Merge branch 'master' into GH660_fix_cnv_discordant_read_calls

docs/source/Af1.rst

@@ -71,6 +71,7 @@ SNP data access
     is_accessible
     biallelic_snp_calls
     biallelic_diplotypes
+    biallelic_snps_to_plink
 
 Haplotype data access
 ---------------------

docs/source/Ag3.rst

@@ -72,6 +72,7 @@ SNP data access
     is_accessible
     biallelic_snp_calls
     biallelic_diplotypes
+    biallelic_snps_to_plink
 
 Haplotype data access
 ---------------------

malariagen_data/__init__.py

@@ -4,6 +4,7 @@
 from .amin1 import Amin1
 from .anopheles import AnophelesDataResource, Region
 from .pf7 import Pf7
+from .pf8 import Pf8
 from .pv4 import Pv4
 from .util import SiteClass
 

malariagen_data/anoph/cnv_data.py

@@ -751,6 +751,8 @@ def plot_cnv_hmm_coverage(
         line_kwargs: Optional[gplt_params.line_kwargs] = None,
         show: gplt_params.show = True,
         output_backend: gplt_params.output_backend = gplt_params.output_backend_default,
+        gene_labels: Optional[gplt_params.gene_labels] = None,
+        gene_labelset: Optional[gplt_params.gene_labelset] = None,
     ) -> gplt_params.figure:
         debug = self._log.debug
 
@@ -782,6 +784,8 @@ def plot_cnv_hmm_coverage(
             x_range=fig1.x_range,
             show=False,
             output_backend=output_backend,
+            gene_labels=gene_labels,
+            gene_labelset=gene_labelset,
         )
 
         debug("combine plots into a single figure")
@@ -960,6 +964,8 @@ def plot_cnv_hmm_heatmap(
         track_height: Optional[gplt_params.track_height] = None,
         genes_height: gplt_params.genes_height = gplt_params.genes_height_default,
         show: gplt_params.show = True,
+        gene_labels: Optional[gplt_params.gene_labels] = None,
+        gene_labelset: Optional[gplt_params.gene_labelset] = None,
     ) -> gplt_params.figure:
         debug = self._log.debug
 
@@ -989,6 +995,8 @@ def plot_cnv_hmm_heatmap(
             height=genes_height,
             x_range=fig1.x_range,
             show=False,
+            gene_labels=gene_labels,
+            gene_labelset=gene_labelset,
         )
 
         debug("combine plots into a single figure")

malariagen_data/anoph/distance.py

@@ -6,7 +6,6 @@
 import numba  # type: ignore
 import numpy as np
 from numpydoc_decorator import doc  # type: ignore
-import anjl.params  # type: ignore
 
 # Internal imports.
 from .snp_data import AnophelesSnpData
@@ -410,10 +409,10 @@ def plot_njt(
         metric: distance_params.distance_metric = distance_params.default_distance_metric,
         distance_sort: Optional[tree_params.distance_sort] = None,
         count_sort: Optional[tree_params.count_sort] = None,
-        center_x: anjl.params.center_x = 0,
-        center_y: anjl.params.center_y = 0,
-        arc_start: anjl.params.arc_start = 0,
-        arc_stop: anjl.params.arc_stop = 2 * math.pi,
+        center_x: distance_params.center_x = 0,
+        center_y: distance_params.center_y = 0,
+        arc_start: distance_params.arc_start = 0,
+        arc_stop: distance_params.arc_stop = 2 * math.pi,
         width: plotly_params.fig_width = 800,
         height: plotly_params.fig_height = 600,
         show: plotly_params.show = True,
@@ -426,8 +425,8 @@ def plot_njt(
         color_discrete_sequence: plotly_params.color_discrete_sequence = None,
         color_discrete_map: plotly_params.color_discrete_map = None,
         category_orders: plotly_params.category_order = None,
-        edge_legend: anjl.params.edge_legend = False,
-        leaf_legend: anjl.params.leaf_legend = True,
+        edge_legend: distance_params.edge_legend = False,
+        leaf_legend: distance_params.leaf_legend = True,
         legend_sizing: plotly_params.legend_sizing = "constant",
         thin_offset: base_params.thin_offset = 0,
         sample_sets: Optional[base_params.sample_sets] = None,
@@ -449,6 +448,10 @@ def plot_njt(
         inline_array: base_params.inline_array = base_params.inline_array_default,
         chunks: base_params.chunks = base_params.native_chunks,
     ) -> plotly_params.figure:
+        # Only import anjl if needed, as it requires a couple of seconds to compile
+        # functions.
+        import anjl  # type: ignore
+
         # Normalise params.
         if count_sort is None and distance_sort is None:
             count_sort = True

