Merge Dev changes

.github/workflows/ci.yml

@@ -45,9 +45,9 @@ jobs:
       - name: Run black formatter
         run: poetry run black --check --exclude '__pycache__|scripts|sentieon_cli/archive.py' --line-length 79 sentieon_cli
       - name: Run mypy
-        run: poetry run mypy . 
+        run: poetry run mypy sentieon_cli
       - name: Run flake8
-        run: poetry run flake8 . --extend-ignore E231,E221, --exclude .github/scripts/license_message.py,sentieon_cli/scripts/gvcf_combine.py,sentieon_cli/scripts/vcf_mod.py,sentieon_cli/scripts/hybrid_anno.py,sentieon_cli/scripts/hybrid_select.py,sentieon_cli/archive.py # false+ from python 3.12
+        run: poetry run flake8 . --extend-ignore E231,E221, --exclude .github/scripts/license_message.py,sentieon_cli/scripts/gvcf_combine.py,sentieon_cli/scripts/vcf_mod.py,sentieon_cli/scripts/hybrid_anno.py,sentieon_cli/scripts/hybrid_select.py,sentieon_cli/archive.py,tests # false+ from python 3.12
       - name: Run the automated tests
         run: poetry run pytest -v
       - name: Run doct tests

pyproject.toml

@@ -2,7 +2,7 @@
 #https://stackoverflow.com/questions/75408641/whats-difference-between-tool-poetry-and-project-in-pyproject-toml
 [tool.poetry]
 name = "sentieon_cli"
-version = "1.2.3"
+version = "1.3.0"
 description = "entry point for sentieon command-line tools"
 authors = ["Don Freed <don.freed@sentieon.com>", "Brent <bpederse@gmail.com>"]
 readme = "README.md"

sentieon_cli/command_strings.py

@@ -451,7 +451,7 @@ def bcftools_subset(
         ]
     )
     return (
-        f'if [ -s "{regions_bed}" ]; then   '
+        f'if [ -s "{regions_bed}" ]; then   '  # noqa
         + bcftools_subset_cmd
         + " | "
         + vcfconvert_cmd

sentieon_cli/dnascope.py

@@ -44,7 +44,7 @@
     check_version,
     library_preloaded,
     path_arg,
-    spit_alignment,
+    split_alignment,
     total_memory,
 )
 
@@ -75,16 +75,10 @@ class DNAscopePipeline(BasePipeline):
     """The DNAscope pipeline"""
 
