Merge pull request #111 from PyEED/graph-db

Graph db

Author: haeussma

.github/workflows/lint.yaml

@@ -0,0 +1,28 @@
+name: Lint
+
+on: pull_request
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.x"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install poetry
+          poetry install --with dev
+
+      - name: Run Ruff
+        run: |
+          poetry run ruff check .
+          poetry run ruff format --check .
+
+      - name: Run mypy
+        run: |
+          poetry run mypy src/

.gitignore

@@ -5,6 +5,8 @@ __pycache__/
 
 # C extensions
 *.so
+.vscode/
+.huggingface/
 
 # Distribution / packaging
 .Python
@@ -158,4 +160,9 @@ pyrightconfig.json
 
 poetry.lock
 
-.ruff_cache
+.ruff_cache
+
+# Test python files
+test.py
+
+docker-compose.yml

README.md

@@ -7,9 +7,11 @@
 [![Documentation](https://github.com/PyEED/pyeed/actions/workflows/make_docs.yaml/badge.svg)](https://github.com/PyEED/pyeed/actions/workflows/make_docs.yaml)
 
 ## About 📖
-pyEED is a toolkit enabling object-oriented analysis of protein sequences, instead of working with sequences in a file-oriented fashion. This will enable the user to easily access and manipulate sequence information and to perform analyses on the sequence data.  
+pyeed is a toolkit enabling object-oriented analysis of protein sequences, instead of working with sequences in a file-oriented fashion. This will enable the user to easily access and manipulate sequence information and to perform analyses on the sequence data.  
 This library is currently under development and thus the API is subject to change.
 
+![PyEED](./docs/figs/pyeed-model.png)
+
 
 ## Installation ⚙️
 
@@ -20,9 +22,4 @@ pip install git+https://github.com/PyEED/pyeed.git
 
 ## Quick start 🚀
 
-Library is currently refactored, quick start will be updated soon!
-
-## Documentation 📘
-
-Check out the [documentation](https://pyeed.github.io/pyeed/) for in-depth information on how to setup `pyeed`, 
-use the build-in tools, and store sequence data in databases. 
+### Launch Neo4j database via Docker and mount to a local directory

docker/blast/Dockerfile

@@ -0,0 +1,17 @@
+FROM ncbi/blast
+
+# Install Python and Flask
+RUN apt-get update && apt-get install -y python3 python3-pip
+RUN pip3 install fastapi uvicorn
+
+# Add the Python script to the container
+COPY app.py /usr/local/bin/app.py
+
+# Set the working directory
+WORKDIR /usr/local/bin
+
+# Disable Python output buffering
+ENV PYTHONUNBUFFERED=1
+
+# Run the Python server script
+CMD ["python3", "app.py"]

