def _read(filename, backed=False, sheet=None, ext=None, delimiter=None,
first_column_names=None, backup_url=None, cache=False,
suppress_cache_warning=False):
if ext is not None and ext not in avail_exts:
raise ValueError('Please provide one of the available extensions.\n'
+ avail_exts)
else:
ext = is_valid_filename(filename, return_ext=True)
is_present = check_datafile_present_and_download(filename,
backup_url=backup_url)
if not is_present: logg.msg('... did not find original file', filename)
# read hdf5 files
if ext in {'h5', 'h5ad'}:
if sheet is None:
return read_h5ad(filename, backed=backed)
else:
logg.msg('reading sheet', sheet, 'from file', filename, v=4)
return read_hdf(filename, sheet)
# read other file types
filename_cache = (settings.cachedir + filename.lstrip(
'./').replace('/', '-').replace('.' + ext, '.h5ad'))
if cache and os.path.exists(filename_cache):
logg.info('... reading from cache file', filename_cache)
adata = read_h5ad(filename_cache, backed=False)
else:
if not is_present:
raise FileNotFoundError('Did not find file {}.'.format(filename))
logg.msg('reading', filename, v=4)
if not cache and not suppress_cache_warning:
logg.hint('This might be very slow. Consider passing `cache=True`, '
'which enables much faster reading from a cache file.')
# do the actual reading
if ext == 'xlsx' or ext == 'xls':
if sheet is None:
raise ValueError(
'Provide `sheet` parameter when reading \'.xlsx\' files.')
else:
adata = read_excel(filename, sheet)
elif ext == 'mtx':
adata = read_mtx(filename)
elif ext == 'csv':
adata = read_csv(filename, first_column_names=first_column_names)
elif ext in {'txt', 'tab', 'data', 'tsv'}:
if ext == 'data':
logg.msg('... assuming \'.data\' means tab or white-space '
'separated text file', v=3)
logg.hint('change this by passing `ext` to sc.read')
adata = read_text(filename, delimiter, first_column_names)
elif ext == 'soft.gz':
adata = _read_softgz(filename)
else:
raise ValueError('Unkown extension {}.'.format(ext))
if cache:
logg.info('... writing an', settings.file_format_data,
'cache file to speedup reading next time')
if not os.path.exists(os.path.dirname(filename_cache)):
os.makedirs(os.path.dirname(filename_cache))
# write for faster reading when calling the next time
adata.write(filename_cache)
return adata
def setUp(self):
self.adata = ad.read_csv(input_file) # regular anndata
input_file_zarr = tmp_dir()
self.adata.write_zarr(
input_file_zarr,
chunks=(2, 5)) # write as zarr, so we can read using a RDD
self.adata_rdd = AnnDataRdd.from_zarr(self.sc, input_file_zarr)
def load_file(filepath):
if filepath == 'default' or filepath == 'datasets/user_uploaded/default':
filepath = join_root("../datasets/default.csv")
elif filepath == 'test':
filepath = join_root('../../datasets/server/testdataset.h5ad')
dataset = os.path.basename(filepath)
dataset = os.path.splitext(dataset)[0]
try:
if filepath[-4:] == 'h5ad':
adata = anndata.read_h5ad(filepath)
if filepath[-3:] == 'csv':
# TODO remove transpose
adata = anndata.read_csv(filepath).T
if filepath[-4:] == 'xlsx':
adata = anndata.read_excel(filepath)
if filepath[-3:] == 'mtx':
adata = anndata.read_mtx(filepath)
if filepath[-3:] == 'txt' or filepath[-3:] == 'tab' or filepath[
-4:] == 'data':
adata = anndata.read_text(filepath)
if filepath[-2:] == 'h5':
adata = anndata.read_hdf(filepath)
if filepath[-4:] == 'loom':
adata = anndata.read_loom(filepath)
except Exception as e:
print(str(e))
raise IncorrectFileFormat(
"File does not exist or file format is incorrect.")
adata.uns['dataset'] = dataset
return adata
def from_csv(cls, sc, csv_file, chunk_size):
"""
Read a CSV file as an anndata object (for the metadata) and with the
data matrix (X) as an RDD of numpy arrays.
*Note* the anndata object currently also stores the data matrix, which is
redundant and won't scale. This should be improved, possibly by changing anndata.
