feat: chanjo2 activation

.github/workflows/docker_build_publish_develop.yml

@@ -15,7 +15,7 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        container-name: [align_qc, annotate, ascatNgs, cadd, cnvkit, cnvpytor, coverage_qc, delly, gatk, htslib, multiqc, msisensorpro, purecn, somalier, varcall_py3, varcall_py27, vcf2cytosure]
+        container-name: [align_qc, annotate, ascatNgs, cadd, cnvkit, cnvpytor, coverage_qc, delly, d4tools, gatk, htslib, multiqc, msisensorpro, purecn, somalier, varcall_py3, varcall_py27, vcf2cytosure]
     steps:
       - name: Git checkout
         id: git_checkout

.github/workflows/docker_build_publish_release.yml

@@ -11,7 +11,7 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        container-name: [align_qc, annotate, ascatNgs, cadd, cnvkit, cnvpytor, coverage_qc, delly, gatk, htslib, msisensorpro, multiqc, purecn, somalier, varcall_py3, varcall_py27, vcf2cytosure]
+        container-name: [align_qc, annotate, ascatNgs, cadd, cnvkit, cnvpytor, coverage_qc, delly, d4tools, gatk, htslib, msisensorpro, multiqc, purecn, somalier, varcall_py3, varcall_py27, vcf2cytosure]
     steps:
       - name: Git checkout
         id: git_checkout

BALSAMIC/assets/scripts/cluster_job_status.py

@@ -0,0 +1,27 @@
+#!/usr/bin/env python3
+
+import subprocess
+import sys
+
+jobid = sys.argv[1]
+
+try:
+    output = subprocess.check_output(
+        ["/usr/bin/sacct", "-j", jobid, "--format=State", "--noheader"],
+        stderr=subprocess.DEVNULL,
+    )
+    state = output.decode().split()[0].strip()
+except subprocess.CalledProcessError:
+    # Job not found, maybe it was purged
+    print("unknown")
+    sys.exit(0)
+
+# Normalize states for Snakemake
+if "COMPLETED" in state:
+    print("success")
+elif any(
+    x in state for x in ["FAILED", "CANCELLED", "TIMEOUT", "NODE_FAIL", "OUT_OF_MEMORY"]
+):
+    print("failed")
+else:
+    print("running")

BALSAMIC/assets/scripts/scan_finished_jobid_status.py

@@ -0,0 +1,94 @@
+import click
+import re
+import subprocess
+from pathlib import Path
+
+
+def extract_job_ids(log_dir):
+    jobid_pattern = re.compile(r"\.(\d+)\.(?:out|err)$")
+    return {
+        match.group(1)
+        for file in log_dir.iterdir()
+        if (match := jobid_pattern.search(file.name))
+    }
+
+
+def get_job_state(jobid):
+    try:
+        result = subprocess.run(
+            ["/usr/bin/scontrol", "show", "job", jobid],
+            capture_output=True,
+            text=True,
+            check=True,
+        )
+        return result.stdout
+    except subprocess.CalledProcessError:
+        click.echo(f"Could not check job {jobid} (may not exist).")
+        return None
+
+
+def extract_stderr_path(output_text):
+    match = re.search(r"StdErr=(\S+)", output_text)
+    return match.group(1) if match else "N/A"
+
+
+def categorize_job(jobid, output_text, failed, cancelled):
+    stderr_path = extract_stderr_path(output_text)
+    if "JobState=FAILED" in output_text:
+        failed.append((jobid, stderr_path))
+    elif "JobState=CANCELLED" in output_text:
+        cancelled.append((jobid, stderr_path))
+
+
+def write_results(output_file, failed, cancelled):
+    with output_file.open("a") as out_f:
+        if failed:
+            out_f.write("Failed jobs:\n")
+            for jobid, stderr in failed:
+                out_f.write(f"{jobid}\t{stderr}\n")
+        elif cancelled:
+            out_f.write("Cancelled jobs:\n")
+            for jobid, stderr in cancelled:
+                out_f.write(f"{jobid}\t{stderr}\n")
+        else:
+            click.echo("All jobs completed successfully.")
+    click.echo(f"Results written to {output_file}")
+
+
+@click.command()
+@click.argument(
+    "log_dir", type=click.Path(exists=True, file_okay=False, path_type=Path)
+)
+@click.option(
+    "--output",
+    "-o",
+    required=True,
+    type=click.Path(writable=True, path_type=Path),
+    help="Path to output file for failed jobs.",
+)
+def check_failed_jobs(log_dir: Path, output: Path):
+    """
+    Scan LOG_DIR for SLURM log files (*.out, *.err), extract job IDs,
+    and check if any jobs have failed or been cancelled using `scontrol show job JOBID`.
+
+    If --output is provided, results are written to a file.
+    """
+    job_ids = extract_job_ids(log_dir)
+
+    if not job_ids:
+        click.echo("No job IDs found in log filenames.")
+        return
+
+    failed_jobs_info = []
+    cancelled_jobs_info = []
+
+    for jobid in sorted(job_ids):
+        output_text = get_job_state(jobid)
+        if output_text:
+            categorize_job(jobid, output_text, failed_jobs_info, cancelled_jobs_info)
+
+    write_results(output, failed_jobs_info, cancelled_jobs_info)
+
+
+if __name__ == "__main__":
+    check_failed_jobs()

