+        try:
+            summary = summarizer(enriched_query)
+            if summary:
+                break
+        except Exception:
+            continue
 
-    # Literature from PubMed
-    citations = run_pubmed_literature(query, max_results=10)
+    if not summary:
+        summary = "No summary generated — please refine your query."
 
-    # Molecular structures
+    # 4 — Citations extraction & PubMed fallback
+    citations = extract_citations(summary)
+    if not citations:
+        citations = search_pubmed_literature(query)
+
+    # 5 — Structures (NCBI, ChEMBL)
     structures = fetch_structures_for_terms(expanded_terms)
 
-    # Image generation
-    visual_image_url = run_image_generation(query)
+    # 6 — Image generation with fallback
+    image_url = None
+    for img_fn in [run_gemini_image, run_openai_image, run_hf_image]:
+        try:
+            image_url = img_fn(query)
+            if image_url:
+                break
+        except Exception:
+            continue
+
+    # 7 — Funding, Trials, Regulation, Safety, Biosecurity
+    funding_data = fetch_funding_data(query)
+    trial_data = fetch_clinical_trials(query)
+    regulation_data = fetch_regulatory_info(query)
+    safety_data = analyze_safety_concerns(query)
+    biosecurity_data = analyze_biosecurity_risks(query)
 
-    # GraphDB integration
-    if graph_preview and NEO4J_URI:
+    # 8 — Graph visualizations
+    pathway_graph = generate_pathway_graph(query, expanded_terms)
+    funding_graph = generate_funding_network(query, funding_data)
+
+    # 9 — Save to Neo4j
+    if NEO4J_URI:
         write_topic_and_papers(query, citations, expanded_terms)
 
-    # Narration
-    audio_url = narrate_text(polished_summary) if narration and ELEVEN_LABS_API_KEY else None
+    # 10 — Optional narration
+    audio_url = None
+    if narration and ELEVEN_LABS_API_KEY:
+        audio_url = narrate_text_elevenlabs(summary)
+
+    # 11 — Optional PDF export
+    pdf_path = None
+    if generate_pdf:
+        pdf_path = export_report_to_pdf(query, summary, citations, structures, funding_data, regulation_data)
 
+    # 12 — Build output
     return {
         "timestamp": datetime.utcnow().isoformat(),
         "query": query,
         "expanded_terms": expanded_terms,
-        "summary": polished_summary,
+        "summary": summary,
         "citations": citations,
         "structures": structures,
-        "visual_image_url": visual_image_url,
-        "audio_url": audio_url
+        "image_url": image_url,
+        "funding_data": funding_data,
+        "trial_data": trial_data,
+        "regulation_data": regulation_data,
+        "safety_data": safety_data,
+        "biosecurity_data": biosecurity_data,
+        "pathway_graph": pathway_graph,
+        "funding_graph": funding_graph,
+        "audio_url": audio_url,
+        "pdf_path": pdf_path
     }