genmod 3.8.3__tar.gz → 3.10__tar.gz

genmod-3.10/.github/workflows/build_and_publish.yml

@@ -0,0 +1,63 @@
+name: Publish to PyPI
+
+on:
+ release:
+  types:
+   - created
+
+jobs:
+ pypi:
+    name: Build and publish to PyPI
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v3
+      - run: uv build
+      - run: uv publish --trusted-publishing always
+
+ docker-image-CI:
+   name: Docker Image CI
+   runs-on: ubuntu-latest
+   steps:
+
+    - name: Check out git repository
+      uses: actions/checkout@v4
+
+    - name: Login to Docker Hub
+      uses: docker/login-action@v3
+      with:
+        username: ${{ secrets.DOCKER_USERNAME }}
+        password: ${{ secrets.DOCKER_PASSWORD }}
+
+    - name: Set up Docker Buildx
+      id: buildx
+      uses: docker/setup-buildx-action@v3
+
+    - name: Publish server image (Dockerfile-server) to Registry
+      uses: docker/build-push-action@v6
+      with:
+        context: ./
+        file: ./Dockerfile
+        push: true
+        provenance: mode=max
+        sbom: true
+        tags: "clinicalgenomics/genmod:latest, clinicalgenomics/genmod:${{ github.event.release.tag_name }}"
+
+
+ deploy-docs:
+    name: Deploy Docs to GitHubIO
+    runs-on: ubuntu-latest
+    steps:
+     - name: Checkout repo
+       uses: actions/checkout@v4
+     - name: Setup environment for docs deployment
+       uses: actions/setup-python@v5
+       with:
+         python-version: 3.x
+     - name: Install mkdocs
+       run: pip install mkdocs mkdocs-material markdown-include
+     - name: Deploy documentation
+       run: mkdocs gh-deploy --force
+

genmod-3.10/.github/workflows/check_format.yml

@@ -0,0 +1,26 @@
+# Basic CI setup: Lint format with ruff
+name: Format-check
+
+on:
+  pull_request:
+    types: [ opened, synchronize, reopened, ready_for_review, labeled, unlabeled ]
+
+jobs:
+  lint-format:
+    name: Ruff includes and format
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Ruff check import sorting
+        uses: astral-sh/ruff-action@v3
+        with:
+          version: "latest"
+          args: "check --select I ."
+
+      - name: Ruff format diff
+        uses: astral-sh/ruff-action@v3
+        with:
+          version: "latest"
+          args: "format --diff ."
+

genmod-3.10/.github/workflows/keep_a_changelog.yml

@@ -0,0 +1,15 @@
+name: "Changelog Reminder"
+on:
+  pull_request:
+      types: [opened, synchronize, reopened, ready_for_review, labeled, unlabeled]
+
+jobs:
+  # Enforces the update of a changelog file on every pull request
+  changelog:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - uses: dangoslen/changelog-enforcer@v3
+      with:
+        changeLogPath: 'CHANGELOG.md'
+        skipLabels: 'Skip-Changelog'

genmod-3.10/.github/workflows/lint.yml

@@ -0,0 +1,19 @@
+# Basic CI setup: Lint with ruff
+name: Lint
+
+on:
+  pull_request:
+    types: [ opened, synchronize, reopened, ready_for_review, labeled, unlabeled ]
+
+jobs:
+  lint:
+    name: Lint
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Ruff lint
+        uses: astral-sh/ruff-action@v3
+        with:
+          version: "latest"
+          args: "check ."

genmod-3.10/.github/workflows/test.yml

@@ -0,0 +1,24 @@
+name: Tests
+
+on:
+  pull_request:
+  #push:
+
+jobs:
+  run-tests:
+    timeout-minutes: 30
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+        with:
+          ref: "${{github.event.inputs.branch_name}}"
+          fetch-depth: 0
+
+      - name: Run Tests
+        run: |
+          make test
+
+      - name: Run Packaging Test
+        run: |
+          make test_dist

genmod-3.10/.gitignore

@@ -0,0 +1,20 @@
+/data
+/res
+/doc
+/dist
+/build
+/pickles
+/local
+/publication
+/things
+/venv
+/.idea
+*.pyc
+.DS_Store
+*.egg-info
+*.tmproj
+*.ipynb
+*.tmp
+*.temp
+*.bak
+notes.mdsite/

