gwasstudio 2.12.1__tar.gz

gwasstudio-2.12.1/PKG-INFO

@@ -0,0 +1,87 @@
+Metadata-Version: 2.3
+Name: gwasstudio
+Version: 2.12.1
+Summary: 
+Author: Gianmauro Cuccuru
+Author-email: gianmauro.cuccuru@fht.org
+Requires-Python: >=3.10,<3.13
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Provides-Extra: plot
+Requires-Dist: bokeh (>=3.7.3,<4.0.0)
+Requires-Dist: boto3 (>=1.37.11,<2.0.0)
+Requires-Dist: botocore (>=1.37.11,<2.0.0)
+Requires-Dist: click (>=8.1.8,<9.0.0)
+Requires-Dist: cloup (>=3.0.5,<4.0.0)
+Requires-Dist: dash-bio (>=1.0.1,<2.0.0) ; extra == "plot"
+Requires-Dist: dask (>=2024.12.1,<2025.0.0)
+Requires-Dist: dask-gateway (>=2024.1.0,<2025.0.0)
+Requires-Dist: dask-jobqueue (>=0.9.0,<0.10.0)
+Requires-Dist: hvac (>=2.3.0,<3.0.0)
+Requires-Dist: loguru (>=0.7.3,<0.8.0)
+Requires-Dist: mongoengine (>=0.29.1,<0.30.0)
+Requires-Dist: numpy (>=2.2.1,<2.3.0)
+Requires-Dist: pandas (>=2.2.3,<3.0.0)
+Requires-Dist: platformdirs (>=4.3.8,<5.0.0)
+Requires-Dist: plotly (==6.1.0) ; extra == "plot"
+Requires-Dist: polars (>=1.19.0,<2.0.0)
+Requires-Dist: pyarrow (>=18.1.0,<19.0.0)
+Requires-Dist: ruamel-yaml (>=0.18.10,<0.19.0)
+Requires-Dist: scipy (>=1.15.3,<2.0.0)
+Requires-Dist: tiledb (>=0.33.2,<0.34.0)
+Description-Content-Type: text/markdown
+
+
+
+# GWASStudio: A Tool for Genomic Data Management
+
+![alt text](image.png)
+
+
+## Overview
+
+GWASStudio is a powerful CLI tool designed for efficient storage, retrieval, and querying of genomic summary statistics. It offers a high-performance infrastructure for handling and analyzing large-scale GWAS and QTL datasets, enabling seamless cross-dataset exploration.
+
+## Core Purpose
+
+GWASStudio provides a unified interface across the [CDH](https://github.com/ht-diva/cdh_in_a_box) infrastructure, handling the ingestion, storage, querying and export of genomic data using high-performance technologies.
+
+## Key Functionalities
+
+GWASStudio consists of several key functionalities:
+
+### 1. Data Ingestion
+- **Data Ingestion**: Imports summary statistics data and its metadata associated.
+- **Support for Multiple Storage Options**: Works with both local filesystems and cloud storage (S3).
+
+### 2. Data Querying
+- **Flexible Search**: Enables searching metadata using template files.
+
+### 3. Data Export
+- **Selective Export**: Extracts subsets of data and its metadata associated based on genomic regions, SNPs, or the entire set of data.
+
+## Technical Architecture
+
+GWASStudio leverages several advanced technologies:
+
+1. **TileDB Embedded**: A high-performance array storage engine that enables efficient storage and retrieval of genomic data.
+2. **MongoDB**: A flexible, scalable NoSQL database used for storing and querying metadata associated with genomic datasets.
+3. **Dask**: Provides distributed computing capabilities for processing large datasets.
+4. **Python Ecosystem**: Built on Python with libraries like Click/Cloup for CLI interfaces, Pandas for data manipulation, and various genomics-specific tools.
+
+## Installation
+
+For detailed installation instructions, please refer to the documentation at [https://ht-diva.github.io/gwasstudio/](https://ht-diva.github.io/gwasstudio/)
+
+## Usage
+
+For detailed instructions on how to use this tool, please refer to the [documentation](https://ht-diva.github.io/gwasstudio/) and check the [cli_test](scripts/) script for a practical guide by examples.
+
+## Citation
+
+Example files are derived from:
+
+The variant call format provides efficient and robust storage of GWAS summary statistics. Matthew Lyon, Shea J Andrews, Ben Elsworth, Tom R Gaunt, Gibran Hemani, Edoardo Marcora. bioRxiv 2020.05.29.115824; doi: https://doi.org/10.1101/2020.05.29.115824
+

