fix: HG30 sv calling feasible due to performance gains (#28)

Co-authored-by: Vinzenz May <may-vinzenz@t-online.de>

Author: vinzenzmay

.github/workflows/main.yml

@@ -67,9 +67,7 @@ jobs:
                     --reference examples/muc1/data/muc1.fa \
                     --trf examples/muc1/data/muc1.trf.bed \
                     --mononucleotides examples/muc1/data/muc1.mononucleotides.lt6.bed \
-                    --lamassemble-mat data/lamassemble-mats/promethion.mat \
-                    --unique-regions examples/muc1/data/muc1.unique.bed
-
+                    --lamassemble-mat data/lamassemble-mats/promethion.mat
             pixi run \
                 svirlpool sv-calling \
                     --threads 1 \

README.md

@@ -57,12 +57,12 @@ pixi run \
         --threads 1 \
         --samplename muc1test \
         --workdir /tmp/workdir/result \
+        --output /tmp/workdir/result/svirltile.db \
         --alignments examples/muc1/data/muc1.bam \
         --reference examples/muc1/data/muc1.fa \
         --trf examples/muc1/data/muc1.trf.bed \
         --mononucleotides examples/muc1/data/muc1.mononucleotides.lt6.bed \
-        --lamassemble-mat data/lamassemble-mats/promethion.mat \
-        --unique-regions examples/muc1/data/muc1.unique.bed
+        --lamassemble-mat data/lamassemble-mats/promethion.mat
 ```
 
 The directory `/tmp/workdir/result` will contain a number of files. The most important one is the file `/tmp/svirltile.db` that is necessary for the subsequent (potentially joint) SV calling and creation of a VCF file.
@@ -145,7 +145,6 @@ THREADS=16
 TRF=$DATADIR/pbsv-annotations/human_hs37d5.trf.bed
 MAT=$SVIRLPOOLDIR/data/lamassemble-mats/promethion.mat
 MNNTS=$DATADIR/HG19/hs37d5.mononucleotides.lt6.bed.gz
-UNIQUER=$DATADIR/HG19/hs37d5.unique.bed.gz
 ```
 
 Now cd into a directory of your choice, where your data shall be processed, e.g.
@@ -166,7 +165,6 @@ svirlpool run \
     --trf $TRF \
     --lamassemble-mat $MAT \
     --mononucleotides $ MNNTS \
-    --unique-regions UNIQUER \
     --threads $THREADS \
     --min-sv-size 30
 ```
@@ -183,7 +181,6 @@ svirlpool run \
     --trf $TRF \
     --lamassemble-mat $MAT \
     --mononucleotides $ MNNTS \
-    --unique-regions UNIQUER \
     --threads $THREADS \
     --min-sv-size 30
 ```

pixi.lock

@@ -22,7 +22,7 @@ classifiers = [
     "Programming Language :: Python :: 3.13",
     "Programming Language :: Python :: 3.14",
 ]
-dependencies = ["numpy>=2.3.4,<3", "pandas>=2.3.3,<3", "matplotlib>=3.10.7,<4", "scipy>=1.16.3,<2", "scikit-learn>=1.7.2,<2", "biopython>=1.86,<2", "plotly>=6.3.1,<7", "tqdm>=4.67.1,<5", "attrs>=25.4.0,<26", "cattrs>=25.3.0,<26", "intervaltree>=3.1.0,<4", "vcfpy>=0.14.2,<0.15", "pyyaml>=6.0.3,<7", "typer>=0.20.0,<0.21", "rich", "pydantic>=2.12.3,<3", "requests>=2.32.5,<3", "click", "setuptools~=70.0.0", "snakemake>=9.13.4,<10"]
+dependencies = ["numpy>=2.3.4,<3", "pandas>=2.3.3,<3", "matplotlib>=3.10.7,<4", "scipy>=1.16.3,<2", "scikit-learn>=1.7.2,<2", "biopython>=1.86,<2", "plotly>=6.3.1,<7", "tqdm>=4.67.1,<5", "attrs>=25.4.0,<26", "cattrs>=25.3.0,<26", "intervaltree>=3.1.0,<4", "vcfpy>=0.14.2,<0.15", "pyyaml>=6.0.3,<7", "typer>=0.20.0,<0.21", "rich", "pydantic>=2.12.3,<3", "requests>=2.32.5,<3", "click", "setuptools~=70.0.0", "snakemake>=9.13.4,<10", "xxhash>=0.8.3"]
 
 [project.scripts]
 svirlpool = "svirlpool.__main__:main"
@@ -74,32 +74,13 @@ exclude = [
     "**/node_modules",
     "**/__pycache__",
 ]
+typeCheckingMode = "basic"
 defineConstant = { DEBUG = true }
 stubPath = "stubs"
 
 pythonVersion = "3.12"
 pythonPlatform = "Linux"
 
-# Missing type annotation reports
-reportMissingParameterType = "error"
-reportUnknownParameterType = "error"
-reportUnknownVariableType = "error"
-reportUnknownMemberType = "error"
-reportUnknownArgumentType = "error"
-reportMissingTypeArgument = "error"
-
-# Other useful reports for type safety
-reportGeneralTypeIssues = "error"
-reportOptionalMemberAccess = "error"
-reportOptionalSubscript = "error"
-reportPrivateImportUsage = "error"
-
-# Stub files
-reportMissingTypeStubs = "error"
-reportImportCycles = "error"
-reportUnusedImport = "error"
-reportUnusedVariable = "error"
-
 [tool.ruff]
 lint.ignore = [
   "E501", # line too long, handled by black