Dev

.github/workflows/ci.yaml

@@ -13,7 +13,7 @@ jobs:
 
     strategy:
       matrix:
-        os: [macos-13, ubuntu-latest]
+        os: [macos-latest, ubuntu-latest]
         python-version: ["3.9"]
 
     steps:
@@ -34,11 +34,10 @@ jobs:
       - name: Install project
         shell: bash -l {0}
         run: |
-          conda install python=${{ matrix.python-version }}
+          conda install python=${{ matrix.python-version }} pip
           python -m pip install --upgrade pip
           pip install -e .
-          pip install black
-          pip install isort
+          pip install ruff
           pip install pytest
           pip install pytest-cov
       - name: Check formatting

.github/workflows/release.yaml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: conda-incubator/setup-miniconda@v3
         with:
           python-version: 3.9
@@ -26,10 +26,7 @@ jobs:
         run: |
           python -m pip install -U pip
           pip install -e .
-          pip install black
-          pip install isort
-          pip install pytest
-          pip install pytest-cov
+          pip install ruff
       - name: Build a binary wheel and a source tarball
         shell: bash -l {0}
         run: just build

HISTORY.md

@@ -1,5 +1,12 @@
 # History
 
+# 1.4.0
+
+* Fixes [#102](https://github.com/gbouras13/dnaapler/issues/102). `dnaapler largest`, `mystery` and `nearest` could reorient to the wrong coordinate when the chosen CDS was on the negative strand, as the lowest coordinate of the CDS was used instead of its actual start codon. The reoriented sequence now correctly begins at the start codon. A related latent bug in the negative-strand fallback of the MMseqs2-based reorientation was also fixed.
+* If you run `dnaapler` with GFA input, it now also writes a `{prefix}_reoriented.fasta` alongside the `{prefix}_reoriented.gfa`. This FASTA contains all contigs from the GFA (circular contigs reoriented with overlap trimmed, non-circular contigs passed through unchanged), so it can be fed directly to downstream tools such as polishers.
+* If a GFA input contains no circular sequences, `dnaapler` no longer exits with an error. Instead it warns, copies the input GFA to the output, and writes all sequences out as a linear `{prefix}_reoriented.fasta`. For `dnaapler all` and `dnaapler bulk`, a reorientation summary is also written with every contig marked as not reoriented.
+* Internal: migrated linting and formatting to [ruff](https://docs.astral.sh/ruff/), added golden-output regression tests, and fixed the CI workflows.
+
 # 1.3.0 (2025-08-21)
 
 * Thanks @mbhall88 for extending the functionality of `--ignore` and generally cleaning up the codebase a bit

docs/output.md

@@ -4,7 +4,9 @@
 
 dnaapler creates a number of output files. For all subcommands that are not `dnaapler bulk`, inside the output directory you will find:
 
-* A `{prefix}_reoriented.fasta` containing the reoriented genome. If the input file was in GFA format, this will instead be `{prefix}_reoriented.gfa`.
+* A `{prefix}_reoriented.fasta` containing the reoriented genome. If the input file was in GFA format, dnaapler will additionally write a `{prefix}_reoriented.gfa`. In this case the `{prefix}_reoriented.fasta` contains all contigs from the GFA — circular contigs reoriented (with overlap trimmed), and non-circular contigs passed through unchanged — so it can be fed directly to downstream tools such as polishers. Reoriented contigs are indicated in the FASTA header with `rotated=True`.
+
+* If the input GFA contains no circular sequences, there is nothing to reorient. Rather than exiting with an error, dnaapler will warn, copy the input GFA to `{prefix}_reoriented.gfa`, and write all sequences out as a linear `{prefix}_reoriented.fasta` unchanged. For `dnaapler all` and `dnaapler bulk`, a reorientation summary is also written (`{prefix}_all_reorientation_summary.tsv` / `{prefix}_bulk_reorientation_summary.tsv`) with every contig marked `No_reorientation`.
 
