aurelian 0.3.2__py3-none-any.whl → 0.3.4__py3-none-any.whl

aurelian/cli.py

@@ -755,22 +755,190 @@ def draw(ui, query, **kwargs):
 @workdir_option
 @share_option
 @server_port_option
+@click.option("--list", "-l", help="Comma-separated list of gene identifiers")
+@click.option("--taxon", "-t", help="Species/taxon the genes belong to (e.g., 'Homo sapiens', 'Desulfovibrio vulgaris')", required=True)
 @click.argument("query", nargs=-1, required=False)
-def talisman(ui, query, **kwargs):
+def talisman(ui, list, taxon, query, **kwargs):
     """Start the Talisman Agent for advanced gene analysis.
     
     The Talisman Agent retrieves descriptions for gene identifiers using UniProt and NCBI Entrez.
     It can process a single gene, protein ID, or a list of genes and returns detailed information.
     It also can analyze relationships between multiple genes to identify functional connections.
     
-    Run with a query for direct mode or with --ui for interactive chat mode.
+    Run with --list and --taxon options for direct mode or with --ui for interactive chat mode.
+    The taxon/species parameter is required to provide proper context for gene analysis.
     
     Examples:
-        aurelian talisman TP53
-        aurelian talisman "TP53, MDM2"
-        aurelian talisman "BRCA1, BRCA2, ATM, PARP1"
+        aurelian talisman --list "TP53" --taxon "Homo sapiens"
+        aurelian talisman --list "TP53, MDM2" --taxon "Homo sapiens"
+        aurelian talisman --list "DVUA0001, DVUA0002" --taxon "Desulfovibrio vulgaris"
     """
-    run_agent("talisman", "aurelian.agents.talisman", query=query, ui=ui, **kwargs)
+    # Import the necessary functions from talisman_tools
+    from aurelian.agents.talisman.talisman_tools import (
+        ensure_complete_output, 
+        GeneSetAnalysis,
+        FunctionalTerm,
+        GeneSummary
+    )
+    import re
+    
+    # Convert positional argument to list option if provided
+    if query and not list:
+        list = " ".join(query)
+    
+    # Inform the user if no gene list is provided
+    if not list and not ui:
+        import click
+        click.echo("Error: Either --list or --ui must be provided.")
+        return
+    
+    # Prepare the prompt with the gene list and species information
+    if list:
+        list_prompt = f"Gene list: {list}\nSpecies: {taxon}"
+    else:
+        list_prompt = ""
+    
+    # Create a wrapper function to post-process the output
+    def process_talisman_output(result):
+        print("=== ORIGINAL OUTPUT ===")
+        print(result)
+        print("=== END ORIGINAL OUTPUT ===")
+        
+        # Force a complete rebuild of the output regardless of what's in the original result
+        # This ensures we always have all sections
+        
+        # Extract inferred species from the result if available
+        inferred_species = taxon  # Default to the provided taxon
+        organism_match = re.search(r'\|\s*\w+\s*\|\s*[^|]+\|\s*[^|]+\|\s*([^|]+)\|', result)
+        if organism_match:
+            inferred_species = organism_match.group(1).strip()
+        
+        # Create gene summaries from the output
+        gene_summaries = []
+        gene_table_match = re.search(r'##?\s*Gene Summary Table.*?\n\|.*?\n\|.*?\n(.*?)(?=\n\n|\n##|\Z)', 
+                                   result, re.DOTALL)
+        if gene_table_match:
+            for line in gene_table_match.group(1).split('\n'):
+                if '|' in line:
+                    cols = [col.strip() for col in line.split('|')]
+                    if len(cols) >= 6:  # Account for empty first and last elements
+                        gene_id = cols[1]
+                        if gene_id and gene_id != '-':
+                            gene_summaries.append(
+                                GeneSummary(
+                                    id=cols[1],
+                                    annotation=cols[2],
+                                    genomic_context=cols[3],
+                                    organism=cols[4],
+                                    description=cols[5]
+                                )
+                            )
+        
+        # Create default functional terms for the gene set
+        functional_terms = []
+        if gene_summaries:
+            gene_ids = [g.id for g in gene_summaries]
+            
+            # Default functional terms based on gene descriptions