malariagen_data/anoph/distance_params.py

@@ -19,3 +19,20 @@
 ]
 
 default_nj_algorithm: nj_algorithm = "dynamic"
+
+center_x: TypeAlias = Annotated[int | float, "X coordinate where plotting is centered."]
+
+center_y: TypeAlias = Annotated[int | float, "Y coordinate where plotting is centered."]
+
+arc_start: TypeAlias = Annotated[int | float, "Angle where tree layout begins."]
+
+arc_stop: TypeAlias = Annotated[int | float, "Angle where tree layout ends."]
+
+edge_legend: TypeAlias = Annotated[
+    bool, "Show legend entries for the different edge (line) colors."
+]
+
+leaf_legend: TypeAlias = Annotated[
+    bool,
+    "Show legend entries for the different leaf node (scatter) colors and symbols.",
+]

malariagen_data/anoph/fst.py

@@ -293,6 +293,8 @@ def plot_fst_gwss(
         show: gplt_params.show = True,
         output_backend: gplt_params.output_backend = gplt_params.output_backend_default,
         clip_min: fst_params.clip_min = 0.0,
+        gene_labels: Optional[gplt_params.gene_labels] = None,
+        gene_labelset: Optional[gplt_params.gene_labelset] = None,
     ) -> gplt_params.figure:
         # gwss track
         fig1 = self.plot_fst_gwss_track(
@@ -327,6 +329,8 @@ def plot_fst_gwss(
             x_range=fig1.x_range,
             show=False,
             output_backend=output_backend,
+            gene_labels=gene_labels,
+            gene_labelset=gene_labelset,
         )
 
         # combine plots into a single figure

malariagen_data/anoph/g123.py

@@ -438,6 +438,8 @@ def plot_g123_gwss(
         output_backend: gplt_params.output_backend = gplt_params.output_backend_default,
         inline_array: base_params.inline_array = base_params.inline_array_default,
         chunks: base_params.chunks = base_params.native_chunks,
+        gene_labels: Optional[gplt_params.gene_labels] = None,
+        gene_labelset: Optional[gplt_params.gene_labelset] = None,
     ) -> gplt_params.figure:
         # gwss track
         fig1 = self.plot_g123_gwss_track(
@@ -472,6 +474,8 @@ def plot_g123_gwss(
             x_range=fig1.x_range,
             show=False,
             output_backend=output_backend,
+            gene_labels=gene_labels,
+            gene_labelset=gene_labelset,
         )
 
         # combine plots into a single figure

malariagen_data/anoph/genome_features.py

@@ -333,6 +333,8 @@ def plot_genes(
         x_range: Optional[gplt_params.x_range] = None,
         title: Optional[gplt_params.title] = None,
         output_backend: gplt_params.output_backend = gplt_params.output_backend_default,
+        gene_labels: Optional[gplt_params.gene_labels] = None,
+        gene_labelset: Optional[gplt_params.gene_labelset] = None,
     ) -> gplt_params.figure:
         debug = self._log.debug
 
@@ -408,6 +410,101 @@ def plot_genes(
             line_width=0,
         )
 
