Merge pull request #8 from PennChopMicrobiomeProgram/dev

Add CI and conda env

.github/workflows/codecov.yml

@@ -0,0 +1,35 @@
+name: CodeCov
+
+on:
+  pull_request:
+    branches: [master, main]
+  push:
+    branches: [master, main]
+  schedule:
+    - cron: "0 13 * * 1"
+
+jobs:
+  run:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.10'
+      - name: setup-conda
+        uses: s-weigand/setup-conda@v1.1.0
+        with:
+          conda-channels: ''
+      - name: Install dependencies
+        run: |
+          conda env update --file primertrim_env.yml
+          python -m pip install --upgrade pip
+          python -m pip install pytest
+          python -m pip install pytest-cov
+          python -m pip install -e .
+      - name: Run tests and collect coverage
+        run: pytest --cov tests/
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v3

.github/workflows/linter.yml

@@ -0,0 +1,26 @@
+name: Super-Linter
+
+on:
+  pull_request:
+    branches: [master, main, dev]
+  push:
+    branches: [master, main]
+
+jobs:
+  super-linter:
+    name: Lint Codebase
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v3
+
+      - name: Run Super-Linter
+        uses: github/super-linter@v4
+        env:
+          VALIDATE_ALL_CODEBASE: true
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+          VALIDATE_PYTHON_BLACK: true
+
+          FILTER_REGEX_INCLUDE: primertrim/.*|tests/.*|setup.py

.github/workflows/python-publish.yml

@@ -0,0 +1,39 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#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]
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - 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
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/tests.yml

@@ -0,0 +1,45 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Tests
+
+on:
+  pull_request:
+    branches: [master, main, dev]
+  push:
+    branches: [master, main]
+  schedule:
+    - cron: "0 13 * * 1"
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.8", "3.9", "3.10"]
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: setup-conda
+      uses: s-weigand/setup-conda@v1.1.0
+      with:
+        conda-channels: ''
+    - name: Install dependencies
+      run: |
+        conda env update --file primertrim_env.yml
+        python -m pip install --upgrade pip
+        python -m pip install pytest
+        python -m pip install -e .
+    - name: Unit tests
+      run: |
+        pytest -vvl tests/
+    - name: Other tests
+      if: matrix.python-version == '3.10'
+      run: |
+        echo "Other tests"

README.md

@@ -1,13 +1,23 @@
 # Primer trim
 
+<!-- Begin badges -->
+[![Tests](https://github.com/PennChopMicrobiomeProgram/primertrim/actions/workflows/tests.yml/badge.svg)](https://github.com/PennChopMicrobiomeProgram/primertrim/actions/workflows/tests.yml)
+[![CodeCov](https://github.com/PennChopMicrobiomeProgram/primertrim/actions/workflows/codecov.yml/badge.svg)](https://github.com/PennChopMicrobiomeProgram/primertrim/actions/workflows/codecov.yml)
+[![Super-Linter](https://github.com/PennChopMicrobiomeProgram/primertrim/actions/workflows/linter.yml/badge.svg)](https://github.com/PennChopMicrobiomeProgram/primertrim/actions/workflows/linter.yml)
+<!--  End badges  -->
+
 Detect short primer sequences in FASTQ reads and trim the reads accordingly.
 
 ## Installation
 
+Primertrim requires vsearch, our recommended method of installation is through conda and is shown here:
+
 ```bash
 git clone https://github.com/PennChopMicrobiomeProgram/primertrim.git
 cd primertrim
-pip install -e .
+conda env create -f primertrim_env.yml -n primertrim
+conda activate primertrim
+pip install .
 ```
 
 ## Algorithm

primertrim/align.py

@@ -3,8 +3,21 @@
 import tempfile
 
 DEFAULT_BLAST_FIELDS = [
-    "qseqid", "sseqid", "pident", "length", "mismatch", "gapopen",
-    "qstart", "qend", "sstart", "send", "qlen", "slen", "qseq", "sseq", "qstrand",
+    "qseqid",
+    "sseqid",
+    "pident",
+    "length",
+    "mismatch",
+    "gapopen",
+    "qstart",
+    "qend",
+    "sstart",
+    "send",
+    "qlen",
+    "slen",
+    "qseq",
+    "sseq",
+    "qstrand",
 ]
 
 BLAST_FIELD_TYPES = {
@@ -43,10 +56,12 @@
     "qstrand": "qstrand",
 }
 
+
 def write_fasta(f, seqs):
     for seq_id, seq in seqs:
         f.write(">{}\n{}\n".format(seq_id, seq))
 
+
 class VsearchAligner:
     def __init__(self, ref_seqs_fp):
         self.ref_seqs_fp = ref_seqs_fp
@@ -58,7 +73,8 @@ def search(self, seqs, input_fp=None, output_fp=None, **kwargs):
         """Search seqs and return hits"""
         if input_fp is None:
             infile = tempfile.NamedTemporaryFile(
-                suffix=".fasta", mode="w+t", encoding="utf-8")
+                suffix=".fasta", mode="w+t", encoding="utf-8"
+            )
             write_fasta(infile, seqs)
             infile.seek(0)
             input_fp = infile.name
@@ -67,8 +83,7 @@ def search(self, seqs, input_fp=None, output_fp=None, **kwargs):
                 write_fasta(f, seqs)
 
         if output_fp is None:
-            outfile = tempfile.NamedTemporaryFile(
-                suffix=".txt", mode="wt")
+            outfile = tempfile.NamedTemporaryFile(suffix=".txt", mode="wt")
             output_fp = outfile.name
 
         self._call(input_fp, output_fp, **kwargs)
@@ -82,18 +97,29 @@ def _call(self, query_fp, output_fp, min_id=0.85, threads=None):
         userfields_arg = "+".join(BLAST_TO_VSEARCH[f] for f in self.fields)
         args = [
             "vsearch",
-            "--usearch_global", query_fp,
-            "--minseqlength", "10",
-            "--mincols", "10",
-            "--id", id_arg,
-            "--wordlength", "4",
-            "--strand", "both",
-            "--maxaccepts", "4",
-            "--minwordmatches", "3",
+            "--usearch_global",
+            query_fp,
+            "--minseqlength",
+            "10",
+            "--mincols",
+            "10",
+            "--id",
+            id_arg,
+            "--wordlength",
+            "4",
+            "--strand",
+            "both",
+            "--maxaccepts",
+            "4",
+            "--minwordmatches",
+            "3",
             "--top_hits_only",
-            "--userfields", userfields_arg,
-            "--db", self.ref_seqs_fp,
-            "--userout", output_fp,
+            "--userfields",
+            userfields_arg,
+            "--db",
+            self.ref_seqs_fp,
+            "--userout",
+            output_fp,
         ]
         if threads is not None:
             threads_arg = "{:d}".format(threads)