"""
adata = ad.read_csv(csv_file)
return cls._from_anndata(sc, adata, chunk_size,
read_chunk_csv(csv_file, chunk_size))
def load_mouseAllen_10X_data(data_dir, ind=None, celltype_gran=0, curate=False):
'''Load mouse Allen cortex data from 10X reads
@ind: individual sample -> 49 mice originally, 3 remained after filtering on male
@celltype_gran: major cell types (0) or sub-cell types (1)
@curate: whether to curate to the same name as mouse FC, mouse pFC, mouse protocol
'''
adata = anndata.read_csv(data_dir+os.sep+'AllenBrain/filtered_matrix.csv')
adata.var["gene_symboles"] = adata.var.index
adata.var_names_make_unique(join="-")
adata.obs['barcode'] = adata.obs.index
adata.obs_names_make_unique(join="-")
## load metadata
meta_df = pd.read_csv(data_dir+os.sep+'AllenBrain/filtered_metadata.csv', index_col=0)
meta_df['external_donor_name_label'] = meta_df['external_donor_name_label'].astype(str)
sample_info = pd.read_csv(data_dir+os.sep+'AllenBrain/sample_info.csv', index_col=0) ## use to filter gender
merged_meta_df = meta_df.merge(sample_info, how='left', left_on="external_donor_name_label", right_on="external_donor_name")
adata.obs = adata.obs.merge(merged_meta_df, left_index=True, right_on="sample_name", how='left') ## merge anndata with metadata
adata.obs.index = adata.obs["barcode"]
adata.obs.index.name = None
adata = adata[adata.obs['sex_label'] == 'M'] ## filter males out
if 0 == celltype_gran:
if curate:
adata_obs = adata.obs
adata_obs['cell.type'].replace(['L2 IT HATA', 'L2 IT RSP-ACA', 'L2/3 IT APr',
'L2/3 IT CTX', 'L2/3 IT PPP', 'L3 RSP-ACA', 'L4/5 IT CTX', 'L5 IT CTX',
'L5 NP CTX', 'L5 PT CTX', 'L5 PT RSP-ACA', 'L5/6 IT CTX', 'L6 CT CTX',
'L6 Car3', 'L6 IT CTX', 'L6 NP CT CTX', 'L6b CTX','NP PPP', 'NP SUB',
'CA2-IG-FC', 'L6b RHP', 'L6 IT RHP', 'L2/3 IT ENTl', 'L2 IT RSPv',
'L5 IT TPE-ENT', 'L2/3 IT TPE', 'L2 IT ProS'], 'Neuron', inplace=True) ## 27 types
adata_obs['cell.type'].replace(['Sncg', 'Pvalb', 'Pvalb Vipr2', 'Sst',
'Sst Chodl', 'Vip', 'Lamp5', 'Lamp5 Lhx6', 'Pax6', 'Ndnf HPF'], 'Interneuron', inplace=True) ## 10 types
adata_obs['cell.type'].replace(['Astro'], 'Astrocytes', inplace=True)
adata_obs['cell.type'].replace(['Endo'], 'Endothelial', inplace=True)
adata_obs['cell.type'].replace(['Micro'], 'Microglia', inplace=True)
adata_obs['cell.type'].replace(['OPC'], 'Polydendrocytes', inplace=True)
adata_obs['cell.type'].replace(['Oligo'], 'Oligodendrocytes', inplace=True)
adata_obs['cell.type'].replace(['Peri'], 'Pericytes', inplace=True)
adata.obs = adata_obs
## 'CR', 'PVM', 'SMC', 'VLMC' celltype are out of all other database, therefore not included
remained_idx = ~adata.obs['cell.type'].isin(['CR', 'PVM', 'SMC', 'VLMC'])
adata = adata[remained_idx]
if 1 == celltype_gran: ## for sub-celltypes
adata.obs.rename(columns={"cell.type": "major_celltype"}, inplace=True)
adata.obs.rename(columns={"cell_type_alias_label": "cell.type"}, inplace=True)
if ind is not None:
ind_cells = adata.obs[adata.obs["external_donor_name_label"].isin(ind.split('_'))].index
adata = adata[ind_cells]
return adata
def load_mouseAllen_SS_data(data_dir, ind=None, celltype_gran=0, curate=False):
'''Load mouse Allen cortex data from Smart-seq exon reads
@ind: individual sample -> 529 mice originally, 19 mice after filtering
@celltype_gran: major cell types (0) or sub-cell types (1)
@curate: whether to curate to the same name as mouse FC, mouse pFC, mouse protocol
'''
adata = anndata.read_csv(data_dir+os.sep+'AllenBrain/filtered_SS_matrix.csv')
