Merge pull request #3 from frapercan/dev

Dev

Dockerfile

@@ -15,16 +15,14 @@ RUN python3 -m venv /opt/venv
 
 # Activate the virtual environment and install Python packages
 RUN /opt/venv/bin/pip install --upgrade pip \
-    && /opt/venv/bin/pip install protein-metamorphisms-is --no-cache-dir
+    && /opt/venv/bin/pip install fantasia --no-cache-dir
 
 
 # Add the virtual environment to the PATH
 ENV PATH="/opt/venv/bin:$PATH"
 
 # Copy application files and set the working directory
-COPY . /app
-WORKDIR /app
 
 # Default command to keep the container running
-ENTRYPOINT ["python3", "-m", "FANTASIA.main"]
+ENTRYPOINT ["python3", "-m", "fantasia.main"]
 

docker-compose.yml

@@ -16,6 +16,8 @@ services:
       - fantasia-network
     volumes:
       - $HOME/fantasia:/root/fantasia  # Sincroniza /home/xaxi/fantasia con /root/fantasia en el contenedor
+      - $HOME/.cache/huggingface:/root/.cache/huggingface  # Monta la caché de Hugging Face en el contenedor
+
 
 
 

fantasia/config.yaml

@@ -8,7 +8,7 @@ DB_HOST: pgvectorsql
 DB_PORT: 5432
 DB_NAME: BioData
 
-rabbitmq_host: localhost
+rabbitmq_host: rabbitmq
 rabbitmq_user: guest
 rabbitmq_password: guest
 
@@ -24,15 +24,15 @@ fantasia_output_csv: ~/fantasia/results/
 redundancy_file: ~/fantasia/redundancy/output.fasta
 
 fantasia_prefix: finger_zinc
-max_distance: 1.1
+max_distance: 0.5
 length_filter: 5000
 redundancy_filter: 0.65
 
 embedding:
   types:
     - 1 # ESM
     - 2 # Prost
-    - 3 # Prot
+#    - 3 # Prot
   batch_size: 50 # Queue
 
   embedding_batch_size: 10 # Model input size
@@ -41,6 +41,6 @@ topgo?: True
 
 
 
-constants: "./fantasia/constants.yaml"
+constants: "./opt/venv/lib/python3.12/site-packages/fantasia/constants.yaml"
 
 

fantasia/main.py

@@ -29,14 +29,7 @@ def initialize(config_path):
     load_dump_to_db(tar_path, conf)
 
 
-def run_pipeline(config_path, fasta_path=None):
-    # Leer la configuración
-    conf = read_yaml_config(config_path)
-
-    # Actualizar la ruta del FASTA si se proporciona
-    if fasta_path:
-        conf["fantasia_input_fasta"] = fasta_path
-
+def run_pipeline(conf):
     # Ejecutar el pipeline de fantasia
     current_date = datetime.now().strftime("%Y%m%d%H%M%S")
     embedder = SequenceEmbedder(conf, current_date)
@@ -59,16 +52,37 @@ def wait_forever():
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="fantasia: Command Handler")
     parser.add_argument("command", type=str, nargs="?", default=None, help="Command to execute: initialize or run")
-    parser.add_argument("--config", type=str, default="./fantasia/config.yaml", help="Path to the configuration YAML file.")
+    parser.add_argument("--config", type=str, default="./opt/venv/lib/python3.12/site-packages/fantasia/config.yaml", help="Path to the configuration YAML file.")
     parser.add_argument("--fasta", type=str, help="Path to the input FASTA file.")
+    parser.add_argument("--prefix", type=str, help="Prefix for output files.")
+    parser.add_argument("--max_distance", type=float, help="Maximum distance for similarity matching.")
+    parser.add_argument("--length_filter", type=int, help="Length filter threshold for sequences.")
+    parser.add_argument("--redundancy_filter", type=float, help="Redundancy filter threshold.")
     args = parser.parse_args()
 
     if args.command == "initialize":
         print("Initializing embeddings and database...")
         initialize(args.config)
     elif args.command == "run":
         print("Running the fantasia pipeline...")
-        run_pipeline(config_path=args.config, fasta_path=args.fasta)
+
+        # Leer la configuración una sola vez
+        conf = read_yaml_config(args.config)
+
+        # Sobrescribir parámetros con los valores del CLI
+        if args.fasta:
+            conf["fantasia_input_fasta"] = args.fasta
+        if args.prefix:
+            conf["fantasia_prefix"] = args.prefix
+        if args.max_distance is not None:
+            conf["max_distance"] = args.max_distance
+        if args.length_filter is not None:
+            conf["length_filter"] = args.length_filter
+        if args.redundancy_filter is not None:
+            conf["redundancy_filter"] = args.redundancy_filter
+
+        # Pasar la configuración modificada directamente
+        run_pipeline(conf)
     elif args.command is None:
         wait_forever()
     else:

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "FANTASIA"
-version = "0.1.0"
+version = "0.2.0"
 description = "Functional ANnoTAtion based on embedding space SImilArity"
 authors = ["Francisco Miguel Pérez Canales <[email protected]>","Gemma Martínez Redondo <[email protected]>"]
 readme = "README.md"