In [1]:

import hisepy
import os
import pandas as pd
import scanpy as sc

In [2]:

def read_adata_uuid(h5ad_uuid):
    h5ad_path = '/home/jupyter/cache/{u}'.format(u = h5ad_uuid)
    if not os.path.isdir(h5ad_path):
        hise_res = hisepy.reader.cache_files([h5ad_uuid])
    h5ad_filename = os.listdir(h5ad_path)[0]
    h5ad_file = '{p}/{f}'.format(p = h5ad_path, f = h5ad_filename)
    adata = sc.read_h5ad(h5ad_file)
    return adata

In [3]:

def read_parquet_uuid(pq_uuid):
    pq_path = '/home/jupyter/cache/{u}'.format(u = pq_uuid)
    if not os.path.isdir(pq_path):
        hise_res = hisepy.reader.cache_files([pq_uuid])
    pq_filename = os.listdir(pq_path)[0]
    pq_file = '{p}/{f}'.format(p = pq_path, f = pq_filename)
    df = pd.read_parquet(pq_file)
    return df

Read subclustering and barcode annotations from HISE¶

In [4]:

cell_class = 't-cells'

In [5]:

h5ad_uuid = 'd6ebc576-34ea-4394-a569-e35e16f20253'

In [6]:

adata = read_adata_uuid(h5ad_uuid)

In [7]:

anno_uuid = '75cb6602-0179-4128-9171-83c269a2b340'

In [8]:

anno = read_parquet_uuid(anno_uuid)

In [9]:

anno.head()

Out[9]:

	barcodes	AIFI_L1	AIFI_L2	AIFI_L3
0	cf71f47048b611ea8957bafe6d70929e	T cell	MAIT	CD8 MAIT
1	cf71f54248b611ea8957bafe6d70929e	T cell	Naive CD4 T cell	Core naive CD4 T cell
2	cf71fb7848b611ea8957bafe6d70929e	T cell	Memory CD4 T cell	CM CD4 T cell
3	cf7216a848b611ea8957bafe6d70929e	T cell	Memory CD4 T cell	GZMB- CD27+ EM CD4 T cell
4	cf72178448b611ea8957bafe6d70929e	T cell	Naive CD4 T cell	SOX4+ naive CD4 T cell

Add annotations to barcodes¶

In [10]:

obs = adata.obs
obs = obs.reset_index(drop = True)
obs = obs.merge(anno, on = 'barcodes', how = 'left')
obs = obs.set_index('barcodes', drop = False)

In [11]:

adata.obs = obs

Drop doublet/contamination labels¶

In [12]:

exclude_terms = [
    'Contamination', 'contamination',
    'Doublet', 'doublet',
    'Mito', 'mito'
]

In [13]:

all_types = adata.obs['AIFI_L3'].unique().tolist()

In [14]:

exclude_types = []
for cell_type in all_types:
    for term in exclude_terms:
        if term in cell_type:
            exclude_types.append(cell_type)

In [15]:

exclude_types

Out[15]:

['Contamination',
 'Naive CD8 T cell Platelet Doublets',
 'C5_C12_Contamination',
 'Proliferating Cells+Monocytes Doublets',
 'CD4 naive Platelet Doublets',
 'CD4 naive CD16 Monocytes Doublets']

In [16]:

keep_types = []
for cell_type in all_types:
    if not cell_type in exclude_types:
        keep_types.append(cell_type)

In [17]:

adata = adata[adata.obs['AIFI_L3'].isin(keep_types)]
adata.shape

Out[17]:

(1157700, 1487)

Plot L2 marker expression¶

In [18]:

l2_markers = [
    'CD3E', 'CD4', 'CD8A', 'TRAC', 'TRDC', 
    'LEF1', 'TCF7', 'CCR7', 'SELL', 'ITGB1', 
    'FAS', 'CD27', 'CD28', 'FOXP3', 'RTKN2', 
    'IKZF2', 'ZNF683', 'NKG7', 'KLRC2', 'KLRF1', 
    'KLRB1', 'KLRD1', 'GZMA', 'GZMK', 'GZMB', 
    'PRF1', 'GNLY', 'IFI44L', 'IRF7', 'MKI67', 
    'TRDV1', 'TRDV2', 'TRDV3', 'MME', 'SOX4'
]

