Spaces:
Sleeping
Sleeping
Update components/pubmed_search.py
Browse files- components/pubmed_search.py +53 -25
components/pubmed_search.py
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
from Bio import Entrez
|
| 2 |
-
import os
|
| 3 |
-
|
| 4 |
-
# ---------------------------- Configuration ----------------------------
|
| 5 |
|
| 6 |
# ---------------------------- Helper Functions ----------------------------
|
| 7 |
|
|
@@ -14,50 +13,79 @@ def log_error(message: str):
|
|
| 14 |
except:
|
| 15 |
print("Couldn't write to error log file.") #If logging fails, still print to console
|
| 16 |
|
| 17 |
-
# ----------------------------
|
| 18 |
|
| 19 |
def search_pubmed(query: str) -> list:
|
| 20 |
"""Searches PubMed and returns a list of article IDs using semantic search."""
|
|
|
|
| 21 |
try:
|
| 22 |
Entrez.email = ENTREZ_EMAIL
|
| 23 |
print(f"Entrez Email: {Entrez.email}") # DEBUG: Check the email being used
|
| 24 |
print(f"PubMed Query: {query}") # DEBUG: Check the query being sent
|
| 25 |
|
| 26 |
-
|
| 27 |
-
from sentence_transformers import SentenceTransformer, util
|
| 28 |
-
|
| 29 |
-
model = SentenceTransformer('all-mpnet-base-v2') #Model by all-mpnet-base-v2
|
| 30 |
-
|
| 31 |
# Fetch PubMed IDs
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
|
|
|
|
| 36 |
# Fetch abstracts for all IDs:
|
| 37 |
abstracts = []
|
| 38 |
for article_id in id_list:
|
| 39 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
abstract_embeddings = model.encode(abstracts)
|
| 44 |
|
| 45 |
-
|
| 46 |
-
similarities = util.cos_sim(query_embedding, abstract_embeddings)[0]
|
| 47 |
|
| 48 |
-
|
| 49 |
-
ranked_articles = sorted(zip(id_list, similarities), key=lambda x: x[1], reverse=True)
|
| 50 |
|
| 51 |
-
|
| 52 |
-
|
|
|
|
| 53 |
|
| 54 |
-
print(f"PubMed Results: {ranked_ids}") # DEBUG: Check the results
|
| 55 |
-
return ranked_ids
|
| 56 |
except Exception as e:
|
| 57 |
log_error(f"PubMed search error: {e}")
|
| 58 |
return [f"Error during PubMed search: {e}"]
|
| 59 |
|
| 60 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
def medai_agent(query: str) -> str:
|
| 63 |
"""Orchestrates the medical literature review and presents abstract."""
|
|
|
|
| 1 |
from Bio import Entrez
|
| 2 |
+
import os
|
| 3 |
+
from sentence_transformers import SentenceTransformer, util
|
|
|
|
| 4 |
|
| 5 |
# ---------------------------- Helper Functions ----------------------------
|
| 6 |
|
|
|
|
| 13 |
except:
|
| 14 |
print("Couldn't write to error log file.") #If logging fails, still print to console
|
| 15 |
|
| 16 |
+
# ---------------------------- Functions ----------------------------
|
| 17 |
|
| 18 |
def search_pubmed(query: str) -> list:
|
| 19 |
"""Searches PubMed and returns a list of article IDs using semantic search."""