 * A `{prefix}_blast_output.txt` if a BLAST based method is used. This file will contain the raw blastx results in BLAST output format 6.
 

justfile

@@ -2,19 +2,15 @@ PROJECT := "dnaapler"
 OPEN := if os() == "macos" { "open" } else { "xdg-open" }
 VERSION := `poetry version | rg -o '\d+\.\d+\.\d+'`
 
-# format code with black and isort
+# format code with ruff
 fmt:
-    poetry run black .
-    poetry run isort .
+    poetry run ruff format .
+    poetry run ruff check --fix .
 
-# check format of code with black and isort
+# check formatting and lint with ruff
 check-fmt:
-    poetry run black --check .
-    poetry run isort --check .
-
-# lint code with flake8
-lint:
-    poetry run flake8 .
+    poetry run ruff format --check .
+    poetry run ruff check .
 
 # install latest version with poetry
 install:

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dnaapler"
-version = "1.3.0" # change VERSION too
+version = "1.4.0" # change VERSION too
 description = "Reorients assembled microbial sequences"
 authors = ["George Bouras <george.bouras@adelaide.edu.au>"]
 license = "MIT"
@@ -26,11 +26,9 @@ pyrodigal = ">=3.0.0"
 
 
 [tool.poetry.dev-dependencies]
-black = ">=22.3.0"
-isort = ">=5.10.1"
+ruff = ">=0.4.0"
 pytest = ">=6.2.5"
 pytest-cov = ">=3.0.0"
-flake8 = ">=3.0.1"
 
 [[tool.poetry.source]]
 name = "pypi-test"
@@ -41,5 +39,10 @@ priority = "primary"
 requires = ["poetry-core>=1.0.0"]
 build-backend = "poetry.core.masonry.api"
 
-[tool.isort]
-profile = "black"
+[tool.ruff]
+line-length = 88
+exclude = ["*.ipynb"]
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "I"]
+ignore = ["E501"]

src/dnaapler/__init__.py

@@ -189,7 +189,10 @@ def chromosome(
 
     # validates fasta or gfa
     validate_input(input)
-    input_is_gfa, input, original_gfa = prep_gfa(input, output)
+    input_is_gfa, input, original_gfa, gfa_no_circular = prep_gfa(input, output, prefix)
+    if gfa_no_circular:
+        end_dnaapler(start_time)
+        return
 
     # validate E-value
     check_evalue(evalue)
@@ -270,7 +273,10 @@ def archaea(
 
     # validates fasta or gfa
     validate_input(input)
-    input_is_gfa, input, original_gfa = prep_gfa(input, output)
+    input_is_gfa, input, original_gfa, gfa_no_circular = prep_gfa(input, output, prefix)
+    if gfa_no_circular:
+        end_dnaapler(start_time)
+        return
 
     # validate E-value
     check_evalue(evalue)
@@ -351,7 +357,10 @@ def plasmid(
 
     # validates fasta or gfa
     validate_input(input)
-    input_is_gfa, input, original_gfa = prep_gfa(input, output)
+    input_is_gfa, input, original_gfa, gfa_no_circular = prep_gfa(input, output, prefix)
+    if gfa_no_circular:
+        end_dnaapler(start_time)
+        return
 
     # validate E-value
     check_evalue(evalue)
@@ -432,7 +441,10 @@ def phage(
 
     # validates fasta or gfa
     validate_input(input)
-    input_is_gfa, input, original_gfa = prep_gfa(input, output)
+    input_is_gfa, input, original_gfa, gfa_no_circular = prep_gfa(input, output, prefix)
+    if gfa_no_circular:
+        end_dnaapler(start_time)
+        return
 
     # validate E-value
     check_evalue(evalue)
@@ -520,7 +532,10 @@ def custom(
 
     # validates fasta or gfa
     validate_input(input)
-    input_is_gfa, input, original_gfa = prep_gfa(input, output)
+    input_is_gfa, input, original_gfa, gfa_no_circular = prep_gfa(input, output, prefix)
+    if gfa_no_circular:
+        end_dnaapler(start_time)
+        return
 
