aiagents4pharma 1.39.4__tar.gz → 1.39.5__tar.gz

{aiagents4pharma-1.39.4 → aiagents4pharma-1.39.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aiagents4pharma
-Version: 1.39.4
+Version: 1.39.5
 Summary: AI Agents for drug discovery, drug development, and other pharmaceutical R&D.
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License

{aiagents4pharma-1.39.4 → aiagents4pharma-1.39.5}/aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_ols.py

@@ -42,11 +42,11 @@ def test_enrich_documents(enrich_obj):
         "XYZ_0000000",
     ]
     descriptions = enrich_obj.enrich_documents(ols_terms)
-    assert descriptions[0].startswith(CL_DESC)
-    assert descriptions[1].startswith(GO_DESC)
-    assert descriptions[2].startswith(UBERON_DESC)
-    assert descriptions[3].startswith(HP_DESC)
-    assert descriptions[4].startswith(MONDO_DESC)
+    assert CL_DESC in descriptions[0]
+    assert GO_DESC in descriptions[1]
+    assert UBERON_DESC in descriptions[2]
+    assert HP_DESC in descriptions[3]
+    assert MONDO_DESC in descriptions[4]
     assert descriptions[5] is None
 
 
@@ -61,9 +61,9 @@ def test_enrich_documents_with_rag(enrich_obj):
         "XYZ_0000000",
     ]
     descriptions = enrich_obj.enrich_documents_with_rag(ols_terms, None)
-    assert descriptions[0].startswith(CL_DESC)
-    assert descriptions[1].startswith(GO_DESC)
-    assert descriptions[2].startswith(UBERON_DESC)
-    assert descriptions[3].startswith(HP_DESC)
-    assert descriptions[4].startswith(MONDO_DESC)
+    assert CL_DESC in descriptions[0]
+    assert GO_DESC in descriptions[1]
+    assert UBERON_DESC in descriptions[2]
+    assert HP_DESC in descriptions[3]
+    assert MONDO_DESC in descriptions[4]
     assert descriptions[5] is None

{aiagents4pharma-1.39.4 → aiagents4pharma-1.39.5}/aiagents4pharma/talk2knowledgegraphs/tests/test_utils_pubchem_utils.py

@@ -4,6 +4,17 @@ Test cases for utils/pubchem_utils.py
 
 from ..utils import pubchem_utils
 
+def test_cas_rn2pubchem_cid():
+    """
+    Test the casRN2pubchem_cid function.
+
+    The CAS RN for ethyl cabonate is 105-58-8.
+    The PubChem CID for ethyl cabonate is 7766.
+    """
+    casrn = "105-58-8"
+    pubchem_cid = pubchem_utils.cas_rn2pubchem_cid(casrn)
+    assert pubchem_cid == 7766
+
 def test_external_id2pubchem_cid():
     """
     Test the external_id2pubchem_cid function.

{aiagents4pharma-1.39.4 → aiagents4pharma-1.39.5}/aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ols_terms.py

@@ -54,13 +54,21 @@ class EnrichmentWithOLS(Enrichments):
                 descriptions.append(None)
                 continue
             # Add the description to the list
-            description = response_body['_embedded']['terms'][0]['description']
-            # Add synonyms to the description
-            description += response_body['_embedded']['terms'][0]['synonyms']
-            # Add the label to the description
-            # Label is not provided as list, so we need to convert it to a list
-            description += [response_body['_embedded']['terms'][0]['label']]
-            descriptions.append('\n'.join(description))
+            description = []
+            for term in response_body['_embedded']['terms']:
+                # If the term has a description, add it to the list
+                description += term.get('description', [])
+                # Add synonyms to the description
+                description += term.get('synonyms', [])
+                # Add the label to the description
+                # Label is not provided as list, so we need to convert it to a list
+                description += [term.get('label', [])]
+            # Make unique the description
+            description = list(set(description))
+            # Join the description with new line
+            description = '\n'.join(description)
+            # Add the description to the list
+            descriptions.append(description)
         return descriptions
 
     def enrich_documents_with_rag(self, texts, docs):

aiagents4pharma-1.39.5/aiagents4pharma/talk2knowledgegraphs/utils/enrichments/pubchem_strings.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python3
+
+"""
+Enrichment class for enriching PubChem IDs with their STRINGS representation and descriptions.
+"""
+
+import logging
+from typing import List
+import requests
+import hydra
+from .enrichments import Enrichments
+from ..pubchem_utils import pubchem_cid_description
+
+# Initialize logger
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+class EnrichmentWithPubChem(Enrichments):
+    """
+    Enrichment class using PubChem
+    """
+    def enrich_documents(self, texts: List[str]) -> List[str]:
+        """
+        Enrich a list of input PubChem IDs with their STRINGS representation.
+
+        Args:
+            texts: The list of pubchem IDs to be enriched.
+
+        Returns:
+            The list of enriched STRINGS and their descriptions.
+        """
+
+        enriched_pubchem_ids_smiles = []
+        enriched_pubchem_ids_descriptions = []
+
+        # Load Hydra configuration to get the base URL for PubChem
+        with hydra.initialize(version_base=None, config_path="../../configs"):
+            cfg = hydra.compose(config_name='config',
+                                overrides=['utils/pubchem_utils=default'])
+            cfg = cfg.utils.pubchem_utils
+        # Iterate over each PubChem ID in the input list
+        pubchem_cids = texts
+        for pubchem_cid in pubchem_cids:
+            # Prepare the URL
+            pubchem_url = f"{cfg.pubchem_cid2smiles_url}/{pubchem_cid}/property/smiles/JSON"
+            # Get the data
+            response = requests.get(pubchem_url, timeout=60)
+            data = response.json()
+            # Extract the PubChem CID SMILES
+            smiles = ''
+            description = ''
+            if "PropertyTable" in data:
+                for prop in data["PropertyTable"]['Properties']:
+                    smiles = prop.get("SMILES", '')
+                    description = pubchem_cid_description(pubchem_cid)
+            else:
+                # If the PubChem ID is not found, set smiles and description to None
+                smiles = None
+                description = None
+            enriched_pubchem_ids_smiles.append(smiles)
+            enriched_pubchem_ids_descriptions.append(description)
+
+        return enriched_pubchem_ids_descriptions, enriched_pubchem_ids_smiles
+
+    def enrich_documents_with_rag(self, texts, docs):
+        """
+        Enrich a list of input PubChem IDs with their STRINGS representation.
+
+        Args:
+            texts: The list of pubchem IDs to be enriched.
+            docs: None
+
+        Returns:
+            The list of enriched STRINGS
+        """
+        return self.enrich_documents(texts)

