aiagents4pharma 1.39.3__py3-none-any.whl → 1.39.5__py3-none-any.whl

aiagents4pharma/talk2biomodels/configs/tools/get_annotation/default.yaml

@@ -3,4 +3,6 @@ prompt: >
   Given the user question, extract the relevant species names.
   If the user aks for a specific species, extract that species.
   If none of the species match the user question, return None.
-  If the user asks for all species, return all species.
+  If the user asks for all species, return all species.
+  If the user does not specify any species or simpley asks for
+  model annotations, return all species.

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/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/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/talk2knowledgegraphs/utils/enrichments/pubchem_strings.py

@@ -4,11 +4,17 @@
 Enrichment class for enriching PubChem IDs with their STRINGS representation and descriptions.
 """
 
+import logging
 from typing import List
-import pubchempy as pcp
+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
@@ -27,16 +33,32 @@ class EnrichmentWithPubChem(Enrichments):
         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:
-            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))
+            # 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
 

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-1.39.3.dist-info → aiagents4pharma-1.39.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aiagents4pharma
-Version: 1.39.3
+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-1.39.3.dist-info → aiagents4pharma-1.39.5.dist-info}/RECORD

@@ -28,7 +28,7 @@ aiagents4pharma/talk2biomodels/configs/tools/ask_question/default.yaml,sha256=7k
 aiagents4pharma/talk2biomodels/configs/tools/custom_plotter/__init__.py,sha256=-fAORvyFmG2iSvFOFDixmt9OTQRR58y89uhhu2EgbA8,46
 aiagents4pharma/talk2biomodels/configs/tools/custom_plotter/default.yaml,sha256=14Aic9IDr1eOyeLo_YGMwZL40CYsgqOXix2j9ucB4EA,464
 aiagents4pharma/talk2biomodels/configs/tools/get_annotation/__init__.py,sha256=-fAORvyFmG2iSvFOFDixmt9OTQRR58y89uhhu2EgbA8,46
-aiagents4pharma/talk2biomodels/configs/tools/get_annotation/default.yaml,sha256=o5kqLJ5QGJsLMUhAqotudIMhxxNfPUVcDVH1tdRIutU,304
+aiagents4pharma/talk2biomodels/configs/tools/get_annotation/default.yaml,sha256=Dx6afMdafUEZjN4LWEFQWkjXHw7DChSpQeb_wlQXRUo,408
 aiagents4pharma/talk2biomodels/models/__init__.py,sha256=5fTHHm3PVloYPNKXbgNlcPgv3-u28ZquxGydFYDfhJA,122
 aiagents4pharma/talk2biomodels/models/basico_model.py,sha256=4LjeHKGcXsdm1gFxs9SGVNDerajZ7REvCeNch0s2pDg,5242
 aiagents4pharma/talk2biomodels/models/sys_bio_model.py,sha256=JeoiGQAvQABHnG0wKR2XBmmxqQdtgO6kxaLDUTUmr1s,2001
@@ -113,12 +113,12 @@ aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_ollama.py,sha25
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_sentencetransformer.py,sha256=Xkuf2UFGCXldj1zcsh6kqfQYLDf5i0B6KP3KcmNLSzQ,1452
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_enrichments.py,sha256=N6HRr4lWHXY7bTHe2uXJe4D_EG9WqZPibZne6qLl9_k,1447
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_ollama.py,sha256=JhY7axvVULLywDJ2ctA-gob5YPeaJYWsaMNjHT6L9CU,3021
-aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_ols.py,sha256=5GTSkfKSDS5geR0YfilfnDyUsYli0hv7N8PiDwRvlIE,2370
+aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_ols.py,sha256=5nSBLwfBnwq4K78Q4GM0zTeym5csxHhOwGwx2utBBEU,2280
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_pubchem.py,sha256=0SgYvqdvxseUYTHx2KuSNI2hnmQ3VVVz0F-79_-P41o,1769
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_reactome.py,sha256=r1D74mavsnSCm4xnWl0n0nM9PZqgm3doD2dulNrKNVQ,1754
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_uniprot.py,sha256=G13Diw7cA5TGINUNO1CDnN4rM6KbepxRXNjuzY578DI,1611
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_kg_utils.py,sha256=pal76wi7WgQWUNk56BrzfFV8jKpbDaHHdbwtgx_gXLI,2410
-aiagents4pharma/talk2knowledgegraphs/tests/test_utils_pubchem_utils.py,sha256=K1Y6QM0MDP1IrAdcWkigl8R-O-i-lsL4NCyOrWewhdM,1246
+aiagents4pharma/talk2knowledgegraphs/tests/test_utils_pubchem_utils.py,sha256=31WPX8MrhnztoHUROAlH5KvHeXMbB_Jndp3ypAKJO9E,1543
