如何使用自定义调色板绘制树状图？

Question

我想使用自定义调色板 (

color_list

) 来根据

train_clusters["Cluster_Label"]

中的唯一值绘制相关热图。

注意：train_clusters["Sample"] 对应于

train_combined_df.index

。绘图数据位于

train_combined_df

。

问题：我在此示例中只有两种颜色

color_list

（即，

train_clusters["Cluster_Label"]

中的两个唯一值各有一种颜色），但输出却有四种颜色。

代码：

import plotly.figure_factory as ff
import plotly.graph_objects as go
from scipy.spatial.distance import pdist, squareform

color_list = ['#003f5c', '#ffa600']
# Initialize figure by creating upper dendrogram
fig = ff.create_dendrogram(train_combined_df.values, orientation='bottom')
fig.for_each_trace(lambda trace: trace.update(visible=False))

for i in range(len(fig['data'])):
    fig['data'][i]['yaxis'] = 'y2'

# Create Side Dendrogram
dendro_side = ff.create_dendrogram(train_combined_df.to_numpy(), orientation='right', colorscale=color_list)
for i in range(len(dendro_side['data'])):
    dendro_side['data'][i]['xaxis'] = 'x2'

# Add Side Dendrogram Data to Figure
for data in dendro_side['data']:
    fig.add_trace(data)

# Create Heatmap
dendro_leaves = dendro_side['layout']['yaxis']['ticktext']
dendro_leaves = list(map(int, dendro_leaves))
data_dist = pdist(train_combined_df.values)
heat_data = squareform(data_dist)
heat_data = heat_data[dendro_leaves,:]
heat_data = heat_data[:,dendro_leaves]

# Change to upper triangular form
for i in range(len(heat_data)):
    for j in range(len(heat_data)):
        if i > j:
            heat_data[i][j] = None

heatmap = [
    go.Heatmap(
        x = dendro_leaves,
        y = dendro_leaves,
        z = heat_data,
        colorscale = [
            [0.0, '#f1f1f1'],
            [0.1, '#ffa600'],
            [0.2, '#ff7c43'],
            [0.3, '#f95d6a'],
            [0.4, '#d45087'],
            [0.5, '#a05195'],
            [0.6, '#665191'],
            [0.7, '#2f4b7c'],
            [0.8, '#003f5c'],
            [1.0, '#0e0e0e']
        ]
    )
]

heatmap[0]['x'] = fig['layout']['xaxis']['tickvals']
heatmap[0]['y'] = dendro_side['layout']['yaxis']['tickvals']

# Add Heatmap Data to Figure
for data in heatmap:
    fig.add_trace(data)

# Edit Layout
fig.update_layout({'width':800, 'height':800,
                         'showlegend':False, 'hovermode': 'closest',
                         })
# Edit xaxis
fig.update_layout(xaxis={'domain': [.15, 1],
                                  'mirror': False,
                                  'showgrid': False,
                                  'showline': False,
                                  'zeroline': False,
                                  'ticks':""})
# Edit xaxis2
fig.update_layout(xaxis2={'domain': [0, .15],
                                   'mirror': False,
                                   'showgrid': False,
                                   'showline': False,
                                   'zeroline': False,
                                   'showticklabels': False,
                                   'ticks':""})

# Edit yaxis
fig.update_layout(yaxis={'domain': [0, 1],
                                  'mirror': False,
                                  'showgrid': False,
                                  'showline': False,
                                  'zeroline': False,
                                  'showticklabels': False,
                                  'ticks': ""
                        })
# # Edit yaxis2
fig.update_layout(yaxis2={'domain':[.825, .975],
                                   'mirror': False,
                                   'showgrid': False,
                                   'showline': False,
                                   'zeroline': False,
                                   'showticklabels': False,
                                   'ticks':""})

fig.update_layout(paper_bgcolor="rgba(0,0,0,0)",
                  plot_bgcolor="rgba(0,0,0,0)",
                  xaxis_tickfont = dict(color = 'rgba(0,0,0,0)'))

# Modify dendrogram colors based on cluster labels
for i, label in enumerate(train_clusters['Cluster_Label']):
    sample_index = train_clusters.loc[i, 'Sample']
    for j, dendro_data in enumerate(fig['data']):
        if dendro_data['x'][0] == sample_index:
            fig['data'][j]['line']['color'] = color_list[label]
            break

fig.show()

# Save plot as PDF
fig.write_image("VAENMFspectral_consensus_heatmap_KIRP.pdf")

电流输出：

输入：

train_clusters

pd.DataFrame({'Sample': {48: 'TCGA.A3.3367.01',
  51: 'TCGA.A3.3387.01',
  18: 'TCGA.B0.4710.01',
  0: 'TCGA.B0.4818.01',
  23: 'TCGA.B0.4821.01'},
 'Cluster_Label': {48: 1, 51: 1, 18: 1, 0: 2, 23: 2}})

train_combined_df

{'AASDH': {'TCGA.A3.3367.01': 0.5320696873033979,
  'TCGA.A3.3387.01': 0.4562592849092732,
  'TCGA.B0.4710.01': 0.4931201843239812,
  'TCGA.B0.4818.01': 0.4741494239287809,
  'TCGA.B0.4821.01': 0.4037527663931228},
 'AATK': {'TCGA.A3.3367.01': 0.409362763143499,
  'TCGA.A3.3387.01': 0.33823090552783364,
  'TCGA.B0.4710.01': 0.4781561801809045,
  'TCGA.B0.4818.01': 0.42083527521271474,
  'TCGA.B0.4821.01': 0.3520165708740812},
 'ABCD3': {'TCGA.A3.3367.01': 0.6804749459297832,
  'TCGA.A3.3387.01': 0.6502961267286307,
  'TCGA.B0.4710.01': 0.629857235378111,
  'TCGA.B0.4818.01': 0.6768727064918065,
  'TCGA.B0.4821.01': 0.5811571216803231},
 'ABHD10': {'TCGA.A3.3367.01': 0.6096662921739531,
  'TCGA.A3.3387.01': 0.6022759681938674,
  'TCGA.B0.4710.01': 0.6348323089026715,
  'TCGA.B0.4818.01': 0.6413746053093422,
  'TCGA.B0.4821.01': 0.5779754640688728},
 'ABHD14B': {'TCGA.A3.3367.01': 0.665834495540351,
  'TCGA.A3.3387.01': 0.6129179752341758,
  'TCGA.B0.4710.01': 0.6366922055392048,
  'TCGA.B0.4818.01': 0.6739641283003278,
  'TCGA.B0.4821.01': 0.6648293093129545}}

Answer 1

颜色的数量取决于树状图识别的簇的数量，您必须将

color_threshold

arg 设置为在树状图中仅显示 2 个簇，然后它将仅具有您在

color_list

中指定的颜色。