Merge pull request #3 from PyEED/blastToolsLocally

Blast tools locally

README.md

@@ -2,3 +2,11 @@
 [![Publish Docker image](https://github.com/EnzymeML/EnzymeML_JupyterLab/actions/workflows/release_image.yaml/badge.svg)](https://github.com/EnzymeML/EnzymeML_JupyterLab/actions/workflows/release_image.yaml)
 
  🐳 Docker image with JupyterLab and `pyeed`
+
+ #### Ports Used by different containers
+
+ - `cytoscape` uses `6080` and `8787`
+ - jupyterlab uses `8888`
+ - clustalo uses `5001`
+ - blast uses `6001`
+ - mmseq2 uses `8000`

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
+
+# Expose the port the server will run on
+EXPOSE 6001
+
+# Run the Python server script
+CMD ["python3", "app.py"]

blast/app.py

@@ -0,0 +1,71 @@
+from fastapi import FastAPI, HTTPException, Request
+from pydantic import BaseModel
+import subprocess
+import os
+import uuid
+from typing import Optional
+import logging
+
+app = FastAPI()
+logger = logging.getLogger(__name__)
+
+class BlastRequest(BaseModel):
+    tool: str
+    query: str
+    db: str
+    evalue: str
+    outfmt: str
+
+
+## ENDPOINTS --------------------------
+
+def create_fastas_file_from_seq(seq, filename):
+    with open(filename, 'w') as file:
+        file.write(f">seq\n{seq}\n")
+
+@app.get("/")
+async def read_root():
+    return {"message": "Welcome to the BLAST API!"}
+
+# this get json params
+@app.post("/run_blast")
+async def run_blast(request: Request):
+    request = await request.json()
+
+    query_filename = f"in.fasta"
+    result_filename = f"out.out"
+    # create empty file
+    open(result_filename, 'w').close()
+
+    # Create the FASTA file
+    create_fastas_file_from_seq(request['query'], query_filename)
+
+    # Run the BLAST command
+    command = [
+        request['tool'],
+        '-query', query_filename,
+        '-db', request['db'],
+        '-evalue', request['evalue'],
+        '-outfmt', request['outfmt'],
+        '-num_threads', request['num_threads'],
+        '-out', result_filename,
+        '-max_target_seqs', '10000'
+    ]
+
+    try:
+        subprocess.run(command, check=True)
+    except subprocess.CalledProcessError as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+    with open(result_filename, 'r') as file:
+        result = file.read()
+
+    return result
+
+
+
+if __name__ == '__main__':
+    import uvicorn
+
+    uvicorn.run("app:app", host="0.0.0.0", port=6001, reload=True)

blast/reload_development.sh

@@ -0,0 +1,4 @@
+sudo docker stop blast_docker
+sudo docker remove blast_docker
+sudo docker build --no-cache -t blast_docker .
+sudo docker run --name blast_docker --volume /mnt/databases:/blast/blastdb -p 6001:6001 blast_docker

clustalo/Dockerfile

@@ -11,4 +11,7 @@ RUN wget http://www.clustal.org/omega/clustalo-1.2.4-Ubuntu-x86_64 \
 COPY requirements.txt .
 RUN pip install -r requirements.txt
 
+COPY app.py .
+
+
 CMD ["python", "app.py"]

clustalo/requirements.txt

@@ -1,3 +1,3 @@
 fastapi
 python-multipart
-uvicorn
+uvicorn

mmseqs2/Dockerfile

@@ -0,0 +1,19 @@
+# Base image for mmseqs2
+FROM soedinglab/mmseqs2:latest
+
+# Add the standard Debian repositories to ensure we can install all packages
+RUN echo "deb http://deb.debian.org/debian bullseye main contrib non-free" > /etc/apt/sources.list
+RUN echo "deb http://security.debian.org/debian-security bullseye-security main contrib non-free" >> /etc/apt/sources.list
+
+# Install Python and Flask
+RUN apt-get update && apt-get install -y python3 python3-pip
+RUN pip3 install fastapi uvicorn
+
+# Copy the FastAPI app to the container
+COPY app.py app.py
+
+# Expose the port on which FastAPI will run
+EXPOSE 8000
+
+# Start the FastAPI server when the container starts
+CMD ["python3", "app.py"]

