Skip to content

inverse RNA seq #65

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
Xiou113 wants to merge 11 commits into
base: master
Choose a base branch
from
Open

inverse RNA seq #65

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
03fe3b2
рабочий тест (rna+chip)
Xiou113 Mar 16, 2022
f962177
14.04 продолжаем пработу
Xiou113 Apr 14, 2022
7ee73a9
21.04 продолжаем работу
Xiou113 Apr 21, 2022
288aaa1
файнали инверсия
Xiou113 May 12, 2022
52a8c1e
inversion rna-seq
Xiou113 May 23, 2022
eedf7b4
inversion rna-seq
Xiou113 May 24, 2022
e3d3091
inversion rna-seq
Xiou113 May 24, 2022
a1366e8
add tests
Xiou113 May 24, 2022
926345f
add tests
Xiou113 May 24, 2022
3a784d4
add tests
Xiou113 May 24, 2022
f8f55e1
add tests
Xiou113 May 24, 2022
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
63 changes: 63 additions & 0 deletions source/RNASeqReader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,3 +156,66 @@ def duplicate_region_RNA(self, interval, tss_file):
lambda x: pd.Interval(x.start, x.end, closed="both"), axis="columns"), inplace=True)
self.chr_data[interval.chr].drop(['Strand', 'Gene stable ID'], axis=1, inplace=True)
assert len(self.chr_data[interval.chr]) - debug == old_length

# Modifies data according to the relationship between the "start" and "end" of genes, transcription direction
# (tss file) and the "start" and "end" of the duplication interval.
def inverse_region_RNA(self, interval, tss_file):
st, en = self.get_interval(interval, return_ids=True)
old_length = len(self.chr_data[interval.chr])
tss_file = pd.read_csv(tss_file, encoding='utf-8', sep='\t')
# Add a column with the direction of transcription by merging RNAseq data and tss file:
self.chr_data[interval.chr] = pd.merge(self.chr_data[interval.chr],
tss_file.loc[:, ['Strand', 'Gene stable ID']], how="left",
left_on="gene", right_on="Gene stable ID")

# Find genes affected by inversion. Create a list of their indices:
drop_indices = list(np.where(
(((self.chr_data[interval.chr].Strand == 1) & ((self.chr_data[interval.chr].start < interval.start) &
((self.chr_data[interval.chr].start + 2000 *
self.chr_data[
interval.chr].Strand) > interval.start)) |
((self.chr_data[interval.chr].start < interval.end) &
((self.chr_data[interval.chr].start + 2000 * self.chr_data[
interval.chr].Strand) > interval.end)))) |
(((self.chr_data[interval.chr].Strand == -1) & ((self.chr_data[interval.chr].end > interval.start) &
((self.chr_data[interval.chr].end + 2000 *
self.chr_data[
interval.chr].Strand) < interval.start)) |
((self.chr_data[interval.chr].end > interval.end) &
((self.chr_data[interval.chr].end + 2000 * self.chr_data[interval.chr].Strand) < interval.end)))))[
0])

debug = len(self.chr_data[interval.chr])
# new coordinates for inverted genes
starts = self.chr_data[interval.chr].iloc[st:en + 1,
self.chr_data[interval.chr].columns.get_loc("end")].apply(lambda x:
interval.start + (
interval.end - x) if x > (
interval.start + interval.len / 2) else interval.end - (
x - interval.start))
# print(starts, 'starts')
ends = self.chr_data[interval.chr].iloc[st:en + 1,
self.chr_data[interval.chr].columns.get_loc("start")].apply(lambda x:
interval.start + (
interval.end - x) if x > (
interval.start + interval.len / 2) else interval.end - (
x - interval.start))
# print(ends, 'ends')
# exit()
if len(starts) > 0:
self.chr_data[interval.chr].iloc[st:en + 1,
self.chr_data[interval.chr].columns.get_loc("start")] = starts
if len(ends) > 0:
self.chr_data[interval.chr].iloc[st:en + 1, self.chr_data[interval.chr].columns.get_loc("end")] = ends

self.chr_data[interval.chr].sort_values(by="start", inplace=True)

# Delete genes affected by inversion:
if len(drop_indices) > 0:
self.chr_data[interval.chr].drop(drop_indices, inplace=True)

# Set new indices according new "start" and "end":
self.chr_data[interval.chr].set_index(self.chr_data[interval.chr].apply(
lambda x: pd.Interval(x.start, x.end, closed="both"), axis="columns"), inplace=True)
self.chr_data[interval.chr].drop(['Strand', 'Gene stable ID'], axis=1, inplace=True)
assert old_length - debug == 0
Loading