adata.var["gene_symboles"] = adata.var.index
adata.var_names_make_unique(join="-")
adata.obs['barcode'] = adata.obs.index
adata.obs_names_make_unique(join="-")
## load metadata
meta_df = pd.read_csv(data_dir+os.sep+'AllenBrain/filtered_SS_metadata.csv', index_col=0)
adata.obs = adata.obs.merge(meta_df, left_on='barcode', right_on='barcode', how='left') ## merge anndata with metadata
adata.obs.index = adata.obs["barcode"]
adata.obs.index.name = None
adata.obs = adata.obs[['barcode', 'donor_label', 'region_label', 'joint_region_label', 'label', 'cluster_label', 'ss_cluster_label']]
if 0 == celltype_gran:
adata.obs.rename(columns={'label':'cell.type'}, inplace=True)
if curate:
adata_obs = adata.obs
adata_obs['cell.type'].replace(['L2/3 IT CTX', 'L2/3 IT RSP', 'L2/3 IT RSPv',
'L2 IT ENTl', 'L4/5 IT CTX', 'L4 RSP-ACA', 'L5/6 IT CTX', 'L5 IT CTX',
'L5 IT TPE-ENT', 'L5 NP CT CTX ', 'L5 NP CTX', 'L5 PT CTX', 'L6b CTX',
'L6 CT CTX', 'L6 IT CTX', 'CA1', 'CA1-ProS', 'CA2-IG-FC', 'CA3',
'CT SUB', 'Car3', 'DG', 'L2 IT ENTm', 'L2 IT PAR', 'L2/3 IT APr',
'L2/3 IT ENTl', 'L2/3 IT HATA', 'L2/3 IT PPP', 'L3 IT ENTl', 'L3 IT ENTm',
'L5 PPP', 'L6 IT ENTl', 'L6b/CT ENT', 'NP PPP', 'NP SUB', 'SUB', 'SUB-ProS'], 'Neuron', inplace=True)
adata_obs['cell.type'].replace(['Lamp5', 'Lamp5 Lhx6', 'Pax6', 'Pvalb',
'Sncg', 'Sst', 'Sst Chodl', 'Vip'], 'Interneuron', inplace=True)
adata_obs['cell.type'].replace(['Astro'], 'Astrocytes', inplace=True)
adata_obs['cell.type'].replace(['Endo'], 'Endothelial', inplace=True)
adata_obs['cell.type'].replace(['Micro-PVM'], 'Microglia', inplace=True)
adata_obs['cell.type'].replace(['Oligo'], 'Oligodendrocytes', inplace=True)
adata_obs['cell.type'].replace(['SMC-Peri'], 'Pericytes', inplace=True)
adata.obs = adata_obs
## 'CR', 'Meis2', 'Meis2 HPF', 'Ndnf HPF', 'VLMC' celltype are out of all other database, therefore not included
## The polydendrocytes (OPCs) are missing
remained_idx = ~adata.obs['cell.type'].isin(['CR', 'Meis2', 'Meis2 HPF', 'Ndnf HPF', 'VLMC'])
adata = adata[remained_idx]
if 1 == celltype_gran: ## for sub-celltypes
adata.obs.rename(columns={"cluster_label": "cell.type"}, inplace=True)
if ind is not None:
ind_cells = adata.obs[adata.obs["donor_label"].isin(ind.split('_'))].index
adata = adata[ind_cells]
return adata
def _load_csv(
path_to_file: str,
gene_by_cell: bool = False,
delimiter: str = ",",
first_column_names: bool = None,
):
logger.info("Loading dataset from {}".format(path_to_file))
adata = anndata.read_csv(path_to_file,
delimiter=delimiter,
first_column_names=first_column_names)
if gene_by_cell:
adata.X = adata.X.T
logger.info("Finished loading dataset")
return adata
def test_anndata():
try:
anndata
except NameError:
# anndata not installed
return
scdata = anndata.read_csv("../data/test_data.csv")
fast_magic_operator = magic.MAGIC(t='auto', a=None, k=10)
sc_magic = fast_magic_operator.fit_transform(scdata, genes="all_genes")
assert np.all(sc_magic.var_names == scdata.var_names)
assert np.all(sc_magic.obs_names == scdata.obs_names)
sc_magic = fast_magic_operator.fit_transform(scdata, genes=['VIM', 'ZEB1'])
assert np.all(sc_magic.var_names.values == np.array(['VIM', 'ZEB1']))
assert np.all(sc_magic.obs_names == scdata.obs_names)
def test_anndata():
try:
anndata
except NameError:
# anndata not installed
return
scdata = anndata.read_csv(data_path)
fast_magic_operator = magic.MAGIC(
t="auto", solver="approximate", decay=None, knn=10, verbose=False