gwasstudio-2.12.1/README.md

@@ -0,0 +1,51 @@
+
+
+# GWASStudio: A Tool for Genomic Data Management
+
+![alt text](image.png)
+
+
+## Overview
+
+GWASStudio is a powerful CLI tool designed for efficient storage, retrieval, and querying of genomic summary statistics. It offers a high-performance infrastructure for handling and analyzing large-scale GWAS and QTL datasets, enabling seamless cross-dataset exploration.
+
+## Core Purpose
+
+GWASStudio provides a unified interface across the [CDH](https://github.com/ht-diva/cdh_in_a_box) infrastructure, handling the ingestion, storage, querying and export of genomic data using high-performance technologies.
+
+## Key Functionalities
+
+GWASStudio consists of several key functionalities:
+
+### 1. Data Ingestion
+- **Data Ingestion**: Imports summary statistics data and its metadata associated.
+- **Support for Multiple Storage Options**: Works with both local filesystems and cloud storage (S3).
+
+### 2. Data Querying
+- **Flexible Search**: Enables searching metadata using template files.
+
+### 3. Data Export
+- **Selective Export**: Extracts subsets of data and its metadata associated based on genomic regions, SNPs, or the entire set of data.
+
+## Technical Architecture
+
+GWASStudio leverages several advanced technologies:
+
+1. **TileDB Embedded**: A high-performance array storage engine that enables efficient storage and retrieval of genomic data.
+2. **MongoDB**: A flexible, scalable NoSQL database used for storing and querying metadata associated with genomic datasets.
+3. **Dask**: Provides distributed computing capabilities for processing large datasets.
+4. **Python Ecosystem**: Built on Python with libraries like Click/Cloup for CLI interfaces, Pandas for data manipulation, and various genomics-specific tools.
+
+## Installation
+
+For detailed installation instructions, please refer to the documentation at [https://ht-diva.github.io/gwasstudio/](https://ht-diva.github.io/gwasstudio/)
+
+## Usage
+
+For detailed instructions on how to use this tool, please refer to the [documentation](https://ht-diva.github.io/gwasstudio/) and check the [cli_test](scripts/) script for a practical guide by examples.
+
+## Citation
+
+Example files are derived from:
+
+The variant call format provides efficient and robust storage of GWAS summary statistics. Matthew Lyon, Shea J Andrews, Ben Elsworth, Tom R Gaunt, Gibran Hemani, Edoardo Marcora. bioRxiv 2020.05.29.115824; doi: https://doi.org/10.1101/2020.05.29.115824

