Last active
March 4, 2021 04:14
-
-
Save geocarvalho/8ce0179d4a503b8639199f34d15675eb to your computer and use it in GitHub Desktop.
This file contains hidden or 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 pandas as pd | |
| file = "input.bed" | |
| df = pd.read_csv(file, sep="\t", names=["chr", "start", "end", "interval", "score", "strand"]) | |
| df[["gene", "extra"]] = df["interval"].str.split("_", 1, expand=True) | |
| df.drop(["interval", "score", "strand", "extra"], axis=1, inplace=True) | |
| new_df = df.groupby("gene").agg({"chr":"unique", "start":min, "end":max}) | |
| new_df.reset_index(inplace=True) | |
| new_df["chr"] = new_df["chr"].apply(lambda chr: chr[0]) | |
| new_df["start"] = new_df["start"].astype("str") | |
| new_df["end"] = new_df["end"].astype("str") | |
| new_df["list"] = new_df["chr"] + ":" + new_df["start"] + "-" + new_df["end"] | |
| new_df["list"] = new_df["list"].str.replace("chr", "") | |
| new_df["chr"] = new_df["chr"].str.replace("chr", "") | |
| new_df["chr"] = new_df["chr"].str.replace("X", "23") | |
| new_df["chr"] = new_df["chr"].str.replace("Y", "24") | |
| new_df[["chr", "start", "end"]] = new_df[["chr", "start", "end"]].astype(int) | |
| new_df.sort_values(by=["chr", "start", "end"], inplace=True) | |
| new_df["list"].to_csv("input.list", index=False, header=False) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment