aurelian 0.3.2__tar.gz → 0.3.3__tar.gz

{aurelian-0.3.2 → aurelian-0.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: aurelian
-Version: 0.3.2
+Version: 0.3.3
 Summary: aurelian
 License: MIT
 Author: Author 1

{aurelian-0.3.2 → aurelian-0.3.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "aurelian"
-version = "0.3.2"
+version = "0.3.3"
 description = "aurelian"
 authors = ["Author 1 <author@org.org>"]
 license = "MIT"

aurelian-0.3.3/src/aurelian/agents/talisman/__main__.py

@@ -0,0 +1,17 @@
+#!/usr/bin/env python3
+"""
+Main entry point to run the talisman agent.
+"""
+import os
+import sys
+from pydantic_ai import chat
+
+# Add the parent directory to the path for absolute imports
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "../../../")))
+
+from aurelian.agents.talisman.talisman_agent import talisman_agent
+from aurelian.agents.talisman.talisman_config import get_config
+
+if __name__ == "__main__":
+    config = get_config()
+    chat(talisman_agent, deps=config)

aurelian-0.3.3/src/aurelian/agents/talisman/cli.py

@@ -0,0 +1,70 @@
+"""
+CLI interface for the talisman agent.
+This may not be in the original code, but let's add it to make sure it's properly configured.
+"""
+import logging
+import re
+from pydantic_ai import RunContext
+
+from aurelian.agents.talisman.talisman_config import TalismanConfig
+from aurelian.agents.talisman.talisman_tools import GeneSetAnalysis, FunctionalTerm, GeneSummary
+
+def format_talisman_output(result):
+    """Format the talisman output to ensure it always has all three sections."""
+    logging.info("Post-processing talisman output")
+    
+    # Check if output already has proper sections
+    has_narrative = re.search(r'^\s*##\s*Narrative', result, re.MULTILINE) is not None
+    has_functional_terms = re.search(r'^\s*##\s*Functional Terms Table', result, re.MULTILINE) is not None
+    has_gene_summary = re.search(r'^\s*##\s*Gene Summary Table', result, re.MULTILINE) is not None
+    
+    # If all sections are present, return as is
+    if has_narrative and has_functional_terms and has_gene_summary:
+        return result
+    
+    # Need to reconstruct the output
+    # Extract gene summary table if it exists
+    gene_table_match = re.search(r'^\s*##\s*Gene Summary Table\s*\n(.*?)(?=$|\n\n|\Z)', 
+                                result, re.MULTILINE | re.DOTALL)
+    
+    if gene_table_match:
+        gene_table = gene_table_match.group(0)
+        
+        # Extract existing text that might be a narrative
+        narrative_text = result.replace(gene_table, '').strip()
+        
+        # Create a proper narrative section if missing
+        if not has_narrative and narrative_text:
+            narrative_section = "## Narrative\n" + narrative_text + "\n\n"
+        else:
+            narrative_section = "## Narrative\nThese genes may have related functions as indicated in the gene summary table.\n\n"
+        
+        # Create a functional terms section if missing
+        if not has_functional_terms:
+            # Extract gene IDs from the gene table
+            gene_ids = []
+            for line in gene_table.split('\n'):
+                if '|' in line and not line.strip().startswith('|--') and not 'ID |' in line:
+                    parts = line.split('|')
+                    if len(parts) > 1:
+                        gene_id = parts[1].strip()
+                        if gene_id and gene_id != 'ID':
+                            gene_ids.append(gene_id)
+            
+            # Create a simple functional terms table
+            functional_terms = "## Functional Terms Table\n"
+            functional_terms += "| Functional Term | Genes | Source |\n"
+            functional_terms += "|-----------------|-------|--------|\n"
+            functional_terms += f"| Gene set | {', '.join(gene_ids)} | Analysis |\n\n"
+        else:
+            # Find and extract existing functional terms section
+            ft_match = re.search(r'^\s*##\s*Functional Terms Table\s*\n(.*?)(?=^\s*##\s*|\Z)', 
+                                result, re.MULTILINE | re.DOTALL)
+            functional_terms = ft_match.group(0) if ft_match else ""
+        
+        # Reconstruct the output with all sections
+        formatted_output = "# Gene Set Analysis\n\n" + narrative_section + functional_terms + gene_table
+        return formatted_output
+    
+    # If no gene table was found, return the original result
+    return result

aurelian-0.3.3/src/aurelian/agents/talisman/run_talisman.py

@@ -0,0 +1,18 @@
+#!/usr/bin/env python3
+"""
+Standalone script to run the talisman agent directly.
+"""
+import os
+import sys
+from pydantic_ai import chat
+
+# Add the src directory to the path for imports
+src_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../../../"))
+sys.path.insert(0, src_dir)
+
+from aurelian.agents.talisman.talisman_agent import talisman_agent
+from aurelian.agents.talisman.talisman_config import get_config
+
+if __name__ == "__main__":
+    config = get_config()
+    chat(talisman_agent, deps=config)

{aurelian-0.3.2 → aurelian-0.3.3}/src/aurelian/agents/talisman/talisman_agent.py

@@ -1,5 +1,6 @@
 """
 Agent for working with gene information using the UniProt API and NCBI Entrez.
+Provides structured information in the form of Narrative, Functional Terms Table, and Gene Summary Table.
 """
 from pydantic_ai import Agent
 
@@ -70,38 +71,54 @@ The analysis will cover multiple types of relationships:
 - Physical interactions
 - Genetic interactions
 
