Created
October 7, 2019 11:36
-
-
Save Ken-Kuroki/5184a21aa3eb60fb2041abac85b5d1e6 to your computer and use it in GitHub Desktop.
Generate iTOL "color strip" annotation file from pandas series
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import pandas as pd | |
from ete3 import PhyloTree | |
from itertools import cycle | |
def generate_colorstrip(labels: pd.Series, save_file: str, palette: list = None) -> None: | |
# labels must be a pd.Series whose index are leaf names and values are their labels | |
if palette is None: | |
palette = ["#4E79A7", "#A0CBE8", "#F28E2B", "#FFBE7D", "#59A14F", | |
"#8CD17D", "#B6992D", "#F1CE63", "#499894", "#86BDB6", | |
"#E15759", "#FF9D9A", "#79706E", "#BAB0AC", "#B37295", | |
"#FABFD2", "#B07AA1", "#D4A6C8", "#9D7660", "#D7B5A6"] | |
categories = labels.value_counts().index.tolist() | |
categories_colors = {category: color for category, color in zip(categories, cycle(palette))} | |
df = labels.rename("label").rename_axis("ids").reset_index() | |
df["color"] = df["label"].map(categories_colors) | |
output = """DATASET_COLORSTRIP\n | |
SEPARATOR COMMA\n | |
DATASET_LABEL,label_colorstrip\n | |
DATA\n"""+df.loc[:,["ids", "color", "label"]].to_csv(header=False, index=False) | |
with open(save_file, "w") as f: | |
f.write(output) | |
labels = pd.Series(["type A", "type B", "type B", "type C"], index=["sample 1", "sample 2", "sample 3", "sample 4"]) | |
generate_colorstrip(labels, "colorstrip.txt") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment