move concat_subplots outside of dipclust.py to plotly_dendrogram.py

Author: sanjaynagi

malariagen_data/anoph/dipclust.py

@@ -13,7 +13,7 @@
     multiallelic_diplotype_mean_sqeuclidean,
     multiallelic_diplotype_mean_cityblock,
 )
-from ..plotly_dendrogram import plot_dendrogram
+from ..plotly_dendrogram import plot_dendrogram, concat_clustering_subplots
 from . import (
     base_params,
     plotly_params,
@@ -499,56 +499,6 @@ def _dipclust_snp_trace(
 
         return snp_trace, n_snps
 
-    def _dipclust_concat_subplots(
-        self,
-        figures,
-        width,
-        height,
-        row_heights,
-        region: base_params.regions,
-        n_snps: int,
-        sample_sets: Optional[base_params.sample_sets],
-        sample_query: Optional[base_params.sample_query],
-    ):
-        from plotly.subplots import make_subplots  # type: ignore
-
-        title_lines = []
-        if sample_sets is not None:
-            title_lines.append(f"sample sets: {sample_sets}")
-        if sample_query is not None:
-            title_lines.append(f"sample query: {sample_query}")
-        title_lines.append(f"genomic region: {region} ({n_snps} SNPs)")
-        title = "<br>".join(title_lines)
-
-        # make subplots
-        fig = make_subplots(
-            rows=len(figures),
-            cols=1,
-            shared_xaxes=True,
-            vertical_spacing=0.02,
-            row_heights=row_heights,
-        )
-
-        for i, figure in enumerate(figures):
-            if isinstance(figure, go.Figure):
-                # This is a figure, access the traces within it.
-                for trace in range(len(figure["data"])):
-                    fig.append_trace(figure["data"][trace], row=i + 1, col=1)
-            else:
-                # Assume this is a trace, add directly.
-                fig.append_trace(figure, row=i + 1, col=1)
-
-        fig.update_xaxes(visible=False)
-        fig.update_layout(
-            title=title,
-            width=width,
-            height=height,
-            hovermode="closest",
-            plot_bgcolor="white",
-        )
-
-        return fig
-
     def _insert_dipclust_snp_trace(
         self,
         *,
@@ -768,7 +718,7 @@ def plot_diplotype_clustering_advanced(
         # Calculate total height based on subplot heights, plus a fixed
         # additional component to allow for title, axes etc.
         height = sum(subplot_heights) + 50
-        fig = self._dipclust_concat_subplots(
+        fig = concat_clustering_subplots(
             figures=figures,
             width=width,
             height=height,

malariagen_data/anoph/hapclust.py

@@ -6,7 +6,7 @@
 from numpydoc_decorator import doc  # type: ignore
 
 from ..util import CacheMiss, check_types, pdist_abs_hamming, pandas_apply
-from ..plotly_dendrogram import plot_dendrogram
+from ..plotly_dendrogram import plot_dendrogram, concat_clustering_subplots
 from . import (
     base_params,
     plotly_params,
@@ -19,12 +19,9 @@
 from .snp_data import AnophelesSnpData
 from .snp_frq import AA_CHANGE_QUERY, _make_snp_label_effect
 from .hap_data import AnophelesHapData
-from .dipclust import AnophelesDipClustAnalysis
 
 
-class AnophelesHapClustAnalysis(
-    AnophelesHapData, AnophelesSnpData, AnophelesDipClustAnalysis
-):
+class AnophelesHapClustAnalysis(AnophelesHapData, AnophelesSnpData):
     def __init__(
         self,
         **kwargs,
@@ -343,6 +340,10 @@ def _haplotype_pairwise_distances(
         parameters=dict(
             snp_transcript="Plot amino acid variants for these transcripts.",
             snp_filter_min_maf="Filter amino acid variants with alternate allele frequency below this threshold.",
+            snp_query="Query to filter SNPs for amino acid heatmap. Default is to include all non-synonymous SNPs.",
+            cluster_threshold="Height at which to cut the dendrogram to form clusters. If not provided, no clusters assignment is not performed.",
+            min_cluster_size="Minimum number of haplotypes required in a cluster to be included when cutting the dendrogram. Default is 5.",
+            cluster_criterion="The cluster_criterion to use in forming flat clusters. One of 'inconsistent', 'distance', 'maxclust', 'maxclust_monochronic', 'monocrit'. See scipy.cluster.hierarchy.fcluster for details.",
         ),
     )
     def plot_haplotype_clustering_advanced(
@@ -360,7 +361,7 @@ def plot_haplotype_clustering_advanced(
         cohort_size: Optional[base_params.cohort_size] = None,
         distance_metric: hapclust_params.distance_metric = hapclust_params.distance_metric_default,
         cluster_threshold: Optional[float] = None,
-        min_cluster_size: Optional[int] = None,
+        min_cluster_size: Optional[int] = 5,
         cluster_criterion="distance",
         color: plotly_params.color = None,
         symbol: plotly_params.symbol = None,
@@ -487,7 +488,7 @@ def plot_haplotype_clustering_advanced(
         # Calculate total height based on subplot heights, plus a fixed
         # additional component to allow for title, axes etc.
         height = sum(subplot_heights) + 50
-        fig = self._dipclust_concat_subplots(
+        fig = concat_clustering_subplots(
             figures=figures,
             width=width,
             height=height,

malariagen_data/plotly_dendrogram.py

@@ -130,3 +130,54 @@ def plot_dendrogram(
     )
 
     return fig, leaf_data
+
+
+def concat_clustering_subplots(
+    figures,
+    width,
+    height,
+    row_heights,
+    region,
+    n_snps,
+    sample_sets,
+    sample_query,
+):
+    from plotly.subplots import make_subplots  # type: ignore
+    import plotly.graph_objects as go  # type: ignore
+
+    title_lines = []
+    if sample_sets is not None:
+        title_lines.append(f"sample sets: {sample_sets}")
+    if sample_query is not None:
+        title_lines.append(f"sample query: {sample_query}")
+    title_lines.append(f"genomic region: {region} ({n_snps} SNPs)")
+    title = "<br>".join(title_lines)
+
+    # make subplots
+    fig = make_subplots(
+        rows=len(figures),
+        cols=1,
+        shared_xaxes=True,
+        vertical_spacing=0.02,
+        row_heights=row_heights,
+    )
+
+    for i, figure in enumerate(figures):
+        if isinstance(figure, go.Figure):
+            # This is a figure, access the traces within it.
+            for trace in range(len(figure["data"])):
+                fig.append_trace(figure["data"][trace], row=i + 1, col=1)
+        else:
+            # Assume this is a trace, add directly.
+            fig.append_trace(figure, row=i + 1, col=1)
+
+    fig.update_xaxes(visible=False)
+    fig.update_layout(
+        title=title,
+        width=width,
+        height=height,
+        hovermode="closest",
+        plot_bgcolor="white",
+    )
+
+    return fig