-IMPORTANT: For gene set analysis, ALWAYS include a distinct section titled "## Terms" 
-that contains a semicolon-delimited list of functional terms relevant to the gene set, 
-ordered by relevance. These terms should include:
-- Gene Ontology biological process terms (e.g., DNA repair, oxidative phosphorylation, signal transduction)
-- Molecular function terms (e.g., kinase activity, DNA binding, transporter activity)
-- Cellular component/localization terms (e.g., nucleus, plasma membrane, mitochondria)
-- Pathway names (e.g., glycolysis, TCA cycle, MAPK signaling)
-- Co-regulation terms (e.g., stress response regulon, heat shock response)
-- Interaction networks (e.g., protein complex formation, signaling cascade)
-- Metabolic process terms (e.g., fatty acid synthesis, amino acid metabolism)
-- Regulatory mechanisms (e.g., transcriptional regulation, post-translational modification)
-- Disease associations (if relevant, e.g., virulence, pathogenesis, antibiotic resistance)
-- Structural and functional domains/motifs (e.g., helix-turn-helix, zinc finger)
-
-Example of Terms section:
-## Terms
-DNA damage response; p53 signaling pathway; apoptosis; cell cycle regulation; tumor suppression; DNA repair; protein ubiquitination; transcriptional regulation; nuclear localization; cancer predisposition
-
-IMPORTANT: After the Terms section, ALWAYS include a "## Gene Summary Table" with a markdown table 
-summarizing the genes analyzed, with the following columns in this exact order:
-- ID: The gene identifier (same as Gene Symbol)
-- Annotation: Genomic coordinates or accession with position information
-- Genomic Context: Information about the genomic location (chromosome, plasmid, etc.)
-- Organism: The organism the gene belongs to
-- Description: The protein/gene function description
+For gene set analysis, your output MUST always include three distinct sections:
+
+1. First, a "## Narrative" section providing a concise explanation of the functional and categorical relationships between the genes. This should:
+   - Prioritize explanations involving most or all genes in the set
+   - Refer to specific subsets of genes when discussing specialized functions
+   - Highlight the most significant shared pathways, processes, or disease associations
+   - Be clear, concise, and focused on biological meaning
+
+2. Second, a "## Functional Terms Table" that presents key functional terms in a tabular format with these columns:
+   - Functional Term: The biological term or concept (e.g., DNA repair, kinase activity)
+   - Genes: The genes associated with this term (comma-separated list)
+   - Source: The likely source database or ontology (e.g., GO-BP, KEGG, Reactome, GO-MF, GO-CC, Disease)
+
+The functional terms should include various types:
+- Gene Ontology biological process terms (e.g., DNA repair, oxidative phosphorylation)
+- Molecular function terms (e.g., kinase activity, DNA binding)
+- Cellular component/localization terms (e.g., nucleus, plasma membrane)
+- Pathway names (e.g., glycolysis, MAPK signaling)
+- Disease associations (if relevant)
+- Structural and functional domains/motifs (if relevant)
+
+Example of Functional Terms Table:
+## Functional Terms Table
+| Functional Term | Genes | Source |
+|-----------------|-------|--------|
+| DNA damage response | BRCA1, BRCA2, ATM | GO-BP |
+| Homologous recombination | BRCA1, BRCA2 | Reactome |
+| Tumor suppression | BRCA1, BRCA2, ATM | Disease |
+| Nuclear localization | BRCA1, BRCA2, ATM | GO-CC |
+| Kinase activity | ATM | GO-MF |
+| PARP inhibitor sensitivity | BRCA1, BRCA2, PARP1 | Pathway |
+
+3. Third, a "## Gene Summary Table" with a markdown table summarizing the genes analyzed, 
+with the following columns in this exact order:
+   - ID: The gene identifier (same as Gene Symbol)
+   - Annotation: Genomic coordinates or accession with position information
+   - Genomic Context: Information about the genomic location (chromosome, plasmid, etc.)
+   - Organism: The organism the gene belongs to
+   - Description: The protein/gene function description
 
 Example of Gene Summary Table:
 ## Gene Summary Table
 | ID | Annotation | Genomic Context | Organism | Description |
 |-------------|-------------|----------|----------------|------------|
 | BRCA1 | NC_000017.11 (43044295..43125483) | Chromosome 17 | Homo sapiens | Breast cancer type 1 susceptibility protein |
-| TP53 | NC_000017.11 (7668402..7687550) | Chromosome 17 | Homo sapiens | Tumor suppressor protein |
+| BRCA2 | NC_000013.11 (32315474..32400266) | Chromosome 13 | Homo sapiens | Breast cancer type 2 susceptibility protein |
+| ATM | NC_000011.10 (108222484..108369102) | Chromosome 11 | Homo sapiens | ATM serine/threonine kinase |
+| PARP1 | NC_000001.11 (226360251..226408516) | Chromosome 1 | Homo sapiens | Poly(ADP-ribose) polymerase 1 |
 
 For bacterial genes, the table format would be:
 | ID | Annotation | Genomic Context | Organism | Description |
@@ -123,4 +140,4 @@ talisman_agent = Agent(
 talisman_agent.tool(get_gene_description)
 talisman_agent.tool(get_gene_descriptions)
 talisman_agent.tool(get_genes_from_list)
-talisman_agent.tool(analyze_gene_set)
+#talisman_agent.tool(analyze_gene_set)