aiagents4pharma 1.32.0__py3-none-any.whl → 1.33.0__py3-none-any.whl

aiagents4pharma/talk2knowledgegraphs/configs/config.yaml

@@ -5,4 +5,5 @@ defaults:
   - tools/subgraph_summarization: default
   - tools/graphrag_reasoning: default
   - utils/pubchem_utils: default
+  - utils/enrichments/uniprot_proteins: default
   - app/frontend: default

aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_uniprot.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+
+"""
+Test cases for utils/enrichments/uniprot_proteins.py
+"""
+
+import pytest
+from ..utils.enrichments.uniprot_proteins import EnrichmentWithUniProt
+
+# In this test, we will consider 2 examples:
+# 1. Gene Name: TP53
+# 2. Gene Name: TP5 (Incomplete; must return empty results)
+# 2. Gene Name: XZ (Shorter than 3 characters; must return empty results)
+# The expected description of TP53 startswith:
+START_DESCP = "Multifunctional transcription factor"
+# The expected amino acid sequence of TP53 startswith:
+START_SEQ = "MEEPQSDPSV"
+
+@pytest.fixture(name="enrich_obj")
+def fixture_uniprot_config():
+    """Return a dictionary with the configuration for UniProt enrichment."""
+    return EnrichmentWithUniProt()
+
+def test_enrich_documents(enrich_obj):
+    """Test the enrich_documents method."""
+    gene_names = ["TP53", "TP5", "XZ"]
+    descriptions, sequences = enrich_obj.enrich_documents(gene_names)
+    assert descriptions[0].startswith(START_DESCP)
+    assert sequences[0].startswith(START_SEQ)
+    assert descriptions[1] is None
+    assert sequences[1] is None
+    assert descriptions[2] is None
+    assert sequences[2] is None
+
+def test_enrich_documents_with_rag(enrich_obj):
+    """Test the enrich_documents_with_rag method."""
+    gene_names = ["TP53", "TP5", "XZ"]
+    descriptions, sequences = enrich_obj.enrich_documents_with_rag(gene_names, None)
+    assert descriptions[0].startswith(START_DESCP)
+    assert sequences[0].startswith(START_SEQ)
+    assert descriptions[1] is None
+    assert sequences[1] is None
+    assert descriptions[2] is None
+    assert sequences[2] is None

aiagents4pharma/talk2knowledgegraphs/utils/enrichments/__init__.py

@@ -4,3 +4,4 @@ This package contains modules to use the enrichment model
 from . import enrichments
 from . import ollama
 from . import pubchem_strings
+from . import uniprot_proteins

aiagents4pharma/talk2knowledgegraphs/utils/enrichments/uniprot_proteins.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+
+"""
+Enrichment class for enriching Gene names with their function and sequence using UniProt.
+"""
+
+from typing import List
+import logging
+import json
+import hydra
+import requests
+from .enrichments import Enrichments
+
+# Initialize logger
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+class EnrichmentWithUniProt(Enrichments):
+    """
+    Enrichment class using UniProt
+    """
+    def enrich_documents(self, texts: List[str]) -> List[str]:
+        """
+        Enrich a list of input UniProt gene names with their function and sequence.
+
+        Args:
+            texts: The list of gene names to be enriched.
+
+        Returns:
+            The list of enriched functions and sequences
+        """
+
+        enriched_gene_names = texts
+
+        logger.log(logging.INFO,
+                   "Load Hydra configuration for Gene enrichment with description and sequence.")
+        with hydra.initialize(version_base=None, config_path="../../configs"):
+            cfg = hydra.compose(config_name='config',
+                                overrides=['utils/enrichments/uniprot_proteins=default'])
+            cfg = cfg.utils.enrichments.uniprot_proteins
+
+
+        descriptions = []
+        sequences = []
+        for gene in enriched_gene_names:
+            params = {
+                "reviewed": cfg.reviewed,
+                "isoform": cfg.isoform,
+                "exact_gene": gene,
+                "organism": cfg.organism,
+                # You can get the list of all available organisms here:
+                # https://www.uniprot.org/help/taxonomy
+            }
+
+            r = requests.get(cfg.uniprot_url,
+                             headers={ "Accept" : "application/json"},
+                             params=params,
+                             timeout=cfg.timeout)
+            # if the response is not ok
+            if not r.ok:
+                descriptions.append(None)
+                sequences.append(None)
+                continue
+            response_body = json.loads(r.text)
+            # if the response body is empty
+            if not response_body:
+                descriptions.append(None)
+                sequences.append(None)
+                continue
+            description = ''
+            for comment in response_body[0]['comments']:
+                if comment['type'] == 'FUNCTION':
+                    for value in comment['text']:
+                        description += value['value']
+            sequence = response_body[0]['sequence']['sequence']
+            descriptions.append(description)
+            sequences.append(sequence)
+        return descriptions, sequences
+
+    def enrich_documents_with_rag(self, texts, docs):
+        """
+        Enrich a list of input UniProt gene names with their function and sequence.
+
+        Args:
+            texts: The list of gene names to be enriched.
+
+        Returns:
+            The list of enriched functions and sequences
+        """
+        return self.enrich_documents(texts)