     params: Dict[str, Dict[str, Any]] = {
-        "reference": {
-            "flags": ["-r", "--reference"],
+        "model_bundle": {
+            "flags": ["-m", "--model_bundle"],
+            "help": "The model bundle file.",
             "required": True,
-            "help": "fasta for reference genome.",
-            "type": path_arg(exists=True, is_file=True),
-        },
-        "sample_input": {
-            "flags": ["-i", "--sample_input"],
-            "nargs": "*",
-            "help": "sample BAM or CRAM file.",
             "type": path_arg(exists=True, is_file=True),
         },
         "r1_fastq": {
@@ -101,19 +95,36 @@ class DNAscopePipeline(BasePipeline):
             "nargs": "*",
             "help": "Readgroup information for the fastq files.",
         },
-        "model_bundle": {
-            "flags": ["-m", "--model_bundle"],
-            "help": "The model bundle file.",
+        "reference": {
+            "flags": ["-r", "--reference"],
             "required": True,
+            "help": "fasta for reference genome.",
             "type": path_arg(exists=True, is_file=True),
         },
-        "dbsnp": {
-            "flags": ["-d", "--dbsnp"],
+        "sample_input": {
+            "flags": ["-i", "--sample_input"],
+            "nargs": "*",
+            "help": "sample BAM or CRAM file.",
+            "type": path_arg(exists=True, is_file=True),
+        },
+        "align": {
             "help": (
-                "dbSNP vcf file Supplying this file will annotate variants "
-                "with their dbSNP refSNP ID numbers."
+                "Align the reads in the input uBAM/uCRAM file to the "
+                "reference genome. Assumes paired reads are collated in the "
+                "input file."
             ),
-            "type": path_arg(exists=True, is_file=True),
+            "action": "store_true",
+        },
+        "assay": {
+            "help": "The type of assay, WGS or WES.",
+            "choices": ["WGS", "WES"],
+            "default": "WGS",
+        },
+        "bam_format": {
+            "help": (
+                "Use the BAM format instead of CRAM for output aligned files"
+            ),
+            "action": "store_true",
         },
         "bed": {
             "flags": ["-b", "--bed"],
@@ -123,9 +134,17 @@ class DNAscopePipeline(BasePipeline):
             ),
             "type": path_arg(exists=True, is_file=True),
         },
-        "interval_padding": {
-            "help": "Amount to pad all intervals.",
-            "type": int,
+        "collate_align": {
+            "help": (
+                "Collate and align the reads in the input BAM/CRAM file to "
+                "the reference genome. Suitable for coordinate-sorted "
+                "BAM/CRAM input."
+            ),
+            "action": "store_true",
+        },
+        "consensus": {
+            "help": "Generate consensus reads during dedup",
+            "action": "store_true",
         },
         "cores": {
             "flags": ["-t", "--cores"],
@@ -135,42 +154,44 @@ class DNAscopePipeline(BasePipeline):
             ),
             "default": mp.cpu_count(),
         },
-        "pcr_free": {
-            "help": "Use arguments for PCR-free data processing",
-            "action": "store_true",
-        },
-        "gvcf": {
-            "flags": ["-g", "--gvcf"],
+        "dbsnp": {
+            "flags": ["-d", "--dbsnp"],
             "help": (
-                "Generate a gVCF output file along with the VCF."
-                " (default generates only the VCF)"
+                "dbSNP vcf file Supplying this file will annotate variants "
+                "with their dbSNP refSNP ID numbers."
             ),
+            "type": path_arg(exists=True, is_file=True),
+        },
+        "dry_run": {
+            "help": "Print the commands without running them.",
             "action": "store_true",
         },
         "duplicate_marking": {
             "help": "Options for duplicate marking.",
             "choices": ["markdup", "rmdup", "none"],
             "default": "markdup",
         },
-        "assay": {
-            "help": "The type of assay, WGS or WES.",
-            "choices": ["WGS", "WES"],
-            "default": "WGS",
-        },
-        "consensus": {
-            "help": "Generate consensus reads during dedup",
+        "gvcf": {
+            "flags": ["-g", "--gvcf"],
+            "help": (
+                "Generate a gVCF output file along with the VCF."
+                " (default generates only the VCF)"
+            ),
             "action": "store_true",
         },
-        "dry_run": {
-            "help": "Print the commands without running them.",
-            "action": "store_true",
+        "input_ref": {
+            "help": (
+                "Used to decode the input alignment file. Required if the "
+                "input file is in the CRAM/uCRAM formats."
+            ),
+            "type": path_arg(exists=True, is_file=True),
         },
-        "skip_small_variants": {
-            "help": "Skip small variant (SNV/indel) calling",
-            "action": "store_true",
+        "interval_padding": {
+            "help": "Amount to pad all intervals.",
+            "type": int,
         },
-        "skip_svs": {
-            "help": "Skip SV calling",
+        "pcr_free": {
+            "help": "Use arguments for PCR-free data processing",
             "action": "store_true",
         },
         "skip_metrics": {
@@ -181,50 +202,23 @@ class DNAscopePipeline(BasePipeline):
             "help": "Skip multiQC report generation",
             "action": "store_true",
         },
-        "align": {
-            "help": (
-                "Align the reads in the input uBAM/uCRAM file to the "
-                "reference genome. Assumes paired reads are collated in the "
-                "input file."
-            ),
-            "action": "store_true",
-        },
-        "collate_align": {
-            "help": (
-                "Collate and align the reads in the input BAM/CRAM file to "
-                "the reference genome. Suitable for coordinate-sorted "
-                "BAM/CRAM input."
-            ),
+        "skip_small_variants": {
+            "help": "Skip small variant (SNV/indel) calling",
             "action": "store_true",
         },
-        "input_ref": {
-            "help": (
-                "Used to decode the input alignment file. Required if the "
-                "input file is in the CRAM/uCRAM formats."
-            ),
-            "type": path_arg(exists=True, is_file=True),
-        },
-        "bam_format": {
-            "help": (
-                "Use the BAM format instead of CRAM for output aligned files"
-            ),
+        "skip_svs": {
+            "help": "Skip SV calling",
             "action": "store_true",
         },
         "bwa_args": {
-            "help": "Extra arguments for sentieon bwa",
+            # "help": "Extra arguments for sentieon bwa",
+            "help": argparse.SUPPRESS,
             "default": "",
         },
         "bwa_k": {
-            "help": "The '-K' argument in bwa",
-            "default": 100000000,
-        },
-        "util_sort_args": {
-            "help": "Extra arguments for sentieon util sort",
-            "default": "--cram_write_options version=3.0,compressor=rans",
-        },
-        "skip_version_check": {
+            # "help": "The '-K' argument in bwa",
             "help": argparse.SUPPRESS,
-            "action": "store_true",
+            "default": 100000000,
         },
         "bwt_max_mem": {
             # Manually set `bwt_max_mem`
@@ -239,6 +233,15 @@ class DNAscopePipeline(BasePipeline):
             "help": argparse.SUPPRESS,
             "action": "store_true",
         },
+        "skip_version_check": {
+            "help": argparse.SUPPRESS,
+            "action": "store_true",
+        },
+        "util_sort_args": {
+            # "help": "Extra arguments for sentieon util sort",
+            "help": argparse.SUPPRESS,
+            "default": "--cram_write_options version=3.0,compressor=rans",
+        },
     }
 
     positionals: Dict[str, Dict[str, Any]] = {
@@ -343,7 +346,7 @@ def configure_alignment(self) -> None:
         self.numa_nodes: List[str] = []
         n_alignment_jobs = 1
         if not self.no_split_alignment:
-            self.numa_nodes = spit_alignment(self.cores)
+            self.numa_nodes = split_alignment(self.cores)
         n_alignment_jobs = max(1, len(self.numa_nodes))
 
         total_input_size = 0