Set L2 category order

In [19]:

category_order = [
    'Naive CD4 T cell',
    'Naive CD8 T cell',
    'DN T cell',
    'Memory CD4 T cell',
    'Treg',
    'Proliferating T cell',
    'MAIT',
    'CD8aa',
    'Memory CD8 T cell',
    'gdT'
]

adata.obs['AIFI_L2'] = (
    adata.obs['AIFI_L2']
    .cat
    .set_categories(category_order, ordered=True)
)

/tmp/ipykernel_4263/4156893413.py:14: ImplicitModificationWarning: Trying to modify attribute `.obs` of view, initializing view as actual.
  adata.obs['AIFI_L2'] = (

In [20]:

sc.pl.dotplot(
    adata,
    groupby = 'AIFI_L2',
    var_names = l2_markers,
    log = True
)

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_dotplot.py:168: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.
  obs_bool.groupby(level=0).sum() / obs_bool.groupby(level=0).count()
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_dotplot.py:178: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.
  dot_color_df = self.obs_tidy.groupby(level=0).mean()
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_dotplot.py:747: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap', 'norm' will be ignored
  dot_ax.scatter(x, y, **kwds)

Plot L3 marker expression¶

In [32]:

l3_markers = [
    'CD27', 'CD28', 'KLRF1', 'KLRB1', 'KLRD1', 
    'KLRC1', 'KLRC2', 'GZMA', 'GZMB', 'GZMK', 
    'GZMH', 'PRF1', 'CCL5', 'GNLY', 'GATA3', 
    'TBX21', 'EOMES', 'LEF1', 'TCF7', 'IKZF2',
    'SOX4', 'IFI44L'
]

Set L3 category order

In [29]:

category_order = [
    'Naive CD4 Treg',
    'Core naive CD8 T cell',
    'SOX4+ naive CD8 T cell',
    'Core naive CD4 T cell',
    'SOX4+ naive CD4 T cell',
    'CM CD4 T cell',
    'GZMB- CD27- EM CD4 T cell',
    'ISG+ memory CD4 T cell',
    'ISG+ memory CD8 T cell',
    'ISG+ naive CD4 T cell',
    'ISG+ naive CD8 T cell',
    'Proliferating T cell',
    'DN T cell',
    'KLRB1+ memory CD8 Treg',
    'GZMK+ memory CD4 Treg',
    'KLRB1+ memory CD4 Treg',
    'Memory CD4 Treg',
    'Memory CD8 Treg',
    'KLRF1- GZMB+ CD27- EM CD8 T cell',
    'KLRF1- GZMB+ CD27- memory CD4 T cell',
    'KLRF1- effector Vd1 gdT',
    'KLRF1+ GZMB+ CD27- EM CD8 T cell',
    'KLRF1+ effector Vd1 gdT',
    'GZMK+ CD27+ EM CD8 T cell',
    'GZMB+ Vd2 gdT',
    'GZMK+ Vd2 gdT',
    'CD8aa',
    'Naive Vd1 gdT',
    'SOX4+ Vd1 gdT',
    'ISG+ MAIT',
    'CD4 MAIT',
    'CD8 MAIT',
    'GZMB- CD27+ EM CD4 T cell',
    'CM CD8 T cell',
    'GZMK- CD27+ EM CD8 T cell'
]

In [30]:

adata.obs['AIFI_L3'] = (
    adata.obs['AIFI_L3']
    .cat
    .set_categories(category_order, ordered=True)
)

In [33]:

sc.pl.dotplot(
    adata,
    groupby = 'AIFI_L3',
    var_names = l3_markers,
    log = True
)

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_dotplot.py:168: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.
  obs_bool.groupby(level=0).sum() / obs_bool.groupby(level=0).count()
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_dotplot.py:178: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.
  dot_color_df = self.obs_tidy.groupby(level=0).mean()
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_dotplot.py:747: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap', 'norm' will be ignored
  dot_ax.scatter(x, y, **kwds)

In [24]:

import session_info
session_info.show()

Out[24]:

Click to view session information

-----
anndata             0.10.3
hisepy              0.3.0
pandas              2.1.4
scanpy              1.9.6
session_info        1.0.0
-----