)
sc_magic = fast_magic_operator.fit_transform(scdata, genes="all_genes")
assert np.all(sc_magic.var_names == scdata.var_names)
assert np.all(sc_magic.obs_names == scdata.obs_names)
sc_magic = fast_magic_operator.fit_transform(scdata, genes=["VIM", "ZEB1"])
assert np.all(sc_magic.var_names.values == np.array(["VIM", "ZEB1"]))
assert np.all(sc_magic.obs_names == scdata.obs_names)
def load_file(filepath):
t_flag = False
if filepath == 'default' or filepath == 'datasets/user_uploaded/default':
filepath = join_root("../datasets/default.csv")
t_flag = True
elif filepath == 'test':
filepath = join_root('../../datasets/server/testdataset.h5ad')
dataset = os.path.basename(filepath)
dataset = os.path.splitext(dataset)[0]
try:
if filepath[-4:] == 'h5ad':
adata = anndata.read_h5ad(filepath)
if filepath[-3:] == 'csv':
adata = anndata.read_csv(filepath)
if t_flag:
adata = adata.T
if filepath[-4:] == 'xlsx':
adata = anndata.read_excel(filepath)
if filepath[-3:] == 'mtx':
adata = anndata.read_mtx(filepath)
if filepath[-3:] == 'txt' or filepath[-3:] == 'tab' or filepath[-4:] == 'data':
adata = anndata.read_text(filepath)
if filepath[-2:] == 'h5':
adata = anndata.read_hdf(filepath)
if filepath[-4:] == 'loom':
adata = anndata.read_loom(filepath)
except Exception as e:
print(str(e))
raise IncorrectFileFormat(
"File does not exist or file format is incorrect.")
# Make sure cluster names are in proper format
if 'cluster_names' in adata.uns:
adata.uns['cluster_names'] = bidict(adata.uns['cluster_names'])
for key in list(adata.uns['cluster_names'].keys()):
adata.uns['cluster_names'][int(key)] = \
adata.uns['cluster_names'].pop(key, None)
adata.uns['dataset'] = dataset
return adata
def ReadData(feature, phen):
RawData = ad.read_csv(feature, delimiter='\t', first_column_names=True)
phen = pd.read_csv(phen, sep='\t', header=0, index_col=0)
phen.index = [str(i) for i in phen.index]
RawData.obs['phen'] = phen.loc[RawData.obs.index, :]
return RawData
def read_one_chunk(chunk_index):
adata = ad.read_csv(csv_file)
return read_adata_chunk(adata, chunk_size, chunk_index)
def _read(
filename: Path,
backed=None,
sheet=None,
ext=None,
delimiter=None,
first_column_names=None,
backup_url=None,
cache=False,
cache_compression=None,
suppress_cache_warning=False,
**kwargs,
):
if ext is not None and ext not in avail_exts:
raise ValueError('Please provide one of the available extensions.\n'
f'{avail_exts}')
else:
ext = is_valid_filename(filename, return_ext=True)
is_present = _check_datafile_present_and_download(
filename,
backup_url=backup_url,
)
if not is_present:
logg.debug(f'... did not find original file {filename}')
# read hdf5 files
if ext in {'h5', 'h5ad'}:
if sheet is None:
return read_h5ad(filename, backed=backed)
else:
logg.debug(f'reading sheet {sheet} from file {filename}')
return read_hdf(filename, sheet)
# read other file types
path_cache = settings.cachedir / _slugify(filename).replace(
'.' + ext, '.h5ad') # type: Path
if path_cache.suffix in {'.gz', '.bz2'}:
path_cache = path_cache.with_suffix('')
if cache and path_cache.is_file():
logg.info(f'... reading from cache file {path_cache}')
return read_h5ad(path_cache)
if not is_present:
raise FileNotFoundError(f'Did not find file {filename}.')
logg.debug(f'reading {filename}')
if not cache and not suppress_cache_warning:
logg.hint('This might be very slow. Consider passing `cache=True`, '
'which enables much faster reading from a cache file.')