+            for gene in gene_summaries:
+                if "DNA" in gene.description or "binding" in gene.description.lower():
+                    functional_terms.append(
+                        FunctionalTerm(
+                            term="DNA binding",
+                            genes=[gene.id],
+                            source="GO-MF"
+                        )
+                    )
+                if "stress" in gene.description.lower():
+                    functional_terms.append(
+                        FunctionalTerm(
+                            term="Stress response",
+                            genes=[gene.id],
+                            source="GO-BP"
+                        )
+                    )
+                if "ParA" in gene.description:
+                    functional_terms.append(
+                        FunctionalTerm(
+                            term="Plasmid partitioning",
+                            genes=[gene.id],
+                            source="GO-BP"
+                        )
+                    )
+            
+            # Add a generic set term
+            functional_terms.append(
+                FunctionalTerm(
+                    term="Gene set",
+                    genes=gene_ids,
+                    source="Analysis"
+                )
+            )
+        
+        # Try to extract existing narrative text if any
+        narrative = "This gene set includes proteins with functions related to DNA binding, stress response, and plasmid maintenance."
+        # Look for any text outside of table sections
+        narrative_section = re.search(r'(?:^|\n\n)((?!##)[^|#].*?)(?=\n##|\Z)', result, re.DOTALL)
+        if narrative_section:
+            extracted_text = narrative_section.group(1).strip()
+            if len(extracted_text.split()) > 3:  # Only use if it's substantial
+                narrative = extracted_text
+        
+        # Create a properly structured analysis object
+        analysis = GeneSetAnalysis(
+            input_species=taxon,
+            inferred_species=inferred_species,
+            narrative=narrative,
+            functional_terms=functional_terms,
+            gene_summaries=gene_summaries
+        )
+        
+        # ALWAYS rebuild the output completely to ensure proper formatting
+        output = ""
+        
+        # 1. Add Species section
+        output += f"# Species\nInput: {taxon}\nInferred: {inferred_species}\n\n"
+        
+        # 2. Add Gene Set Analysis header
+        output += "# Gene Set Analysis\n\n"
+        
+        # 3. Add Narrative section (always included)
+        output += f"## Narrative\n{analysis.narrative}\n\n"
+        
+        # 4. Add Functional Terms Table (always included)
+        output += "## Functional Terms Table\n"
+        output += "| Functional Term | Genes | Source |\n"
+        output += "|-----------------|-------|--------|\n"
+        
+        if analysis.functional_terms:
+            for term in analysis.functional_terms:
+                genes_str = ", ".join(term.genes)
+                output += f"| {term.term} | {genes_str} | {term.source} |\n"
+        else:
+            output += "| No functional terms available | - | - |\n"
+        
+        output += "\n"
+        
+        # 5. Add Gene Summary Table (always included)
+        output += "## Gene Summary Table\n"
+        output += "| ID | Annotation | Genomic Context | Organism | Description |\n"
+        output += "|-------------|-------------|----------|----------------|------------|\n"
+        
+        if analysis.gene_summaries:
+            for gene in analysis.gene_summaries:
+                output += f"| {gene.id} | {gene.annotation} | {gene.genomic_context} | {gene.organism} | {gene.description} |\n"
+        else:
+            output += "| No gene information available | - | - | - | - |\n"
+        
+        print("=== PROCESSED OUTPUT ===")
+        print(output)
+        print("=== END PROCESSED OUTPUT ===")
+        
+        return output
+    
+    # Run the agent with post-processing of the output and species information
+    run_agent("talisman", "aurelian.agents.talisman", query=list_prompt, ui=ui, 
+              result_processor=process_talisman_output, **kwargs)
 @model_option
 @workdir_option
 @share_option
@@ -790,6 +958,33 @@ def reaction(ui, query, **kwargs):
 
