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

v0.1.7 #91

Merged
merged 17 commits into from
Aug 6, 2021
Merged

v0.1.7 #91

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
2972266
Update _utilities.py
zktuong Aug 5, 2021
5ffc68a
Update _utilities.py
zktuong Aug 5, 2021
4e04e1a
Update _utilities.py
zktuong Aug 5, 2021
863303e
Update _utilities.py
zktuong Aug 5, 2021
1b4a8ef
Update _utilities.py
zktuong Aug 5, 2021
22256a7
Revert "Update _utilities.py"
zktuong Aug 5, 2021
e840547
Update _utilities.py
zktuong Aug 5, 2021
b5e44db
Update _utilities.py
zktuong Aug 5, 2021
045972a
Refactoring retrieve_metadata
zktuong Aug 5, 2021
e1b8d42
Update _network.py
zktuong Aug 5, 2021
8058b30
Update .gitignore
zktuong Aug 5, 2021
e4f0bbf
clean up tests
zktuong Aug 6, 2021
f2aa59b
Update test_travdv.py
zktuong Aug 6, 2021
29cbc51
Update _core.py
zktuong Aug 6, 2021
d62b52a
Update _core.py
zktuong Aug 6, 2021
3bc88bb
update notebooks
zktuong Aug 6, 2021
a3328ce
Merge branch 'master' into devel
zktuong Aug 6, 2021
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
7 changes: 7 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,3 +19,10 @@ dandelion/logging/version.py
reassigned_all/
reassigned_filtered/

data/pbmc3k_raw.h5ad
test_mouse/test_mouse_heavy_igblast_db-pass.tsv
test_mouse/test_mouse_heavy_igblast_db-pass_germ-pass.tsv
test_mouse/test_mouse_light_igblast_db-pass.tsv
test_mouse/test_mouse_light_igblast_db-pass_germ-pass.tsv
container/database/blast/human/human_BCR_C.fasta.nin
container/database/blast/mouse/mouse_BCR_C.fasta.nin
8 changes: 2 additions & 6 deletions dandelion/preprocessing/_preprocessing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
# @Author: kt16
# @Date: 2020-05-12 17:56:02
# @Last Modified by: Kelvin
# @Last Modified time: 2021-08-04 10:44:53
# @Last Modified time: 2021-08-05 23:28:58

import os
import pandas as pd
Expand Down Expand Up @@ -2002,7 +2002,6 @@ def filter_contigs(data: Union[Dandelion, pd.DataFrame, str],
filter_missing: bool = True,
productive_only: bool = True,
simple: bool = False,
locus: Optional[Literal['ig', 'tr-ab', 'tr-gd']] = None,
save: Optional[str] = None,
**kwargs) -> Tuple[Dandelion, AnnData]:
"""
Expand Down Expand Up @@ -2074,9 +2073,6 @@ def filter_contigs(data: Union[Dandelion, pd.DataFrame, str],
else:
dat = dat_.copy()

if locus is None:
locus = best_guess_locus(dat)

adata_ = adata.copy()

if 'cell_id' not in dat.columns:
Expand Down Expand Up @@ -2235,7 +2231,7 @@ def filter_contigs(data: Union[Dandelion, pd.DataFrame, str],
adata_.obs['contig_QC_pass'] = pd.Series(contig_check['contig_QC_pass'])

print('Initializing Dandelion object')
out_dat = Dandelion(data=_dat, locus=locus, **kwargs)
out_dat = Dandelion(data=_dat, **kwargs)
if data.__class__ == Dandelion:
out_dat.germline = data.germline

