malariagen_data 2.1.0__tar.gz → 2.2.0__tar.gz

{malariagen_data-2.1.0 → malariagen_data-2.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: malariagen-data
-Version: 2.1.0
+Version: 2.2.0
 Summary: A package for accessing MalariaGEN public data.
 License: MIT
 Author: Alistair Miles
@@ -12,6 +12,7 @@ Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Requires-Dist: BioPython
+Requires-Dist: bokeh
 Requires-Dist: dask[array]
 Requires-Dist: fsspec
 Requires-Dist: gcsfs

{malariagen_data-2.1.0 → malariagen_data-2.2.0}/malariagen_data/ag3.py

@@ -2250,6 +2250,46 @@ class Ag3:
         # check parameters
         _check_param_min_cohort_size(min_cohort_size)
 
+        if isinstance(contig, str):
+            contig = [contig]
+
+        df = pd.concat(
+            [
+                self._gene_cnv_frequencies(
+                    contig=c,
+                    cohorts=cohorts,
+                    sample_query=sample_query,
+                    cohorts_analysis=cohorts_analysis,
+                    min_cohort_size=min_cohort_size,
+                    species_analysis=species_analysis,
+                    sample_sets=sample_sets,
+                    drop_invariant=drop_invariant,
+                    max_coverage_variance=max_coverage_variance,
+                )
+                for c in contig
+            ],
+            axis=0,
+        )
+
+        return df
+
+    def _gene_cnv_frequencies(
+        self,
+        *,
+        contig,
+        cohorts,
+        sample_query,
+        cohorts_analysis,
+        min_cohort_size,
+        species_analysis,
+        sample_sets,
+        drop_invariant,
+        max_coverage_variance,
+    ):
+
+        # sanity check - this function is one contig at a time
+        assert isinstance(contig, str)
+
         # load sample metadata
         df_samples = self.sample_metadata(
             sample_sets=sample_sets,
@@ -3342,8 +3382,9 @@ class Ag3:
 
         Parameters
         ----------
-        contig : str
-            Chromosome arm, e.g., "3R".
+        contig : str or list of str
+            Chromosome arm, e.g., "3R". Multiple values can be provided
+            as a list, in which case data will be concatenated, e.g., ["2R", "3R"].
         area_by : str
             Column name in the sample metadata to use to group samples spatially. E.g.,
             use "admin1_iso" or "admin1_name" to group by level 1 administrative divisions,
@@ -3388,6 +3429,52 @@ class Ag3:
         # check parameters
         _check_param_min_cohort_size(min_cohort_size)
 
+        if isinstance(contig, str):
+            contig = [contig]
+
+        ds = xarray_concat(
+            [
+                self._gene_cnv_frequencies_advanced(
+                    contig=c,
+                    area_by=area_by,
+                    period_by=period_by,
+                    sample_sets=sample_sets,
+                    sample_query=sample_query,
+                    min_cohort_size=min_cohort_size,
+                    variant_query=variant_query,
+                    drop_invariant=drop_invariant,
+                    max_coverage_variance=max_coverage_variance,
+                    ci_method=ci_method,
+                    cohorts_analysis=cohorts_analysis,
+                    species_analysis=species_analysis,
+                )
+                for c in contig
+            ],
+            dim="variants",
+        )
+
+        return ds
+
+    def _gene_cnv_frequencies_advanced(
+        self,
+        *,
+        contig,
+        area_by,
+        period_by,
+        sample_sets,
+        sample_query,
+        min_cohort_size,
+        variant_query,
+        drop_invariant,
+        max_coverage_variance,
+        ci_method,
+        cohorts_analysis,
+        species_analysis,
+    ):
+
+        # sanity check - here we deal with one contig only
+        assert isinstance(contig, str)
+
         # load sample metadata
         df_samples = self.sample_metadata(
             sample_sets=sample_sets,
@@ -3813,6 +3900,248 @@ class Ag3:
 