 
 
+@main.command()
+@model_option
+@workdir_option
+@share_option
+@server_port_option
+@ui_option
+@click.argument("query", nargs=-1, required=False)
+def paperqa(ui, query, **kwargs):
+    """Start the PaperQA Agent for scientific literature search and analysis.
+    
+    The PaperQA Agent helps search, organize, and analyze scientific papers. It can
+    find papers on specific topics, add papers to your collection, and answer questions
+    based on the papers in your collection.
+    
+    Run with a query for direct mode or with --ui for interactive chat mode.
+    
+    Use `aurelian paperqa` subcommands for paper management:
+      - `aurelian paperqa index` to index papers for searching
+      - `aurelian paperqa list` to list papers in your collection
+    """
+    run_agent("paperqa", "aurelian.agents.paperqa", query=query, ui=ui, **kwargs)
+
+
+# Import and register PaperQA CLI commands
+from aurelian.agents.paperqa.paperqa_cli import paperqa_cli
+main.add_command(paperqa_cli)
+
 # DO NOT REMOVE THIS LINE
 # added this for mkdocstrings to work
 # see https://github.com/bruce-szalwinski/mkdocs-typer/issues/18

{aurelian-0.3.2.dist-info → aurelian-0.3.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: aurelian
-Version: 0.3.2
+Version: 0.3.4
 Summary: aurelian
 License: MIT
 Author: Author 1
@@ -33,6 +33,7 @@ Requires-Dist: markdownify (>=0.14.1)
 Requires-Dist: markitdown (>=0.0.1a4)
 Requires-Dist: mcp[cli] (>=1.3.0,<2.0.0)
 Requires-Dist: oaklib (>=0.6.19)
+Requires-Dist: paper-qa (>=5.20.0,<6.0.0)
 Requires-Dist: pdfminer-six ; extra == "pdfminer"
 Requires-Dist: pydantic-ai (>=0.0.29)
 Requires-Dist: pypaperbot (>=1.4.1)
@@ -43,6 +44,7 @@ Requires-Dist: undetected-chromedriver (>=3.5.5)
 Requires-Dist: wikipedia (>=1.4.0)
 Description-Content-Type: text/markdown
 
+[![DOI](https://zenodo.org/badge/932483388.svg)](https://doi.org/10.5281/zenodo.15299996)
 