+        if gene_labels:
+            debug("determine new figure height and range to accommodate gene labels")
+
+            # Increase the figure height by a certain factor, to accommodate labels.
+            height_increase_factor = 1.3
+            fig.height = int(fig.height * height_increase_factor)
+
+            # Get the original y_range.
+            # Note: fig.y_range is not subscriptable.
+            orig_y_range = fig.y_range.start, fig.y_range.end
+
+            # Determine the midpoint of the original range, to rescale outward from there.
+            orig_mid_y_range = (orig_y_range[0] + orig_y_range[1]) / 2
+            orig_y_range_extent = orig_y_range[1] - orig_y_range[0]
+
+            # Determine the new start and end points of the extended range.
+            new_y_range_extent = orig_y_range_extent * height_increase_factor
+            new_y_range_extent_half = new_y_range_extent / 2
+            new_y_start = orig_mid_y_range - new_y_range_extent_half
+            new_y_end = orig_mid_y_range + new_y_range_extent_half
+
+            # Set the new y_range.
+            fig.y_range = bokeh.models.Range1d(new_y_start, new_y_end)
+
+            debug("determine midpoint of each gene rectangle")
+            data["mid_x"] = (data["start"] + data["end"]) / 2
+
+            debug("make gene labels and pointers")
+
+            # Put gene_labels into a new column, where the gene_id matches.
+            # Fill unmapped genes with empty strings, otherwise "NaN" would be displayed.
+            data["gene_label"] = data["ID"].map(gene_labels).fillna("")
+
+            # Put gene pointers (▲ or ▼) in a new column, depending on the strand.
+            # Except if the gene_label is null or an empty string, which should not be shown.
+            data["gene_pointer"] = data.apply(
+                lambda row: ("▼" if row["strand"] == "+" else "▲")
+                if row["gene_label"]
+                else "",
+                axis=1,
+            )
+
+            # Put the pointer above or below the gene rectangle, depending on + or - strand.
+            neg_strand_pointer_y = orig_mid_y_range - 1.1
+            pos_strand_pointer_y = orig_mid_y_range + 1.1
+            data["pointer_y"] = data["strand"].apply(
+                lambda strand: pos_strand_pointer_y
+                if strand == "+"
+                else neg_strand_pointer_y
+            )
+
+            # Put the label above or below the gene rectangle, depending on + or - strand.
+            neg_strand_label_y = orig_mid_y_range - 1.25
+            pos_strand_label_y = orig_mid_y_range + 1.3
+            data["label_y"] = data["strand"].apply(
+                lambda strand: pos_strand_label_y
+                if strand == "+"
+                else neg_strand_label_y
+            )
+
+            # Get the data as a ColumnDataSource.
+            data_as_cds = bokeh.models.ColumnDataSource(data)
+
+            # Create a LabelSet for the gene pointers.
+            gene_pointers_ls = bokeh.models.LabelSet(
+                source=data_as_cds,
+                x="mid_x",
+                y="pointer_y",
+                text="gene_pointer",
+                text_align="center",
+                text_baseline="middle",
+                text_font_size="9pt",
+                text_color="#444444",
+            )
+
+            # Create a LabelSet for the gene labels.
+            gene_labels_ls = bokeh.models.LabelSet(
+                source=data_as_cds,
+                x="mid_x",
+                y="label_y",
+                text="gene_label",
+                text_align="left",
+                text_baseline="middle",
+                text_font_size="9pt",
+                text_color="#444444",
+                x_offset=8,
+            )
+
+            # Add the markers and labels to the figure.
+            fig.add_layout(gene_pointers_ls)
+            fig.add_layout(gene_labels_ls)
+
+        if gene_labelset:
+            fig.add_layout(gene_labelset)
+
         debug("tidy up the plot")
         fig.ygrid.visible = False
         yticks = [0.4, 1.4]

malariagen_data/anoph/gplt_params.py

@@ -120,3 +120,13 @@
 contig_colors_default: Final[contig_colors] = list(bokeh.palettes.d3["Category20b"][5])
 
 colors: TypeAlias = Annotated[Sequence[str], "List of colors."]
+
+gene_labels: TypeAlias = Annotated[
+    Mapping[str, str],
+    "A mapping of gene identifiers to custom labels, which will appear in the plot.",
+]
+
+gene_labelset: TypeAlias = Annotated[
+    bokeh.models.LabelSet,
+    "A LabelSet to use in the plot.",
+]

malariagen_data/anoph/h12.py

@@ -473,6 +473,8 @@ def plot_h12_gwss(
         output_backend: gplt_params.output_backend = gplt_params.output_backend_default,
         chunks: base_params.chunks = base_params.native_chunks,
         inline_array: base_params.inline_array = base_params.inline_array_default,
+        gene_labels: Optional[gplt_params.gene_labels] = None,
+        gene_labelset: Optional[gplt_params.gene_labelset] = None,
     ) -> gplt_params.figure:
         # Plot GWSS track.
         fig1 = self.plot_h12_gwss_track(
@@ -508,6 +510,8 @@ def plot_h12_gwss(
             x_range=fig1.x_range,
             show=False,
             output_backend=output_backend,
+            gene_labels=gene_labels,
+            gene_labelset=gene_labelset,
         )
 