gwasstudio-2.12.1/pyproject.toml

@@ -0,0 +1,128 @@
+[project]
+name = "gwasstudio"
+version = "2.12.1"
+description = ""
+authors = [
+    { name = "Gianmauro Cuccuru", email = "gianmauro.cuccuru@fht.org" },
+    { name = "Bruno Ariano", email = "bruno.ariano@fht.org" },
+]
+readme = "README.md"
+requires-python = ">=3.10,<3.13"
+dependencies = [
+    "bokeh (>=3.7.3,<4.0.0)",
+    "boto3 (>=1.37.11,<2.0.0)",
+    "botocore (>=1.37.11,<2.0.0)",
+    "click (>=8.1.8,<9.0.0)",
+    "cloup (>=3.0.5,<4.0.0)",
+    "dask (>=2024.12.1,<2025.0.0)",
+    "dask-gateway (>=2024.1.0,<2025.0.0)",
+    "dask-jobqueue (>=0.9.0,<0.10.0)",
+    "hvac (>=2.3.0,<3.0.0)",
+    "loguru (>=0.7.3,<0.8.0)",
+    "mongoengine (>=0.29.1,<0.30.0)",
+    "numpy (>=2.2.1,<2.3.0)",
+    "pandas (>=2.2.3,<3.0.0)",
+    "platformdirs (>=4.3.8,<5.0.0)",
+    "polars (>=1.19.0,<2.0.0)",
+    "pyarrow (>=18.1.0,<19.0.0)",
+    "ruamel-yaml (>=0.18.10,<0.19.0)",
+    "scipy (>=1.15.3,<2.0.0)",
+    "tiledb (>=0.33.2,<0.34.0)",
+]
+
+[project.optional-dependencies]
+plot = [
+    "plotly (==6.1.0)",
+    "dash-bio (>=1.0.1,<2.0.0)",
+]
+
+[project.scripts]
+gwasstudio = "gwasstudio.main:main"
+
+[build-system]
+requires = [
+    "poetry-core>=2.0.0,<3.0.0",
+]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry.group.dev.dependencies]
+pre-commit = "^4.0.1"
+mongomock = "^4.3.0"
+setuptools = "^75.8.0"
+pytest = "^8.3.4"
+pytest-cov = "^6.0.0"
+pytest-randomly = "^3.16.0"
+pandas-stubs = "^2.3.0.250703"
+git-cliff = "^2.10.1"
+deptry = "^0.23.1"
+ruff = "^0.14.0"
+
+[tool.poetry.group.docs.dependencies]
+mkdocs-material = "^9.6.20"
+mkdocs-git-revision-date-plugin = "^0.3.2"
+tomli = "^2.3.0"
+tomli-w = "^1.2.0"
+
+[tool.ruff]
+line-length = 120
+
+[tool.deptry]
+extend_exclude = [
+    "scripts",
+]
+
+[tool.deptry.per_rule_ignores]
+DEP003 = [
+    "gwasstudio",
+]
+DEP004 = [
+    "mongomock",
+    "tomli",
+    "tomli_w",
+]
+DEP002 = [
+    "pyarrow",
+    "bokeh",
+]
+
+[tool.git-cliff.changelog]
+header = "# Changelog\n\nAll notable changes to this project will be documented in this file.\n\n[Git history](https://github.com/ht-diva/gwasstudio/commits/main/)\n"
+body = "{% if version %}## [{{ version | trim_start_matches(pat=\"v\") }}] - {{ timestamp | date(format=\"%Y-%m-%d\") }}\n{% else %}## [unreleased]\n{% endif %}{% for group, commits in commits | filter(attribute=\"merge_commit\", value=false) | unique(attribute=\"message\")| group_by(attribute=\"group\") %}\n    ### {{ group | striptags | trim | upper_first }}\n    {% for commit in commits %}\n        - {% if commit.scope %}*({{ commit.scope }})* {% endif %}{% if commit.breaking %}[**breaking**] {% endif %}{{ commit.message | upper_first }}{% endfor %}\n{% endfor %}\n\n"
+trim = true
+render_always = true
+postprocessors = [
+    { pattern = "\\((\\w+\\s)?#([0-9]+)\\)", replace = "([#${2}](<REPO>/issues/${2}))" },
+    { pattern = ".*", replace_command = "typos --write-changes -" },
+]
+
+[tool.git-cliff.git]
+conventional_commits = true
+filter_unconventional = false
+require_conventional = false
+split_commits = false
+commit_preprocessors = []
+protect_breaking_commits = false
+commit_parsers = [
+    { message = "^feat", group = "<!-- 0 -->🚀 Features" },
+    { message = "^fix", group = "<!-- 1 -->🐛 Bug Fixes" },
+    { message = "^doc", group = "<!-- 3 -->📚 Documentation" },
+    { message = "^perf", group = "<!-- 4 -->⚡ Performance" },
+    { message = "^refactor", group = "<!-- 2 -->🚜 Refactor" },
+    { message = "^style", group = "<!-- 5 -->🎨 Styling" },
+    { message = "^test", group = "<!-- 6 -->🧪 Testing" },
+    { message = "^chore\\(release\\): prepare for", skip = true },
+    { message = "^chore\\(deps.*\\)", skip = true },
+    { message = "^chore\\(pr\\)", skip = true },
+    { message = "^chore\\(pull\\)", skip = true },
+    { message = "^chore|^ci", group = "<!-- 7 -->⚙️ Miscellaneous Tasks" },
+    { body = ".*security", group = "<!-- 8 -->🛡️ Security" },
+    { message = "^revert", group = "<!-- 9 -->◀️ Revert" },
+    { message = ".*", group = "<!-- 10 -->💼 Other" },
+]
+filter_commits = false
+link_parsers = []
+use_branch_tags = false
+topo_order = false
+topo_order_commits = true
+sort_commits = "oldest"
+recurse_submodules = false

