fix: add sleep rule before start

BALSAMIC/constants/rules.py

@@ -30,6 +30,7 @@
 
 SNAKEMAKE_RULES: Dict[str, Dict[str, list]] = {
     "common": {
+        "misc": ["snakemake_rules/misc/sleep.rule"],
         "qc": [
             "snakemake_rules/quality_control/fastqc.rule",
             "snakemake_rules/quality_control/multiqc.rule",

BALSAMIC/constants/workflow_params.py

@@ -108,6 +108,8 @@
     },
 }
 
+SLEEP_BEFORE_START = 300
+
 WORKFLOW_PARAMS = {
     "common": {
         "pcr_model": "NONE",

BALSAMIC/snakemake_rules/misc/sleep.rule

@@ -0,0 +1,15 @@
+
+rule sleep_before_start:
+    """Wait the specified number of seconds before starting any processing to avoid key_error issue."""
+    output:
+        wake_up = result_dir + "start_analysis"
+    params:
+        sleep_seconds = SLEEP_BEFORE_START
+    threads: get_threads(cluster_config, "sleep_before_start")
+    message:
+        "Sleeping for {params.sleep_seconds} seconds before starting analysis."
+    shell:
+        """
+sleep {params.sleep_seconds}
+echo "Waited: {params.sleep_seconds} seconds. Now starting analysis." >> {output.wake_up}
+        """

BALSAMIC/snakemake_rules/quality_control/fastp_tga.rule

@@ -3,6 +3,7 @@
 rule fastp_umi_trim:
     """Fastq TGA data pre-processing to remove UMIs."""
     input:
+        wake_up = result_dir + "start_analysis",
         fastq_r1 = lambda wildcards: config_model.get_fastq_by_fastq_pattern(wildcards.fastq_pattern, FastqName.FWD),
         fastq_r2 = lambda wildcards: config_model.get_fastq_by_fastq_pattern(wildcards.fastq_pattern, FastqName.REV)
     output:

BALSAMIC/snakemake_rules/quality_control/fastp_wgs.rule

@@ -4,6 +4,7 @@
 rule fastp_quality_trim_wgs:
     """Fastq data pre-processing for WGS."""
     input:
+        wake_up = result_dir + "start_analysis",
         fastq_r1 = lambda wildcards: config_model.get_fastq_by_fastq_pattern(wildcards.fastq_pattern, FastqName.FWD),
         fastq_r2 = lambda wildcards: config_model.get_fastq_by_fastq_pattern(wildcards.fastq_pattern, FastqName.REV)
     output:

BALSAMIC/snakemake_rules/quality_control/fastqc.rule

@@ -4,6 +4,7 @@
 rule fastqc:
     """Perform quality control checks on raw sequence data."""
     input:
+        wake_up = result_dir + "start_analysis",
         fastq = input_fastq_dir + "{fastq_file_names}.fastq.gz"
     output:
         fastqc_zip = fastqc_dir + "{fastq_file_names}_fastqc.zip"

BALSAMIC/snakemake_rules/umi/concatenation_umi.rule

@@ -4,6 +4,7 @@
 
 rule concatenate_umi_reads:
     input:
+        wake_up = result_dir + "start_analysis",
         fastqs_fwd=lambda wildcards: config_model.get_all_fastqs_for_sample(
             sample_name=wildcards.sample, fastq_types=[FastqName.FWD]
         ),

BALSAMIC/workflows/PON.smk

@@ -10,13 +10,14 @@ from typing import Dict, List
 
 from BALSAMIC.constants.analysis import FastqName, Gender, PONWorkflow, SampleType, SequencingType
 from BALSAMIC.constants.paths import BALSAMIC_DIR
-from BALSAMIC.constants.workflow_params import WORKFLOW_PARAMS
+from BALSAMIC.constants.workflow_params import WORKFLOW_PARAMS, SLEEP_BEFORE_START
 from BALSAMIC.models.config import ConfigModel
 from BALSAMIC.models.params import BalsamicWorkflowConfig
 from BALSAMIC.utils.exc import BalsamicError
 from BALSAMIC.utils.io import write_finish_file
 from BALSAMIC.utils.rule import get_fastp_parameters, get_result_dir, get_threads
 
+
 # Initialize ConfigModel
 config_model = ConfigModel.model_validate(config)
 
@@ -81,6 +82,7 @@ if not Path(config["SENTIEON_EXEC"]).exists():
 
 sequence_type = config['analysis']["sequencing_type"]
 rules_to_include = []
+rules_to_include.append("snakemake_rules/misc/sleep.rule")
 if sequence_type == SequencingType.TARGETED:
     rules_to_include.append("snakemake_rules/quality_control/fastp_tga.rule")
 else:

BALSAMIC/workflows/QC.smk

@@ -9,7 +9,7 @@ from typing import Dict, List
 from BALSAMIC.constants.analysis import AnalysisType, FastqName, SampleType
 from BALSAMIC.constants.paths import BALSAMIC_DIR
 from BALSAMIC.constants.rules import SNAKEMAKE_RULES
-from BALSAMIC.constants.workflow_params import WORKFLOW_PARAMS
+from BALSAMIC.constants.workflow_params import WORKFLOW_PARAMS, SLEEP_BEFORE_START
 from BALSAMIC.models.config import ConfigModel
 from BALSAMIC.models.params import BalsamicWorkflowConfig
 from BALSAMIC.utils.cli import check_executable, generate_h5
@@ -112,9 +112,10 @@ sequence_type = config['analysis']["sequencing_type"]
 rules_to_include = []
 for workflow_type, value in SNAKEMAKE_RULES.items():
     if workflow_type in ["common", analysis_type + "_" + sequence_type]:
-        rules_to_include.extend(value.get("qc", []) + value.get("align", []))
+        rules_to_include.extend(value.get("qc", []) + value.get("align", []) + value.get("misc", []))
 rules_to_include = [rule for rule in rules_to_include if "umi" not in rule and "report" not in rule]
 
+
 # Somalier only implemented for hg38 and hg19
 if "canfam3" in config["reference"]["reference_genome"]:
     rules_to_include.remove("snakemake_rules/quality_control/somalier.rule")

BALSAMIC/workflows/balsamic.smk

@@ -18,7 +18,7 @@ from BALSAMIC.constants.variant_filters import (
     SVDB_FILTER_SETTINGS,
     VARDICT_SETTINGS,
 )
-from BALSAMIC.constants.workflow_params import VARCALL_PARAMS, WORKFLOW_PARAMS
+from BALSAMIC.constants.workflow_params import VARCALL_PARAMS, WORKFLOW_PARAMS, SLEEP_BEFORE_START
 from BALSAMIC.models.config import ConfigModel
 from BALSAMIC.models.params import BalsamicWorkflowConfig, VarCallerFilter
 from BALSAMIC.utils.cli import check_executable, generate_h5
@@ -83,7 +83,6 @@ delivery_dir: str = Path(result_dir, "delivery").as_posix() + "/"
 umi_dir: str = Path(result_dir, "umi").as_posix() + "/"
 umi_qc_dir: str = Path(qc_dir, "umi_qc").as_posix() + "/"
 
-
 # Annotations
 research_annotations = []
 clinical_annotations = []

CHANGELOG.rst

@@ -1,3 +1,11 @@
+[13.0.1]
+-------
+
+Added:
+^^^^^^
+* Sleep rule before start to fix key_error https://github.com/Clinical-Genomics/BALSAMIC/pull/1310
+
+
 [13.0.0]
 -------
 
@@ -35,6 +43,7 @@ Added:
 * `wkhtmltopdf` to system requirements https://github.com/Clinical-Genomics/BALSAMIC/pull/1339
 * Store WGS CNV report plots https://github.com/Clinical-Genomics/BALSAMIC/pull/1347
 
+
 Changed:
 ^^^^^^^^
 * Changed CN header field in cnvpytor in cnvpytor_tumor_only to be Float instead of Integer https://github.com/Clinical-Genomics/BALSAMIC/pull/1182