genmod-3.10/.python-version

@@ -0,0 +1 @@
+3.13

genmod-3.10/.travis.yml

@@ -0,0 +1,16 @@
+# config file for automatic testing at travis-ci.org
+language: python
+
+python:
+    - "2.7"
+
+install:
+    # install test dependencies and package
+    - pip install pytest
+    - pip install .
+
+script:
+    - py.test
+
+notifications:
+    email: no

genmod-3.10/CHANGELOG.md

@@ -0,0 +1,49 @@
+# Change Log
+All notable changes to this project will be documented in this file.
+This project adheres to [Semantic Versioning](http://semver.org/).
+
+About changelog [here](https://keepachangelog.com/en/1.0.0/)
+
+Please add a new candidate release at the top after changing the latest one. Feel free to copy paste from the "squash and commit" box that gets generated when creating PRs
+
+Try to use the following format:
+
+## [3.10]
+### Changed
+- Use `uv` with `hatchling` to build and publish ([#104](https://github.com/Clinical-Genomics/genmod/issues/143))
+- Automation for Docker publish and mkdocs githubio ([#161](https://github.com/Clinical-Genomics/genmod/issues/161))
+### Fixed
+- The optional fields Source and Version are allowed in the VCF header([#106](https://github.com/Clinical-Genomics/genmod/pull/106))
+- Released the constraint on Python 3.8 (collections, pkg_resources to importlib, tests) ([#142](https://github.com/Clinical-Genomics/genmod/pull/142))
+- Update annotation examples ([#144](https://github.com/Clinical-Genomics/genmod/pull/144))
+- Updated documentation with warning about compounds only being scored within the first family in the VCF ([#151](https://github.com/Clinical-Genomics/genmod/pull/151))
+- Fixed sorting of variants ([#152](https://github.com/Clinical-Genomics/genmod/pull/152))
+- genmod annotate for mitochondrial variants when using the `chrM` notation ([#157](https://github.com/Clinical-Genomics/genmod/pull/157))
+- Fix linting issues ([#154](https://github.com/Clinical-Genomics/genmod/issues/154))
+- genmod models adds headers to VCF even if it contains no variants ([#160](https://github.com/Clinical-Genomics/genmod/pull/160)) 
+
+## [3.9]
+- Fixed wrong models when chromosome X was named `chrX` and not `X` ([#135](https://github.com/Clinical-Genomics/genmod/pull/135))
+- Added GitHub Actions workflows for automatic publishing to PyPI on release, and keep a changelog reminder ([#136](https://github.com/Clinical-Genomics/genmod/pull/136))
+- Optional user defined threshold and penalty for compound scoring ([#138](https://github.com/Clinical-Genomics/genmod/pull/138))
+- Update README with current github.io docs page ([#140](https://github.com/Clinical-Genomics/genmod/pull/140))
+
+## [3.8.3]
+- Fixed unstable compounds order in models output ([#134](https://github.com/Clinical-Genomics/genmod/pull/134))
+- Added `six` to requirements.txt and setup.py ([#134](https://github.com/Clinical-Genomics/genmod/pull/134))
+
+## [3.8.0]
+- Rank score normalisation
+
+## [3.7.4]
+
+### Fixed
+- OSError crashes due to socket address conflicts when using containers
+
+## [x.x.x]
+
+### Changed
+- Adds support for escaped characters in FORMAT description header strings
+
+### Fixed
+- Documentation about cli options `strict` and `phased`

genmod-3.10/CITATION.cff

@@ -0,0 +1,16 @@
+cff-version: 1.2.0
+message: If you use this software, please cite it using these metadata.
+title: genmod
+abstract: Tool for annotating patterns of genetic inheritance in Variant Call Format (VCF) files.
+authors:
+  - family-names: Magnusson
+    given-names: Måns
+    orcid: "https:// https://orcid.org/0000-0002-0001-1047"
+version: 3.7.3
+date-released: "2018-11-15"
+identifiers:
+  - description: Updates click dependency
+    type: doi
+    value: "10.5281/zenodo.3841142"
+license: MIT Licence
+repository-code: "https://github.com/Clinical-Genomics/genmod"

genmod-3.10/DEVELOPING.md

@@ -0,0 +1,19 @@
+# Developing
+
+## Host Requirements
+* Docker
+* package "build-essentials" for running Makefile
+
+## Run pytest
+There's support for pytest via Docker.
+
+Run the following to run pytest:
+
+```
+make test
+```
+
+## Running Genmod CLI
+```
+python3 -m genmod.commands.base
+```

