Update genesis/literature.py

genesis/literature.py

@@ -1,69 +1,50 @@
 # genesis/literature.py
+"""
+Literature intelligence for GENESIS-AI
+Fetches biomedical, biotech, and synthetic biology publications.
+"""
+
 import os
 import requests
-from typing import List, Dict
 
-NCBI_API_KEY = os.getenv("NCBI_API_KEY")
 NCBI_EMAIL = os.getenv("NCBI_EMAIL")
+PUBMED_SEARCH_URL = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
+PUBMED_FETCH_URL = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi"
+
+CHEMBL_API = "https://www.ebi.ac.uk/chembl/api/data/molecule"
 
-def search_pubmed(query: str, max_results: int = 5, sort: str = "relevance") -> List[Dict]:
-    """
-    Search PubMed for research articles.
-    
-    sort: "relevance", "pub date", or "most recent"
-    Returns: List of dicts with title, authors, journal, year, and link.
-    """
+def search_pubmed(query, max_results=10):
+    """Search PubMed and return article IDs."""
     try:
-        # Step 1: Search PubMed for IDs
-        search_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
-        search_params = {
+        params = {
             "db": "pubmed",
             "term": query,
             "retmax": max_results,
-            "api_key": NCBI_API_KEY,
-            "email": NCBI_EMAIL,
-            "sort": "relevance" if sort == "relevance" else "pub+date" if sort == "most recent" else "pub+date",
-            "retmode": "json"
+            "retmode": "json",
+            "email": NCBI_EMAIL
         }
-        r = requests.get(search_url, params=search_params, timeout=10)
+        r = requests.get(PUBMED_SEARCH_URL, params=params)
         r.raise_for_status()
-        ids = r.json().get("esearchresult", {}).get("idlist", [])
-        if not ids:
-            return []
-
-        # Step 2: Fetch summaries for IDs
-        summary_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi"
-        summary_params = {
-            "db": "pubmed",
-            "id": ",".join(ids),
-            "retmode": "json"
-        }
-        s = requests.get(summary_url, params=summary_params, timeout=10)
-        s.raise_for_status()
-        summaries = s.json().get("result", {})
+        return r.json()
+    except Exception as e:
+        return {"error": str(e)}
 
-        papers = []
-        for pmid in ids:
-            paper = summaries.get(pmid, {})
-            authors = [a["name"] for a in paper.get("authors", [])]
-            papers.append({
-                "title": paper.get("title", "N/A"),
-                "authors": ", ".join(authors) if authors else "N/A",
-                "journal": paper.get("fulljournalname", "N/A"),
-                "year": paper.get("pubdate", "N/A"),
-                "pmid": pmid,
-                "url": f"https://pubmed.ncbi.nlm.nih.gov/{pmid}/"
-            })
-        return papers
+def fetch_pubmed_details(id_list):
+    """Fetch details for a list of PubMed IDs."""
+    try:
+        ids = ",".join(id_list)
+        params = {"db": "pubmed", "id": ids, "retmode": "xml"}
+        r = requests.get(PUBMED_FETCH_URL, params=params)
+        r.raise_for_status()
+        return r.text  # XML response
     except Exception as e:
-        print(f"[PubMed] Failed: {e}")
-        return []
+        return {"error": str(e)}
 
-def format_literature_markdown(papers: List[Dict]) -> str:
-    """Format literature list into markdown table."""
-    if not papers:
-        return "No relevant papers found."
-    md = "| Title | Authors | Journal | Year |\n|-------|---------|---------|------|\n"
-    for p in papers:
-        md += f"| [{p['title']}]({p['url']}) | {p['authors']} | {p['journal']} | {p['year']} |\n"
-    return md
+def search_chembl(query):
+    """Search ChEMBL molecules by name."""
+    try:
+        r = requests.get(f"{CHEMBL_API}?molecule_synonyms__icontains={query}")
+        r.raise_for_status()
+        return r.json()
+    except Exception as e:
+        return {"error": str(e)}