Skip to content

Make dataframe of all genes #3

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
julianhess wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Make dataframe of all genes #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4894ab0
Make dataframe of all genes
julianhess May 4, 2022
8339cd9
Make progress indicators a bit nicer
julianhess May 4, 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
18 changes: 15 additions & 3 deletions qtl/annotation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,10 @@
import numpy as np
import pandas as pd
import os
import tempfile
import subprocess
import sys
import tempfile
import tqdm
import matplotlib.pyplot as plt
import matplotlib.patches as patches
import matplotlib.path as mpath
Expand Down Expand Up @@ -494,6 +496,7 @@ def __init__(self, varin, verbose=True):
else:
opener = open(gtfpath, 'r')

print("Loading genes from GTF ...", file = sys.stderr)
with opener as gtf:
for row in gtf:
if row[0] == '#':
Expand Down Expand Up @@ -585,9 +588,9 @@ def __init__(self, varin, verbose=True):
pass

if len(self.genes) % 1000 == 0 and verbose:
print(f'\rGenes parsed: {len(self.genes)}', end='')
print(f'\rGenes parsed: {len(self.genes)}', end='', file = sys.stderr)
if verbose:
print(f'\rGenes parsed: {len(self.genes)}')
print(f'\rGenes parsed: {len(self.genes)}', file = sys.stderr)

self.gene_ids = np.array(self.gene_ids)
self.gene_names = np.array(self.gene_names)
Expand All @@ -610,6 +613,15 @@ def __init__(self, varin, verbose=True):
self.chr_index = dict([(chrs[i], [sidx[i],eidx[i]]) for i in range(len(chrs))])
self.chr_genes = dict([(chrs[i], self.genes[sidx[i]:eidx[i]+1]) for i in range(len(chrs))])

# dataframe of all genes
columns = ["name", "chr", "start_pos", "end_pos", "tss", "transcripts", "strand", "type"]
self.gene_df = pd.DataFrame(index = self.gene_ids, columns = columns)
print("Making gene dataframe ...", file = sys.stderr)
for g in tqdm.tqdm(self.genes):
self.gene_df.loc[g.id, :] = pd.Series(
{ x : getattr(g, x) for x in columns }
)

# interval trees with gene starts/ends for each chr
self.gene_interval_trees = defaultdict()
for g in self.genes:
Expand Down
1 change: 1 addition & 0 deletions setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
'seaborn',
'pyBigWig',
'bx-python',
'tqdm',
],
classifiers = [
"Programming Language :: Python :: 3",
Expand Down