Merge pull request #2 from RIVM-bioinformatics/dev

Add `--keep-gaps` flag

.github/workflows/publish.yaml

@@ -0,0 +1,31 @@
+name: Publish Python package
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  publish:
+    name: Publish package
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+
+      - name: Build package
+        run: |
+          python -m pip install --upgrade pip build
+          python -m build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          user: __token__
+          password: ${{ secrets.PYPI_TOKEN_PROD }}

.github/workflows/release.yml

@@ -0,0 +1,54 @@
+name: Build and release
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  bump-version:
+    name: Release version
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: GoogleCloudPlatform/release-please-action@v3
+        id: release
+        with:
+          release-type: python
+          package-name: AminoExtract
+          token: ${{ secrets.RELEASE_TOKEN }}
+
+  # update-docs:
+  #   needs: bump-version
+  #   name: Update docs
+  #   runs-on: ubuntu-latest
+  #   if: "contains(github.event.head_commit.message, 'chore(main):')"
+  #   steps:
+  #     - name: Checkout main
+  #       uses: actions/checkout@v3
+  #       with:
+  #         fetch-depth: 0
+
+  #     - name: Copy Changelog
+  #       uses: canastro/copy-file-action@master
+  #       with:
+  #         source: "CHANGELOG.md"
+  #         target: "docs/changelog.md"
+
+  #     - name: Setup Git
+  #       run: |
+  #         git config --global user.name "Github Actions"
+  #         git config --global user.email '41898282+github-actions[bot]@users.noreply.github.com'
+
+  #     - name: Setup Python
+  #       uses: actions/setup-python@v4
+  #       with:
+  #         python-version: "3.10"
+
+  #     - name: Install dependencies
+  #       run: |
+  #         python -m pip install --upgrade pip
+  #         pip install -r docs-requirements.txt
+
+  #     - name: Publish docs
+  #       run: |
+  #         mike deploy --config-file mkdocs.yml --push --force --update-aliases $(git tag --sort=committerdate | tail -1 | sed 's/v//') latest

.github/workflows/sync.yml

@@ -0,0 +1,29 @@
+name: Sync Branches
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  sync-branches:
+    runs-on: ubuntu-latest
+    name: Syncing branches
+    if: "contains(github.event.head_commit.message, 'chore(main):')"
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Set up Node
+        uses: actions/setup-node@v3
+        with:
+          node-version: 12
+
+      - name: Opening pull request
+        id: pull
+        uses: tretuna/sync-branches@1.4.0
+        with:
+          GITHUB_TOKEN: ${{secrets.GITHUB_TOKEN}}
+          FROM_BRANCH: "main"
+          TO_BRANCH: "dev"
+          PULL_REQUEST_TITLE: "chore: sync main to dev"

AminoExtract/__main__.py

@@ -59,6 +59,8 @@ def main() -> None:
     sys.exit(1) if empty_dataframe(GFF_Obj.df, args.feature_type) else None
     SeqRecords = filter_sequences(GFF_Obj, fasta_records)
 
-    AA_dict = Extract_AminoAcids(GFFobj=GFF_Obj, SeqRecords=SeqRecords, verbose=True)
+    AA_dict = Extract_AminoAcids(
+        GFFobj=GFF_Obj, SeqRecords=SeqRecords, keep_gaps=args.keep_gaps, verbose=True
+    )
 
     write_aa_file(AA_dict, args.output, args.name, args.outtype)

AminoExtract/args.py

@@ -4,8 +4,6 @@
 import re
 import sys
 
-from rich import print
-
 from AminoExtract import __prog__, __version__
 from AminoExtract.functions import QuickArgFormatter, RichParser, log
 
@@ -150,6 +148,15 @@ def get_args(givenargs: list[str] | None = None) -> argparse.Namespace:
         required=False,
     )
 
