Funky heatmap¶
Integration benchmark of single-cell methods (scIB, human immune cells), after panel a of Luecken et al. 2022: the seven best and seven worst of 69 runs. Bars show the overall scores, circles the metric scores (size) and their ranks (color).
import polars as pl
from ggrust import *
from ggrust.bistro import funky_heatmap, position_arguments
DATA = "https://raw.githubusercontent.com/datavil/ggrust/main/docs/data/"
runs = pl.read_csv(DATA + "scib_immune.csv")
batch = {
"PCR_batch": "PCR batch",
"ASW_label/batch": "Batch ASW",
"iLISI": "Graph iLISI",
"graph_conn": "Graph connectivity",
"kBET": "kBET",
}
bio = {
"NMI_cluster/label": "NMI cluster/label",
"ARI_cluster/label": "ARI cluster/label",
"ASW_label": "Cell type ASW",
"isolated_label_F1": "Isolated label F1",
"isolated_label_silhouette": "Isolated label silhouette",
"cLISI": "Graph cLISI",
"cell_cycle_conservation": "Cell cycle conservation",
"hvg_overlap": "HVG conservation",
"trajectory": "Trajectory conservation",
}
methods = {
"scanorama": "Scanorama",
"fastmnn": "fastMNN",
"scanvi": "scANVI*",
"harmony": "Harmony",
"scgen": "scGen*",
"saucie": "SAUCIE",
}
icons = {"full": "genes", "embed": "embedding", "knn": "graph"}
def rank_color(column: str) -> pl.Expr:
"""Rank 1 (best) -> 1.0 (lightest color), last -> 0.0."""
rank = pl.col(column).rank("min", descending=True)
return 1 - (rank - 1) / (rank.max() - 1)
scores = (
runs.with_columns(
(pl.col(name) - pl.col(name).min()) / (pl.col(name).max() - pl.col(name).min())
for name in [*batch, *bio]
)
.with_columns(batch=pl.mean_horizontal(*batch), bio=pl.mean_horizontal(*bio))
.with_columns(overall=0.4 * pl.col("batch") + 0.6 * pl.col("bio"))
.with_columns(
rank_color(name).alias(f"{name}_rank") for name in ["overall", "batch", "bio", *batch, *bio]
)
.sort("overall", descending=True)
.with_columns(
id=pl.int_range(pl.len()).cast(pl.String),
name=pl.col("method").replace(methods),
icon=DATA + "scib_icons/" + pl.col("output").replace_strict(icons) + ".png",
features=pl.col("features").replace({"full_feature": "FULL", "hvg": "HVG"}),
scaling=pl.col("scaling").replace({"scaled": "+", "unscaled": "\u2013"}),
)
)
shown = pl.concat([scores.head(7), scores.tail(7)])
separator = pl.DataFrame({"id": ["hidden"]})
table = pl.concat([shown.head(7), separator, shown.tail(7)], how="diagonal_relaxed")
def score(column: str, name: str, geom: str, group: str) -> dict:
"""Describe a score column: its size from ``column``, its color from the rank."""
width = 2.5 if group == "overall" else 1.5 if geom == "bar" else 1
return {
"id": column,
"id_color": f"{column}_rank",
"name": name,
"geom": geom,
"group": group,
"palette": group,
"draw_outline": False,
"options": {"width": width},
}
def method(column: str, name: str, geom: str, width: float, **options: object) -> dict:
"""Describe a method column."""
return {
"id": column,
"name": name,
"geom": geom,
"group": "method",
"options": {"width": width, **options},
}
column_info = [
method("name", "Name", "text", 4.5, hjust=0),
method("icon", "Output", "image", 1.5),
{**method("features", "Features", "text", 2), "palette": "features", "id_color": "features"},
method("scaling", "Scaling", "text", 1.5),
score("overall", "Overall score", "bar", "overall"),
score("batch", "Overall score", "bar", "batch"),
*[score(column, name, "circle", "batch") for column, name in batch.items()],
score("bio", "Overall score", "bar", "bio"),
*[score(column, name, "circle", "bio") for column, name in bio.items()],
]
column_groups = [
{"header": "Method", "group": "method", "palette": "black"},
{"header": "Overall", "group": "overall", "palette": "overall"},
{"header": "Batch correction", "group": "batch", "palette": "batch"},
{"header": "Bio conservation", "group": "bio", "palette": "bio"},
]
def brewer(codes: str) -> list[str]:
"""Colors from dark (rank 69) to light (rank 1)."""
return ["#" + code for code in reversed(codes.split())]
palettes = {
"black": ["black", "black"],
"features": {"FULL": "#808080", "HVG": "#008000"},
"overall": brewer("FFFFD9 EDF8B1 C7E9B4 7FCDBB 41B6C4 1D91C0 225EA8 253494 081D58"),
"batch": brewer("F7FCFD E0ECF4 BFD3E6 9EBCDA 8C96C6 8C6BB1 88419D 810F7C 4D004B"),
"bio": brewer("FFF7F3 FDE0DD FCC5C0 FA9FB5 F768A1 DD3497 AE017E 7A0177 49006A"),
}
ranks = ["69", "", "", "", "1"]
legends = [
{
"title": "Output",
"geom": "image",
"labels": [DATA + f"scib_icons/{icon}.png" for icon in icons.values()],
"values": ["Genes", "Embedding", "Graph"],
},
{
"title": "Scaling",
"geom": "text",
"labels": ["+", "\u2013"],
"values": ["Scaled", "Unscaled"],
},
{"title": "Overall rank", "palette": "overall", "geom": "rect", "labels": ranks, "size": 1},
{
"title": "Batch correction rank",
"palette": "batch",
"geom": "rect",
"labels": ranks,
"size": 1,
},
{
"title": "Bio conservation rank",
"palette": "bio",
"geom": "rect",
"labels": ranks,
"size": 1,
},
{"title": "Score", "geom": "circle", "labels": ["0%", "", "", "", "100%"], "color": "white"},
]
heatmap = funky_heatmap(
table,
column_info=column_info,
column_groups=column_groups,
palettes=palettes,
legends=legends,
position_args=position_arguments(
col_annot_position="bottom",
col_annot_angle=90,
col_annot_offset=6,
col_group_radius=0.5,
legend_position="right",
expand_xmax=1,
),
scale_column=False,
add_abc=False,
)
# The hidden runs: a dark band on the separator row (row 8 is centred at y = -8 x 1.1).
# Its x range is the row background: 0.25 past the first and last column (0.1, 32.3).
hidden = len(scores) - len(shown)
band = pl.DataFrame(
{
"xmin": [-0.15],
"xmax": [32.55],
"ymin": [-9.35],
"ymax": [-8.25],
"x": [0.2],
"y": [-8.8],
"label": [f"{hidden} additional rows not shown"],
}
)
plot = (
heatmap
+ geom_rect(
aes(xmin="xmin", xmax="xmax", ymin="ymin", ymax="ymax"),
data=band,
fill="#555555",
color=None,
)
+ geom_text(aes(x="x", y="y", label="label"), data=band, color="white", hjust=0, size=7.6)
)
plot