mmseqs2/app.py

@@ -0,0 +1,133 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import subprocess
+import os
+from uuid import uuid4
+import shutil
+
+app = FastAPI()
+
+# Define a model for the input parameters
+class MMSeqsParams(BaseModel):
+    query: str  # The query sequence
+    database: str
+    output: str  # The output directory
+    sensitivity: float = 7.5  # Sensitivity parameter for mmseqs2
+    threads: int = 4  # Number of threads to use
+    blast_format: bool = True  # Option to convert to BLAST+ format
+
+# Dictionary to keep track of running jobs and results
+job_results = {}
+
+def create_fastas_file_from_seq(seq, filename):
+    with open(filename, 'w') as file:
+        file.write(f">seq\n{seq}\n")
+
+def create_queryDB_from_seq(filename):
+    # this will create a db from a single sequence file
+    # the command is mmseqs createdb <input> <output>
+    # the output should be a file with the same name as the input but with the extension .db
+
+    command = [
+        "mmseqs", "createdb",
+        filename,
+        filename.replace('fasta', '') + ".db"
+    ]
+
+    try:
+        subprocess.run(command, check=True)
+
+    except subprocess.CalledProcessError as e:
+        raise HTTPException(status_code=600, detail=str(e))
+
+
+@app.get("/")
+async def read_root():
+    return {"message": "Welcome to the MMSeqs2 API!"}
+
+@app.post("/run_mmseqs")
+async def run_mmseqs(params: MMSeqsParams):
+    # Create a unique job id
+    job_id = str(uuid4())
+    output_dir = f"/tmp/{job_id}"
+
+    # Prepare the output directory
+    os.makedirs(output_dir, exist_ok=True)
+
+    # Prepare paths
+    result_m8_path = os.path.join(output_dir, "result.m8")
+    result_tsv_path = os.path.join(output_dir, "result.tsv")
+
+    # Create the FASTA file
+    path_query = os.path.join(output_dir, "query.fasta")
+    path_queryDB = path_query.replace('fasta', '') + ".db"
+    create_fastas_file_from_seq(params.query, path_query)
+    create_queryDB_from_seq(path_query)
+
+    # Run the mmseqs2 search command
+    command = [
+        "mmseqs", "search", 
+        path_queryDB, 
+        params.database, 
+        os.path.join(output_dir, "result"), 
+        output_dir, 
+        "--threads", str(params.threads), 
+        "--sensitivity", str(params.sensitivity)
+    ]
+
+    try:
+        # Execute mmseqs search
+        subprocess.run(command, check=True)
+
+        # Convert the results to BLAST+ format if requested
+        if params.blast_format:
+            # mmseqs convertalis queryDB targetDB resultDB resultDB.m8
+            # Convert to BLAST tabular format (BLAST m8 format)
+            convert_command = [
+                "mmseqs", "convertalis", 
+                params.query, 
+                params.database, 
+                os.path.join(output_dir, "result"), 
+                result_m8_path, 
+            ]
+            subprocess.run(convert_command, check=True)
+
+            # Store the result path for m8 format
+            job_results[job_id] = {
+                "status": "completed",
+                "result_path": result_m8_path
+            }
+        else:
+            # Store the result path for standard mmseqs2 output (TSV format)
+            job_results[job_id] = {
+                "status": "completed",
+                "result_path": result_tsv_path
+            }
+
+        return {"job_id": job_id}
+    except subprocess.CalledProcessError as e:
+        raise HTTPException(status_code=500, detail=f"mmseqs2 failed: {str(e)}")
+
+@app.get("/results/{job_id}")
+async def get_results(job_id: str):
+    # Check if the job exists
+    if job_id not in job_results:
+        raise HTTPException(status_code=404, detail="Job not found")
+
+    # Get the result path
+    result = job_results[job_id]
+
+    # Read and return the result (assuming it's a text file you want to read and return)
+    result_file = result["result_path"]
+    if os.path.exists(result_file):
+        with open(result_file, "r") as file:
+            data = file.read()
+        return {"status": result["status"], "results": data}
+    else:
+        raise HTTPException(status_code=404, detail="Result file not found")
+
+
+if __name__ == '__main__':
+    import uvicorn
+
+    uvicorn.run("app:app", host="0.0.0.0", port=8000, reload=True)

mmseqs2/reload_development.sh

@@ -0,0 +1,4 @@
+sudo docker stop mmseq_docker
+sudo docker remove mmseq_docker
+sudo docker build --no-cache -t mmseq_docker .
+sudo docker run --name mmseq_docker --volume /mnt/databases:/app -p 8000:8000 mmseq_docker

requirements.txt

@@ -1,2 +1,5 @@
 pyeed @ git+https://github.com/PyEED/pyeed.git@main
+chromatopy @ git+https://github.com/FAIRChemistry/chromatopy.git
+MTPHandler @ git+https://github.com/FAIRChemistry/MTPHandler.git
 python-multipart
+