vcf-subset 1.0.0__tar.gz

vcf_subset-1.0.0/PKG-INFO

@@ -0,0 +1,12 @@
+Metadata-Version: 2.1
+Name: vcf_subset
+Version: 1.0.0
+Summary: Efficient VCF subsetting by genome position.
+Home-page: https://github.com/GlobalPathogenAnalysisService/vcf_subset
+Author: Jeremy Westhead
+Author-email: jeremy.westhead@ndm.ox.ac.uk
+License: MIT
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+
+Efficient VCF subsetting by genome position.

vcf_subset-1.0.0/README.md

@@ -0,0 +1,23 @@
+# vcf_subset
+Efficient VCF subsetting by genome position. Written in C++, but provided as a python module to save ~3 minutes per TB GVCF
+
+## Install
+```
+pip install vcf_subset
+```
+
+## Local (dev) install
+```
+# Optional virtual environment
+python -m virtualenv env
+source env/bin/activate
+
+# Install requirements
+pip install build
+
+# Build dist
+python -m build --sdist --outdir dist
+
+# Install
+pip install .
+```

vcf_subset-1.0.0/pyproject.toml

@@ -0,0 +1,6 @@
+[build-system]
+requires = [
+    "setuptools>=42",
+    "pybind11>=2.10.0",
+]
+build-backend = "setuptools.build_meta"

vcf_subset-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

vcf_subset-1.0.0/setup.py

@@ -0,0 +1,38 @@
+# Based on example https://github.com/pybind/python_example
+from pybind11.setup_helpers import Pybind11Extension
+from setuptools import setup
+import os
+
+__version__ = "v1.0.0"
+
+long_description = "Efficient VCF subsetting by genome position."
+
+files = sorted(["vcf_subset.cpp"])
+
+ext_modules = [
+    Pybind11Extension(
+        "vcf_subset",
+        files,
+        include_dirs=[],
+        extra_compile_args=["-std=c++2a", "-O3"],
+        # Example: passing in the version to the compiled code
+        define_macros=[("VERSION_INFO", __version__)],
+    ),
+]
+
+setup(
+    name="vcf_subset",
+    version=__version__,
+    author="Jeremy Westhead",
+    author_email="jeremy.westhead@ndm.ox.ac.uk",
+    url="https://github.com/GlobalPathogenAnalysisService/vcf_subset",
+    description="Efficient VCF subsetting by genome position.",
+    ext_modules=ext_modules,
+    zip_safe=False,
+    python_requires=">=3.7",
+    license="MIT",
+    long_description=long_description,
+    long_description_content_type='text/markdown',
+    include_package_data=True,
+    package_data={'vcf_subset': ['./**']}
+)

vcf_subset-1.0.0/vcf_subset.cpp

@@ -0,0 +1,80 @@
+#include<iostream>
+#include<fstream>
+#include<vector>
+#include<algorithm>
+
+#include <pybind11/pybind11.h>
+#include <pybind11/stl.h>
+
+#define STRINGIFY(x) #x
+#define MACRO_STRINGIFY(x) STRINGIFY(x)
+
+using namespace std;
+namespace py = pybind11;
+
+
+vector<string> subset_gvcf(string filename, vector<int> positions){
+    vector<string> header;
+    vector<string> output;
+    fstream fin(filename, fstream::in);
+    if(!fin.good()){
+        throw invalid_argument("Invalid gvcf path: " + filename);
+    }
+    char ch;
+    string acc;
+    size_t pos = 0;
+    while (fin >> noskipws >> ch) {
+        if(ch == '\n'){
+            if(acc[0] == '#'){
+                header.push_back(acc);
+                acc = "";
+                continue;
+            }
+            // Pull out the second column (which should be the position)
+            string line = acc;
+            pos = acc.find("\t");
+            acc.erase(0, pos + 1);
+            pos = acc.find("\t");
+            string p = acc.substr(0, pos);
+            int genome_pos = stoi(p);
+
+            if(binary_search(positions.begin(), positions.end(), genome_pos)){
+                output.push_back(line);
+            }
+
+            acc = "";
+        }
+        else{
+            acc += ch;
+        }
+    }
+    fin.close();
+    header.insert( header.end(), output.begin(), output.end() );
+    return header;
+
+}
+
+PYBIND11_MODULE(vcf_subset, m) {
+    m.doc() =  R"pbdoc(
+        Efficient VCF subsetting by genome position.
+        Designed for subsetting a gVCF file, but should work for any VCF.
+        -----------------------
+           subset_gvcf
+    )pbdoc";
+    #ifdef VERSION_INFO
+        m.attr("__version__") = MACRO_STRINGIFY(VERSION_INFO);
+    #else
+        m.attr("__version__") = "dev";
+    #endif
+    m.def("subset_vcf", &subset_gvcf, R"pbdoc(
+        Subset a given VCF file to just the given positions (and the header).
+        -----------------------
+
+        Args:
+            str filename: Path to the VCF file to subset. Must not be gzipped.
+            list[int] positions: List of genome positions to keep
+        
+        Returns:
+            list[str]: Lines of the VCF file that match the given positions (and the header)
+        )pbdoc", py::arg("filename"), py::arg("positions"));
+}

vcf_subset-1.0.0/vcf_subset.egg-info/PKG-INFO

@@ -0,0 +1,12 @@
+Metadata-Version: 2.1
+Name: vcf_subset
+Version: 1.0.0
+Summary: Efficient VCF subsetting by genome position.
+Home-page: https://github.com/GlobalPathogenAnalysisService/vcf_subset
+Author: Jeremy Westhead
+Author-email: jeremy.westhead@ndm.ox.ac.uk
+License: MIT
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+
+Efficient VCF subsetting by genome position.

vcf_subset-1.0.0/vcf_subset.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+README.md
+pyproject.toml
+setup.py
+vcf_subset.cpp
+vcf_subset.egg-info/PKG-INFO
+vcf_subset.egg-info/SOURCES.txt
+vcf_subset.egg-info/dependency_links.txt
+vcf_subset.egg-info/not-zip-safe
+vcf_subset.egg-info/top_level.txt

vcf_subset-1.0.0/vcf_subset.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

vcf_subset-1.0.0/vcf_subset.egg-info/not-zip-safe

@@ -0,0 +1 @@
+

vcf_subset-1.0.0/vcf_subset.egg-info/top_level.txt

@@ -0,0 +1 @@
+vcf_subset