13 inversion detection #16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged

jonperdomo merged 134 commits into main from 13-inversion-detection

Aug 1, 2025

.github/workflows/build-tests.yml

-Original file line number
+Diff line change
@@ Expand Up / @@ -23,26 +23,40 @@ jobs: @@
           shell: bash --login {0}
           run: unzip TestData.zip
-        - name: Set up conda environment
+        - name: Set up conda (Miniconda only)
           uses: conda-incubator/setup-miniconda@v2
           with:
-            activate-environment: contextsv
-            environment-file: environment.yml
-            python-version: 3.9
-            auto-activate-base: false
+            auto-activate-base: true
-        - name: Install samtools and bcftools using sudo apt-get
+        - name: Configure conda channels and create environment
+          shell: bash -l {0}
           run: |
-            sudo apt-get update
-            sudo apt-get install -y samtools bcftools
+            conda config --remove channels defaults || true
+            conda config --add channels conda-forge
+            conda config --add channels bioconda
+            conda config --set channel_priority strict
+            conda info  # confirm the change
+            conda env create -f environment.yml
         - name: Build C++ code
           shell: bash --login {0}  # --login enables PATH variable access
           run: |
-            make
+            source $(conda info --base)/etc/profile.d/conda.sh
+            conda activate contextsv
+            echo "CONDA_PREFIX=$CONDA_PREFIX"
+            ls -l $CONDA_PREFIX/include/htslib
+            make CONDA_PREFIX=$CONDA_PREFIX
         - name: Run unit tests
           shell: bash --login {0}
           run: |
-            mkdir -p tests/output
-            python -m pytest -s -v tests/test_general.py
+            source $(conda info --base)/etc/profile.d/conda.sh
+            conda activate contextsv
+            ./build/contextsv --version
+            ./build/contextsv --help
+          # run: |
+          #   source $(conda info --base)/etc/profile.d/conda.sh
+          #   conda activate contextsv
+          #   mkdir -p tests/output
+          #   python -m pytest -s -v tests/test_general.py

.gitignore

-Original file line number
+Diff line change
@@ Expand Up / @@ -55,6 +55,7 @@ CMakeSettings.json @@
     # Output folder
     output/
+    python/
     # Doxygen
     docs/html/
@@ Expand All / @@ -67,12 +68,15 @@ python/dbscan @@
     python/agglo
     linktoscripts
     tests/data
+    tests/cpp_module_out
     # Population allele frequency filepaths
     data/gnomadv2_filepaths.txt
     data/gnomadv3_filepaths.txt
     data/gnomadv4_filepaths.txt
+    data/gnomadv4_filepaths_ssd.txt
     data/gnomadv4_hg19_filepaths.txt
+    data/gnomadv4_hg19_filepaths_ssd.txt
     # Training data
     data/sv_scoring_dataset/
@@ Expand All / @@ -84,3 +88,17 @@ data/hg19ToHg38.over.chain.gz @@
     # Test images
     python/dbscan_clustering*.png
     python/dist_plots
+    upset_plot*.png
+    # Temporary files
+    lib/.nfs*
+    valgrind.log
+    # Log files
+    *.log
+    *.err
+    *.out
+    # Snakemake files
+    .snakemake
+    snakemake_bench/results/