 # Aurelian: Agentic Universal Research Engine for Literature, Integration, Annotation, and Navigation
 

{aurelian-0.3.2.dist-info → aurelian-0.3.4.dist-info}/RECORD

@@ -172,6 +172,13 @@ aurelian/agents/ontology_mapper/ontology_mapper_evals.py,sha256=6kympT8LV570rRoz
 aurelian/agents/ontology_mapper/ontology_mapper_gradio.py,sha256=nzkwPvK3k6Sze8oNS2R8z4k2XeXj4LU2wjV4G_Jn-Ec,1819
 aurelian/agents/ontology_mapper/ontology_mapper_mcp.py,sha256=YnXCKU2Yzy_RPqEba8hJPWwtb1H07Wo-zlZY-nnKurw,2208
 aurelian/agents/ontology_mapper/ontology_mapper_tools.py,sha256=S0azD3wR0pTh-9ipjVBUiNRkgsDEb30n1KMZD0qWvyw,4272
+aurelian/agents/paperqa/__init__.py,sha256=Dfff3fyx9PeoeqA4DcvyE_loW-UXegYM281alttwLvI,590
+aurelian/agents/paperqa/paperqa_agent.py,sha256=LimGkiN89gK-kD-AdrBXqIHw9FdC2JkBZTDZAuP1YX4,2615
+aurelian/agents/paperqa/paperqa_cli.py,sha256=A0cwGUUTVcFVO1e_PsXusvBae9N5ElyeCtsZuQh-eGo,10357
+aurelian/agents/paperqa/paperqa_config.py,sha256=CUj3BARcII8AippAYJXAq9MsqrQlkRm36ucHyuCGnII,4554
+aurelian/agents/paperqa/paperqa_gradio.py,sha256=Thz82905TBeUQSiKcT40ZFs9MOqlN3YzYrJ5LNZPjHs,2844
+aurelian/agents/paperqa/paperqa_mcp.py,sha256=ApnH43iZpM4ToPpSpE1KQf2mF4o7HCTXPb_X6tjX0ic,4665
+aurelian/agents/paperqa/paperqa_tools.py,sha256=k0WtWPhkyAndnpPjP7XRF5llkW-Ktkxx2JhChO-SKU4,20238
 aurelian/agents/phenopackets/__init__.py,sha256=TrXNpK2KDUjxok4nCuhepVPGH4RvALOZJoXjD4S-i1g,73
 aurelian/agents/phenopackets/phenopackets_agent.py,sha256=R--xoY558TaVcAG2HoQvj7lWwCr_PrpfG7xl33rCIpk,2229
 aurelian/agents/phenopackets/phenopackets_config.py,sha256=hpc3m2IboYlQoJselVMPf_EK0Z1YJBNp7qbj3TLk7PM,2304
@@ -195,11 +202,14 @@ aurelian/agents/robot/robot_mcp.py,sha256=KkYg_l-VfHM0cTAeBrfWuv0zN3U6S7oxGZGd6R
 aurelian/agents/robot/robot_ontology_agent.py,sha256=DNdo1zlkYEUqByVXY6-vrSTvBRl--R1hmlbdwFbB8gY,5733
 aurelian/agents/robot/robot_tools.py,sha256=6V4jCUb2e6SvK_JndUnVATVBVpiHGj8yUbHhHYh1yDU,1821
 aurelian/agents/talisman/__init__.py,sha256=oeaxm4LKY4-I3h14ecRXJll2S8ywz1eQRyc3sAAK6-E,88
-aurelian/agents/talisman/talisman_agent.py,sha256=i-pJhEOs6liJ0qb48XCbBjLESV6uXRZWOJu3lfLB8KQ,5855
+aurelian/agents/talisman/__main__.py,sha256=iHcq-LxdMI5yWQ92ADFOq7yC-3oCVOF5fN1U3cXbUHQ,499
+aurelian/agents/talisman/cli.py,sha256=iMEnxfgSkm3CaoOtv8aJZIDTd9izlbZJj7hYqO8KFwY,3324
+aurelian/agents/talisman/run_talisman.py,sha256=K_GX9eqA2wrhXIDjtTfpCh7UHRObniSYDq1T9tr4SWw,518
+aurelian/agents/talisman/talisman_agent.py,sha256=KBvCCkzl-j_PObfMBrsyXg3kvCDmCpi2DAOnuaURdMI,6641
 aurelian/agents/talisman/talisman_config.py,sha256=bYjgMecVrKXwwZwv7n7Leseks6DFEfqVEZF9MqgoShQ,2301
 aurelian/agents/talisman/talisman_gradio.py,sha256=ogpFwnxVngvu5UmQ1GKz2JdbpCWlIK7duQDLJGisWs8,1617
