Skip to content

update to prev #24

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
afuentri wants to merge 2 commits into
base: main
Choose a base branch
from
Open

update to prev #24

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
79a716a
fixed possible bug on calc_splizvd.py line 257
afuentri Aug 18, 2023
2925e98
made changes more general
Aug 21, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions bin/calc_splizvd.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -231,17 +231,17 @@ def main():
split_dict = {True : ["ann"], False : ["unann"]}

# remove constitutive splicing
df["posA_group"] = df["juncStart"].astype(str) + df["gene"]
df["posB_group"] = df["juncEnd"].astype(str) + df["gene"]
df["posStart_group"] = df["juncStart"].astype(str) + df["gene"]
df["posEnd_group"] = df["juncEnd"].astype(str) + df["gene"]

df["rank_acc"] = df.groupby("posA_group")["juncEnd"].rank(method="dense")
df["rank_don"] = df.groupby("posB_group")["juncStart"].rank(method="dense")
df["rank_acc"] = df.groupby("posStart_group")["juncEnd"].rank(method="dense")
df["rank_don"] = df.groupby("posEnd_group")["juncStart"].rank(method="dense")
# remove "almost consistutive splicing"
if args.rank_quant > 0:
let_dict2 = {"A" : "acc", "B" : "don"}
let_dict2 = {"Start" : "acc", "End" : "don"}

# threshold ranks for each donor and acceptor
for let in ["A","B"]:
for let in ["Start","End"]:
df["bottom_{}_quant".format(let_dict2[let])] = df["pos{}_group".format(let)].map(df.groupby("pos{}_group".format(let))["rank_{}".format(let_dict2[let])].quantile(q=args.rank_quant))
df["top_{}_quant".format(let_dict2[let])] = df["pos{}_group".format(let)].map(df.groupby("pos{}_group".format(let))["rank_{}".format(let_dict2[let])].quantile(q=1 - args.rank_quant))
df["rank_{}".format(let_dict2[let])] = df[["bottom_{}_quant".format(let_dict2[let]),"rank_{}".format(let_dict2[let])]].max(axis=1)
Expand All @@ -250,8 +250,8 @@ def main():
# start ranks at 1 (in case 1 is removed by quantiling)
df["rank_{}".format(let_dict2[let])] = df["rank_{}".format(let_dict2[let])] - df["bottom_{}_quant".format(let_dict2[let])] + 1

df["max_rank_acc"] = df["posA_group"].map(df.groupby("posA_group")["rank_acc"].max())
df["max_rank_don"] = df["posB_group"].map(df.groupby("posB_group")["rank_don"].max())
df["max_rank_acc"] = df["posStart_group"].map(df.groupby("posStart_group")["rank_acc"].max())
df["max_rank_don"] = df["posEnd_group"].map(df.groupby("posEnd_group")["rank_don"].max())

# add domain columns
letters = ["Start", "End"]
Expand Down