         # Combine plots into a single figure.
@@ -674,6 +678,8 @@ def plot_h12_gwss_multi_overlay(
         genes_height: gplt_params.genes_height = gplt_params.genes_height_default,
         show: gplt_params.show = True,
         output_backend: gplt_params.output_backend = gplt_params.output_backend_default,
+        gene_labels: Optional[gplt_params.gene_labels] = None,
+        gene_labelset: Optional[gplt_params.gene_labelset] = None,
     ) -> gplt_params.figure:
         # Plot GWSS track.
         fig1 = self.plot_h12_gwss_multi_overlay_track(
@@ -710,6 +716,8 @@ def plot_h12_gwss_multi_overlay(
             x_range=fig1.x_range,
             show=False,
             output_backend=output_backend,
+            gene_labels=gene_labels,
+            gene_labelset=gene_labelset,
         )
 
         # Combine plots into a single figure.
@@ -755,6 +763,8 @@ def plot_h12_gwss_multi_panel(
         genes_height: gplt_params.genes_height = gplt_params.genes_height_default,
         show: gplt_params.show = True,
         output_backend: gplt_params.output_backend = gplt_params.output_backend_default,
+        gene_labels: Optional[gplt_params.gene_labels] = None,
+        gene_labelset: Optional[gplt_params.gene_labelset] = None,
     ) -> gplt_params.figure:
         cohort_queries = self._setup_cohort_queries(
             cohorts=cohorts,
@@ -807,6 +817,8 @@ def plot_h12_gwss_multi_panel(
             x_range=figs[0].x_range,
             show=False,
             output_backend=output_backend,
+            gene_labels=gene_labels,
+            gene_labelset=gene_labelset,
         )
 
         figs.append(fig2)

malariagen_data/anoph/h1x.py

@@ -305,6 +305,8 @@ def plot_h1x_gwss(
         output_backend: gplt_params.output_backend = gplt_params.output_backend_default,
         chunks: base_params.chunks = base_params.native_chunks,
         inline_array: base_params.inline_array = base_params.inline_array_default,
+        gene_labels: Optional[gplt_params.gene_labels] = None,
+        gene_labelset: Optional[gplt_params.gene_labelset] = None,
     ) -> gplt_params.figure:
         # Plot GWSS track.
         fig1 = self.plot_h1x_gwss_track(
@@ -341,6 +343,8 @@ def plot_h1x_gwss(
             x_range=fig1.x_range,
             show=False,
             output_backend=output_backend,
+            gene_labels=gene_labels,
+            gene_labelset=gene_labelset,
         )
 
         # Combine plots into a single figure.

malariagen_data/anoph/plink_params.py

@@ -0,0 +1,18 @@
+"""Parameters for Plink converter functions."""
+
+from typing_extensions import Annotated, TypeAlias
+
+overwrite: TypeAlias = Annotated[
+    bool,
+    """
+    A boolean indicating whether a previously written file with the same name ought
+    to be overwritten. Default is False.
+    """,
+]
+
+output_dir: TypeAlias = Annotated[
+    str,
+    """
+    A string indicating the desired output file location.
+    """,
+]

malariagen_data/anoph/snp_data.py

@@ -1305,6 +1305,8 @@ def plot_snps(
         genes_height: gplt_params.genes_height = gplt_params.genes_height_default,
         max_snps: int = 200_000,
         show: gplt_params.show = True,
+        gene_labels: Optional[gplt_params.gene_labels] = None,
+        gene_labelset: Optional[gplt_params.gene_labelset] = None,
     ) -> gplt_params.figure:
         # Plot SNPs track.
         fig1 = self.plot_snps_track(
@@ -1330,6 +1332,8 @@ def plot_snps(
             height=genes_height,
             x_range=fig1.x_range,
             show=False,
+            gene_labels=gene_labels,
+            gene_labelset=gene_labelset,
         )
 
         # Layout tracks in a grid.