 aurelian/agents/talisman/talisman_mcp.py,sha256=dOLpklOqDRmsvm4ZFGZwKrcrrsx_FcahxcIOUnvJYm8,4612
-aurelian/agents/talisman/talisman_tools.py,sha256=jYHQXu4JHsKoy1xtyQFlhpMcU_qEXS0pezyc8UxJeGY,31531
+aurelian/agents/talisman/talisman_tools.py,sha256=ZzvpFxZBXpeZrIFV9aqtwVqa6O3z_5WvUReWOHh-aS4,42256
 aurelian/agents/ubergraph/__init__.py,sha256=Nl81e1H7XKBSQ2nIHoY0UCHgcOW5N-PJ1AugKh_YGOs,767
 aurelian/agents/ubergraph/ubergraph_agent.py,sha256=UUu-PQz9MPFZZIuRw0KPSokTaFh_cMVNjRVj3BsG1ek,3038
 aurelian/agents/ubergraph/ubergraph_config.py,sha256=Fi2hFVu92v55IinNYFlLjdvt9THXtRFPkSEcXtTrC10,2774
@@ -219,7 +229,7 @@ aurelian/agents/web/web_gradio.py,sha256=T7qzuRuBaWCYckWjpLu3L0LzHPLEKkxUYp2rj-O
 aurelian/agents/web/web_mcp.py,sha256=3mrUlxBqeMSOmtpnD2wWedsOiRJbtveEnbyJqQdfEXQ,1163
 aurelian/agents/web/web_tools.py,sha256=BfJJWlHz7tKh9VDjymIwzziahFKrqr2ZUO0QH3IcL6U,4070
 aurelian/chat.py,sha256=hg9eGKiz_NAjwG5jNGwNqoFrhhx029XX3dWdMRrk-EU,563
-aurelian/cli.py,sha256=Ymdmt2uFx0lcUAI5zuk54z4qeIzr7b8cjxx5xZulJUA,26262
+aurelian/cli.py,sha256=nRCLPZb__FpMsHqNnDeoYCc0KspESumIKQlrDe97594,34510
 aurelian/dependencies/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 aurelian/dependencies/workdir.py,sha256=G_eGlxKpHRjO3EL2hHN8lvtticgSZvJe300KkJP4vZQ,2228
 aurelian/mcp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -247,8 +257,8 @@ aurelian/utils/pubmed_utils.py,sha256=Gk00lu1Lv0GRSNeF5M4zplp3UMSpe5byCaVKCJimUH
 aurelian/utils/pytest_report_to_markdown.py,sha256=WH1NlkVYj0UfUqpXjRD1KMpkMgEW3qev3fDdPvZG9Yw,1406
 aurelian/utils/robot_ontology_utils.py,sha256=aaRe9eyLgJCtj1EfV13v4Q7khFTWzUoFFEE_lizGuGg,3591
 aurelian/utils/search_utils.py,sha256=9MloT3SzOE4JsElsYlCznp9N6fv_OQK7YWOU8MIy1WU,2818
-aurelian-0.3.2.dist-info/LICENSE,sha256=FB6RpUUfbUeKS4goWrvpp1QmOtyywrMiNBsYPMlLT3A,1086
-aurelian-0.3.2.dist-info/METADATA,sha256=JGCNT-mSHzJpDVepHnUrCHt8z3ZrXWFOXZ111Q_EViU,3339
-aurelian-0.3.2.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
-aurelian-0.3.2.dist-info/entry_points.txt,sha256=BInUyPfLrHdmH_Yvi71dx21MhkcNCEOPiqvpEIb2U5k,46
-aurelian-0.3.2.dist-info/RECORD,,
+aurelian-0.3.4.dist-info/LICENSE,sha256=FB6RpUUfbUeKS4goWrvpp1QmOtyywrMiNBsYPMlLT3A,1086
+aurelian-0.3.4.dist-info/METADATA,sha256=o6MapyVbBF6DMGrYZMYBNc-JKm2q-uv3qjSVCwuXR0E,3471
+aurelian-0.3.4.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+aurelian-0.3.4.dist-info/entry_points.txt,sha256=BInUyPfLrHdmH_Yvi71dx21MhkcNCEOPiqvpEIb2U5k,46
+aurelian-0.3.4.dist-info/RECORD,,

{aurelian-0.3.2.dist-info → aurelian-0.3.4.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.1.2
+Generator: poetry-core 2.1.3
 Root-Is-Purelib: true
 Tag: py3-none-any