     # validate E-value
     check_evalue(evalue)
@@ -645,7 +660,10 @@ def nearest(ctx, input, output, threads, prefix, force, **kwargs):
 
     # validates fasta or gfa
     validate_input(input)
-    input_is_gfa, input, original_gfa = prep_gfa(input, output)
+    input_is_gfa, input, original_gfa, gfa_no_circular = prep_gfa(input, output, prefix)
+    if gfa_no_circular:
+        end_dnaapler(start_time)
+        return
 
     # run the nearest workflow
     run_nearest(ctx, input, output, prefix)
@@ -691,7 +709,10 @@ def largest(ctx, input, output, threads, prefix, force, **kwargs):
 
     # validates fasta or gfa
     validate_input(input)
-    input_is_gfa, input, original_gfa = prep_gfa(input, output)
+    input_is_gfa, input, original_gfa, gfa_no_circular = prep_gfa(input, output, prefix)
+    if gfa_no_circular:
+        end_dnaapler(start_time)
+        return
 
     # run the nearest workflow
     run_largest(ctx, input, output, prefix)
@@ -781,7 +802,12 @@ def bulk(
     # validates fasta or gfa
     validate_input_bulk(input)
     check_duplicate_headers(input)
-    input_is_gfa, input, original_gfa = prep_gfa(input, output)
+    input_is_gfa, input, original_gfa, gfa_no_circular = prep_gfa(
+        input, output, prefix, summary_type="bulk"
+    )
+    if gfa_no_circular:
+        end_dnaapler(start_time)
+        return
 
     # validate E-value
     check_evalue(evalue)
@@ -954,7 +980,12 @@ def all(
     # validates fasta or gfa
     validate_input_all(input)
     check_duplicate_headers(input)
-    input_is_gfa, input, original_gfa = prep_gfa(input, output)
+    input_is_gfa, input, original_gfa, gfa_no_circular = prep_gfa(
+        input, output, prefix, summary_type="all"
+    )
+    if gfa_no_circular:
+        end_dnaapler(start_time)
+        return
 
     # validate E-value
     check_evalue(evalue)

src/dnaapler/utils/cds_methods.py

@@ -59,8 +59,11 @@ def run_mystery(ctx, input: Path, seed_value: int, output: Path, prefix: str) ->
         reorient_gene_number = random.randint(2, gene_count - 1)
 
         logger.info(f"Gene number {reorient_gene_number} was selected.")
-        start = genes[reorient_gene_number].begin
         strand = genes[reorient_gene_number].strand
+        if strand == 1:
+            start = genes[reorient_gene_number].begin
+        else:
+            start = genes[reorient_gene_number].end
 
         if strand == 1:
             strand_eng = "forward"
@@ -112,8 +115,11 @@ def run_nearest(ctx, input: Path, output: Path, prefix: str) -> None:
 
         reorient_gene_number = 1
 
-        start = genes[reorient_gene_number].begin
         strand = genes[reorient_gene_number].strand
+        if strand == 1:
+            start = genes[reorient_gene_number].begin
+        else:
+            start = genes[reorient_gene_number].end
 
         if strand == 1:
             strand_eng = "forward"
@@ -176,8 +182,11 @@ def run_largest(ctx, input: Path, output: Path, prefix: str) -> None:
         # Find the gene with the max overlap
         largest_gene_index = max(size_dict, key=lambda key: size_dict[key])
 
-        start = genes[largest_gene_index].begin
         strand = genes[largest_gene_index].strand
+        if strand == 1:
+            start = genes[largest_gene_index].begin
+        else:
+            start = genes[largest_gene_index].end
         max_size = size_dict[largest_gene_index] / 3
 
         if strand == 1: