Add helper script to generate SLURM cluster configuration from annotation config

Author: wyim-pgl

README.md

@@ -109,6 +109,9 @@ snakemake -n --snakefile bin/Snakefile_annotate
 ./bin/annotate_toydata.sh
 ```
 
+Helper script:
+- `bin/generate_cluster_from_config.py`: regenerate `cluster_annotate.yml` from `config_annotate.yml` so SLURM 요청 자원이 파이프라인 threads/memory와 동기화될 때 사용.
+
 For a detailed tutorial with toy data, see the **[Wiki](Wiki.md)**.
 
 ## Installation
@@ -168,10 +171,12 @@ snakemake -n --snakefile bin/Snakefile_annotate
 # Submit to SLURM
 sbatch -A [account] -p [partition] -c 1 --mem=1g \
   -J annotate -o annotate.out -e annotate.err \
-  --wrap="./bin/annotate_toydata.sh"
+  --wrap="./bin/annotate_toydata.sh
+"
 
 # Or run directly
 ./bin/annotate_toydata.sh
+
 ```
 
 **Output:** `results/complete_draft.gff3`

Wiki.md

@@ -547,3 +547,16 @@ With the test environment above (4 nodes, 256 CPUs, 256 GB/node), the toy datase
 
 - Issues: https://github.com/plantgenomicslab/Sylvan/issues
 - See also: [README.md](README.md) for configuration reference
+
+
+### Generate cluster config from config_annotate
+```
+python bin/generate_cluster_from_config.py   --config config/config_annotate.yml   --out    config/cluster_annotate.yml   --account cpu-s1-pgl-0 --partition cpu-s1-pgl-0
+```
+(To regenerate toydata cluster config, point --config/--out to toydata paths.)
+```
+python bin/generate_cluster_from_config.py   --config toydata/config/config_annotate.yml   --out    toydata/config/cluster_annotate.yml   --account cpu-s1-pgl-0 --partition cpu-s1-pgl-0
+```
+```
+chmod 775 bin/generate_cluster_from_config.py
+```

bin/generate_cluster_from_config.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python
+"""
+Generate a cluster_annotate.yml from a config_annotate.yml.
+
+Usage:
+  python bin/generate_cluster_from_config.py \
+    --config config/config_annotate.yml \
+    --out config/cluster_annotate.yml \
+    --account cpu-s1-pgl-0 --partition cpu-s1-pgl-0
+
+Only top-level sections that contain ncpus/threads/memory/time are copied.
+"""
+
+from __future__ import annotations
+
+import argparse
+from pathlib import Path
+from typing import Any, Dict
+
+import yaml
+
+
+def build_arg_parser() -> argparse.ArgumentParser:
+    p = argparse.ArgumentParser(description="Generate cluster_annotate.yml from config_annotate.yml")
+    p.add_argument("--config", required=True, help="Path to config_annotate.yml")
+    p.add_argument("--out", required=True, help="Output path for cluster_annotate.yml")
+    p.add_argument("--account", default="placeholder", help="SLURM account (default: placeholder)")
+    p.add_argument("--partition", default="placeholder", help="SLURM partition (default: placeholder)")
+    p.add_argument("--time", default="14-00:00:00", help="Walltime (default: 14-00:00:00)")
+    p.add_argument("--default-memory", default="4g", help="Default memory for __default__ (default: 4g)")
+    p.add_argument("--default-ncpus", type=int, default=1, help="Default CPUs for __default__ (default: 1)")
+    p.add_argument(
+        "--output-pattern",
+        default="results/logs/{rule}_{wildcards}.out",
+        help="Output log pattern for __default__",
+    )
+    p.add_argument(
+        "--error-pattern",
+        default="results/logs/{rule}_{wildcards}.err",
+        help="Error log pattern for __default__",
+    )
+    return p
+
+
+def load_config(path: Path) -> Dict[str, Any]:
+    with path.open() as fh:
+        return yaml.safe_load(fh) or {}
+
+
+def should_copy_section(section: Dict[str, Any]) -> bool:
+    return any(key in section for key in ("ncpus", "threads", "memory", "time"))
+
+
+def main() -> None:
+    args = build_arg_parser().parse_args()
+    cfg_path = Path(args.config)
+    out_path = Path(args.out)
+
+    cfg = load_config(cfg_path)
+
+    cluster: Dict[str, Any] = {
+        "__default__": {
+            "account": args.account,
+            "partition": args.partition,
+            "memory": args.default_memory,
+            "ncpus": args.default_ncpus,
+            "nodes": 1,
+            "time": args.time,
+            "name": "{rule}.{wildcards}",
+            "output": args.output_pattern,
+            "error": args.error_pattern,
+        }
+    }
+
+    for name, section in cfg.items():
+        if isinstance(section, dict) and should_copy_section(section):
+            cluster[name] = {}
+            for key in ("ncpus", "threads", "memory", "time"):
+                if key in section:
+                    cluster[name][key] = section[key]
+
+    out_path.parent.mkdir(parents=True, exist_ok=True)
+    with out_path.open("w") as fh:
+        yaml.safe_dump(cluster, fh, sort_keys=False, default_flow_style=False)
+
+    print(f"Wrote cluster config to {out_path}")
+
+
+if __name__ == "__main__":
+    main()