tooluniverse 1.0.10__py3-none-any.whl → 1.0.11__py3-none-any.whl

tooluniverse/jaspar_tool.py

@@ -0,0 +1,30 @@
+import requests
+from typing import Any, Dict
+from .base_tool import BaseTool
+from .tool_registry import register_tool
+
+
+@register_tool("JASPARRESTTool")
+class JASPARRESTTool(BaseTool):
+    def __init__(self, tool_config: Dict):
+        super().__init__(tool_config)
+        self.base_url = "https://jaspar.elixir.no/api/v1"
+        self.session = requests.Session()
+        self.session.headers.update({"Accept": "application/json"})
+        self.timeout = 30
+
+    def _build_url(self, args: Dict[str, Any]) -> str:
+        url = self.tool_config["fields"]["endpoint"]
+        for k, v in args.items():
+            url = url.replace(f"{{{k}}}", str(v))
+        return url
+
+    def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
+        try:
+            url = self._build_url(arguments)
+            response = self.session.get(url, timeout=self.timeout)
+            response.raise_for_status()
+            data = response.json()
+            return {"status": "success", "data": data, "url": url}
+        except Exception as e:
+            return {"status": "error", "error": f"JASPAR API error: {str(e)}"}

tooluniverse/kegg_tool.py

@@ -0,0 +1,230 @@
+"""
+KEGG Database REST API Tool
+
+This tool provides access to the KEGG (Kyoto Encyclopedia of Genes and Genomes)
+database for pathway analysis, gene information, and organism data.
+"""
+
+import requests
+from typing import Dict, Any, Optional
+from .base_tool import BaseTool
+from .tool_registry import register_tool
+
+
+class KEGGRESTTool(BaseTool):
+    """Base class for KEGG REST API tools."""
+
+    def __init__(self, tool_config):
+        super().__init__(tool_config)
+        self.base_url = "https://rest.kegg.jp"
+        self.session = requests.Session()
+        self.session.headers.update(
+            {"Accept": "text/plain, application/json", "User-Agent": "ToolUniverse/1.0"}
+        )
+        self.timeout = 30
+
+    def _make_request(
+        self, endpoint: str, params: Optional[Dict] = None
+    ) -> Dict[str, Any]:
+        """Make a request to the KEGG API."""
+        url = f"{self.base_url}{endpoint}"
+        try:
+            response = self.session.get(url, params=params, timeout=self.timeout)
+            response.raise_for_status()
+
+            # KEGG API returns text/plain by default, parse as text
+            content = response.text.strip()
+
+            # Try to parse as structured data if possible
+            if content.startswith("{") or content.startswith("["):
+                try:
+                    return {"status": "success", "data": response.json()}
+                except Exception:
+                    pass
+
+            # Return as text data
+            return {
+                "status": "success",
+                "data": content,
+                "url": url,
+                "content_type": response.headers.get("content-type", "text/plain"),
+            }
+
+        except requests.exceptions.RequestException as e:
+            return {
+                "status": "error",
+                "error": f"KEGG API request failed: {str(e)}",
+                "url": url,
+            }
+
+    def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
+        """Execute the tool with given arguments."""
+        return self._make_request(self.endpoint, arguments)
+
+
+@register_tool("KEGGSearchPathway")
+class KEGGSearchPathway(KEGGRESTTool):
+    """Search KEGG pathways by keyword."""
+
+    def __init__(self, tool_config):
+        super().__init__(tool_config)
+        self.endpoint = "/find/pathway"
+
+    def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
+        """Search pathways with keyword."""
+        keyword = arguments.get("keyword", "")
+        if not keyword:
+            return {"status": "error", "error": "keyword is required"}
+
+        # KEGG API requires the search term in the URL path
+        endpoint = f"{self.endpoint}/{keyword}"
+        result = self._make_request(endpoint)
+
+        # Parse pathway results
+        if result.get("status") == "success" and isinstance(result.get("data"), str):
+            lines = result["data"].split("\n")
+            pathways = []
+            for line in lines:
+                if "\t" in line:
+                    parts = line.split("\t", 1)
+                    if len(parts) == 2:
+                        pathways.append(
+                            {"pathway_id": parts[0], "description": parts[1]}
+                        )
+            result["data"] = pathways
+            result["count"] = len(pathways)
+
+        return result