# do the actual reading
if ext == 'xlsx' or ext == 'xls':
if sheet is None:
raise ValueError(
"Provide `sheet` parameter when reading '.xlsx' files.")
else:
adata = read_excel(filename, sheet)
elif ext in {'mtx', 'mtx.gz'}:
adata = read_mtx(filename)
elif ext == 'csv':
adata = read_csv(filename, first_column_names=first_column_names)
elif ext in {'txt', 'tab', 'data', 'tsv'}:
if ext == 'data':
logg.hint(
"... assuming '.data' means tab or white-space "
'separated text file', )
logg.hint('change this by passing `ext` to sc.read')
adata = read_text(filename, delimiter, first_column_names)
elif ext == 'soft.gz':
adata = _read_softgz(filename)
elif ext == 'loom':
adata = read_loom(filename=filename, **kwargs)
else:
raise ValueError(f'Unknown extension {ext}.')
if cache:
logg.info(f'... writing an {settings.file_format_data} '
'cache file to speedup reading next time')
if cache_compression is _empty:
cache_compression = settings.cache_compression
if not path_cache.parent.is_dir():
path_cache.parent.mkdir(parents=True)
# write for faster reading when calling the next time
adata.write(path_cache, compression=cache_compression)
return adata
def get_clusters_et_al(path,
size=5,
filter_ncounts=False,
filter_mito=False,
reload_file=False):
f = path
ext = os.path.splitext(f)[-1]
if not reload_file and (ext == '.h5ad'
or os.path.exists(path.replace(ext, '.h5ad'))):
results_file = path.replace(ext, '.h5ad')
adata = ad.read_h5ad(results_file)
elif ext == '.csv' or os.path.exists(path.replace(ext, '.csv')):
results_file = path.replace(ext, '.h5ad')
path = path.replace(ext, '.csv')
adata = ad.read_csv(path).transpose()
sc.pp.filter_genes(adata, min_cells=3)
sc.pp.filter_cells(adata, min_genes=200)
if filter_ncounts:
if isinstance(filter_ncounts, bool):
adata.obs['n_counts'] = adata.X.sum(axis=1)
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(8, 4))
ax1.hist(adata.obs.n_genes,
bins=100,
range=(0, np.percentile(adata.obs.n_genes, 99)))
ax1.set_xlabel('Number of counts')
ax1.set_ylabel('Number of cells')
ax2.hist(adata.obs.n_genes,
bins=100,
cumulative=True,
density=True,
range=(0, np.percentile(adata.obs.n_genes, 99)))
ax2.set_xlabel('Number of counts')
ax2.set_ylabel('Ratio of cells')
ax2.grid(True, axis='both')
fig.tight_layout()
plt.show()
th_ncount = input(
'Please enter the threshold value for the maximum number of counts: '
)
th_ncount = get_threshold(th_ncount, adata.obs.n_genes)
while not is_number(th_ncount):
th_ncount = input('Please enter a numeric value: ')
th_ncount = float(th_ncount)
else:
th_ncount = filter_ncounts
fig, ax = plt.subplots(1, 1)
filter_tab_ncounts = adata.obs.n_genes < th_ncount
ax.hist([
adata.obs.n_genes[filter_tab_ncounts],
adata.obs.n_genes[filter_tab_ncounts == False]
],
color=['k', 'r'],
label=['kept', 'removed'],
bins=100,
histtype='barstacked',
range=(0, np.percentile(adata.obs.n_genes, 99)))
ax.set_xlabel('Number of counts')
ax.set_ylabel('Number of cells')
ax.legend()
plt.show()
else:
filter_tab_ncounts = np.ones(adata.shape[0], dtype=bool)
if filter_mito:
if isinstance(filter_mito, bool):
mito_genes = (adata.var_names.str.startswith('mt-')
| adata.var_names.str.startswith('Mt-')
| adata.var_names.str.startswith('MT-'))
adata.obs['percent_mito'] = np.sum(
adata[:, mito_genes].X, axis=1) / np.sum(adata.X, axis=1)