|
| 20 |
+
ENTREZ_EMAIL = os.environ.get("ENTREZ_EMAIL", "your_email@example.com")
|
| 21 |
try:
|
| 22 |
Entrez.email = ENTREZ_EMAIL
|
| 23 |
print(f"Entrez Email: {Entrez.email}") # DEBUG: Check the email being used
|
| 24 |
print(f"PubMed Query: {query}") # DEBUG: Check the query being sent
|
| 25 |
|
| 26 |
+
"" Added code ""
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
# Fetch PubMed IDs
|
| 28 |
+
try:
|
| 29 |
+
handle = Entrez.esearch(db="pubmed", term=query, retmax="5")
|
| 30 |
+
record = Entrez.read(handle)
|
| 31 |
+
id_list = record["IdList"]
|
| 32 |
+
print(f"Original PubMed Results: {id_list}")
|
| 33 |
+
|
| 34 |
+
except Exception as e:
|
| 35 |
+
log_error(f"First step of PubMed search error: {e}")
|
| 36 |
+
return [f"First step of Error during PubMed search: {e}"]
|
| 37 |
|
| 38 |
+
"" Added code ""
|
| 39 |
# Fetch abstracts for all IDs:
|
| 40 |
abstracts = []
|
| 41 |
for article_id in id_list:
|
| 42 |
+
abstract_text = fetch_abstract(article_id)
|
| 43 |
+
if "Error" in abstract_text:
|
| 44 |
+
print(f"Skipping article {article_id} due to abstract error: {abstract_text}")
|
| 45 |
+
continue
|
| 46 |
+
abstracts.append(abstract_text)
|
| 47 |
+
|
| 48 |
+
"" Added code ""
|
| 49 |
+
# Semantic Search Using Sentence Transformers:
|
| 50 |
+
try:
|
| 51 |
+
model = SentenceTransformer('all-mpnet-base-v2') #Model by all-mpnet-base-v2
|
| 52 |
+
# Generate embeddings for abstracts and the query:
|
| 53 |
+
query_embedding = model.encode(query)
|
| 54 |
+
abstract_embeddings = model.encode(abstracts)
|
| 55 |
+
|
| 56 |
+
# Calculate cosine similarities
|
| 57 |
+
similarities = util.cos_sim(query_embedding, abstract_embeddings)[0]
|
| 58 |
+
|
| 59 |
+
# Sort by similarity (higher is better)
|
| 60 |
+
ranked_articles = sorted(zip(id_list, similarities), key=lambda x: x[1], reverse=True)
|
| 61 |
|
| 62 |
+
# Extract ranked IDs:
|
| 63 |
+
ranked_ids = [article_id for article_id, similarity in ranked_articles]
|
|
|
|
| 64 |
|
| 65 |
+
print(f"Semantic search code: {ranked_ids}") # DEBUG: Check the results
|
|
|
|
| 66 |
|
| 67 |
+
return ranked_ids
|
|
|
|
| 68 |
|
| 69 |
+
except Exception as e:
|
| 70 |
+
log_error(f"Semantic search code. : {e}")
|
| 71 |
+
return [f"Error during semantic search code: {e}"]
|
| 72 |
|
|
|
|
|
|
|
| 73 |
except Exception as e:
|
| 74 |
log_error(f"PubMed search error: {e}")
|
| 75 |
return [f"Error during PubMed search: {e}"]
|
| 76 |
|
| 77 |
+
def fetch_abstract(article_id: str) -> str:
|
| 78 |
+
"""Fetches the abstract for a given PubMed article ID."""
|
| 79 |
+
ENTREZ_EMAIL = os.environ.get("ENTREZ_EMAIL", "your_email@example.com")
|
| 80 |
+
try:
|
| 81 |
+
Entrez.email = ENTREZ_EMAIL
|
| 82 |
+
handle = Entrez.efetch(db="pubmed", id=article_id, rettype="abstract", retmode="text")
|
| 83 |
+
abstract = handle.read()
|
| 84 |
+
handle.close()
|
| 85 |
+
return abstract
|
| 86 |
+
except Exception as e:
|
| 87 |
+
log_error(f"Error fetching abstract for {article_id}: {e}")
|
| 88 |
+
return f"Error fetching abstract for {article_id}: {e}"
|
| 89 |
|
| 90 |
def medai_agent(query: str) -> str:
|
| 91 |
"""Orchestrates the medical literature review and presents abstract."""
|