genmod-3.10/Dockerfile

@@ -0,0 +1,17 @@
+###############################################
+# Dockerfile to build GeMod container image
+###############################################
+FROM ghcr.io/astral-sh/uv:python3.13-alpine
+
+RUN apk update & apk add build-base zlib-dev
+# Copy the project into the image
+ADD . /app
+
+# Sync the project into a new virtual environment, using the frozen lockfile
+WORKDIR /app
+RUN uv sync --frozen
+
+# Add the project venv to PATH to be able to run genmod without changing to the environment
+ENV PATH="/app/.venv/bin:$PATH"
+
+ENTRYPOINT ["genmod"]

genmod-3.10/Dockerfile.pytest

@@ -0,0 +1,9 @@
+# Dockerfile to run genmod pytest suite
+FROM ghcr.io/astral-sh/uv:python3.13-bookworm
+
+ADD . /app
+
+WORKDIR /app
+RUN uv sync --all-extras --dev
+
+ENTRYPOINT ["uv", "run", "pytest"]

{genmod-3.8.3 → genmod-3.10}/MANIFEST.in

@@ -1,5 +1,9 @@
+include CHANGELOG.md
+include LICENSE.txt
+include README.md
+
 recursive-include examples *.ped *.vcf *.gz *.tbi
 recursive-include genmod/annotations *.gz
 recursive-include genmod/configs *.ini
 recursive-exclude * __pycache__
-recursive-exclude * *.py[co]
+recursive-exclude * *.py[co]

genmod-3.10/Makefile

@@ -0,0 +1,24 @@
+.PHONY: *
+
+DOCKER=DOCKER_BUILDKIT=1 docker
+
+all:
+	# Nothing to be built
+
+docker-build:
+	$(DOCKER) build -t genmod/test --force-rm=true --rm=true -f Dockerfile.pytest .
+
+test: docker-build
+	$(DOCKER) run -i -l genmod-test genmod/test -v
+
+test_%: docker-build
+	$(DOCKER) run -i -l genmod-test genmod/test -v -k $@
+
+test_dist: docker-build
+	$(DOCKER) run -i -l genmod-test --entrypoint=bash genmod/test -c \
+		"uv build && \
+		pip3 install dist/genmod*.tar.gz && \
+		uv run genmod -v annotate --annotate-regions --genome-build 37 examples/test_vcf.vcf"
+
+docker-clean-images:
+	docker system prune

genmod-3.8.3/README.md → genmod-3.10/PKG-INFO

@@ -1,9 +1,43 @@
+Metadata-Version: 2.4
+Name: genmod
+Version: 3.10
+Summary: Annotate genetic inheritance models in Variant Call Format (VCF) files
+Project-URL: Repository, http://github.com/Clinical-Genomics/genmod
+Project-URL: Changelog, https://github.com/Clinical-Genomics/genmod/blob/main/CHANGELOG.md
+Project-URL: Bug Tracker, https://github.com/Clinical-Genomics/genmod/issues
+Author-email: Mans Magnuson <mans.magnusson@scilifelab.se>, Tor Björgen <tor.bjorgen@scilifelab.se>, Felix Lenner <felix.lenner@scilifelab.se>, Anders Jemt <anders.jemt@scilifelab.se>, Daniel Nilsson <daniel.nilsson@ki.se>
+License: MIT License
+License-File: LICENSE.txt
+Keywords: inheritance,variants,vcf
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: Unix
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
+Requires-Python: >=3.7
+Requires-Dist: click
+Requires-Dist: configobj
+Requires-Dist: extract-vcf
+Requires-Dist: importlib-resources
+Requires-Dist: interval-tree>=0.3.4
+Requires-Dist: intervaltree>=3.1.0
+Requires-Dist: ped-parser
+Requires-Dist: pytabix
+Requires-Dist: six
+Requires-Dist: vcftoolbox
+Description-Content-Type: text/markdown
+
 # GENMOD #
 
 
 
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3841142.svg)](https://doi.org/10.5281/zenodo.3841142)
-[![Build Status](https://travis-ci.org/moonso/vcf_parser.svg)](https://travis-ci.org/moonso/genmod)
+![Build Status - GitHub][actions-build-status]
 