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(8, 4))
ax1.hist(adata.obs.percent_mito,
bins=100,
range=(0, np.percentile(adata.obs.percent_mito, 99)))
ax1.set_xlabel('Percent of mito expression')
ax1.set_ylabel('Number of cells')
ax2.hist(adata.obs.percent_mito,
bins=100,
cumulative=True,
density=True,
range=(0, np.percentile(adata.obs.percent_mito, 99)))
ax2.set_xlabel('Percent of mito expression')
ax2.set_ylabel('Ratio of cells')
ax2.grid(True, axis='both')
fig.tight_layout()
plt.show()
th_mito = input(
'Please enter the threshold value for the maximum percent of mito expression: '
)
th_mito = get_threshold(th_mito, adata.obs.percent_mito)
while not is_number(th_mito):
th_mito = input('Please enter a numeric value: ')
th_mito = float(th_mito)
else:
th_mito = filter_mito
plt.close(fig)
filter_tab_mito = adata.obs.percent_mito < th_mito
fig, ax = plt.subplots(1, 1)
ax.hist([
adata.obs.percent_mito[filter_tab_mito],
adata.obs.percent_mito[filter_tab_mito == False]
],
color=['k', 'r'],
label=['kept', 'removed'],
bins=100,
histtype='barstacked',
range=(0, np.percentile(adata.obs.percent_mito, 99)))
ax.set_xlabel('Number of counts')
ax.set_ylabel('Number of cells')
ax.legend()
plt.show()
else:
filter_tab_mito = np.ones(adata.shape[0], dtype=bool)
final_filt = np.ones(adata.shape[0], dtype=bool)
if filter_ncounts:
final_filt[filter_tab_ncounts == False] = False
if filter_mito:
final_filt[filter_tab_mito == False] = False
both = np.sum((filter_tab_ncounts.astype(int) + filter_tab_mito) == 0)
diff = filter_tab_ncounts.astype(int) - filter_tab_mito
nc = np.sum(diff == -1)
mito = np.sum(diff == 1)
pie_values = [np.sum(final_filt), nc, both, mito]
fig, ax = plt.subplots()
ax.pie(pie_values,
labels=['Kept', 'ncounts', 'both', 'mito'],
shadow=False,
startangle=90)
ax.axis('equal')
adata = adata[final_filt, :]
sc.pp.normalize_total(adata, target_sum=1e4)
sc.pp.log1p(adata)
sc.pp.highly_variable_genes(adata,
min_mean=0.0125,
max_mean=3,
min_disp=0.5)
adata.raw = adata
adata = adata[:, adata.var.highly_variable]
sc.pp.scale(adata, max_value=10)
sc.tl.pca(adata, svd_solver='arpack')
sc.pp.neighbors(adata, n_neighbors=10, n_pcs=40)
sc.tl.umap(adata)
sc.tl.leiden(adata, .25)
adata.write(results_file)
else:
print('Can only work with .csv or .h5ad files (you gave {})'.format(
path))
return
# sc.pl.highly_variable_genes(adata.raw)
sc.pl.pca(adata, color=['Bmp2', 'Sox9', 'Sox17'], size=size)
sc.pl.pca_variance_ratio(adata, log=True)
fig = sc.pl.umap(adata,
color=['Bmp2', 'Sox9', 'Wnt3'],
size=size,
show=False,
return_fig=True)
fig.set_figwidth(20)
fig.set_figheight(6)
c_name = os.path.splitext(
os.path.split('data/' + results_file)[-1])[0] + '.0.25'
fig = sc.pl.umap(adata,
color=['leiden', 'Bmp2', 'Sox9'],
size=size,
show=False,
return_fig=True)
fig.set_figwidth(20)
fig.set_figheight(5)
fig.savefig('figures/Umap.{:s}.pdf'.format(c_name))
sc.tl.rank_genes_groups(adata, 'leiden', method='t-test')
sc.pl.rank_genes_groups(adata,
n_genes=25,
sharey=False,
show=True,
return_fig=True,
save='.t-test.{:s}.pdf'.format(c_name))
sc.tl.rank_genes_groups(adata, 'leiden', method='wilcoxon')
sc.pl.rank_genes_groups(adata,
n_genes=25,
sharey=False,
show=True,
return_fig=True,
save='.wilcoxon.{:s}.pdf'.format(c_name))
return adata
def load_FC_adata(data_dir,
devstage=None,
ind=None,
treatment=None,
celltype_gran=0,
curate=False):