{aiagents4pharma-1.32.0.dist-info → aiagents4pharma-1.33.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aiagents4pharma
-Version: 1.32.0
+Version: 1.33.0
 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-1.32.0.dist-info → aiagents4pharma-1.33.0.dist-info}/RECORD

@@ -75,7 +75,7 @@ aiagents4pharma/talk2knowledgegraphs/__init__.py,sha256=Z0Eo7LTiKk0STsr8VI7wkCLq
 aiagents4pharma/talk2knowledgegraphs/agents/__init__.py,sha256=iOAzuy_8A03tQDFtSBhC9dldUo62z5gfxcVtXAdLOJs,92
 aiagents4pharma/talk2knowledgegraphs/agents/t2kg_agent.py,sha256=IcXSZ2qQA1m-gS-o0Pj_g1oar8uPdhsbaovloUFka3Q,3058
 aiagents4pharma/talk2knowledgegraphs/configs/__init__.py,sha256=4_DVdpahaJ55yPl0aZotlFA_MYWLFF2cubWyKtBVI_Q,126
-aiagents4pharma/talk2knowledgegraphs/configs/config.yaml,sha256=bag4w3JCSqaojG37MTksy3ZehAPe3qoVzjIN2uh3nrc,229
+aiagents4pharma/talk2knowledgegraphs/configs/config.yaml,sha256=KubbjqcaMgSMiJ4085F7O-cul-dYUAF7cWLqaM8Ss-g,277
 aiagents4pharma/talk2knowledgegraphs/configs/agents/t2kg_agent/__init__.py,sha256=-fAORvyFmG2iSvFOFDixmt9OTQRR58y89uhhu2EgbA8,46
 aiagents4pharma/talk2knowledgegraphs/configs/agents/t2kg_agent/default.yaml,sha256=ENCGROwYFpR6g4QD518h73sshdn3vPVpotBMk1QJcpU,4830
 aiagents4pharma/talk2knowledgegraphs/configs/app/__init__.py,sha256=fKfc3FR7g5KjY9b6jzrU6cwKTVVpkoVZQS3dvUowu34,69
@@ -112,6 +112,7 @@ aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_sentencetransfo
 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_pubchem.py,sha256=bk27KElJxOvKJ2RTz4ftleExQPMyWWS755KKmlImzbk,1241
+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=C07YqUNYW7ofpKAzKh0lBovXKLvaiXFb3oJU6k1dvu4,411
 aiagents4pharma/talk2knowledgegraphs/tools/__init__.py,sha256=zpD4h7EYtyq0QNOqLd6bkxrPlPb2XN64ceI9ncgESrA,171
@@ -128,10 +129,11 @@ aiagents4pharma/talk2knowledgegraphs/utils/embeddings/huggingface.py,sha256=2vi_
 aiagents4pharma/talk2knowledgegraphs/utils/embeddings/nim_molmim.py,sha256=XH6JNfmMS38UEU7UGJeeabHfRykharnQpQaqjO86OlQ,1537
 aiagents4pharma/talk2knowledgegraphs/utils/embeddings/ollama.py,sha256=8w0sjt3Ex5YJ_XvpKl9UbhdTiiaoMIarbPUxLBU-1Uw,2378
 aiagents4pharma/talk2knowledgegraphs/utils/embeddings/sentence_transformer.py,sha256=36iKlisOpMtGR5xfTAlSHXWvPqVC_Jbezod8kbBBMVg,2136