Expand Down
22 changes: 2 additions & 20 deletions dandelion/tools/_diversity.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
# @Author: Kelvin
# @Date: 2020-08-13 21:08:53
# @Last Modified by: Kelvin
# @Last Modified time: 2021-07-31 22:16:53
# @Last Modified time: 2021-08-06 00:04:38

import pandas as pd
import numpy as np
Expand Down Expand Up @@ -128,7 +128,6 @@ def clone_diversity(
expanded_only: bool = False,
use_contracted: bool = False,
key_added: Optional[str] = None,
locus: Optional[Literal['ig', 'tr-ab', 'tr-gd']] = None,
**kwargs,
) -> Union[pd.DataFrame, Dandelion, AnnData]:
"""
Expand Down Expand Up @@ -174,8 +173,6 @@ def clone_diversity(
This is to try and preserve the single-cell properties of the network.
key_added : str, list, Optional
column names for output.
locus : str
Mode of data. Only used for method = 'gini', Accepts one of 'ig', 'tr-ab' or 'tr-gd'. None defaults to 'ig'.
**kwargs
passed to dandelion.tl.generate_nework
Returns
Expand All @@ -185,12 +182,6 @@ def clone_diversity(
if downsample is not None:
resample = True

if locus is None:
if self.__class__ == Dandelion:
locus = best_guess_locus(self.data)
else:
locus = 'ig'

if method == 'gini':
if update_obs_meta:
diversity_gini(self,
Expand All @@ -206,7 +197,6 @@ def clone_diversity(
expanded_only=expanded_only,
use_contracted=use_contracted,
key_added=key_added,
locus=locus,
**kwargs)
else:
return (diversity_gini(self,
Expand All @@ -222,7 +212,6 @@ def clone_diversity(
expanded_only=expanded_only,
use_contracted=use_contracted,
key_added=key_added,
locus=locus,
**kwargs))
if method == 'chao1':
if update_obs_meta:
Expand Down Expand Up @@ -382,7 +371,6 @@ def diversity_gini(self: Union[Dandelion, AnnData],
expanded_only: bool = False,
use_contracted: bool = False,
key_added: Optional[str] = None,
locus: Optional[Literal['ig', 'tr-ab', 'tr-gd']] = None,
**kwargs) -> Union[pd.DataFrame, Dandelion]:
"""
Compute B cell clones Gini indices.
Expand Down Expand Up @@ -423,8 +411,6 @@ def diversity_gini(self: Union[Dandelion, AnnData],
This is to try and preserve the single-cell properties of the network.
key_added : str, list, Optional
column names for output.
locus : str
Mode of data. Accepts one of 'ig', 'tr-ab' or 'tr-gd'. None defaults to 'ig'.
**kwargs
passed to dandelion.tl.generate_nework
Returns
Expand All @@ -444,7 +430,6 @@ def gini_indices(self: Dandelion,
expanded_only: bool = False,
contracted: bool = False,
key_added: Optional[str] = None,
locus: Optional[Literal['ig', 'tr-ab', 'tr-gd']] = None,
**kwargs) -> pd.DataFrame:
if self.__class__ == AnnData:
raise TypeError('Only Dandelion class object accepted.')
Expand Down Expand Up @@ -541,7 +526,7 @@ def gini_indices(self: Dandelion,
# clone size distribution
_dat = metadata[metadata[groupby] == g]
_data = data[data['cell_id'].isin(list(_dat.index))]
ddl_dat = Dandelion(_data, metadata=_dat, locus=locus)
ddl_dat = Dandelion(_data, metadata=_dat)
if resample:
sizelist = []
if self.__class__ == Dandelion:
Expand All @@ -552,7 +537,6 @@ def gini_indices(self: Dandelion,
clone_key=clonekey,
downsample=minsize,
verbose=False,
locus=locus,
**kwargs)
if met == 'clone_network':
n_n, v_s, c_s = clone_networkstats(
Expand Down Expand Up @@ -685,7 +669,6 @@ def gini_indices(self: Dandelion,
generate_network(ddl_dat,
clone_key=clonekey,
verbose=False,
locus=locus,
**kwargs)
n_n, v_s, c_s = clone_networkstats(
ddl_dat,
Expand Down Expand Up @@ -794,7 +777,6 @@ def transfer_gini_indices(self: Dandelion, gini_results: pd.DataFrame,
expanded_only=expanded_only,
contracted=use_contracted,
key_added=key_added,
locus=locus,
**kwargs)

if diversity_key is None:
Expand Down
39 changes: 8 additions & 31 deletions dandelion/tools/_network.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
# @Author: Kelvin
# @Date: 2020-08-12 18:08:04
# @Last Modified by: Kelvin
# @Last Modified time: 2021-07-31 22:11:33
# @Last Modified time: 2021-08-06 00:24:57