 aiagents4pharma/talk2knowledgegraphs/tools/__init__.py,sha256=uleTEbhgvlYw4fOqV4NmoFvxGTon2Oim7jTQ5qPmYoU,216
 aiagents4pharma/talk2knowledgegraphs/tools/graphrag_reasoning.py,sha256=OEuOFncDRdb7TQEGq4rkT5On-jI-R7Nt8K5EBzaND8w,5338
 aiagents4pharma/talk2knowledgegraphs/tools/load_arguments.py,sha256=zhmsRp-8vjB5rRekqTA07d3yb-42HWqng9dDMkvK6hM,623
@@ -127,7 +127,7 @@ aiagents4pharma/talk2knowledgegraphs/tools/subgraph_extraction.py,sha256=te06QMF
 aiagents4pharma/talk2knowledgegraphs/tools/subgraph_summarization.py,sha256=mDSBOxopDfNhEJeU8fVI8b5lXTYrRzcc97aLbFgYSy4,4413
 aiagents4pharma/talk2knowledgegraphs/utils/__init__.py,sha256=cZqb3LZLmBnmyAtWFv2Z-4uJvQmx0M4zKsfiWrlM3Pk,195
 aiagents4pharma/talk2knowledgegraphs/utils/kg_utils.py,sha256=6vQnPkeOWae_8jePjhma3sJuMTngy0I0tqzdFt6OqKg,2507
-aiagents4pharma/talk2knowledgegraphs/utils/pubchem_utils.py,sha256=8cve_KLtQUhG3uMKYpyelZvpETSsNGRdGE4X0NXMk4M,2442
+aiagents4pharma/talk2knowledgegraphs/utils/pubchem_utils.py,sha256=kMSabEZDIa6BruoFtnvWQnUWX47FUmTo22CLihYz8F8,3458
 aiagents4pharma/talk2knowledgegraphs/utils/embeddings/__init__.py,sha256=POSDrSdFAWsBCueOPD-Fok-ARdTywJU1ivwpT9EU1Kw,199
 aiagents4pharma/talk2knowledgegraphs/utils/embeddings/embeddings.py,sha256=1nGznrAj-xT0xuSMBGz2dOujJ7M_IwSR84njxtxsy9A,2523
 aiagents4pharma/talk2knowledgegraphs/utils/embeddings/huggingface.py,sha256=2vi_elf6EgzfagFAO5QnL3a_aXZyN7B1EBziu44MTfM,3806
@@ -137,8 +137,8 @@ aiagents4pharma/talk2knowledgegraphs/utils/embeddings/sentence_transformer.py,sh
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/__init__.py,sha256=K157MWJ4dn2fj3G5ClhyAOXg9jI2H02GP07J6UpasJw,230
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/enrichments.py,sha256=Bx8x6zzk5614ApWB90N_iv4_Y_Uq0-KwUeBwYSdQMU4,924
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ollama.py,sha256=8eoxR-VHo0G7ReQIwje7xEhE-SJlHdef7_wJRpnvFIc,4116
-aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ols_terms.py,sha256=xSPP-h2q9fABz6Sd6ZlH9WiyoO8KZeEnPI5n2nJpWL4,2443
-aiagents4pharma/talk2knowledgegraphs/utils/enrichments/pubchem_strings.py,sha256=CQEGQ6Qsex2T91Vw7zTrclJBbSGGhxeWaVJb8tnURAQ,1691
+aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ols_terms.py,sha256=QLINhZM51A8JwFoF0INzdUFT2pdlc_h0rdYRgKr49vQ,2772
+aiagents4pharma/talk2knowledgegraphs/utils/enrichments/pubchem_strings.py,sha256=zdBYhRxYfdNSViBwDNwc-9DTYkYGTPlyyHB_OIgbb3E,2630
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/reactome_pathways.py,sha256=I0cD0Fk2Uk27_4jEaIhpoGhoMh_RphY1VtkMnk4dkPg,2011
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/uniprot_proteins.py,sha256=z0Jb3tt8VzRjzqI9oVcUvRlPPg6BUdmslfKDIEFE_h8,3013
 aiagents4pharma/talk2knowledgegraphs/utils/extractions/__init__.py,sha256=5bt3H6gGSAwN2K-IG7AHwG2lC4yQeMd2_jbhu2z5XKg,116
@@ -251,8 +251,8 @@ aiagents4pharma/talk2scholars/tools/zotero/utils/review_helper.py,sha256=IPD1V9y
 aiagents4pharma/talk2scholars/tools/zotero/utils/write_helper.py,sha256=ALwLecy1QVebbsmXJiDj1GhGmyhq2R2tZlAyEl1vfhw,7410
 aiagents4pharma/talk2scholars/tools/zotero/utils/zotero_path.py,sha256=oIrfbOySgts50ksHKyjcWjRkPRIS88g3Lc0v9mBkU8w,6375
 aiagents4pharma/talk2scholars/tools/zotero/utils/zotero_pdf_downloader.py,sha256=ERBha8afU6Q1EaRBe9qB8tchOzZ4_KfFgDW6EElOJoU,4816
-aiagents4pharma-1.39.3.dist-info/licenses/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
-aiagents4pharma-1.39.3.dist-info/METADATA,sha256=1nFBKl2FZ5seKMkuixLjF8hQqnR5DFYGrNCO9jUTFug,15462
-aiagents4pharma-1.39.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-aiagents4pharma-1.39.3.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
-aiagents4pharma-1.39.3.dist-info/RECORD,,
+aiagents4pharma-1.39.5.dist-info/licenses/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
+aiagents4pharma-1.39.5.dist-info/METADATA,sha256=plRPPLrdrpqnpbLLT_Kkaw3aONTG5VqpG1_q_1wddAg,15462
+aiagents4pharma-1.39.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+aiagents4pharma-1.39.5.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
+aiagents4pharma-1.39.5.dist-info/RECORD,,