Merge pull request #26 from moshi4/develop

Bump to v0.4.4

docs/api-docs/track.md

@@ -5,6 +5,7 @@
       members:
         - add_feature
         - add_exon_feature
+        - add_features
         - add_genbank_features
         - add_gff_features
         - add_subtrack

mkdocs.yml

@@ -42,8 +42,8 @@ markdown_extensions:
   - pymdownx.highlight:
       anchor_linenums: true
   - pymdownx.emoji:
-      emoji_index: !!python/name:materialx.emoji.twemoji
-      emoji_generator: !!python/name:materialx.emoji.to_svg
+      emoji_index: !!python/name:material.extensions.emoji.twemoji
+      emoji_generator: !!python/name:material.extensions.emoji.to_svg
   - pymdownx.inlinehilite
   - pymdownx.snippets
   - pymdownx.superfences

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pygenomeviz"
-version = "0.4.3"
+version = "0.4.4"
 description = "A genome visualization python package for comparative genomics"
 authors = ["moshi4"]
 license = "MIT"

src/pygenomeviz/__init__.py

@@ -8,7 +8,7 @@
 
 warnings.filterwarnings("ignore")
 
-__version__ = "0.4.3"
+__version__ = "0.4.4"
 
 __all__ = [
     "GenomeViz",

src/pygenomeviz/align.py

@@ -200,7 +200,7 @@ def _run_mummer(self, fa_file1: Path, fa_file2: Path, idx: int) -> list[AlignCoo
         # Run genome alignment using nucmer or promer
         prefix = self.outdir / f"out{idx}"
         delta_file = prefix.with_suffix(".delta")
-        cmd = f"{self._align_binary} --mum {fa_file1} {fa_file2} --prefix={prefix}"
+        cmd = f"{self._align_binary} --mum '{fa_file1}' '{fa_file2}' --prefix={prefix}"
         _ = sp.run(cmd, shell=True, capture_output=True, text=True)
 
         # Run delta-filter to map 'one-to-one' or 'many-to-many' relation
@@ -341,16 +341,14 @@ def run(self) -> list[AlignCoord]:
             with tempfile.TemporaryDirectory() as tmpdir:
                 name1 = fa_file1.with_suffix("").name
                 name2 = fa_file2.with_suffix("").name
-                rbh_result_file = self.outdir / f"{idx+1:02d}_{name1}-{name2}_rbh.tsv"
-                cmd = f"mmseqs easy-rbh {fa_file1} {fa_file2} {rbh_result_file} "
+                rbh_file = self.outdir / f"{idx+1:02d}_{name1}-{name2}_rbh.tsv"
+                cmd = f"mmseqs easy-rbh '{fa_file1}' '{fa_file2}' '{rbh_file}' "
                 cmd += f"{tmpdir} --threads {self.process_num} -e {self.evalue} -v 0"
                 if not self.quiet:
                     print(f"# {idx+1:02d}: {name1}-{name2} RBH search\n$ {cmd}\n")
-                sp.run(cmd, shell=True)
+                _ = sp.run(cmd, shell=True, capture_output=True, text=True)
 
-                align_coords.extend(
-                    self.parse_rbh_result(rbh_result_file, name1, name2)
-                )
+                align_coords.extend(self.parse_rbh_result(rbh_file, name1, name2))
 
         return align_coords
 
@@ -519,7 +517,7 @@ def parse_pmauve_file(self, bbone_file: str | Path) -> list[AlignCoord]:
                     continue
                 rows.append(row)
             # Sort by reference seq coordinates
-            rows = sorted(rows, key=lambda row: row[ref_idx])
+            rows = sorted(rows, key=lambda row: row[ref_idx])  # type: ignore
 
         align_coords = []
         for row in rows:

src/pygenomeviz/gui/utils.py

@@ -31,9 +31,15 @@ def load_gbk_file(gbk_file: str | Path | UploadedFile) -> Genbank:
         return Genbank(gbk_file)
     else:
         filename = Path(gbk_file.name).stem
+        trans_dict = {
+            " ": "_",
+            "|": "_",
+            "(": "[",
+            ")": "]",
+        }
         return Genbank(
             StringIO(gbk_file.getvalue().decode("utf-8")),
-            name=filename.replace(" ", "_").replace("|", "_"),
+            name=filename.translate(str.maketrans(trans_dict)),
         )
 
 

src/pygenomeviz/track.py

@@ -499,6 +499,103 @@ def add_exon_feature(
             )
         )
 
