Merge branch 'develop'

.github/workflows/create_new_release.yml

@@ -0,0 +1,36 @@
+name: Create release
+
+on: 
+  push:
+    tags:
+      - "v.*"
+
+permissions:
+  contents: write
+
+jobs: 
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v3
+        with:
+          python-version: '3.x'
+      - name: Install FluMut
+        run: |
+          python -m pip install --upgrade pip
+          pip install .
+      - name: Run FluMut
+        run: | 
+          cp examples/multiple_samples.fa examples/fasta_input_example.fa
+          flumut --update
+          flumut -x examples/excel_output_example.xlsm examples/multiple_samples.fa
+
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          files: |
+            examples/excel_output_example.xlsm
+            examples/fasta_input_example.fa

.github/workflows/python-publish.yml

@@ -0,0 +1,58 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+    - name: Build package
+      run: python -m build
+    - uses: actions/upload-artifact@v4
+      with:
+        name: dist_folder
+        path: dist
+
+  pypi-publish:
+    name: upload release to PyPI
+    runs-on: ubuntu-latest
+    # Specifying a GitHub environment is optional, but strongly encouraged
+    environment: release
+    permissions:
+      # IMPORTANT: this permission is mandatory for trusted publishing
+      id-token: write
+    steps:
+    - uses: actions/download-artifact@v4
+      with:
+        name: dist_folder
+        path: dist
+    # retrieve your distributions here
+    - name: Publish package distributions to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1

.vscode/launch.json

@@ -8,7 +8,7 @@
             "name": "FluMut",
             "type": "debugpy",
             "request": "launch",
-            "module": "FluMut.FluMut",
+            "module": "flumut.flumut",
             "console": "integratedTerminal",
             "justMyCode": true,
             "args": [
@@ -24,6 +24,17 @@
                 "(?P<sample>.+)_(?P<segment>.+)",
                 "examples/multiple_samples.fa"
             ]
+        },
+        {
+            "name": "FluMutUpdate",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "flumut.flumut",
+            "console": "integratedTerminal",
+            "justMyCode": true,
+            "args": [
+                "--update"
+            ]
         }
     ]
 }

README.md

@@ -2,14 +2,13 @@
 
 FluMut is an open-source tool designed to search for molecular markers with potential impact on the biological characteristics of Influenza A viruses of the A(H5N1) subtype, starting from complete or partial nucleotide genome sequences.
 
-For the complete documentation please visit [FluMut site](TODO).
+For the complete documentation please visit [FluMut site](https://izsvenezie-virology.github.io/FluMut/).
 
 ## Installation
 
 ### Prerequisites
 FluMut is available for Windows, Linux and macOS.
 
-
 #### Pip
 FluMut is available on [PyPI](https://pypi.org/flumut).
 Before installing FluMut via Pip you need:
@@ -39,7 +38,7 @@ You can get the output file in an [Excel format](#excel) (user-friendly) running
 ```
 flumut -x excel_output.xlsm your_fasta.fa
 ```
-If you prefer the [text outputs](TODO) (machine-readable format) run:
+If you prefer the [text outputs](#text-outputs) (machine-readable format) run:
 ```
 flumut -m markers_output.tsv -M mutations_output.tsv -l literature_output.tsv your_fasta.fa
 ```
@@ -59,20 +58,20 @@ Sequences must adhere to the [IUPAC code](https://www.bioinformatics.org/sms/iup
 FluMut relies on the FASTA header to assign the sequence to a specific segment and sample.
 For this reason, the header must contain both a sample ID (consistent among sequences of the same sample) and one of the the following segment names: `PB2`, `PB1`, `PA`, `HA`, `NP`, `NA`, `MP`, `NS`.
 
-An example of input file  can be downloaded [here](TODO).
+An example of input file can be downloaded [here](https://github.com/izsvenezie-virology/FluMut/releases/latest/download/fasta_input_example.fa).
 
 ## Outputs
 FluMut can produce an Excel output or text outputs:
 - [Excel](#excel)
-- [Text outputs](TODO)
+- [Text outputs](#text-outputs)
 
 By default FluMut reports only markers where all mutations are found.
 You can report all markers where at least one mutation is found using option `-r`/`--relaxed`.
 
 ### Excel
 This is the most user-friendly and complete output. 
 You can obtain this output using the `-x`/`--excel-output` option.
-Find out more [here](TODO).
+Find out more [here](https://izsvenezie-virology.github.io/FluMut/docs/output#excel-output).
 
