Merge pull request #139 from pepkit/dev

Release 0.12.7

.github/workflows/python-publish.yml

@@ -11,9 +11,9 @@ jobs:
     permissions:
       id-token: write
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
     - name: Set up Python
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: '3.x'
     - name: Install dependencies

.github/workflows/run-pytest.yml

@@ -15,10 +15,10 @@ jobs:
         os: [ubuntu-latest]
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
 
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
 

README.md

@@ -7,7 +7,9 @@
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg?style=flat)](http://bioconda.github.io/recipes/geofetch/README.html)
 
-`geofetch` is a command-line tool that downloads sequencing data and metadata from GEO and SRA and create metadata tables in [standard PEP format](https://pep.databio.org/). `geofetch` is hosted at [pypi](https://pypi.org/project/geofetch/). You can convert the result of geofetch into unmapped `bam` or `fastq` files with the included `sraconvert` command.
+
+**geofetch** is a command-line tool that downloads sequencing data and metadata from GEO and SRA and create metadata tables in [standard PEP format](https://pep.databio.org/). `geofetch` is hosted at [pypi](https://pypi.org/project/geofetch/). You can convert the result of geofetch into unmapped `bam` or `fastq` files with the included `sraconvert` command.
+
 
 ## Key geofetch features:
 
@@ -20,4 +22,45 @@
 - Can search GEO to find relevant data
 - Can be used either as a command-line tool or from within Python using an API
 
-For more information, see [complete documentation at https://pep.databio.org/geofetch](https://pep.databio.org/geofetch).
+
+## Docs
+
+---
+
+**Documentation**: <a href="https://pep.databio.org/geofetch/" target="_blank">https://pep.databio.org/geofetch/</a>
+
+**Source Code**: <a href="https://github.com/pepkit/geofetch/" target="_blank">https://github.com/pepkit/geofetch/</a>
+
+---
+
+
+## Installation
+To install `geofetch` use this command: 
+```
+pip install geofetch
+```
+or install the latest version from the GitHub repository:
+```
+pip install git+https://github.com/pepkit/geofetch.git
+```
+
+
+## How to cite:
+https://doi.org/10.1093/bioinformatics/btad069
+```bibtex
+@article{10.1093/bioinformatics/btad069,
+    author = {Khoroshevskyi, Oleksandr and LeRoy, Nathan and Reuter, Vincent P and Sheffield, Nathan C},
+    title = "{GEOfetch: a command-line tool for downloading data and standardized metadata from GEO and SRA}",
+    journal = {Bioinformatics},
+    volume = {39},
+    number = {3},
+    pages = {btad069},
+    year = {2023},
+    month = {03},
+    abstract = "{The Gene Expression Omnibus has become an important source of biological data for secondary analysis. However, there is no simple, programmatic way to download data and metadata from Gene Expression Omnibus (GEO) in a standardized annotation format.To address this, we present GEOfetch—a command-line tool that downloads and organizes data and metadata from GEO and SRA. GEOfetch formats the downloaded metadata as a Portable Encapsulated Project, providing universal format for the reanalysis of public data.GEOfetch is available on Bioconda and the Python Package Index (PyPI).}",
+    issn = {1367-4811},
+    doi = {10.1093/bioinformatics/btad069},
+    url = {https://doi.org/10.1093/bioinformatics/btad069},
+    eprint = {https://academic.oup.com/bioinformatics/article-pdf/39/3/btad069/49407404/btad069.pdf},
+}
+```

geofetch/__init__.py

@@ -1,12 +1,11 @@
 """ Package-level data """
 
-import logmuse
 import coloredlogs
+import logmuse
 
-from geofetch.geofetch import Geofetcher
-from geofetch.finder import Finder
 from geofetch._version import __version__
-
+from geofetch.finder import Finder
+from geofetch.geofetch import Geofetcher
 
 __author__ = ["Oleksandr Khoroshevskyi", "Vince Reuter", "Nathan Sheffield"]
 __all__ = ["Finder", "Geofetcher", "__version__"]

geofetch/__main__.py

@@ -1,4 +1,5 @@
 import sys
+
 from geofetch.geofetch import main
 
 if __name__ == "__main__":

geofetch/_version.py

@@ -1 +1 @@
-__version__ = "0.12.6"
+__version__ = "0.12.7"

geofetch/cli.py

@@ -1,6 +1,8 @@
 import argparse
 import os
+
 import logmuse
+
 from geofetch._version import __version__
 
 

geofetch/finder.py

@@ -1,19 +1,20 @@
+import logging
+import os
+import re
+from datetime import datetime, timedelta
+
+import coloredlogs
+import requests
+import xmltodict
+
 from .const import (
-    RETMAX,
-    ETOOLS_GEO_GSE_BASE,
-    ETOOLS_ENDING,
-    TODAY_DATE,
     DATE_FILTER,
+    ETOOLS_ENDING,
+    ETOOLS_GEO_GSE_BASE,
+    RETMAX,
     THREE_MONTH_FILTER,
+    TODAY_DATE,
 )
-import requests
-import xmltodict
-import re
-import os
-import logging
-import coloredlogs
-from datetime import datetime
-from datetime import timedelta
 