'''Loading data from mouse frontal cortex along with metadata information
@devstage: P21 or Adult
@ind: individual sample prediction: P21Sample1-3, PFCSample1-12
@treatment: Saline or Cocaine
@celltype_gran: major cell types or sub-cell types
'''
## load data; set genes and cells
adata = anndata.read_csv(
data_dir + os.sep +
"MouseFC_GSE124952/GSE124952_expression_matrix.csv").T
adata.var["gene_symbols"] = adata.var.index
adata.var_names_make_unique(join="-")
adata.obs['barcode'] = adata.obs.index
adata.obs_names_make_unique(join="-")
## load metadata
meta_df = pd.read_csv(data_dir + os.sep +
"MouseFC_GSE124952/GSE124952_meta_data.csv",
index_col=0)
adata.obs = adata.obs.merge(meta_df, left_index=True, right_index=True)
if 0 == celltype_gran:
adata.obs.rename(columns={"CellType": "cell.type"},
inplace=True) ## change cell type names
if curate: ## if curation is needed for cross dataset prediction
adata_obs = adata.obs
#adata_obs["cell.type"].replace(['Oligo', 'NF Oligo'], 'Oligodendrocytes', inplace=True)
#adata_obs["cell.type"].replace(['OPC'], 'Polydendrocytes', inplace=True)
adata_obs["cell.type"].replace(['Oligo'],
'Oligodendrocytes',
inplace=True)
adata_obs["cell.type"].replace(['OPC', 'NF Oligo'],
'Polydendrocytes',
inplace=True)
adata_obs["cell.type"].replace(['Astro'],
'Astrocytes',
inplace=True)
adata_obs["cell.type"].replace(['Excitatory'],
'Neuron',
inplace=True)
adata_obs["cell.type"].replace(['Inhibitory'],
'Interneuron',
inplace=True)
adata_obs["cell.type"].replace(['Endo'],
'Endothelial',
inplace=True)
## Microglia stays as microglia
adata.obs = adata_obs
elif 1 == celltype_gran:
adata.obs.rename(columns={"L2_clusters": "cell.type"}, inplace=True)
## subset individuals
if ind is not None:
ind_cells = adata.obs[adata.obs['Sample'].isin(ind.split('_'))].index
adata = adata[ind_cells]
if devstage is not None:
dev_cells = adata.obs[adata.obs["DevStage"] == devstage].index
adata = adata[dev_cells]
if treatment is not None:
treat_cells = adata.obs[adata.obs["treatment"] == treatment].index
adata = adata[treat_cells]
return adata
def test_read_csv():
adata = ad.read_csv(HERE / 'adata.csv')
assert adata.obs_names.tolist() == ['r1', 'r2', 'r3']
assert adata.var_names.tolist() == ['c1', 'c2']
assert adata.X.tolist() == X_list
import sys
sys.path.append(".") # Adds higher directory to python modules path.
import anndata
import pycogaps
import scipy.io
import scipy.sparse
import numpy as np
from PyCoGAPS import *
# placeholder until we have anndata samples
# maybe also read files into an anndata object?
path = './data/GIST.csv'
prm = pycogaps.GapsParameters(path)
adata = anndata.read_csv(path)
adataX = adata.X
if scipy.sparse.issparse(adataX):
adataX = adataX.toarray()
# create Matrix object from anndata X
matrix = pycogaps.Matrix(adataX)
result = pycogaps.runCogapsFromMatrix(matrix, prm)
# convert Amean and Pmean results to numpy arrays
Amean = toNumpy(result.Amean)
Pmean = toNumpy(result.Pmean)
# anndata labels
def test_read_csv():
adata = ad.read_csv(HERE / "adata.csv")
assert adata.obs_names.tolist() == ["r1", "r2", "r3"]
assert adata.var_names.tolist() == ["c1", "c2"]
assert adata.X.tolist() == X_list
def _load_input_file(path):
if path[-5:] == '.h5ad':
adata = anndata.read_h5ad(path)
elif path[-4:] == '.csv':
adata = anndata.read_csv(path)
return adata