         return out
 
+    def resolve_region(self, region):
+        """Convert a genome region into a standard data structure.
+
+        Parameters
+        ----------
+        region: str
+            Chromosome arm (e.g., "2L"), gene name (e.g., "AGAP007280") or genomic
+            region defined with coordinates (e.g., "2L:44989425-44998059").
+
+        Returns
+        -------
+        out : Region
+            A named tuple with attributes contig, start and end.
+
+        """
+
+        return resolve_region(self, region)
+
+    def plot_genes(
+        self,
+        region,
+        width=700,
+        height=120,
+        show=True,
+        toolbar_location="above",
+        x_range=None,
+        title="Genes",
+    ):
+        """@@TODO"""
+
+        import bokeh.models as bkmod
+        import bokeh.plotting as bkplt
+
+        # handle region parameter - this determines the genome region to plot
+        region = self.resolve_region(region)
+        contig = region.contig
+        start = region.start
+        end = region.end
+        if start is None:
+            start = 0
+        if end is None:
+            end = len(self.genome_sequence(contig))
+
+        # define x axis range
+        if x_range is None:
+            x_range = bkmod.Range1d(start, end, bounds="auto")
+
+        # select the genes overlapping the requested region
+        df_geneset = self.geneset(attributes=["ID", "Name", "Parent", "description"])
+        # df_geneset = df_geneset.set_index("ID")
+        data = df_geneset.query(
+            f"type == 'gene' and contig == '{contig}' and start < {end} and end > {start}"
+        ).copy()
+
+        # we're going to plot each gene as a rectangle, so add some additional
+        # columns
+        data["bottom"] = np.where(data["strand"] == "+", 1, 0)
+        data["top"] = data["bottom"] + 0.8
+
+        # tidy up some columns for presentation
+        data["Name"].fillna("", inplace=True)
+        data["description"].fillna("", inplace=True)
+
+        # define tooltips for hover
+        tooltips = [
+            ("ID", "@ID"),
+            ("Name", "@Name"),
+            ("Description", "@description"),
+            ("Location", "@contig:@start{,}-@end{,}"),
+        ]
+
+        # make a figure
+        fig = bkplt.figure(
+            title=title,
+            plot_width=width,
+            plot_height=height,
+            tools="xpan,xzoom_in,xzoom_out,xwheel_zoom,reset,tap,hover",
+            toolbar_location=toolbar_location,
+            active_scroll="xwheel_zoom",
+            active_drag="xpan",
+            tooltips=tooltips,
+            x_range=x_range,
+        )
+        fig.toolbar.logo = None
+
+        # add functionality to click through to vectorbase
+        url = "https://vectorbase.org/vectorbase/app/record/gene/@ID"
+        taptool = fig.select(type=bkmod.TapTool)
+        taptool.callback = bkmod.OpenURL(url=url)
+
+        # now plot the genes as rectangles
+        fig.quad(
+            bottom="bottom",
+            top="top",
+            left="start",
+            right="end",
+            source=data,
+            line_width=0.5,
+            fill_alpha=0.5,
+        )
+
+        # tidy up the plot
+        fig.xaxis.axis_label = f"Contig {contig} position (bp)"
+        fig.y_range = bkmod.Range1d(-0.4, 2.2)
+        fig.ygrid.visible = False
+        yticks = [0.4, 1.4]
+        yticklabels = ["-", "+"]
+        fig.yaxis.ticker = yticks
+        fig.yaxis.major_label_overrides = {k: v for k, v in zip(yticks, yticklabels)}
+        fig.xaxis[0].formatter = bkmod.NumeralTickFormatter(format="0,0")
+
+        if show:
+            bkplt.show(fig)
+
+        return fig
+
+    def plot_transcript(
+        self,
+        transcript,
+        width=700,
+        height=120,
+        show=True,
+        x_range=None,
+        toolbar_location="above",
+        title=True,
+    ):
+
+        import bokeh.models as bkmod
+        import bokeh.plotting as bkplt
+
+        # find the transcript annotation
+        df_geneset = self.geneset().set_index("ID")
+        parent = df_geneset.loc[transcript]
+
+        if title is True:
+            title = f"{transcript} ({parent.strand})"
+
+        # define tooltips for hover
+        tooltips = [
+            ("Type", "@type"),
+            ("Location", "@contig:@start{,}-@end{,}"),
+        ]
+
+        # make a figure
+        fig = bkplt.figure(
+            title=title,
+            plot_width=width,
+            plot_height=height,
+            tools="xpan,xzoom_in,xzoom_out,xwheel_zoom,reset,hover",
+            toolbar_location=toolbar_location,
+            active_scroll="xwheel_zoom",
+            active_drag="xpan",
+            tooltips=tooltips,
+            x_range=x_range,
+        )
+        fig.toolbar.logo = None
+
+        # find child components of the transcript
+        data = df_geneset.set_index("Parent").loc[transcript].copy()
+        data["bottom"] = -0.4
+        data["top"] = 0.4
+
+        # plot exons
+        exons = data.query("type == 'exon'")
+        fig.quad(
+            bottom="bottom",
+            top="top",
+            left="start",
+            right="end",
+            source=exons,
+            fill_color=None,
+            line_color="black",
+            line_width=0.5,
+            fill_alpha=0,
+        )
+
+        # plot introns
+        for intron_start, intron_end in zip(exons[:-1]["end"], exons[1:]["start"]):
+            intron_midpoint = (intron_start + intron_end) / 2
+            line_data = pd.DataFrame(
+                {
+                    "x": [intron_start, intron_midpoint, intron_end],
+                    "y": [0, 0.1, 0],
+                    "type": "intron",
+                    "contig": parent.contig,
+                    "start": intron_start,
+                    "end": intron_end,
+                }
+            )
+            fig.line(
+                x="x",
+                y="y",
+                source=line_data,
+                line_width=1,
+                line_color="black",
+            )
+
+        # plot UTRs
+        fig.quad(
+            bottom="bottom",
+            top="top",
+            left="start",
+            right="end",
+            source=data.query("type == 'five_prime_UTR'"),
+            fill_color="green",
+            line_width=0,
+            fill_alpha=0.5,
+        )
+        fig.quad(
+            bottom="bottom",
+            top="top",
+            left="start",
+            right="end",
+            source=data.query("type == 'three_prime_UTR'"),
+            fill_color="red",
+            line_width=0,
+            fill_alpha=0.5,
+        )
+
+        # plot CDSs
+        fig.quad(
+            bottom="bottom",
+            top="top",
+            left="start",
+            right="end",
+            source=data.query("type == 'CDS'"),
+            fill_color="blue",
+            line_width=0,
+            fill_alpha=0.5,
+        )
+
+        # tidy up the figure
+        fig.yaxis.ticker = []
+        fig.y_range = bkmod.Range1d(-0.6, 0.6)
+        fig.xaxis.axis_label = f"Contig {parent.contig} position (bp)"
+        fig.xaxis[0].formatter = bkmod.NumeralTickFormatter(format="0,0")
+
+        if show:
+            bkplt.show(fig)
+
+        return fig
+
 