Makefile

-Original file line number
+Diff line change
@@ -1,11 +1,53 @@
+    # Directories
     INCL_DIR := $(CURDIR)/include
     SRC_DIR := $(CURDIR)/src
+    BUILD_DIR := $(CURDIR)/build
     LIB_DIR := $(CURDIR)/lib
+    # Version header
+    VERSION := $(shell git describe --tags --always)
+    VERSION_HEADER := $(INCL_DIR)/version.h
+    .PHONY: $(VERSION_HEADER)
+    	@echo "#pragma once" > $@
+    	@echo "#define VERSION \"$(VERSION)\"" >> $@
-    all:
-    	# Generate the SWIG wrapper (C++ -> Python)
-    	swig -c++ -python -I$(INCL_DIR) -o $(SRC_DIR)/swig_wrapper.cpp -outdir $(LIB_DIR) $(SRC_DIR)/swig_wrapper.i
+    # Conda environment directories
+    CONDA_PREFIX := $(shell echo $$CONDA_PREFIX)
+    CONDA_INCL_DIR := $(CONDA_PREFIX)/include
+    CONDA_LIB_DIR := $(CONDA_PREFIX)/lib
-    	# Compile the SWIG wrapper using setuptools
-    	python3 setup.py build_ext --build-lib $(LIB_DIR)
+    # Compiler and Flags
+    CXX := g++
+    CXXFLAGS := -std=c++17 -g -I$(INCL_DIR) -I$(CONDA_INCL_DIR) -Wall -Wextra -pedantic
+    # Linker Flags
+    # Ensure that the library paths are set correctly for linking
+    LDFLAGS := -L$(LIB_DIR) -L$(CONDA_LIB_DIR) -Wl,-rpath=$(CONDA_LIB_DIR)  # Add rpath for shared libraries
+    LDLIBS := -lhts  # Link with libhts.a or libhts.so
+    # Sources and Output
+    SOURCES := $(filter-out $(SRC_DIR)/swig_wrapper.cpp, $(wildcard $(SRC_DIR)/*.cpp))  # Filter out the SWIG wrapper from the sources
+    OBJECTS := $(patsubst $(SRC_DIR)/%.cpp,$(BUILD_DIR)/%.o,$(SOURCES))
+    TARGET := $(BUILD_DIR)/contextsv
+    # Default target
+    all: $(TARGET)
+    # Debug target
+    debug: CXXFLAGS += -DDEBUG
+    debug: all
+    # Link the executable
+    $(TARGET): $(OBJECTS)
+    	@mkdir -p $(BUILD_DIR)
+    	$(CXX) $(CXXFLAGS) -o $@ $^ $(LDFLAGS) $(LDLIBS)
+    # Compile source files
+    $(BUILD_DIR)/%.o: $(SRC_DIR)/%.cpp
+    	@mkdir -p $(BUILD_DIR)
+    	$(CXX) $(CXXFLAGS) -c $< -o $@
+    # Clean the build directory
+    clean:
+    	rm -rf $(BUILD_DIR)