-aiagents4pharma/talk2knowledgegraphs/utils/enrichments/__init__.py,sha256=JKGavA-umsGX3ng17_UYAvDBdbg-W-mPn8Q6JfP7J9U,143
+aiagents4pharma/talk2knowledgegraphs/utils/enrichments/__init__.py,sha256=gkHVwImeTnDBP_q4TWjn_CMJ-BMmt8NJqNkA1IOLvuI,174
 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/pubchem_strings.py,sha256=qsVlDCGGDkUCv-R5_xFGhrtLS7P0CfagnM2qATwiOFM,1333
+aiagents4pharma/talk2knowledgegraphs/utils/enrichments/uniprot_proteins.py,sha256=z0Jb3tt8VzRjzqI9oVcUvRlPPg6BUdmslfKDIEFE_h8,3013
 aiagents4pharma/talk2knowledgegraphs/utils/extractions/__init__.py,sha256=7gwwtfzKhB8GuOBD47XRi0NprwEXkOzwNl5eeu-hDTI,86
 aiagents4pharma/talk2knowledgegraphs/utils/extractions/pcst.py,sha256=m5p0yoJb7I19ua5yeQfXPf7c4r6S1XPwttsrM7Qoy94,9336
 aiagents4pharma/talk2scholars/__init__.py,sha256=NOZxTklAH1j1ggu97Ib8Xn9LCKudEWt-8dx8w7yxVD8,180
@@ -219,8 +221,8 @@ aiagents4pharma/talk2scholars/tools/zotero/utils/read_helper.py,sha256=lyrfpx8NH
 aiagents4pharma/talk2scholars/tools/zotero/utils/review_helper.py,sha256=IPD1V9yrBYaDnRe7sR6PrpwR82OBJbA2P_Tc6RbxAbM,2748
 aiagents4pharma/talk2scholars/tools/zotero/utils/write_helper.py,sha256=ALwLecy1QVebbsmXJiDj1GhGmyhq2R2tZlAyEl1vfhw,7410
 aiagents4pharma/talk2scholars/tools/zotero/utils/zotero_path.py,sha256=oIrfbOySgts50ksHKyjcWjRkPRIS88g3Lc0v9mBkU8w,6375
-aiagents4pharma-1.32.0.dist-info/licenses/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
-aiagents4pharma-1.32.0.dist-info/METADATA,sha256=o3uHTzLfOPglRJUlK6_vKAuJ0qwKhGt7BeiQHeF4U_o,16043
-aiagents4pharma-1.32.0.dist-info/WHEEL,sha256=0CuiUZ_p9E4cD6NyLD6UG80LBXYyiSYZOKDm5lp32xk,91
-aiagents4pharma-1.32.0.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
-aiagents4pharma-1.32.0.dist-info/RECORD,,
+aiagents4pharma-1.33.0.dist-info/licenses/LICENSE,sha256=IcIbyB1Hyk5ZDah03VNQvJkbNk2hkBCDqQ8qtnCvB4Q,1077
+aiagents4pharma-1.33.0.dist-info/METADATA,sha256=cv2sm_J63wHmZipscCFn4rQtFNAJSz-trdl-bAsHwDw,16043
+aiagents4pharma-1.33.0.dist-info/WHEEL,sha256=0CuiUZ_p9E4cD6NyLD6UG80LBXYyiSYZOKDm5lp32xk,91
+aiagents4pharma-1.33.0.dist-info/top_level.txt,sha256=-AH8rMmrSnJtq7HaAObS78UU-cTCwvX660dSxeM7a0A,16
+aiagents4pharma-1.33.0.dist-info/RECORD,,