BALSAMIC/commands/config/case.py

@@ -40,7 +40,12 @@
     OPTION_TUMOR_SAMPLE_NAME,
     OPTION_UMI_MIN_READS,
 )
-from BALSAMIC.constants.analysis import BIOINFO_TOOL_ENV, AnalysisWorkflow, Gender
+from BALSAMIC.constants.analysis import (
+    BIOINFO_TOOL_ENV,
+    AnalysisWorkflow,
+    Gender,
+    LogFile,
+)
 from BALSAMIC.constants.cache import GenomeVersion
 from BALSAMIC.constants.constants import FileType
 from BALSAMIC.constants.paths import (
@@ -60,6 +65,7 @@
 )
 from BALSAMIC.utils.io import read_json, write_json
 from BALSAMIC.utils.utils import get_absolute_paths_dict
+from BALSAMIC.utils.logging import add_file_logging
 
 LOG = logging.getLogger(__name__)
 
@@ -129,6 +135,21 @@ def case_config(
     tumor_sample_name: str,
     umi_min_reads: str | None,
 ):
+    """Configure BALSAMIC workflow based on input arguments."""
+
+    LOG.info(f"Starting configuring analysis case: {case_id}.")
+
+    LOG.info(f"Creating case analysis directory: {analysis_dir}/{case_id}.")
+    Path(analysis_dir, case_id).mkdir(exist_ok=True)
+
+    log_file = Path(analysis_dir, case_id, LogFile.LOGNAME).as_posix()
+    LOG.info(f"Setting BALSAMIC logfile path to: {log_file}.")
+    add_file_logging(log_file, logger_name=__name__)
+
+    LOG.info(f"Running BALSAMIC version {balsamic_version} -- CONFIG CASE")
+    LOG.info(f"BALSAMIC started with log level {context.obj['log_level']}.")
+
+    LOG.info("Collecting reference and annotation file paths.")
     references_path: Path = Path(balsamic_cache, cache_version, genome_version)
     references: Dict[str, Path] = get_absolute_paths_dict(
         base_path=references_path,
@@ -154,7 +175,6 @@ def case_config(
                     if path is not None
                 }
             )
-
     variants_observations = {
         "artefact_snv_observations": artefact_snv_observations,
         "clinical_snv_observations": clinical_snv_observations,
@@ -172,10 +192,13 @@ def case_config(
             if path is not None
         }
     )
+    LOG.info(f"Collected references: {references}")
 
     analysis_fastq_dir: str = get_analysis_fastq_files_directory(
         case_dir=Path(analysis_dir, case_id).as_posix(), fastq_path=fastq_path
     )
+    LOG.info(f"Prepared analysis fastq-dir: {analysis_fastq_dir}")
+
     result_dir: Path = Path(analysis_dir, case_id, "analysis")
     log_dir: Path = Path(analysis_dir, case_id, "logs")
     script_dir: Path = Path(analysis_dir, case_id, "scripts")
@@ -186,6 +209,8 @@ def case_config(
     for directory in [result_dir, log_dir, script_dir, benchmark_dir]:
         directory.mkdir(exist_ok=True)
 
