aiagents4pharma 1.32.0__tar.gz → 1.33.0__tar.gz

{aiagents4pharma-1.32.0 → aiagents4pharma-1.33.0}/PKG-INFO

@@ -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 → aiagents4pharma-1.33.0}/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-1.33.0/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-1.32.0 → aiagents4pharma-1.33.0}/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-1.33.0/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 → aiagents4pharma-1.33.0}/aiagents4pharma.egg-info/PKG-INFO

@@ -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 → aiagents4pharma-1.33.0}/aiagents4pharma.egg-info/SOURCES.txt

@@ -121,6 +121,7 @@ aiagents4pharma/talk2knowledgegraphs/tests/test_utils_embeddings_sentencetransfo
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_enrichments.py
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_ollama.py
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_pubchem.py
+aiagents4pharma/talk2knowledgegraphs/tests/test_utils_enrichments_uniprot.py
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_kg_utils.py
 aiagents4pharma/talk2knowledgegraphs/tests/test_utils_pubchem_utils.py
 aiagents4pharma/talk2knowledgegraphs/tools/__init__.py
@@ -141,6 +142,7 @@ aiagents4pharma/talk2knowledgegraphs/utils/enrichments/__init__.py
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/enrichments.py
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/ollama.py
 aiagents4pharma/talk2knowledgegraphs/utils/enrichments/pubchem_strings.py
+aiagents4pharma/talk2knowledgegraphs/utils/enrichments/uniprot_proteins.py
 aiagents4pharma/talk2knowledgegraphs/utils/extractions/__init__.py
 aiagents4pharma/talk2knowledgegraphs/utils/extractions/pcst.py
 aiagents4pharma/talk2scholars/__init__.py

aiagents4pharma-1.33.0/release_version.txt

@@ -0,0 +1 @@
+v1.33.0

aiagents4pharma-1.32.0/release_version.txt

@@ -1 +0,0 @@
-v1.32.0