+
+
+@register_tool("KEGGGetPathwayInfo")
+class KEGGGetPathwayInfo(KEGGRESTTool):
+    """Get detailed pathway information by pathway ID."""
+
+    def __init__(self, tool_config):
+        super().__init__(tool_config)
+        self.endpoint = "/get"
+
+    def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
+        """Get pathway information."""
+        pathway_id = arguments.get("pathway_id", "")
+        if not pathway_id:
+            return {"status": "error", "error": "pathway_id is required"}
+
+        # Add pathway prefix if not present
+        if not pathway_id.startswith("path:"):
+            pathway_id = f"path:{pathway_id}"
+
+        # KEGG API requires the ID in the URL path
+        endpoint = f"{self.endpoint}/{pathway_id}"
+        result = self._make_request(endpoint)
+
+        # Parse pathway data
+        if result.get("status") == "success" and isinstance(result.get("data"), str):
+            lines = result["data"].split("\n")
+            pathway_info = {
+                "pathway_id": pathway_id,
+                "raw_data": result["data"],
+                "lines": len(lines),
+            }
+            result["data"] = pathway_info
+
+        return result
+
+
+@register_tool("KEGGFindGenes")
+class KEGGFindGenes(KEGGRESTTool):
+    """Find genes by keyword in KEGG database."""
+
+    def __init__(self, tool_config):
+        super().__init__(tool_config)
+        self.endpoint = "/find/genes"
+
+    def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
+        """Find genes with keyword."""
+        keyword = arguments.get("keyword", "")
+        if not keyword:
+            return {"status": "error", "error": "keyword is required"}
+
+        # KEGG API requires the search term in the URL path
+        # For gene search, we don't need organism prefix in the URL
+        endpoint = f"{self.endpoint}/{keyword}"
+        result = self._make_request(endpoint)
+
+        # Parse gene results
+        if result.get("status") == "success" and isinstance(result.get("data"), str):
+            lines = result["data"].split("\n")
+            genes = []
+            for line in lines:
+                if "\t" in line:
+                    parts = line.split("\t", 1)
+                    if len(parts) == 2:
+                        genes.append({"gene_id": parts[0], "description": parts[1]})
+            result["data"] = genes
+            result["count"] = len(genes)
+
+        return result
+
+
+@register_tool("KEGGGetGeneInfo")
+class KEGGGetGeneInfo(KEGGRESTTool):
+    """Get detailed gene information by gene ID."""
+
+    def __init__(self, tool_config):
+        super().__init__(tool_config)
+        self.endpoint = "/get"
+
+    def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
+        """Get gene information."""
+        gene_id = arguments.get("gene_id", "")
+        if not gene_id:
+            return {"status": "error", "error": "gene_id is required"}
+
+        # KEGG API requires the ID in the URL path
+        endpoint = f"{self.endpoint}/{gene_id}"
+        result = self._make_request(endpoint)
+
+        # Parse gene data
+        if result.get("status") == "success" and isinstance(result.get("data"), str):
+            lines = result["data"].split("\n")
+            gene_info = {
+                "gene_id": gene_id,
+                "raw_data": result["data"],
+                "lines": len(lines),
+            }
+            result["data"] = gene_info
+
+        return result
+
+
+@register_tool("KEGGListOrganisms")
+class KEGGListOrganisms(KEGGRESTTool):
+    """List available organisms in KEGG database."""
+
+    def __init__(self, tool_config):
+        super().__init__(tool_config)
+        self.endpoint = "/list/organism"
+
+    def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
+        """List organisms."""
+        result = self._make_request(self.endpoint)
+
+        # Parse organism list
+        if result.get("status") == "success" and isinstance(result.get("data"), str):
+            lines = result["data"].split("\n")
+            organisms = []
+            for line in lines:
+                if "\t" in line:
+                    parts = line.split("\t")
+                    if len(parts) >= 3:
+                        organisms.append(
+                            {
+                                "organism_code": parts[0],
+                                "organism_name": parts[1],
+                                "description": parts[2] if len(parts) > 2 else "",
+                            }
+                        )
+            result["data"] = organisms
+            result["count"] = len(organisms)
+
+        return result