+    LOG.info("Created analysis and log directories.")
+    LOG.info("Validating configuration data in pydantic model.")
     config_collection_dict = ConfigModel(
         sentieon={
             "sentieon_install_dir": sentieon_install_dir,

BALSAMIC/commands/init/base.py

@@ -12,9 +12,7 @@
 from BALSAMIC.commands.options import (
     OPTION_CACHE_VERSION,
     OPTION_CLUSTER_ACCOUNT,
-    OPTION_CLUSTER_CONFIG,
-    OPTION_CLUSTER_MAIL,
-    OPTION_CLUSTER_MAIL_TYPE,
+    OPTION_CACHE_PROFILE,
     OPTION_CLUSTER_PROFILE,
     OPTION_CLUSTER_QOS,
     OPTION_COSMIC_KEY,
@@ -31,16 +29,14 @@
 from BALSAMIC.constants.cache import REFERENCE_FILES, GenomeVersion
 from BALSAMIC.constants.cluster import (
     QOS,
-    ClusterConfigType,
-    ClusterMailType,
-    ClusterProfile,
 )
 from BALSAMIC.models.cache import CacheConfig, ReferencesCanFam, ReferencesHg
 from BALSAMIC.models.snakemake import SnakemakeExecutable
 from BALSAMIC.utils.analysis import get_cache_singularity_bind_paths
 from BALSAMIC.utils.cache import get_containers
-from BALSAMIC.utils.cli import get_config_path, get_snakefile
+from BALSAMIC.utils.cli import get_snakefile
 from BALSAMIC.utils.io import generate_workflow_graph, write_json
+from BALSAMIC.utils.rule import get_script_path
 
 LOG = logging.getLogger(__name__)
 
@@ -51,10 +47,8 @@
 @OPTION_OUT_DIR
 @OPTION_CACHE_VERSION
 @OPTION_CLUSTER_ACCOUNT
-@OPTION_CLUSTER_CONFIG
-@OPTION_CLUSTER_MAIL
-@OPTION_CLUSTER_MAIL_TYPE
 @OPTION_CLUSTER_PROFILE
+@OPTION_CACHE_PROFILE
 @OPTION_CLUSTER_QOS
 @OPTION_COSMIC_KEY
 @OPTION_FORCE_ALL
@@ -69,14 +63,12 @@ def initialize(
     context: click.Context,
     account: Optional[str],
     cache_version: str,
-    cluster_config: Path,
     cosmic_key: str,
     force_all: bool,
     genome_version: GenomeVersion,
-    mail_type: Optional[ClusterMailType],
-    mail_user: Optional[str],
     out_dir: str,
-    profile: ClusterProfile,
+    cluster_profile: Path,
+    cache_profile: Path,
     qos: QOS,
     quiet: bool,
     run_analysis: bool,
@@ -149,15 +141,12 @@ def initialize(
     snakemake_executable: SnakemakeExecutable = SnakemakeExecutable(
         account=account,
         case_id=cache_config.analysis.case_id,
-        cluster_config_path=cluster_config
-        if cluster_config
-        else get_config_path(ClusterConfigType.CACHE),
         config_path=config_path,
         force=force_all,
         log_dir=log_dir,
-        mail_type=mail_type,
-        mail_user=mail_user,
-        profile=profile,
+        cluster_profile=cluster_profile,
+        cluster_job_status_script=get_script_path("cluster_job_status.py"),
+        workflow_profile=cache_profile,
         qos=qos,
         quiet=quiet,
         run_analysis=run_analysis,