Click to view modules imported as dependencies

PIL                         10.0.1
anyio                       NA
arrow                       1.3.0
asttokens                   NA
attr                        23.2.0
attrs                       23.2.0
babel                       2.14.0
beatrix_jupyterlab          NA
brotli                      NA
cachetools                  5.3.1
certifi                     2024.02.02
cffi                        1.16.0
charset_normalizer          3.3.2
cloudpickle                 2.2.1
colorama                    0.4.6
comm                        0.1.4
cryptography                41.0.7
cycler                      0.10.0
cython_runtime              NA
dateutil                    2.8.2
db_dtypes                   1.1.1
debugpy                     1.8.0
decorator                   5.1.1
defusedxml                  0.7.1
deprecated                  1.2.14
exceptiongroup              1.2.0
executing                   2.0.1
fastjsonschema              NA
fqdn                        NA
google                      NA
greenlet                    2.0.2
grpc                        1.58.0
grpc_status                 NA
h5py                        3.10.0
idna                        3.6
igraph                      0.10.8
importlib_metadata          NA
ipykernel                   6.28.0
ipython_genutils            0.2.0
ipywidgets                  8.1.1
isoduration                 NA
jedi                        0.19.1
jinja2                      3.1.2
joblib                      1.3.2
json5                       NA
jsonpointer                 2.4
jsonschema                  4.20.0
jsonschema_specifications   NA
jupyter_events              0.9.0
jupyter_server              2.12.1
jupyterlab_server           2.25.2
jwt                         2.8.0
kiwisolver                  1.4.5
leidenalg                   0.10.1
llvmlite                    0.41.0
lz4                         4.3.2
markupsafe                  2.1.3
matplotlib                  3.8.0
matplotlib_inline           0.1.6
mpl_toolkits                NA
mpmath                      1.3.0
natsort                     8.4.0
nbformat                    5.9.2
numba                       0.58.0
numpy                       1.24.0
opentelemetry               NA
overrides                   NA
packaging                   23.2
parso                       0.8.3
pexpect                     4.8.0
pickleshare                 0.7.5
pkg_resources               NA
platformdirs                4.1.0
plotly                      5.18.0
prettytable                 3.9.0
prometheus_client           NA
prompt_toolkit              3.0.42
proto                       NA
psutil                      NA
ptyprocess                  0.7.0
pure_eval                   0.2.2
pyarrow                     13.0.0
pydev_ipython               NA
pydevconsole                NA
pydevd                      2.9.5
pydevd_file_utils           NA
pydevd_plugins              NA
pydevd_tracing              NA
pygments                    2.17.2
pynvml                      NA
pyparsing                   3.1.1
pyreadr                     0.5.0
pythonjsonlogger            NA
pytz                        2023.3.post1
referencing                 NA
requests                    2.31.0
rfc3339_validator           0.1.4
rfc3986_validator           0.1.1
rpds                        NA
scipy                       1.11.4
send2trash                  NA
shapely                     1.8.5.post1
six                         1.16.0
sklearn                     1.3.2
sniffio                     1.3.0
socks                       1.7.1
sql                         NA
sqlalchemy                  2.0.21
sqlparse                    0.4.4
stack_data                  0.6.2
sympy                       1.12
termcolor                   NA
texttable                   1.7.0
threadpoolctl               3.2.0
torch                       2.1.2+cu121
torchgen                    NA
tornado                     6.3.3
tqdm                        4.66.1
traitlets                   5.9.0
typing_extensions           NA
uri_template                NA
urllib3                     1.26.18
wcwidth                     0.2.12
webcolors                   1.13
websocket                   1.7.0
wrapt                       1.15.0
xarray                      2023.12.0
yaml                        6.0.1
zipp                        NA
zmq                         25.1.2
zoneinfo                    NA

-----
IPython             8.19.0
jupyter_client      8.6.0
jupyter_core        5.6.1
jupyterlab          4.1.2
notebook            6.5.4
-----
Python 3.10.13 | packaged by conda-forge | (main, Dec 23 2023, 15:36:39) [GCC 12.3.0]
Linux-5.15.0-1052-gcp-x86_64-with-glibc2.31
-----
Session information updated at 2024-03-07 21:46

In [ ]: