diff --git a/.gitignore b/.gitignore index 0e5e367..2943aae 100644 --- a/.gitignore +++ b/.gitignore @@ -21,4 +21,4 @@ !.pixi/config.toml # claude -**/claude +**/.claude diff --git a/README.md b/README.md index 31a1b86..e89110e 100644 --- a/README.md +++ b/README.md @@ -7,6 +7,13 @@ # Snakemake workflow implementation to create DivRef-style resource +This workflow is inspired by the [DivRef](https://github.com/e9genomics/human-diversity-reference) repository which is used to generate a bundle of FASTA sequences and a corresponding DuckDB index of common human variation. + +The original implementation is via a set of standalone Python scripts and a Makefile. +This implementation: +1. Wraps the Python scripts in a toolkit with added typing, improved parameterization, and added unit testing. +2. Adds a Snakemake workflow and associated configuration to drive the resource generation process. + ## Set up Environment The environment for this analysis is managed using `pixi`. diff --git a/divref/divref/main.py b/divref/divref/main.py index 0e7127b..f7f9979 100644 --- a/divref/divref/main.py +++ b/divref/divref/main.py @@ -5,10 +5,24 @@ import defopt -from divref.tools.hello import hello +from divref.tools.compute_haplotype_statistics import compute_haplotype_statistics +from divref.tools.compute_haplotypes import compute_haplotypes +from divref.tools.compute_variation_ratios import compute_variation_ratios +from divref.tools.create_fasta_and_index import create_fasta_and_index +from divref.tools.create_gnomad_sites_vcf import create_gnomad_sites_vcf +from divref.tools.extract_gnomad_afs import extract_gnomad_afs +from divref.tools.remap_divref import remap_divref +from divref.tools.rewrite_fasta import rewrite_fasta _tools: List[Callable[..., None]] = [ - hello, + compute_haplotype_statistics, + compute_haplotypes, + compute_variation_ratios, + create_fasta_and_index, + create_gnomad_sites_vcf, + extract_gnomad_afs, + remap_divref, + rewrite_fasta, ] diff --git a/divref/divref/tools/hello.py b/divref/divref/tools/hello.py deleted file mode 100644 index 775129f..0000000 --- a/divref/divref/tools/hello.py +++ /dev/null @@ -1,11 +0,0 @@ -def hello( - *, - name: str = "World", -) -> None: - """ - Print a greeting. - - Args: - name: The person to greet. - """ - print(f"Hello, {name}!")