+    def add_features(
+        self,
+        features: list[SeqFeature],
+        label_type: str | None = None,
+        label_handle_func: Callable[[str], str] | None = None,
+        labelsize: int = 15,
+        labelcolor: str = "black",
+        plotstyle: LiteralTypes.PLOTSTYLE = "bigarrow",
+        facecolor: str = "orange",
+        edgecolor: str = "black",
+        linewidth: float = 0,
+        labelrotation: int = 45,
+        labelvpos: LiteralTypes.LABELVPOS = "strand",
+        labelhpos: LiteralTypes.LABELHPOS = "center",
+        labelha: LiteralTypes.LABELHA = "left",
+        arrow_shaft_ratio: float = 0.5,
+        size_ratio: float = 1.0,
+        patch_kws: dict[str, Any] | None = None,
+    ) -> None:
+        """Add features (BioPython's SeqFeature list)
+
+        Parameters
+        ----------
+        features : str, optional
+            BioPython's SeqFeature list
+        label_type : str | None, optional
+            Label type (e.g. `gene`,`protein_id`,`product`,etc...)
+        label_handle_func : Callable[[str], str] | None, optional
+            User defined function to handle label.
+            Useful for filtering out unnecesary labels such as `hypothetical ~~~`,
+            omitting labels with long characters, etc.
+        labelsize : int, optional
+            Feature label size
+        labelcolor : str, optional
+            Feature label color
+        plotstyle : str, optional
+            Feature plot style (`bigarrow`|`arrow`|`bigbox`|`box`|`bigrbox`|`rbox`)
+        facecolor : str, optional
+            Feature facecolor.
+            If Genbank qualifiers has facecolor key (e.g. `/facecolor="red"`),
+            facecolor key value is applied preferentially.
+        edgecolor : str, optional
+            Feature edgecolor
+        linewidth : float, optional
+            Feature edge linewidth
+        labelrotation : int, optional
+            Feature label rotation
+        labelvpos : str, optional
+            Feature label vertical position (`top`|`center`|`bottom`|`strand`)
+            If 'strand' is set, 'top' or 'bottom' is auto selected by strand.
+        labelhpos : str, optional
+            Feature label horizontal position (`left`|`center`|`right`)
+        labelha : str, optional
+            Feature label horizontal alignment (`left`|`center`|`right`)
+        arrow_shaft_ratio : float, optional
+            Feature arrow shaft ratio
+        size_ratio : float, optional
+            Feature size ratio to track
+        patch_kws : dict[str, Any] | None, optional
+            Patch properties (e.g. `dict(fc="red", ec="black", lw=0.5, ...)`)
+            <https://matplotlib.org/stable/api/_as_gen/matplotlib.patches.Patch.html>
+        """
+        for feature in features:
+            # Check if start & end positions are within appropriate track range
+            start = int(str(feature.location.start))
+            end = int(str(feature.location.end))
+            self._within_valid_range(start, end, raise_error_on_false=True)
+
+            # Get label value & apply handle func if exists
+            label = feature.qualifiers.get(label_type, [""])[0]
+            if label_handle_func is not None:
+                label = label_handle_func(label)
+            feat_fc = feature.qualifiers.get("facecolor", [facecolor])[0]
+
+            self.features.append(
+                Feature(
+                    start,
+                    end,
+                    feature.strand,
+                    label,
+                    labelsize,
+                    labelcolor,
+                    plotstyle,
+                    feat_fc,
+                    edgecolor,
+                    linewidth,
+                    labelrotation,
+                    labelvpos,
+                    labelhpos,
+                    labelha,
+                    arrow_shaft_ratio,
+                    size_ratio,
+                    patch_kws,
+                    feature,
+                )
+            )
+
     def add_genbank_features(
         self,
         gbk: Genbank,

tests/test_genomeviz.py

@@ -200,6 +200,19 @@ def test_add_exon_feature(tmp_path: Path):
     assert fig_outfile.exists()
 
 
+def test_add_features(gbk_file: Path, tmp_path: Path):
+    """Test add features (BioPython's SeqFeature list)"""
+    gbk = Genbank(gbk_file)
+
+    gv = GenomeViz()
+    track = gv.add_feature_track(gbk.name, gbk.range_size)
+    track.add_features(gbk.extract_features())
+
+    fig_outfile = tmp_path / "result.png"
+    gv.savefig(fig_outfile)
+    assert fig_outfile.exists()
+
+
 def test_gff_genomeviz(gff_file: Path, tmp_path: Path):
     """Test add_gff_features"""
     gff = Gff(gff_file)