{aiagents4pharma-1.39.4 → aiagents4pharma-1.39.5}/aiagents4pharma/talk2knowledgegraphs/utils/pubchem_utils.py

@@ -12,6 +12,37 @@ import hydra
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
+def cas_rn2pubchem_cid(casrn):
+    """
+    Convert CAS RN to PubChem CID.
+
+    Args:
+        casrn: The CAS RN of the drug.
+
+    Returns:
+        The PubChem CID of the drug.
+    """
+    # Load Hydra configuration for PubChem ID conversion
+    with hydra.initialize(version_base=None, config_path="../configs"):
+        cfg = hydra.compose(config_name='config',
+                            overrides=['utils/pubchem_utils=default'])
+        cfg = cfg.utils.pubchem_utils
+    # Prepare the URL
+    pubchem_url_for_drug = f"{cfg.pubchem_casrn2cid_url}{casrn}/record/JSON"
+    # Get the data
+    response = requests.get(pubchem_url_for_drug, timeout=60)
+    data = response.json()
+    # Extract the PubChem CID
+    cid = None
+    for substance in data.get("PC_Substances", []):
+        for compound in substance.get("compound", []):
+            if "id" in compound and "type" in compound["id"] and compound["id"]["type"] == 1:
+                cid = compound["id"].get("id", {}).get("cid")
+                break
+        if cid is not None:
+            break
+    return cid
+
 def external_id2pubchem_cid(db, db_id):
     """
     Convert external DB ID to PubChem CID.
@@ -26,7 +57,7 @@ def external_id2pubchem_cid(db, db_id):
     Returns:
         The PubChem CID of the drug.
     """
-    logger.log(logging.INFO, "Load Hydra configuration for PubChem ID conversion.")
+    # Load Hydra configuration for PubChem ID conversion
     with hydra.initialize(version_base=None, config_path="../configs"):
         cfg = hydra.compose(config_name='config',
                             overrides=['utils/pubchem_utils=default'])
@@ -55,7 +86,7 @@ def pubchem_cid_description(cid):
     Returns:
         The description of the PubChem CID.
     """
-    logger.log(logging.INFO, "Load Hydra configuration for PubChem CID description.")
+    # Load Hydra configuration for PubChem CID description
     with hydra.initialize(version_base=None, config_path="../configs"):
         cfg = hydra.compose(config_name='config',
                             overrides=['utils/pubchem_utils=default'])

{aiagents4pharma-1.39.4 → aiagents4pharma-1.39.5}/aiagents4pharma.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aiagents4pharma
-Version: 1.39.4
+Version: 1.39.5
 Summary: AI Agents for drug discovery, drug development, and other pharmaceutical R&D.
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License

aiagents4pharma-1.39.5/release_version.txt

@@ -0,0 +1 @@
+v1.39.5

aiagents4pharma-1.39.4/aiagents4pharma/talk2knowledgegraphs/utils/enrichments/pubchem_strings.py

@@ -1,54 +0,0 @@
-#!/usr/bin/env python3
-
-"""
-Enrichment class for enriching PubChem IDs with their STRINGS representation and descriptions.
-"""
-
-from typing import List
-import pubchempy as pcp
-from .enrichments import Enrichments
-from ..pubchem_utils import pubchem_cid_description
-
-class EnrichmentWithPubChem(Enrichments):
-    """
-    Enrichment class using PubChem
-    """
-    def enrich_documents(self, texts: List[str]) -> List[str]:
-        """
-        Enrich a list of input PubChem IDs with their STRINGS representation.
-
-        Args:
-            texts: The list of pubchem IDs to be enriched.
-
-        Returns:
-            The list of enriched STRINGS and their descriptions.
-        """
-
-        enriched_pubchem_ids_smiles = []
-        enriched_pubchem_ids_descriptions = []
-
-        pubchem_cids = texts
-        for pubchem_cid in pubchem_cids:
-            try:
-                c = pcp.Compound.from_cid(pubchem_cid)
-            except pcp.BadRequestError:
-                enriched_pubchem_ids_smiles.append(None)
-                enriched_pubchem_ids_descriptions.append(None)
-                continue
-            enriched_pubchem_ids_smiles.append(c.isomeric_smiles)
-            enriched_pubchem_ids_descriptions.append(pubchem_cid_description(pubchem_cid))
-
-        return enriched_pubchem_ids_descriptions, enriched_pubchem_ids_smiles
-
-    def enrich_documents_with_rag(self, texts, docs):
-        """
-        Enrich a list of input PubChem IDs with their STRINGS representation.
-
-        Args:
-            texts: The list of pubchem IDs to be enriched.
-            docs: None
-
-        Returns:
-            The list of enriched STRINGS
-        """
-        return self.enrich_documents(texts)

aiagents4pharma-1.39.4/release_version.txt

@@ -1 +0,0 @@
-v1.39.4