 @numba.njit("Tuple((int8, int64))(int8[:], int8)")
 def _cn_mode_1d(a, vmax):

{malariagen_data-2.1.0 → malariagen_data-2.2.0}/malariagen_data/util.py

@@ -404,3 +404,35 @@ def xarray_concat(
             join=join,
             **kwargs,
         )
+
+
+def type_error(
+    name,
+    value,
+    expectation,
+):
+    message = (
+        f"Bad type for parameter {name}; expected {expectation}, "
+        f"found {type(value)}"
+    )
+    raise TypeError(message)
+
+
+def value_error(
+    name,
+    value,
+    expectation,
+):
+    message = (
+        f"Bad value for parameter {name}; expected {expectation}, " f"found {value!r}"
+    )
+    raise ValueError(message)
+
+
+def check_type(
+    name,
+    value,
+    expectation,
+):
+    if not isinstance(value, expectation):
+        type_error(name, value, expectation)

{malariagen_data-2.1.0 → malariagen_data-2.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "malariagen_data"
-version = "2.1.0"
+version = "2.2.0"
 description = "A package for accessing MalariaGEN public data."
 authors = ["Alistair Miles <alistair.miles@sanger.ac.uk>", "Chris Clarkson <cc28@sanger.ac.uk>", "Kathryn Murie <km22@sanger.ac.uk>", "Nace Kranjc <n.kranjc@imperial.ac.uk>", "Kelly Bennett <kb25@sanger.ac.uk>"]
 license = "MIT"
@@ -19,6 +19,7 @@ scikit-allel = "*"
 xarray = "*"
 numba = "*"
 plotly = "*"
+bokeh = "*"
 statsmodels = "*"
 ipyleaflet = "*"
 ipywidgets = "*"

{malariagen_data-2.1.0 → malariagen_data-2.2.0}/setup.py

@@ -9,6 +9,7 @@ package_data = \
 
 install_requires = \
 ['BioPython',
+ 'bokeh',
  'dask[array]',
  'fsspec',
  'gcsfs',
@@ -27,7 +28,7 @@ install_requires = \
 
 setup_kwargs = {
     'name': 'malariagen-data',
-    'version': '2.1.0',
+    'version': '2.2.0',
     'description': 'A package for accessing MalariaGEN public data.',
     'long_description': None,
     'author': 'Alistair Miles',