 
 **GENMOD** is a simple to use command line tool for annotating and analyzing genomic variations in the [VCF](http://samtools.github.io/hts-specs/VCFv4.1.pdf) file format.
@@ -17,7 +51,7 @@ The tools in the genmod suite are:
 - **genmod score**, Score the variants of a vcf based on their annotation
 - **genmod filter**, Filter the variants of a vcf based on their annotation
 
-##Installation:##
+## Installation
 
 **GENMOD**
 
@@ -25,18 +59,17 @@ The tools in the genmod suite are:
 
 or
 
-	git clone https://github.com/moonso/genmod.git
+	git clone https://github.com/Clinical-Genomics/genmod.git
 	cd genmod
-	python setup.py install
-
+	uv install genmod
+	uv run genmod
 
-## USAGE: ##
 
-<!-- TODO change documentation link -->
-*This is an overview, for more in depth documentation see [documentation](http://moonso.github.io/genmod/)*
+## Usage
 
+*This is an overview, for more in depth documentation see [documentation](https://Clinical-Genomics.github.io/genmod)*
 
-### Example: ###
+### Example
 
 
 The following command should work when installed successfully. The files are distributed with the package.
@@ -139,17 +172,18 @@ $genmod models <vcf_file> -f/--family_file <family.ped>
 
 ```
 
-<!-- ###genmod annotate###
-
+#### genmod annotate  
 
+```
     genmod annotate variant_file.vcf
+```
 
 This will print a new vcf to standard out with all variants annotated according to the statements below.
 All individuals described in the [ped](http://pngu.mgh.harvard.edu/~purcell/plink/data.shtml#ped) file must be present in the vcf file
 
 See examples in the folder ```genmod/examples```.
 
-**From version 1.9 genmod can split multiallelic calls in vcf:s, use flag -split/--split_variants.**
+**From version 1.9 genmod can split multiallelic calls in VCFs: use flag `-split/--split_variants`.**
 
 To get an example of how splitting variants work, run genmod on the file ```examples/multi_allele_example.vcf``` with the dominant trio.
 That is:
@@ -157,12 +191,6 @@ That is:
 
 Compare the result when not using the ```-split``` flag.
 
-Genmod is distributed with a annotation database that is built from the refGene data.
-If the user wants to build a new annotation set use the command below:
-
-	genmod build_annotation [--type] annotation_file
-
-
 Each variant in the VCF-file will be annotated with which genetic models that are followed in the family if a family file
 (ped file) is provided.
 
@@ -184,7 +212,7 @@ It is possible to run without a family file, in this case all variants will be a
 
 [Variant Effect Predictor](http://www.ensembl.org/info/docs/tools/vep/index.html)(vep) annotations are supported, use the ```--vep```-flag if variants are already annotated with vep.
 
-**GENMOD** will add entrys to the INFO column for the given VCF file depending on what information is given.
+**GENMOD** will add entries to the INFO column for the given VCF file depending on what information is given.
 
 If ```--vep``` is NOT provided:
 
@@ -202,7 +230,6 @@ Also a line for logging is added in the vcf header with the id **genmod**, here
 
 - Compound heterozygote inheritance pattern will be checked if two variants are exonic (or in canonical splice sites) and if they reside in the same gene.
 
-- If compounds should be checked in the whole gene (including introns) use ```--whole_gene```
 - GENMOD supports phased data, use the ```-phased``` flag. Data should follow the [GATK way](http://gatkforums.broadinstitute.org/discussion/45/read-backed-phasing) of phasing.
 
 All annotations will be present only if they have a value.
@@ -218,40 +245,10 @@ All annotations will be present only if they have a value.
 - By default the relative cadd scores is annotated with 'CADD=score', there is also an alternative to annotate with the raw cadd scores using the `--cadd_raw` flag. In this case a info field 'CADD_raw=score'.
 - If your VCF is already annotated with VEP, use `-vep/--vep`
 - If data is phased use `-phased/--phased`
-- If you want to allow compound pairs in intronic regions to use `-gene/--whole_gene`
 - If you want canonical splice site region to be bigger than 2 base pairs on each side of the exons, use `-splice/--splice_padding <integer>`
 - The `-strict/--strict` flag tells **genmod** to only annotate genetic models if they are proved by the data. If a variant is not called in a family member it will not be annotated.
 
-
-###genmod build_annotation###
-
-	genmod build_annotation [--type] [-o/--outdir] annotation_file
-
-The following file formats are supported for building new annotations:
-
-- bed
-- ccds
-- gtf
-- gene_pred
-
-The user can also specify the amount of positions around exon boundaries that should be considered as splice sites. Use
-
-```--splice_padding INTEGER```
-
-###genmod analyze###
-
-From version 1.6 there is also a tool for analyzing the variants annotated by **genmod**. This tool will look at all variants in a vcf and do an analysis based on which inheritance patterns they follow. The variants are then ranked based on the cadd scores, the highest ranked variants for each category is printed to screen and the full list for each category is printed to new vcf files.
-Run with:
-
-	genmod analyze path/to/file.vcf
-
-For more information do
-
-	genmod analyze --help
-
-
-### genmod sort ###
-
+#### genmod sort
 
 Sort a VCF file based on Rank Score.
 
@@ -269,18 +266,9 @@ Options:
   --help                Show this message and exit.
 ```
 