README.md

-Original file line number
+Diff line change
@@ Expand Up @@
     Class documentation is available at <a href="https://wglab.openbioinformatics.org/ContextSV">https://wglab.openbioinformatics.org/ContextSV</a>
     </p>
-    ## Installation (Linux)
-    ### Using Anaconda (recommended)
-    First, install [Anaconda](https://www.anaconda.com/).
+    ## Installation
-    Next, create a new environment. This installation has been tested with Python 3.11:
-    ```
-    conda create -n contextsv python=3.11
-    conda activate contextsv
-    ```
-    ContextSV can then be installed using the following command:
+    ### Building from source (for testing/development)
+    ContextSV requires HTSLib as a dependency that can be installed using  [Anaconda](https://www.anaconda.com/). Create an environment
+    containing HTSLib:
     ```
-    conda install -c bioconda -c wglab contextsv=1.0.0
+    conda create -n htsenv -c bioconda -c conda-forge htslib
+    conda activate htsenv
     ```
-    ### Building from source (for testing/development)
-    First install [Anaconda](https://www.anaconda.com/). Then follow the instructions below to install LongReadSum and its dependencies:
+    Then follow the instructions below to build ContextSV:
     ```
     git clone https://github.com/WGLab/ContextSV
     cd ContextSV
-    conda env create -f environment.yml
     make
     ```
+    ContextSV can then be run:
+    ```
+    ./build/contextsv --help
+    Usage: ./build/contextsv [options]
+    Options:
+      -b, --bam <bam_file>          Long-read BAM file (required)
+      -r, --ref <ref_file>          Reference genome FASTA file (required)
+      -s, --snp <vcf_file>          SNPs VCF file (required)
+      -o, --outdir <output_dir>     Output directory (required)
+      -c, --chr <chromosome>        Chromosome
+      -r, --region <region>         Region (start-end)
+      -t, --threads <thread_count>  Number of threads
+      -h, --hmm <hmm_file>          HMM file
+      -n, --sample-size <size>      Sample size for HMM predictions
+         --min-cnv <min_length>     Minimum CNV length
+         --eps <epsilon>             DBSCAN epsilon
+         --min-pts-pct <min_pts_pct> Percentage of mean chr. coverage to use for DBSCAN minimum points
+      -e, --eth <eth_file>          ETH file
+      -p, --pfb <pfb_file>          PFB file
+         --save-cnv                 Save CNV data
+         --debug                    Debug mode with verbose logging
+         --version                  Print version and exit
+      -h, --help                    Print usage and exit
+    ```
     ## Downloading gnomAD SNP population frequencies
     SNP population allele frequency
     information is used for copy number predictions in this tool (see
@@ Expand All @@
      - **gnomAD v2.1.1 (GRCh37)**: https://gnomad.broadinstitute.org/downloads#2
-    ### Example download
+    ### Script for downloading gnomAD VCFs
     ```
     download_dir="~/data/gnomad/v4.0.0/"
@@ Expand All @@
     Y=~/data/gnomad/v4.0.0/gnomad.genomes.v4.0.sites.chrY.vcf.bgz
     ```
-    ## Calling structural variants
-    ### Example full script generating a merged VCF of structural variants
-    ```
-    # Activate the environment
-    conda activate contextsv
-    # Set the input reference genome
-    ref_file="~/data/GRCh38.fa"
-    # Set the input alignment file (e.g. from minimap2)
-    long_read_bam="~/data/HG002.GRCh38.bam"
-    # Set the input SNPs file (e.g. from NanoCaller)
-    snps_file="~/data/variant_calls.snps.vcf.gz"
-    # Set the SNP population frequencies filepath
-    pfb_file="~/data/gnomadv4_filepaths.txt"
-    # Set the output directory
-    output_dir=~/data/contextSV_output
-    # Specify the number of threads (system-specific)
-    thread_count=40
-    # Run SV calling (~3-4 hours for whole-genome, 40 cores)
-    python contextsv --threads $thread_count -o $output_dir -lr $long_read_bam --snps $snps_file --reference $ref_file --pfb $pfb_file
-    # The output VCF filepath is located here:
-    output_vcf=$output_dir/sv_calls.vcf
-    # Merge SVs (~3-4 hours for whole-genome, 40 cores)
-    python contextsv --merge $output_vcf
-    # The final merged VCF filepath is located here:
-    merged_vcf=$output_dir/sv_calls.merged.vcf
-    ```
-    ## Input arguments
-    ```
-    python contextsv --help
-    ContextSV: A tool for integrative structural variant detection.
-    options:
-      -h, --help            show this help message and exit
-      -lr LONG_READ, --long-read LONG_READ
-                            path to the long read alignment BAM file
-      -g REFERENCE, --reference REFERENCE
-                            path to the reference genome FASTA file
-      -s SNPS, --snps SNPS  path to the SNPs VCF file
-      --pfb PFB             path to the file with SNP population frequency VCF filepaths (see docs for format)
-      -o OUTPUT, --output OUTPUT
-                            path to the output directory
-      -r REGION, --region REGION
-                            region to analyze (e.g. chr1, chr1:1000-2000). If not provided, the entire genome will be analyzed
-      -t THREADS, --threads THREADS
-                            number of threads to use
-      --hmm HMM             path to the PennCNV HMM file
-      --window-size WINDOW_SIZE
-                            window size for calculating log2 ratios for CNV predictions (default: 10 kb)
-      -d, --debug           debug mode (verbose logging)
-      -v, --version         print the version number and exit
-    ```
     ## Revision history
     For release history, please visit [here](https://github.com/WGLab/ContextSV/releases).
@@ Expand Down @@

__main__.py

-Original file line number
+Diff line change
@@ Expand Up / @@ -214,7 +214,6 @@ def main(): @@
         # Set input parameters
         input_data = contextsv.InputData()
         input_data.setVerbose(args.debug)
-        input_data.setShortReadBam(args.short_read)
         input_data.setLongReadBam(args.long_read)
         input_data.setRefGenome(args.reference)
         input_data.setSNPFilepath(args.snps)
@@ Expand Down @@

environment.yml

-Original file line number
+Diff line change
@@ -1,21 +1,9 @@
     name: contextsv
     channels:
-      - defaults
-      - anaconda
-      - conda-forge
       - bioconda
+      - conda-forge
     dependencies:
-      - python
+      - python=3.10
       - numpy
       - htslib
-      - swig
       - pytest
-      - plotly
-    # [A] Generate directly from the file:
-    #  conda env create -f environment.yml -n contextsv
-    # [B] Generate after creating a new environment:
-    # conda create -n contextsv
-    # conda activate contextsv
-    # conda env update -f environment.yml --prune  # Prune removes unused packages

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

13 inversion detection #16

Uh oh!

Diff view

Diff view

There are no files selected for viewing

Uh oh!

Uh oh!