import pandas as pd
import numpy as np
Expand All @@ -28,8 +28,6 @@ def generate_network(self: Union[Dandelion, pd.DataFrame, str],
min_size: int = 2,
downsample: Optional[int] = None,
verbose: bool = True,
locus: Optional[Literal['ig', 'tr-ab',
'tr-gd']] = None,
**kwargs) -> Dandelion:
"""
Generates a Levenshtein distance network based on full length VDJ sequence alignments for heavy and light chain(s).
Expand All @@ -49,8 +47,6 @@ def generate_network(self: Union[Dandelion, pd.DataFrame, str],
whether or not to downsample the number of cells prior to construction of network. If provided, cells will be randomly sampled to the integer provided. A new Dandelion class will be returned.
verbose : bool
whether or not to print the progress bars.
locus : str, Optional
Mode of data. Accepts one of 'ig', 'tr-ab' or 'tr-gd'. None defaults to 'ig'.
**kwargs
additional kwargs passed to options specified in `networkx.drawing.layout.spring_layout`.

Expand Down Expand Up @@ -81,9 +77,6 @@ def generate_network(self: Union[Dandelion, pd.DataFrame, str],
raise ValueError(
'Data does not contain clone information. Please run find_clones.')

if locus is None:
locus = best_guess_locus(dat)

dat = sanitize_data(dat, ignore=clonekey)

# calculate distance
Expand All @@ -108,21 +101,8 @@ def generate_network(self: Union[Dandelion, pd.DataFrame, str],

# So first, create a data frame to hold all possible (full) sequences split by
# heavy (only 1 possible for now) and light (multiple possible)
try:
dat_seq = retrieve_metadata(dat_,
query=key_,
split=True,
collapse=False,
locus=locus,
ignore=clonekey)
except:
dat_seq = retrieve_metadata(dat_,
query=key_,
split=True,
collapse=False,
locus=locus,
ignore=clonekey,
**kwargs)
querier = Query(dat_)
dat_seq = querier.retrieve(query = key_, retrieve_mode = 'split')
dat_seq.columns = [re.sub(key_ + '_', '', i) for i in dat_seq.columns]

# calculate a distance matrix for all vs all and this can be referenced later on to
Expand Down Expand Up @@ -158,9 +138,9 @@ def generate_network(self: Union[Dandelion, pd.DataFrame, str],
if self.__class__ == Dandelion:
out = self.copy()
if downsample is not None:
out = Dandelion(dat_, locus=locus)
out = Dandelion(dat_)
else: # re-initiate a Dandelion class object
out = Dandelion(dat_, locus=locus)
out = Dandelion(dat_)

tmp_totaldist = pd.DataFrame(total_dist,
index=dat_seq.index,
Expand Down Expand Up @@ -351,7 +331,7 @@ def generate_network(self: Union[Dandelion, pd.DataFrame, str],
deep=('Updated Dandelion object: \n'
' \'data\', contig-indexed clone table\n'
' \'metadata\', cell-indexed clone table\n'
' \'distance\', heavy and light chain distance matrices\n'
' \'distance\', distance matrices for VDJ- and VJ- chains\n'
' \'edges\', network edges\n'
' \'layout\', network layout\n'
' \'graph\', network'))
Expand All @@ -371,8 +351,7 @@ def generate_network(self: Union[Dandelion, pd.DataFrame, str],
edges=edge_list_final,
layout=(lyt, lyt_),
graph=(g, g_),
germline=germline_,
locus=locus)
germline=germline_)
out.threshold = threshold_
return (out)
else:
Expand All @@ -383,7 +362,6 @@ def generate_network(self: Union[Dandelion, pd.DataFrame, str],
layout=(lyt, lyt_),
graph=(g, g_),
germline=germline_,
locus=locus,
initialize=False)
self.threshold = threshold_
else:
Expand All @@ -393,8 +371,7 @@ def generate_network(self: Union[Dandelion, pd.DataFrame, str],
edges=edge_list_final,
layout=(lyt, lyt_),
graph=(g, g_),
clone_key=clone_key,
locus=locus)
clone_key=clone_key)
return (out)


Expand Down
Loading