gwasstudio-2.12.1/src/gwasstudio/__init__.py

@@ -0,0 +1,78 @@
+import importlib.metadata
+import tempfile
+from pathlib import Path
+
+import pandas as pd
+from cloup import Context, HelpFormatter, HelpTheme, Style
+from loguru import logger as a_logger
+from platformdirs import user_config_dir, user_data_dir, user_log_dir
+
+# https://pandas.pydata.org/pandas-docs/stable/user_guide/copy_on_write.html#
+pd.options.mode.copy_on_write = True
+
+__all__ = [
+    "__appname__",
+    "__version__",
+    "context_settings",
+    "config_dir",
+    "config_filename",
+    "data_dir",
+    "log_file",
+    "logger",
+    "mongo_db_path",
+    "mongo_db_logpath",
+]
+
+__appname__ = __name__
+
+try:
+    __version__ = importlib.metadata.version(__appname__)
+except importlib.metadata.PackageNotFoundError:
+    __version__ = "unknown"
+
+default_log_dir = Path(user_log_dir(__appname__))
+try:
+    default_log_dir.mkdir(parents=True, exist_ok=True)
+    test_file = default_log_dir / ".write_test"
+    test_file.write_text("test")
+    test_file.unlink()
+    dir_writable = True
+except Exception:
+    dir_writable = False
+
+if dir_writable:
+    log_dir = Path(user_log_dir(__appname__))
+    config_dir = Path(user_config_dir(__appname__))
+    data_dir = Path(user_data_dir(__appname__)) / "data"
+else:
+    tmp_root = Path(tempfile.gettempdir())
+    base_dir = tmp_root / f"{__appname__}_tmp"
+    log_dir = base_dir / "log"
+    config_dir = base_dir / "config"
+    data_dir = base_dir / "data"
+
+log_dir.mkdir(parents=True, exist_ok=True)
+config_dir.mkdir(parents=True, exist_ok=True)
+data_dir.mkdir(parents=True, exist_ok=True)
+
+log_file = log_dir / "gwasstudio.log"
+config_filename = "config.yaml"
+mongo_db_path = data_dir / "mongo_db"
+mongo_db_logpath = log_dir / "mongod.log"
+
+mongo_db_path.mkdir(parents=True, exist_ok=True)
+
+# Check the docs for all available arguments of HelpFormatter and HelpTheme.
+formatter_settings = HelpFormatter.settings(
+    theme=HelpTheme(
+        invoked_command=Style(fg="red"),
+        heading=Style(fg="bright_white", bold=True),
+        constraint=Style(fg="magenta"),
+        col1=Style(fg="yellow"),
+    )
+)
+
+context_settings = Context.settings(formatter_settings=formatter_settings)
+
+logger = a_logger
+logger.remove()

gwasstudio-2.12.1/src/gwasstudio/cli/__init__.py

@@ -0,0 +1,7 @@
+from .export import export
+from .info import info
+from .ingest import ingest
+from .list import list_projects
+from .metadata.query import query_metadata
+
+__all__ = ["export", "info", "ingest", "list_projects", "query_metadata"]