 >**_IMPORTANT:_** To enable the navigation feature the exstension of the Excel file must be `.xlsm`.
 >If you don't care about navigation, you can use `.xlsx` exstension.
@@ -82,9 +81,9 @@ Find out more [here](TODO).
 You can obtain 3 different text outputs:
 | Option | Output | Desctription |
 | -- | -- | -- |
-| `-m`/`--markers-output` | [Markers output](TODO) | List of detected markers |
-| `-M`/`--mutations-output` | [Mutations output](TODO) | List of amino acids present in the positions of mutations of interest for each sample |
-| `-l`/`--literature-output` | [Literature output](TODO) | List of all papers present in the database |
+| `-m`/`--markers-output` | [Markers output](https://izsvenezie-virology.github.io/FluMut/docs/output#markers-output) | List of detected markers |
+| `-M`/`--mutations-output` | [Mutations output](https://izsvenezie-virology.github.io/FluMut/docs/output#mutations-output) | List of amino acids present in the positions of mutations of interest for each sample |
+| `-l`/`--literature-output` | [Literature output](https://izsvenezie-virology.github.io/FluMut/docs/output#literature-output) | List of all papers present in the database |
 
 ## Cite FluMut
 We are currently writing the paper. 
@@ -100,3 +99,6 @@ FluMut is licensed under the GNU Affero v3 license (see [LICENSE](LICENSE)).
 This work was supported by FLU-SWITCH Era-Net ICRAD (grant agreement No 862605) and by the NextGeneration EU-MUR PNRR Extended Partnership initiative on Emerging Infectious Diseases (Project no. PE00000007, INF-ACT)
 
 ![](docs/images/Logo-Flu-Switch.png) ![](docs/images/Logo-Inf-act.jpg) ![](docs/images/Logo-eu.png)
+
+>Views and opinions expressed are however those of the author(s) only and do not necessarily reflect those of the European Union or the European Health and Digital Executive Agency (HEDEA). 
+>Neither the European Union nor the granting authority can be held responsible for them

docs/docs/aknowledgements.md

@@ -9,10 +9,15 @@ permalink: docs/aknowledgements
 
 We are currently writing the paper. 
 Until the publication please cite the GitHub repository:
+
 [https://github.com/izsvenezie-virology/FluMut](https://github.com/izsvenezie-virology/FluMut)
 
 # Fundings
 
 This work was supported by FLU-SWITCH Era-Net ICRAD (grant agreement No 862605) and by the NextGeneration EU-MUR PNRR Extended Partnership initiative on Emerging Infectious Diseases (Project no. PE00000007, INF-ACT)
 
 | ![](../images/Logo-Flu-Switch.png) | ![](../images/Logo-Inf-act.jpg) | ![](../images/Logo-eu.png) |
+
+{: .note-title}
+Views and opinions expressed are however those of the author(s) only and do not necessarily reflect those of the European Union or the European Health and Digital Executive Agency (HEDEA). 
+Neither the European Union nor the granting authority can be held responsible for them.

docs/docs/installation.md

@@ -9,7 +9,7 @@ permalink: docs/installation
 FluMut is a CLI tool, if you prefer a graphical interface see [FluMut-GUI](#flumut-gui) installation
 
 ## Pip
-FluMut is available on [PyPI](https://pypi.org/flumutTODO).
+FluMut is available on [PyPI](https://pypi.org/flumut).
 Before installing FluMut via Pip you need:
 - [Python](https://www.python.org/downloads/)
 - [Pip](https://pypi.org/project/pip/) (often packed with Python)
@@ -23,7 +23,7 @@ pip install flumut
 When installing via Pip it's strongly recommended to install it in a [virtual environment](https://docs.python.org/3/library/venv.html).
 