+    opt_args.add_argument(
+        "--keep-gaps",
+        "-kg",
+        action="store_true",
+        default=False,
+        help='If this flag is set then the amino acid translation will be done including gaps in the nucleotide sequence.\nThis results in an "X" on gap positions in the aminoacid sequence.\n [underline]By default, gaps are removed before translation.[/underline]',
+        required=False,
+    )
+
     opt_args.add_argument(
         "--version",
         "-v",

AminoExtract/filter.py

@@ -1,5 +1,3 @@
-import sys
-
 import pandas as pd
 
 from AminoExtract.functions import log

AminoExtract/reader.py

@@ -3,7 +3,7 @@
 
 import magic
 import pandas as pd
-from Bio import Seq, SeqIO
+from Bio import SeqIO
 
 from AminoExtract.functions import log
 

AminoExtract/sequences.py

@@ -1,7 +1,4 @@
-import sys
-
 from Bio.Seq import Seq
-from rich import print
 
 from AminoExtract.functions import log
 from AminoExtract.reader import GffDataFrame
@@ -25,7 +22,10 @@ def Reverse_complement(seq: str) -> Seq:
 
 
 def Extract_AminoAcids(
-    GFFobj: GffDataFrame, SeqRecords: list, verbose: bool = False
+    GFFobj: GffDataFrame,
+    SeqRecords: list,
+    keep_gaps: bool = False,
+    verbose: bool = False,
 ) -> dict:
     """
     Extract amino acids from the SeqRecord objects based on the start and end positions of the GFFobj.df dataframe
@@ -36,13 +36,18 @@ def Extract_AminoAcids(
         GffDataFrame
     SeqRecords : list
         list of SeqRecord objects
-    feature_type : str
-        str
+    keep_gaps : bool, optional
+        If True, gaps ('-') in the nucleotide sequence will not be removed before AA translation.
+        If False, gaps will be removed from the nucleotide sequence before translation.
+        (default is False)
+    verbose : bool, optional
+        bool = False
 
     Returns
     -------
-    dict
-        A dictionary with the SeqRecord id as the key and the amino acid sequences as the value.
+        A dictionary with the sequence ID as the key and a dictionary as the value. The dictionary has the
+    name of the feature as the key and the amino acid sequence as the value.
+
     """
 
     log.info(
@@ -58,11 +63,12 @@ def Extract_AminoAcids(
     for row in GFFobj.df.itertuples():
         try:
             name = row.Name
-        except AttributeError:	
-            log.warn("No '[green]Name[/green]' attribute found in GFF records. Using '[cyan]ID[/cyan]' instead") if verbose else None
+        except AttributeError:
+            log.warn(
+                "No '[green]Name[/green]' attribute found in GFF records. Using '[cyan]ID[/cyan]' instead"
+            ) if verbose else None
             name = f"ID-{row.ID}"
-
-
+
         # get the sequence ID from the row
         seq_id = row.seqid
 
@@ -75,7 +81,11 @@ def Extract_AminoAcids(
         NucSequence = SeqDict[seq_id]
 
         # get the sequence slice from the start to the end position
-        seq_slice = NucSequence[start:end].replace("-", "")
+        seq_slice = (
+            NucSequence[start:end]
+            if keep_gaps
+            else NucSequence[start:end].replace("-", "")
+        )
 
         # convert the sequence slice to a string
         seq_slice_str = str(seq_slice)

AminoExtract/writer.py

@@ -1,5 +1,4 @@
 import pathlib
-import sys
 
 from Bio import Seq
 

setup.py

@@ -32,4 +32,12 @@
     },
     keywords=[],
     zip_safe=False,
+    classifiers=[
+        "Development Status :: 4 - Beta",
+        "Programming Language :: Python :: 3.10",
+        "License :: OSI Approved :: MIT License",
+        "Topic :: Scientific/Engineering :: Bio-Informatics",
+        "Intended Audience :: Science/Research",
+        "Operating System :: POSIX",
+    ],
 )