Refactor initialization process and add genome configuration

This commit refactors the initialization process in the `cli.py` file to include a new `init` command. The `init` command initializes the seqnado pipeline and sets up the correct environmental variables. It also adds the functionality to initialize genome files using a template file. The `get_genomes` function in the `helpers.py` file is modified to read the genome configuration from a JSON file and return the genome values. The commit also includes the addition of a new `init.sh` script that is used to initialize the environment for the SeqNado project. Lastly, a template file `genomes_template.json` is added to the `workflow/config` directory.

seqnado/cli.py

@@ -6,10 +6,50 @@
 import sys
 import pathlib
 import shlex
+from seqnado.helpers import get_genomes
 
 
 FILE = os.path.abspath(__file__)
 PACKAGE_DIR = os.path.dirname(FILE)
+GENOMES = get_genomes()
+
+
+
+@click.command()
+def init():
+    """
+    Initializes the seqnado pipeline
+     
+    """
+    import loguru.logger as logger
+    import os
+    import json
+
+    # Get current conda environment
+    conda_env = os.environ.get("CONDA_DEFAULT_ENV")
+    conda_env_ok = input(f"Current conda environment is {conda_env}. Is this correct? (y/n): ")
+    if conda_env_ok.lower() != "y":
+        logger.error("Please activate the correct conda environment and re-run the command")
+        sys.exit(1)
+
+    logger.info("Initialising the correct environmental variables for the pipeline")
+    os.system(f"bash {PACKAGE_DIR}/init.sh")
+
+    logger.info("Initialising genome files")
+    seqnado_config_dir = pathlib.Path('~/.config/seqnado').expanduser()
+    seqnado_config_dir.mkdir(parents=True, exist_ok=True)
+
+    genome_template = pathlib.Path(PACKAGE_DIR) / 'workflow' / 'config' / 'genomes_template.json'
+    genome_config = seqnado_config_dir / 'genomes.json'
+    if not genome_config.exists():
+        with open(genome_template, 'r') as f:
+            genome_template = json.load(f)
+
+        with open(genome_config, 'w') as f:
+            json.dump(genome_template, f)
+
+    logger.info("Initialisation complete")
+
 
 
 @click.command(context_settings=dict(ignore_unknown_options=True))

seqnado/helpers.py

@@ -291,3 +291,36 @@ def remove_unwanted_run_files():
 
         except Exception as e:
             print(e)
+
+
+def get_genomes(): 
+
+    import json
+    import sys
+
+    seqnado_config_dir = pathlib.Path('~/.config/seqnado').expanduser()
+    genome_config = seqnado_config_dir / 'genomes.json'
+
+    if genome_config.exists():
+        logger.debug(f"Genome config found at {genome_config}")
+        with open(genome_config, 'r') as f:
+            genome_values = json.load(f)
+
+        if genome_values.get('dm6'):
+            if "PATH" in  genome_values['dm6']['bt2_indices']:
+                logger.error(f'Template genome file found. Please update the genome file {genome_config} with the correct paths.')
+                sys.exit(1)
+
+    return genome_values
+
+
+
+
+
+
+
+
+
+
+    # with open(os.path.join(template_dir, "preset_genomes.json"), "r") as f:
+    #     genome_values = json.load(f)

seqnado/init.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+
+# This script is used to initialize the environment for the SeqNado project.
+
+
+echo "Adding SylabsCloud remote to apptainer - This will allow you to download and run the pre-made containers"
+apptainer remote add --no-login SylabsCloud cloud.sylabs.io
+apptainer remote use SylabsCloud
+
+
+IS_CCB=$(hostname | grep -c "imm-")
+
+if [ -z "$APPTAINER_BINDPATH" ]; then
+    if [ $IS_CCB -eq 1 ]; then
+        export APPTAINER_BINDPATH="/ceph:/ceph, /project:/project, /databank:/databank"
+        echo 'export APPTAINER_BINDPATH="/ceph:/ceph, /project:/project, /databank:/databank" >> ~/.bashrc
+    else
+        echo "This is not a CCB node. Please set the APPTAINER_BINDPATH environment variable to bind the necessary directories."
+    fi
+fi
+
+
+
+
+

seqnado/workflow/config/genomes_template.json

@@ -0,0 +1,9 @@
+{   
+    "dm6": {
+        "bt2_indices": "PATH_TO_INDICIES/dm6",
+        "star_indices": "PATH_TO_STAR/dm6/UCSC/STAR_2.7.10b",
+        "chromosome_sizes": "PATH/dm6/UCSC/sequence/dm6.chrom.sizes",
+        "gtf": "PATH/dm6/UCSC/genes/dm6.ncbiRefSeq.gtf",
+        "blacklist": "PATH/dm6/dm6-blacklist.v2.bed.gz"
+    }
+}