 ## Bioconda
-FluMut is also available on [Bioconda](https://bioconda.github.io/TODO).
+FluMut is also available on [Bioconda](https://bioconda.github.io/recipes/flumut/README.html).
 You can install using Conda or Mamba.
 - [Mamba](https://mamba.readthedocs.io/en/latest/installation/mamba-installation.html) (recommended)
 ```

docs/docs/output.md

@@ -9,6 +9,8 @@ permalink: docs/output
 # Excel output
 This is the most user-friendly and complete output. 
 You can obtain this output using the [`--excel-output` option](usage/usage-cli#options).
+You can download the example file [here](https://github.com/izsvenezie-virology/FluMut/releases/latest/download/excel_output_example.xlsx).
+
 It contains 5 sheets:
 - [Markers per sample](#markers-per-sample-sheet)
 - [Samples per marker](#samples-per-marker)

docs/docs/usage/input_file_specs.md

@@ -9,7 +9,7 @@ permalink: docs/usage/input-file
 # Input File
 FluMut can analyze multiple A(H5N1) Influenza virus sequences simultaneously.
 It can handle partial and complete genome sequences of multiple samples.
-You must provide a single file containing all the nucleotide sequences in FASTA format (an example can be downloaded [here](TODO)).
+You must provide a single file containing all the nucleotide sequences in FASTA format (an example can be downloaded [here](https://github.com/izsvenezie-virology/FluMut/releases/latest/download/fasta_input_example.fa)).
 Sequences must adhere to the [IUPAC code](https://www.bioinformatics.org/sms/iupac.html).
 FluMut relies on the FASTA header to assign the sequence to a specific segment and sample.
 For this reason, the header must contain both a sample ID (consistent among sequences of the same sample) and one of the the following segment names: `PB2`, `PB1`, `PA`, `HA`, `NP`, `NA`, `MP`, `NS`.

pyproject.toml

@@ -1,6 +1,47 @@
-[build-system]
-requires = [
-    "setuptools>=42",
-    "wheel"
-]
-build-backend = "setuptools.build_meta"
+[build-system]
+requires = ["setuptools>=61.2"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "flumut"
+description = "A tool to search for molecular markers with potential impact on the biological characteristics of Influenza A viruses of the A(H5N1) subtype."
+requires-python = ">=3.7"
+dependencies = [
+    "click >=8.0.0",
+    "biopython >=1.81",
+    "openpyxl >= 3.1.2",
+    "importlib-resources >= 1.3",
+]
+authors = [
+    {name = "Edoardo Giussani", email = "[email protected]"},
+    {name = "Alessandro Sartori", email = "[email protected]"},
+]
+dynamic = ["version"]
+
+[project.readme]
+file = "README.md"
+content-type = "text/markdown"
+
+[project.license]
+file = "LICENSE"
+content-type = "text-markdown"
+
+[project.urls]
+Homepage = "https://github.com/izsvenezie-virology/FluMut"
+
+[project.scripts]
+flumut = "flumut.flumut:main"
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+include-package-data = true
+
+[tool.setuptools.packages.find]
+where = ["src"]
+namespaces = true
+
+[tool.setuptools.package-data]
+flumutdata = ["*"]
+
+[tool.setuptools.dynamic]
+version = {attr = "flumut.flumut.__version__"}

src/FluMut/OutputFormatter.py → src/flumut/OutputFormatter.py

@@ -6,7 +6,7 @@
 from openpyxl.worksheet.table import Table, TableStyleInfo
 from openpyxl.utils.cell import get_column_letter
 
-from FluMut.DataClass import Mutation, Sample
+from flumut.DataClass import Mutation, Sample
 
 
 def mutations_dict(mutations: List[Mutation]) -> Tuple[List[str], List[Dict[str, str]]]:
@@ -44,7 +44,7 @@ def write_csv(output_file: File, header: List[str], data: List[Dict[str, str]])
 
 
 def get_workbook(vba: bool) -> Workbook:
-    wb = load_workbook(files('FluMutData').joinpath('flumut_output.xlsm'), keep_vba=vba)
+    wb = load_workbook(files('flumutdata').joinpath('flumut_output.xlsm'), keep_vba=vba)
     wb['Markers per sample']._pivots[0].cache.refreshOnLoad = True
     return wb
 

src/FluMut/FluMut.py → src/flumut/flumut.py

@@ -14,15 +14,15 @@
 from importlib_resources import files
 from Bio.Align import PairwiseAligner
 
-from FluMut.DbReader import close_connection, execute_query, open_connection, to_dict, update_db
-from FluMut import OutputFormatter
-from FluMut.DataClass import Mutation, Sample
+from flumut.DbReader import close_connection, execute_query, open_connection, to_dict, update_db
+from flumut import OutputFormatter
+from flumut.DataClass import Mutation, Sample
 
 PRINT_ALIGNMENT = False
 SKIP_UNMATCH_NAMES_OPT = '--skip-unmatch-names'
 SKIP_UNKNOWN_SEGMENTS_OPT = '--skip-unknown-segments'
-DB_FILE = files('FluMutData').joinpath('flumut_db.sqlite')
-__version__ = '0.5.2'
+DB_FILE = files('flumutdata').joinpath('flumut_db.sqlite')
+__version__ = '0.5.3'
 __author__ = 'Edoardo Giussani'
 __contact__ = '[email protected]'
 

tests/test_name_parser.py

@@ -1,5 +1,5 @@
 import unittest
-import FluMut.FluMut as fm
+import flumut.flumut as fm
 import re
 
 

tests/test_position.py

@@ -1,5 +1,5 @@
 import unittest
-import FluMut.FluMut as fm
+import flumut.flumut as fm
 
 
 class TestPosition(unittest.TestCase):

tests/test_translation.py

@@ -1,5 +1,5 @@
 import unittest
-import FluMut.FluMut as fm
+import flumut.flumut as fm
 
 
 class TestTranslate(unittest.TestCase):