Merge branch 'master' into 600-adding-option-for-multiple-transcripts-to-diplotype_clustering

Author: jonbrenas

.github/workflows/label_issues.yml

@@ -0,0 +1,18 @@
+name: Label issues
+on:
+  issues:
+    types:
+      - reopened
+      - opened
+jobs:
+  label_issues:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+    steps:
+      - run: gh issue edit "$NUMBER" --add-label "$LABELS"
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GH_REPO: ${{ github.repository }}
+          NUMBER: ${{ github.event.issue.number }}
+          LABELS: triage

malariagen_data/af1.py

@@ -123,6 +123,7 @@ def __init__(
             taxon_colors=TAXON_COLORS,
             virtual_contigs=None,
             gene_names=None,
+            inversion_tag_path=None,
         )
 
     def __repr__(self):

malariagen_data/ag3.py

@@ -2,18 +2,11 @@
 
 import dask
 import pandas as pd  # type: ignore
-from pandas import CategoricalDtype
-import numpy as np  # type: ignore
-import allel  # type: ignore
 import plotly.express as px  # type: ignore
 
 import malariagen_data
 from .anopheles import AnophelesDataResource
 
-from numpydoc_decorator import doc
-from .util import check_types, _karyotype_tags_n_alt
-from .anoph import base_params
-from typing import Optional, Literal, Annotated, TypeAlias
 
 # silence dask performance warnings
 dask.config.set(**{"array.slicing.split_native_chunks": False})  # type: ignore
@@ -35,6 +28,7 @@
 GENE_NAMES = {
     "AGAP004707": "Vgsc/para",
 }
+INVERSION_TAG_PATH = "karyotype_tag_snps.csv"
 
 
 def _setup_aim_palettes():
@@ -83,12 +77,6 @@ def _setup_aim_palettes():
 }
 
 
-inversion_param: TypeAlias = Annotated[
-    Literal["2La", "2Rb", "2Rc_gam", "2Rc_col", "2Rd", "2Rj"],
-    "Name of inversion to infer karyotype for.",
-]
-
-
 class Ag3(AnophelesDataResource):
     """Provides access to data from Ag3.x releases.
 
@@ -203,6 +191,7 @@ def __init__(
             taxon_colors=TAXON_COLORS,
             virtual_contigs=VIRTUAL_CONTIGS,
             gene_names=GENE_NAMES,
+            inversion_tag_path=INVERSION_TAG_PATH,
         )
 
         # set up caches
@@ -355,82 +344,3 @@ def _results_cache_add_analysis_params(self, params):
         super()._results_cache_add_analysis_params(params)
         # override parent class to add AIM analysis
         params["aim_analysis"] = self._aim_analysis
-
-    @check_types
-    @doc(
-        summary="Load tag SNPs for a given inversion in Ag.",
-    )
-    def load_inversion_tags(self, inversion: inversion_param) -> pd.DataFrame:
-        # needs to be modified depending on where we are hosting
-        import importlib.resources
-        from . import resources
-
-        with importlib.resources.path(resources, "karyotype_tag_snps.csv") as path:
-            df_tag_snps = pd.read_csv(path, sep=",")
-        return df_tag_snps.query(f"inversion == '{inversion}'").reset_index()
-
-    @check_types
-    @doc(
-        summary="Infer karyotype from tag SNPs for a given inversion in Ag.",
-    )
-    def karyotype(
-        self,
-        inversion: inversion_param,
-        sample_sets: Optional[base_params.sample_sets] = None,
-        sample_query: Optional[base_params.sample_query] = None,
-        sample_query_options: Optional[base_params.sample_query_options] = None,
-    ) -> pd.DataFrame:
-        # load tag snp data
-        df_tagsnps = self.load_inversion_tags(inversion=inversion)
-        inversion_pos = df_tagsnps["position"]
-        inversion_alts = df_tagsnps["alt_allele"]
-        contig = inversion[0:2]
-
-        # get snp calls for inversion region
-        start, end = np.min(inversion_pos), np.max(inversion_pos)
-        region = f"{contig}:{start}-{end}"
-
-        ds_snps = self.snp_calls(
-            region=region,
-            sample_sets=sample_sets,
-            sample_query=sample_query,
-            sample_query_options=sample_query_options,
-        )
-
-        with self._spinner("Inferring karyotype from tag SNPs"):
-            # access variables we need
-            geno = allel.GenotypeDaskArray(ds_snps["call_genotype"].data)
-            pos = allel.SortedIndex(ds_snps["variant_position"].values)
-            samples = ds_snps["sample_id"].values
-            alts = ds_snps["variant_allele"].values.astype(str)
-
-            # subset to position of inversion tags
-            mask = pos.locate_intersection(inversion_pos)[0]
-            alts = alts[mask]
-            geno = geno.compress(mask, axis=0).compute()
-
-            # infer karyotype
-            gn_alt = _karyotype_tags_n_alt(
-                gt=geno, alts=alts, inversion_alts=inversion_alts
-            )
-            is_called = geno.is_called()
-
-            # calculate mean genotype for each sample whilst masking missing calls
-            av_gts = np.mean(np.ma.MaskedArray(gn_alt, mask=~is_called), axis=0)
-            total_sites = np.sum(is_called, axis=0)
-
-            df = pd.DataFrame(
-                {
-                    "sample_id": samples,
-                    "inversion": inversion,
-                    f"karyotype_{inversion}_mean": av_gts,
-                    # round the genotypes then convert to int
-                    f"karyotype_{inversion}": av_gts.round().astype(int),
-                    "total_tag_snps": total_sites,
-                },
-            )
-            # Allow filling missing values with "<NA>" visible placeholder.
-            kt_dtype = CategoricalDtype(categories=[0, 1, 2, "<NA>"], ordered=True)
-            df[f"karyotype_{inversion}"] = df[f"karyotype_{inversion}"].astype(kt_dtype)
-
-        return df

malariagen_data/anoph/cnv_frq.py

@@ -10,24 +10,25 @@
 from numpydoc_decorator import doc  # type: ignore
 
 from . import base_params, cnv_params, frq_params
+from .frq_base import (
+    prep_samples_for_cohort_grouping,
+    build_cohorts_from_sample_grouping,
+    add_frequency_ci,
+)
 from ..util import (
     check_types,
     pandas_apply,
     Region,
     parse_multi_region,
     region_str,
     simple_xarray_concat,
-    prep_samples_for_cohort_grouping,
-    build_cohorts_from_sample_grouping,
-    add_frequency_ci,
 )
 from .cnv_data import AnophelesCnvData
+from .frq_base import AnophelesFrequencyAnalysis
 from .sample_metadata import locate_cohorts
 
 
-class AnophelesCnvFrequencyAnalysis(
-    AnophelesCnvData,
-):
+class AnophelesCnvFrequencyAnalysis(AnophelesCnvData, AnophelesFrequencyAnalysis):
     def __init__(
         self,
         **kwargs,

malariagen_data/anoph/distance.py

@@ -421,7 +421,7 @@ def plot_njt(
         height: plotly_params.fig_height = 600,
         show: plotly_params.show = True,
         renderer: plotly_params.renderer = None,
-        render_mode: plotly_params.render_mode = "auto",
+        render_mode: plotly_params.render_mode = "svg",
         title: plotly_params.title = True,
         title_font_size: plotly_params.title_font_size = 14,
         line_width: plotly_params.line_width = 0.5,