docker/blast/app.py

@@ -0,0 +1,147 @@
+import logging
+import os
+import subprocess
+import sys
+
+from fastapi import FastAPI, HTTPException, Request
+from fastapi.responses import RedirectResponse
+
+app = FastAPI()
+
+# Configure logging to output to stdout without buffering
+logging.basicConfig(
+    level=logging.DEBUG,
+    format="%(levelname)s - %(message)s",
+    stream=sys.stdout,
+)
+logger = logging.getLogger(__name__)
+
+
+def to_fasta(seq: str) -> str:
+    return f">query_sequence\n{seq}"
+
+
+def _check_db_path_correct(db_path: str, db_name: str) -> None:
+    # check if db_path exists
+    if not os.path.exists(db_path):
+        raise HTTPException(
+            status_code=400, detail=f"Database path does not exist: {db_path}"
+        )
+    # check if db_path is a directory
+    if not os.path.isdir(db_path):
+        raise HTTPException(
+            status_code=400, detail=f"Database path is not a directory: {db_path}"
+        )
+
+
+@app.get("/")
+async def read_root() -> None:
+    logger.debug("Entering root endpoint")
+    return RedirectResponse(url="/docs")  # type: ignore
+
+
+@app.get("/blastp_help")
+def blastp_help() -> str:
+    logger.debug("Entering /blastp_help endpoint")
+
+    command = ["blastp", "-help"]
+    logger.debug(f"Running command: {command}")
+
+    try:
+        result = subprocess.run(command, capture_output=True, text=True)
+
+        # Return the help text
+        return result.stdout
+    except subprocess.CalledProcessError as e:
+        # Log and raise an HTTP exception if the subprocess fails
+        logger.error(f"blastp help command failed: {e.stderr}")
+        raise HTTPException(status_code=400, detail=f"Command failed: {e.stderr}")
+
+
+@app.get("/blastn_help")
+def blastn_help() -> str:
+    logger.debug("Entering /blastn_help endpoint")
+
+    command = ["blastn", "-help"]
+    logger.debug(f"Running command: {command}")
+
+    try:
+        result = subprocess.run(command, capture_output=True, text=True)
+        return result.stdout
+    except subprocess.CalledProcessError as e:
+        logger.error(f"blastn help command failed: {e.stderr}")
+        raise HTTPException(status_code=400, detail=f"Command failed: {e.stderr}")
+
+
+@app.post("/blast")
+async def run_blast(request: Request) -> dict[str, str]:
+    """Run BLAST search with provided parameters."""
+    try:
+        data = await request.json()
+        logger.debug(f"Received request data: {data}")
+
+        _check_db_path_correct(data["db_path"], data["db_name"])
+
+        mode = data["mode"]
+        sequence = data["sequence"]
+        logger.debug(f"Sequence received: {sequence}")
+        db_path = data["db_path"]
+        db_name = data["db_name"]
+        evalue = float(data["evalue"])
+        max_target_seqs = int(data["max_target_seqs"])
+        num_threads = int(data["num_threads"])
+
+        query_path = "/usr/local/bin/data/query.fasta"
+        result_path = "/usr/local/bin/data/result.out"
+
+        # Create FASTA file
+        with open(query_path, "w") as file:
+            file.write(to_fasta(sequence))
+        with open(query_path, "r") as file:
+            logger.debug(f" file content: {file.read()}")
+
+        # debug db path exists
+        logger.debug(f"db path exists: {os.path.exists(db_path)}")
+        # debug list all files in db path
+        logger.debug(f"files in db path: {os.listdir(db_path)}")
+        # Run BLAST
+        command = [
+            mode,
+            "-query",
+            query_path,
+            "-db",
+            f"{db_path}/{db_name}",
+            "-evalue",
+            str(evalue),
+            "-outfmt",
+            "6",
+            "-num_threads",
+            str(num_threads),
+            "-out",
+            result_path,
+            "-max_target_seqs",
+            str(max_target_seqs),
+        ]
+
+        logger.debug(f"Running command: {command}")
+        subprocess.run(command, capture_output=True, check=True, text=True)
+
+        # Read results
+        with open(result_path, "r") as file:
+            result_data = file.read()
+
+        # Cleanup
+        os.remove(query_path)
+        os.remove(result_path)
+
+        return {"result": result_data}
+
+    except Exception as e:
+        logger.error(f"Error running BLAST: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run("app:app", host="0.0.0.0", port=6001, reload=True)

docker/blast/reload_development.sh

@@ -0,0 +1,4 @@
+sudo docker stop blast
+sudo docker remove blast
+sudo docker build --no-cache -t blast_image .
+sudo docker run --name blast --volume /home/ala/BA/mydb:/blast/db --volume /mnt/databases_shared/:/blast/db/custom  -p 6001:6001 blast_image

docker/blast/test_db/protein_db.pdb

@@ -0,0 +1,24 @@
+{
+  "version": "1.2",
+  "dbname": "protein_db",
+  "dbtype": "Protein",
+  "db-version": 5,
+  "description": "Protein Database",
+  "number-of-letters": 893,
+  "number-of-sequences": 10,
+  "last-updated": "2025-01-20T15:57:00",
+  "number-of-volumes": 1,
+  "bytes-total": 51054,
+  "bytes-to-cache": 1088,
+  "files": [
+    "protein_db.pdb",
+    "protein_db.phr",
+    "protein_db.pin",
+    "protein_db.pog",
+    "protein_db.pos",
+    "protein_db.pot",
+    "protein_db.psq",
+    "protein_db.ptf",
+    "protein_db.pto"
+  ]
+}