Update genesis/api_clients/chembl_api.py

genesis/api_clients/chembl_api.py

@@ -1,88 +1,75 @@
 # genesis/api_clients/chembl_api.py
-import os
 import requests
-from typing import List, Dict, Optional
+import os
+from typing import Dict, List, Optional
 
-CHEMBL_BASE = "https://www.ebi.ac.uk/chembl/api/data"
+CHEMBL_BASE_URL = "https://www.ebi.ac.uk/chembl/api/data"
 
-def _fetch_paginated(endpoint: str, params: dict) -> List[dict]:
+def chembl_search_molecule(name_or_id: str) -> Dict:
     """
-    Handles paginated ChEMBL API responses.
+    Search for a molecule in ChEMBL by name or ChEMBL ID.
+    Returns detailed information including structure, properties, and targets.
     """
-    results = []
-    url = f"{CHEMBL_BASE}/{endpoint}"
-    
-    while url:
-        r = requests.get(url, params=params)
+    r = requests.get(f"{CHEMBL_BASE_URL}/molecule/{name_or_id}.json")
+    if r.status_code == 404:
+        # Try text search
+        search_url = f"{CHEMBL_BASE_URL}/molecule/search.json?q={name_or_id}"
+        r = requests.get(search_url)
         r.raise_for_status()
-        data = r.json()
-        page_items = data.get(endpoint, [])
-        results.extend(page_items)
-        url = data.get("page_meta", {}).get("next")
-        params = {}  # clear params after first page to avoid duplication
-    return results
-
-
-def search_molecule_by_name(name: str, max_results: int = 10) -> List[dict]:
-    """
-    Search molecules in ChEMBL by name or synonym.
-    """
-    params = {"molecule_synonyms__icontains": name, "limit": max_results}
-    return _fetch_paginated("molecule", params)
-
-
-def get_molecule_details(chembl_id: str) -> dict:
-    """
-    Retrieve detailed information for a molecule by ChEMBL ID.
-    """
-    r = requests.get(f"{CHEMBL_BASE}/molecule/{chembl_id}")
+        results = r.json().get("molecules", [])
+        return results[0] if results else {}
     r.raise_for_status()
     return r.json()
 
 
-def get_molecule_bioactivities(chembl_id: str, max_results: int = 50) -> List[dict]:
+def chembl_bioactivity_for_target(target_chembl_id: str, limit: int = 20) -> List[Dict]:
     """
-    Retrieve bioactivity records for a given molecule.
+    Retrieve bioactivity data for a given target (e.g., CHEMBL203).
     """
-    params = {"molecule_chembl_id": chembl_id, "limit": max_results}
-    return _fetch_paginated("activity", params)
+    r = requests.get(f"{CHEMBL_BASE_URL}/activity.json?target_chembl_id={target_chembl_id}&limit={limit}")
+    r.raise_for_status()
+    activities = r.json().get("activities", [])
+    return activities
 
 
-def search_target_by_name(name: str, max_results: int = 10) -> List[dict]:
+def chembl_target_info(target_chembl_id: str) -> Dict:
     """
-    Search for biological targets by name.
+    Get target details including organism, target type, and components.
     """
-    params = {"target_synonym__icontains": name, "limit": max_results}
-    return _fetch_paginated("target", params)
+    r = requests.get(f"{CHEMBL_BASE_URL}/target/{target_chembl_id}.json")
+    r.raise_for_status()
+    return r.json()
 
 
-def get_target_details(chembl_id: str) -> dict:
+def chembl_assay_info(assay_chembl_id: str) -> Dict:
     """
-    Retrieve detailed target information by ChEMBL ID.
+    Get detailed information about a specific assay.
     """
-    r = requests.get(f"{CHEMBL_BASE}/target/{chembl_id}")
+    r = requests.get(f"{CHEMBL_BASE_URL}/assay/{assay_chembl_id}.json")
     r.raise_for_status()
     return r.json()
 
 
-def search_assays_by_target(target_chembl_id: str, max_results: int = 50) -> List[dict]:
+def chembl_mechanism(molecule_chembl_id: str) -> List[Dict]:
     """
-    Retrieve assays related to a specific target.
+    Retrieve mechanism of action for a molecule.
     """
-    params = {"target_chembl_id": target_chembl_id, "limit": max_results}
-    return _fetch_paginated("assay", params)
+    r = requests.get(f"{CHEMBL_BASE_URL}/mechanism.json?molecule_chembl_id={molecule_chembl_id}")
+    r.raise_for_status()
+    return r.json().get("mechanisms", [])
 
 
-def get_drugs_in_clinical_phase(phase: int, max_results: int = 20) -> List[dict]:
+def chembl_drug_indications(molecule_chembl_id: str) -> List[Dict]:
     """
-    Retrieve drugs by clinical trial phase.
+    Get drug indications linked to a molecule.
     """
-    params = {"max_phase": phase, "limit": max_results}
-    return _fetch_paginated("molecule", params)
+    r = requests.get(f"{CHEMBL_BASE_URL}/drug_indication.json?molecule_chembl_id={molecule_chembl_id}")
+    r.raise_for_status()
+    return r.json().get("drug_indications", [])
 
 
-def get_molecule_image_url(chembl_id: str) -> str:
+def chembl_structure_image(molecule_chembl_id: str, image_size: str = "500") -> str:
     """
-    Generate a URL to the 2D structure image of a molecule.
+    Get the URL to the molecule’s structure image.
     """
-    return f"https://www.ebi.ac.uk/chembl/api/data/image/{chembl_id}.svg"
+    return f"https://www.ebi.ac.uk/chembl/api/utils/image/{molecule_chembl_id}?format=png&size={image_size}"