 __author__ = "Oleksandr Khoroshevskyi"
 

geofetch/geofetch.py

@@ -1,65 +1,65 @@
 import copy
 import csv
+import logging
 import os
+import re
 import sys
+import time
+from typing import Dict, List, NoReturn, Tuple, Union
+
+import logmuse
+import pandas as pd
+import peppy
 import requests
 import xmltodict
 import yaml
-import time
-import logging
-
 from rich.progress import track
-import re
-import logmuse
 from ubiquerg import expandpath
-from typing import List, Union, Dict, Tuple, NoReturn
-import peppy
-import pandas as pd
 
 from geofetch.cli import _parse_cmdl
 from geofetch.const import (
-    GSE_PATTERN,
-    SAMPLE_SUPP_METADATA_FILE,
+    CONFIG_PROCESSED_TEMPLATE_NAME,
+    CONFIG_RAW_TEMPLATE_NAME,
+    CONFIG_SRA_TEMPLATE,
     EXP_SUPP_METADATA_FILE,
-    NEW_GENOME_COL_NAME,
+    EXPERIMENT_PATTERN,
     FILE_RAW_NAME_SAMPLE_PATTERN,
     FILE_RAW_NAME_SUBSAMPLE_PATTERN,
-    CONFIG_RAW_TEMPLATE_NAME,
-    CONFIG_SRA_TEMPLATE,
-    CONFIG_PROCESSED_TEMPLATE_NAME,
+    GSE_PATTERN,
+    NCBI_EFETCH,
+    NCBI_ESEARCH,
+    NEW_GENOME_COL_NAME,
     NUM_RETRIES,
+    PROJECT_PATTERN,
+    SAMPLE_SUPP_METADATA_FILE,
     SER_SUPP_FILE_PATTERN,
     SUPP_FILE_PATTERN,
-    PROJECT_PATTERN,
-    NCBI_EFETCH,
-    NCBI_ESEARCH,
-    EXPERIMENT_PATTERN,
 )
 from geofetch.utils import (
     Accession,
-    build_prefetch_command,
-    parse_accessions,
-    parse_SOFT_line,
-    convert_size,
-    clean_soft_files,
-    run_subprocess,
+    _check_file_existance,
+    _create_dot_yaml,
+    _dict_to_list_converter,
+    _filter_gsm,
     _get_list_of_keys,
     _get_value,
     _read_tar_filelist,
-    _check_file_existance,
-    _separate_list_of_files,
-    _update_columns,
-    _sanitize_name,
     _sanitize_config_string,
-    _create_dot_yaml,
-    _which,
-    _dict_to_list_converter,
-    _standardize_colnames,
+    _sanitize_name,
     _separate_file_url,
-    _filter_gsm,
+    _separate_list_of_files,
+    _standardize_colnames,
     _unify_list_keys,
+    _update_columns,
+    _which,
+    build_prefetch_command,
+    clean_soft_files,
+    convert_size,
     gse_content_to_dict,
     is_prefetch_callable,
+    parse_accessions,
+    parse_SOFT_line,
+    run_subprocess,
 )
 
 _LOGGER = logging.getLogger(__name__)

geofetch/sraconvert.py

@@ -1,10 +1,11 @@
 #!/usr/bin/env python
 
-from argparse import ArgumentParser
 import os
-import pypiper
-import logmuse
 import sys
+from argparse import ArgumentParser
+
+import logmuse
+import pypiper
 
 __version__ = "0.1.0"
 

geofetch/utils.py

@@ -1,14 +1,15 @@
 """ Independently-importable utilities to circumvent true scripts. """
 
+import csv
 import logging
 import os
+import re
 import subprocess
 import sys
-import re
-import requests
 from io import StringIO
-import csv
-from typing import Union, List, NoReturn, Dict
+from typing import Dict, List, NoReturn, Union
+
+import requests
 
 _LOGGER = logging.getLogger(__name__)
 

requirements/requirements-all.txt

@@ -4,6 +4,6 @@ ubiquerg>=0.6.2
 requests>=2.28.1
 xmltodict>=0.13.0
 pandas>=1.5.3
-peppy>=0.40.0
+peppy>=0.40.6
 rich>=12.5.1
 coloredlogs>=15.0.1

setup.py

@@ -1,9 +1,10 @@
 #! /usr/bin/env python
 
 import os
-from setuptools import setup
 import sys
 
+from setuptools import setup
+
 PACKAGE = "geofetch"
 REQDIR = "requirements"
 
@@ -49,6 +50,8 @@ def read_reqs(reqs_name):
         "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "Programming Language :: Python :: 3.13",
         "Topic :: Scientific/Engineering :: Bio-Informatics",
     ],
     keywords="project, bioinformatics, sequencing, ngs, workflow, GUI",

tests/test_geofetch.py

@@ -1,11 +1,12 @@
+import os
+import shutil
+
 import peppy
+import pytest
 
 import geofetch
 from geofetch import Geofetcher, utils
 from geofetch.utils import parse_accessions
-import os
-import pytest
-import shutil
 
 INPUT_ACC_FILE = "tests/test_files/input_acc.txt"
 GSE_FILES = "tests/test_files/soft_files"