-###genmod summarize###
-
-Tool to get basic statistics of the annotated in a vcf file.
-Run
-
-	genmod summarize --help
+## Conditions for Genetic Models
 
-for more information.
-
-## Conditions for Genetic Models ##
-
-### Short explanation of genotype calls in VCF format:###
+### Short explanation of genotype calls in VCF format
 
 Since we only look at humans, that are diploid, the genotypes represent what we see on both alleles in a single position.
 0 represents the reference sequence, 1 is the first of the alternative alleles, 2 second alternative and so on.
@@ -290,8 +278,7 @@ Some chromosomes are only present in one copy in humans, here it is allowed to o
 
 If phasing has been done the pairs are not unordered anymore and the delimiter is then changed to '|', so one can be heterozygote in two ways; 0|1 or 1|0.
 
-
-### Autosomal Recessive ###
+### Autosomal Recessive
 
 For this model individuals can be carriers so healthy individuals can be heterozygous. Both alleles need to have the variant for an individual to be sick so a healthy individual can not be homozygous alternative and a sick individual *has* to be homozygous alternative.
 
@@ -300,19 +287,15 @@ For this model individuals can be carriers so healthy individuals can be heteroz
 * Variant is considered _de novo_ if both parents are genotyped and do not carry the variant
 
 
-### Autosomal Dominant ###
+### Autosomal Dominant
 
 * Affected individuals have to be heterozygous (het.)
 * Healthy individuals cannot have the alternative variant
 * Variant is considered _de novo_ if both parents are genotyped and do not carry the variant
 
-
-### Autosomal Compound Heterozygote ###
+### Autosomal Compound Heterozygote
 
 This model includes pairs of exonic variants that are present within the same gene.
-**The default behaviour of GENMOD is to look for compounds only in exonic/canonical splice sites**.
-The reason for this is that since some genes have huge intronic regions the data will be drowned in compound pairs.
-If the user wants all variants in genes checked use the flag -gene/--whole_gene.
 
 1. Non-phased data:
 	* Affected individuals have to be het. for both variants
@@ -326,7 +309,7 @@ If the user wants all variants in genes checked use the flag -gene/--whole_gene.
 	* If only one or no variant is found in parents it is considered _de novo_
 
 
-### X-Linked Dominant###
+### X-Linked Dominant
 
 These traits are inherited on the x-chromosome, of which men have one allele and women have two.
 
@@ -338,7 +321,7 @@ These traits are inherited on the x-chromosome, of which men have one allele and
 * If sex is female variant is considered _de novo_ if none of the parents carry the variant
 
 
-### X Linked Recessive ###
+### X Linked Recessive
 
 * Variant has to be on chromosome X
 * Affected males have to be het. or hom. alt. (het is theoretically not possible in males, but can occur due to Pseudo Autosomal Regions).
@@ -347,4 +330,7 @@ These traits are inherited on the x-chromosome, of which men have one allele and
 * Healthy males cannot carry the variant
 * If sex is male the variant is considered _de novo_ if mother is genotyped and does not carry the variant
 * If sex is female variant is considered _de novo_ if not both parents carry the variant
- -->
+
+
+
+[actions-build-status]: https://github.com/Clinical-Genomics/genmod/actions/workflows/build_and_publish.yml/badge.svg