115 lines
4.3 KiB
Python
115 lines
4.3 KiB
Python
|
#!/usr/bin/env python3
|
||
|
|
"""Plan B verification: interspecies_synteny multi ref-side species (At, Ha, Os)."""
|
||
|
|
from __future__ import annotations
|
||
|
|
|
||
|
|
import json
|
||
|
|
import sys
|
||
|
|
from datetime import datetime
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
PROJECT_ROOT = Path(__file__).resolve().parents[1]
|
||
|
|
if str(PROJECT_ROOT) not in sys.path:
|
||
|
|
sys.path.insert(0, str(PROJECT_ROOT))
|
||
|
|
|
||
|
|
REAL_JOB = "job_1780471268646_fc6c66"
|
||
|
|
PREFIX = "Ls.SPL"
|
||
|
|
TARGET = "Ls"
|
||
|
|
REFS = ["At", "Ha", "Os"]
|
||
|
|
|
||
|
|
|
||
|
|
def step1_scope_normalization() -> dict:
|
||
|
|
from apps.web.vue3.main import _ensure_gene_family_scope_file
|
||
|
|
|
||
|
|
params = {
|
||
|
|
"scopeMode": "target_plus_reference",
|
||
|
|
"geneFamily": "SPL",
|
||
|
|
"targetSpecies": [TARGET],
|
||
|
|
"referenceSpecies": ["At"],
|
||
|
|
"refSpeciesList": REFS,
|
||
|
|
"comparativeSpecies": [],
|
||
|
|
}
|
||
|
|
scope_file, scope_id = _ensure_gene_family_scope_file(REAL_JOB, PREFIX, "interspecies_synteny", params)
|
||
|
|
scope_path = Path(scope_file)
|
||
|
|
data = json.loads(scope_path.read_text(encoding="utf-8")) if scope_path.exists() else {}
|
||
|
|
selected_refs = [sp for sp in (data.get("selected_species") or []) if sp != TARGET]
|
||
|
|
return {
|
||
|
|
"scope_file": scope_file,
|
||
|
|
"scope_id": scope_id,
|
||
|
|
"reference_species": data.get("reference_species"),
|
||
|
|
"comparative_species": data.get("comparative_species"),
|
||
|
|
"selected_species": data.get("selected_species"),
|
||
|
|
"scope_mode": data.get("scope_mode"),
|
||
|
|
"selected_ref_side": selected_refs,
|
||
|
|
"scope_ok": set(REFS).issubset(set(selected_refs)) and set(data.get("comparative_species") or []) >= {"Ha", "Os"},
|
||
|
|
}
|
||
|
|
|
||
|
|
|
||
|
|
def step2_cli_run(scope_file: str) -> dict:
|
||
|
|
from apps.web.pipeline_backend import JobInfo, run_stage
|
||
|
|
|
||
|
|
ws = PROJECT_ROOT / "workspace" / REAL_JOB
|
||
|
|
job = JobInfo(
|
||
|
|
job_id=REAL_JOB,
|
||
|
|
input_dir=str(PROJECT_ROOT / "input" / REAL_JOB),
|
||
|
|
workspace_dir=str(ws),
|
||
|
|
logs_dir=str(ws / "logs"),
|
||
|
|
created_at=datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
|
||
|
|
)
|
||
|
|
msg, manifest_path = run_stage(
|
||
|
|
stage="interspecies_synteny",
|
||
|
|
job=job,
|
||
|
|
prefix=PREFIX,
|
||
|
|
scope_file=scope_file,
|
||
|
|
target_species=[TARGET],
|
||
|
|
interspecies_ref_species=REFS,
|
||
|
|
interspecies_blast_engine="diamond",
|
||
|
|
)
|
||
|
|
manifest = {}
|
||
|
|
if manifest_path and Path(manifest_path).exists():
|
||
|
|
manifest = json.loads(Path(manifest_path).read_text(encoding="utf-8"))
|
||
|
|
metrics = manifest.get("metrics") or {}
|
||
|
|
params = manifest.get("parameters") or manifest.get("params") or {}
|
||
|
|
pairwise = metrics.get("pairwise_synteny") or metrics.get("pairs") or []
|
||
|
|
pair_keys = []
|
||
|
|
if isinstance(pairwise, dict):
|
||
|
|
pair_keys = list(pairwise.keys())
|
||
|
|
elif isinstance(pairwise, list):
|
||
|
|
pair_keys = [str(item.get("pair") or item) for item in pairwise if item]
|
||
|
|
log_files = sorted((ws / "logs").glob("*interspecies*"))
|
||
|
|
log_text = log_files[-1].read_text(encoding="utf-8", errors="ignore") if log_files else ""
|
||
|
|
cmd_line = next((line for line in log_text.splitlines() if "--ref-species" in line), "")
|
||
|
|
expected_pairs = {f"{TARGET}.{ref}" for ref in REFS}
|
||
|
|
return {
|
||
|
|
"message": msg,
|
||
|
|
"manifest_path": str(manifest_path or ""),
|
||
|
|
"status": manifest.get("status"),
|
||
|
|
"pair_total_count": metrics.get("pair_total_count"),
|
||
|
|
"pair_keys": pair_keys,
|
||
|
|
"selected_ref_species": params.get("selected_ref_species") or params.get("ref_species"),
|
||
|
|
"cmd_has_three_refs": all(ref in cmd_line for ref in REFS),
|
||
|
|
"cmd_line": cmd_line[:500],
|
||
|
|
"pairs_ok": metrics.get("pair_total_count", 0) >= 3 and expected_pairs.issubset(set(pair_keys) | set(metrics.get("pair_ids") or [])),
|
||
|
|
}
|
||
|
|
|
||
|
|
|
||
|
|
def main() -> int:
|
||
|
|
results = {"job": REAL_JOB, "prefix": PREFIX, "refs": REFS}
|
||
|
|
s1 = step1_scope_normalization()
|
||
|
|
results["step1_scope"] = s1
|
||
|
|
if not s1.get("scope_ok"):
|
||
|
|
print(json.dumps(results, indent=2, ensure_ascii=False))
|
||
|
|
print("ALL_CHECKS_PASSED=False")
|
||
|
|
return 1
|
||
|
|
|
||
|
|
s2 = step2_cli_run(s1["scope_file"])
|
||
|
|
results["step2_run"] = s2
|
||
|
|
passed = bool(s1.get("scope_ok") and s2.get("cmd_has_three_refs") and s2.get("pair_total_count", 0) >= 3)
|
||
|
|
results["ALL_CHECKS_PASSED"] = passed
|
||
|
|
print(json.dumps(results, indent=2, ensure_ascii=False))
|
||
|
|
print(f"ALL_CHECKS_PASSED={passed}")
|
||
|
|
return 0 if passed else 1
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
raise SystemExit(main())
|