Skip to content
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

Jump to bottom

Workaround for overflow error mentioned in issue #20 #23

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Workaround for overflow error mentioned in issue #20 #23

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
38d92ff
Update count.py, workaround for overflow
leetaiyi Nov 1, 2023
0d82239
Update count.py
leetaiyi Nov 1, 2023
5dc402e
Removed nb_cpu from count.py
leetaiyi Nov 1, 2023
2a3b0c9
Update count.py – clean chromosome names
leetaiyi Nov 3, 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
41 changes: 40 additions & 1 deletion lapa/count.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
from lapa.utils.io import bw_from_pyranges, \
_read_talon_read_annot_five_prime_count, \
_read_talon_read_annot_three_prime_count
import numpy as np


def _tqdm_counting(iterable):
Expand Down Expand Up @@ -130,14 +131,52 @@ def to_gr(self):
df_bam = pr.read_bam(self.bam_file, mapq=self.mapq, as_df=True)
df_bam['Start'] -= 1

df_bam['Chromosome'] = df_bam['Chromosome'].astype(str)
df_counts = df.groupby(["Chromosome", "Strand"]).size().reset_index(name="Count")
gr_counts = df_bam.groupby(["Chromosome", "Strand"]).size().reset_index(name="Count")
merged_counts = df_counts.merge(gr_counts, on=["Chromosome","Strand"], suffixes=("_df","_gr"))
merged_counts["log2Prod"] = np.log2(merged_counts["Count_df"]) + np.log2(merged_counts["Count_gr"])


filtered_combinations = merged_counts[merged_counts['log2Prod'] > 31]

for index, row in filtered_combinations.iterrows():
if row['log2Prod'] > 31:
num_division = 2**int(np.ceil(row['log2Prod']-31))
starts = list(df[(df['Chromosome'] == row['Chromosome']) & \
(df['Strand'] == row['Strand'])]['Start']) + \
list(df_bam[(df_bam['Chromosome'] == row['Chromosome']) & \
(df_bam['Strand'] == row['Strand'])]['Start'])
percentiles = [np.percentile(starts, i*(100/num_division)) for i in range(1,num_division)]
percentiles = [np.percentile(starts, 0)] + percentiles + [np.percentile(starts, 100)]
for i in range(num_division):
df_ind = (df['Chromosome'] == row['Chromosome']) & \
(df['Strand'] == row['Strand']) & \
(df['Start'] >= percentiles[i]) & \
(df['Start'] <= percentiles[i+1])
df.loc[df_ind,'Chromosome'] = df[df_ind]['Chromosome'].apply(lambda x: str(x) + "$" + str(i))
gr_ind = (df_bam['Chromosome'] == row['Chromosome']) & \
(df_bam['Strand'] == row['Strand']) & \
(df_bam['Start'] >= percentiles[i]) & \
(df_bam['Start'] <= df.loc[df_ind,'End'].max())
df_bam.loc[gr_ind,'Chromosome'] = df_bam[gr_ind]['Chromosome'].apply(lambda x: str(x) + "$" + str(i))

gr_bam = pr.PyRanges(df_bam)
gr_bam = gr_bam[gr_bam.Flag.isin({0, 16})]

return pr.PyRanges(df).count_overlaps(

out = pr.PyRanges(df).count_overlaps(
gr_bam,
overlap_col='coverage',
strandedness='same')

out2 = out.df
out2['Chromosome'] = out2['Chromosome'].astype(str)
out2['Chromosome'] = out2['Chromosome'].str.split('$').str[0]

return pr.PyRanges(out2)


def to_df(self):
return self.to_gr().df.astype({'Chromosome': 'str', 'Strand': 'str'})

Expand Down