tooluniverse/mpd_tool.py

@@ -0,0 +1,42 @@
+import requests
+from typing import Any, Dict
+from .base_tool import BaseTool
+from .tool_registry import register_tool
+
+
+@register_tool("MPDRESTTool")
+class MPDRESTTool(BaseTool):
+    def __init__(self, tool_config: Dict):
+        super().__init__(tool_config)
+        self.session = requests.Session()
+        self.session.headers.update({"Accept": "application/json"})
+        self.timeout = 30
+
+    def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
+        try:
+            # Use ENCODE as alternative data source for biological samples
+            strain = arguments.get("strain", "C57BL/6J")
+            limit = arguments.get("limit", 5)
+
+            # Build ENCODE API URL for experiments
+            # Query for general experiments as MPD alternative
+            url = f"https://www.encodeproject.org/search/?type=Experiment&format=json&limit={limit}"
+
+            response = self.session.get(url, timeout=self.timeout)
+            response.raise_for_status()
+
+            # Parse JSON response
+            data = response.json()
+
+            return {
+                "status": "success",
+                "data": data,
+                "url": url,
+                "query_info": {
+                    "strain": strain,
+                    "limit": limit,
+                    "data_source": "ENCODE (MPD alternative)",
+                },
+            }
+        except Exception as e:
+            return {"status": "error", "error": f"MPD API error: {str(e)}"}

tooluniverse/ncbi_eutils_tool.py

@@ -0,0 +1,96 @@
+"""
+NCBI E-utilities Tool with Rate Limiting
+
+This module provides a base class for NCBI E-utilities API tools with
+built-in rate limiting and retry logic to handle 429 errors.
+"""
+
+import time
+import requests
+from typing import Dict, Any, Optional
+from .base_tool import BaseTool
+
+
+class NCBIEUtilsTool(BaseTool):
+    """Base class for NCBI E-utilities tools with rate limiting."""
+
+    def __init__(self, tool_config):
+        super().__init__(tool_config)
+        self.base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"
+        self.last_request_time = 0
+        self.min_interval = 0.34  # ~3 requests/second (NCBI limit without API key)
+        self.max_retries = 3
+        self.initial_retry_delay = 1
+        self.session = requests.Session()
+        self.session.headers.update(
+            {"Accept": "application/json", "User-Agent": "ToolUniverse/1.0"}
+        )
+        self.timeout = 30
+
+    def _make_request(
+        self, endpoint: str, params: Optional[Dict] = None
+    ) -> Dict[str, Any]:
+        """Make request with rate limiting and retry logic."""
+        url = f"{self.base_url}{endpoint}"
+
+        for attempt in range(self.max_retries):
+            # Rate limiting
+            elapsed = time.time() - self.last_request_time
+            if elapsed < self.min_interval:
+                time.sleep(self.min_interval - elapsed)
+
+            try:
+                response = self.session.get(url, params=params, timeout=self.timeout)
+                self.last_request_time = time.time()
+                response.raise_for_status()
+
+                # Try to parse JSON response
+                try:
+                    data = response.json()
+                except ValueError:
+                    # If not JSON, return text
+                    data = response.text
+
+                return {
+                    "status": "success",
+                    "data": data,
+                    "url": url,
+                    "content_type": response.headers.get(
+                        "content-type", "application/json"
+                    ),
+                }
+
+            except requests.exceptions.HTTPError as e:
+                if e.response.status_code == 429 and attempt < self.max_retries - 1:
+                    # Exponential backoff for rate limiting
+                    delay = self.initial_retry_delay * (2**attempt)
+                    print(
+                        f"Rate limited, retrying in {delay} seconds... (attempt {attempt + 1}/{self.max_retries})"
+                    )
+                    time.sleep(delay)
+                    continue
+                else:
+                    return {
+                        "status": "error",
+                        "error": f"NCBI E-utilities API request failed: {str(e)}",
+                        "url": url,
+                        "status_code": (
+                            e.response.status_code if hasattr(e, "response") else None
+                        ),
+                    }
+            except requests.exceptions.RequestException as e:
+                return {
+                    "status": "error",
+                    "error": f"NCBI E-utilities API request failed: {str(e)}",
+                    "url": url,
+                }
+
+        return {
+            "status": "error",
+            "error": f"NCBI E-utilities API request failed after {self.max_retries} attempts",
+            "url": url,
+        }
+
+    def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
+        """Execute the tool with given arguments."""
+        return self._make_request(self.endpoint, arguments)