def kBET_single(matrix, batch, type_ = None, k0 = 10, knn=None, subsample=0.5, heuristic=True, verbose=False):
"""
params:
matrix: expression matrix (at the moment: a PCA matrix, so do.pca is set to FALSE
batch: series or list of batch assignemnts
subsample: fraction to be subsampled. No subsampling if `subsample=None`
returns:
kBET p-value
"""
anndata2ri.activate()
ro.r("library(kBET)")
if verbose:
print("importing expression matrix")
ro.globalenv['data_mtrx'] = matrix
ro.globalenv['batch'] = batch
#print(matrix.shape)
#print(len(batch))
if verbose:
print("kBET estimation")
#k0 = len(batch) if len(batch) < 50 else 'NULL'
ro.globalenv['knn_graph'] = knn
ro.globalenv['k0'] = k0
batch_estimate = ro.r(f"batch.estimate <- kBET(data_mtrx, batch, knn=knn_graph, k0=k0, plot=FALSE, do.pca=FALSE, heuristic=FALSE, adapt=FALSE, verbose={str(verbose).upper()})")
anndata2ri.deactivate()
try:
ro.r("batch.estimate$average.pval")[0]
except rpy2.rinterface_lib.embedded.RRuntimeError:
return np.nan
else:
return ro.r("batch.estimate$average.pval")[0]
def identify_empty_droplets(data, min_cells=3, **kw):
"""Detect empty droplets using DropletUtils
"""
import rpy2.robjects as robj
from rpy2.robjects import default_converter
from rpy2.robjects.packages import importr
import anndata2ri
from rpy2.robjects.conversion import localconverter
importr("DropletUtils")
adata = data.copy()
col_sum = adata.X.sum(0)
if hasattr(col_sum, 'A'):
col_sum = col_sum.A.squeeze()
keep = col_sum > min_cells
adata = adata[:,keep]
#adata.X = adata.X.tocsc()
anndata2ri.activate()
robj.globalenv["X"] = adata
res = robj.r('res <- emptyDrops(assay(X))')
anndata2ri.deactivate()
keep = res.loc[res.FDR<0.01,:]
data = data[keep.index,:]
data.obs['empty_FDR'] = keep['FDR']
return data
def saveSeurat(adata, path, batch, hvgs=None):
import re
ro.r('library(Seurat)')
ro.r('library(scater)')
anndata2ri.activate()
if sparse.issparse(adata.X):
if not adata.X.has_sorted_indices:
adata.X.sort_indices()
for key in adata.layers:
if sparse.issparse(adata.layers[key]):
if not adata.layers[key].has_sorted_indices:
adata.layers[key].sort_indices()
ro.globalenv['adata'] = adata
ro.r('sobj = as.Seurat(adata, counts="counts", data = "X")')
# Fix error if levels are 0 and 1
# ro.r(f'sobj$batch <- as.character(sobj${batch})')
ro.r(f'Idents(sobj) = "{batch}"')
ro.r(f'saveRDS(sobj, file="{path}")')
if hvgs is not None:
hvg_out = re.sub('\.RDS$', '', path) + '_hvg.RDS'
#hvg_out = path+'_hvg.rds'
ro.globalenv['hvgs'] = hvgs
ro.r('unlist(hvgs)')
ro.r(f'saveRDS(hvgs, file="{hvg_out}")')
anndata2ri.deactivate()
def test_py2rpy_activate(check, shape, dataset):
try:
anndata2ri.activate()
globalenv["adata"] = dataset()
finally:
anndata2ri.deactivate()
ex = globalenv["adata"]
assert tuple(baseenv["dim"](ex)[::-1]) == shape
check(ex)
def test_convert_activate(check, shape, dataset):
try:
anndata2ri.activate()
ad = dataset()
finally:
anndata2ri.deactivate()
assert isinstance(ad, AnnData)
assert ad.shape == shape
check(ad)
def save_adata(adata: AnnData, transpose: bool = False):
anndata2ri.activate()
if transpose:
r.saveRDS(adata.X.T, file="adata_t.rds")
else:
r.saveRDS(adata.X, file="adata.rds")
r.saveRDS(adata.obs_names.values, file="obs_names.rds")
r.saveRDS(adata.var_names.values, file="var_names.rds")
anndata2ri.deactivate()
def test_py2rpy2_numpy_pbmc68k():
"""This has some weird metadata"""
from scanpy.datasets import pbmc68k_reduced
try:
anndata2ri.activate()
with catch_warnings(record=True) as logs: # type: List[WarningMessage]
simplefilter("ignore", DeprecationWarning)
globalenv["adata"] = pbmc68k_reduced()
assert len(logs) == 0, [m.message for m in logs]
finally:
anndata2ri.deactivate()
def log_scran_pooling(adata):
"""Normalize data with scran via rpy2."""
import anndata2ri
import scIB.preprocessing
scprep.run.install_bioconductor("scran")
# Normalize via scran-pooling with own clustering at res=0.5
scIB.preprocessing.normalize(adata)
anndata2ri.deactivate()
# Make lightweight
del adata.raw
def save_stemnet_cluster_pop(size: int, col: int):
anndata2ri.activate()
with open(DATA_DIR / "benchmarking" / "runtime_analysis" / "gpcca.pickle", "rb") as fin:
data = pickle.load(fin)[size][str(col)]
# old name: main_states
cluster_annot = data["terminal_states"]
clusters = cluster_annot.cat.categories
df = pd.DataFrame(dict(zip(clusters, [cluster_annot.isin([c]) for c in clusters])))
r.saveRDS(df, file="cluster_pop.rds")
anndata2ri.deactivate()
def test_py2rpy2_numpy_pbmc68k():
"""This has some weird metadata"""
from scanpy.datasets import pbmc68k_reduced
try:
anndata2ri.activate()
with catch_warnings(record=True) as logs: # type: List[WarningMessage]
simplefilter("ignore", DeprecationWarning)
globalenv["adata"] = pbmc68k_reduced()
assert len(logs) == 1, [m.message for m in logs]
assert logs[0].category is NotConvertedWarning
assert "scipy.sparse.csr.csr_matrix" in str(logs[0].message)
finally:
anndata2ri.deactivate()
def readSeurat(path):
anndata2ri.activate()
ro.r('library(Seurat)')
ro.r('library(scater)')
ro.r(f'sobj <- readRDS("{path}")')
adata = ro.r('as.SingleCellExperiment(sobj)')
anndata2ri.deactivate()
#Test for 'X_EMB'
if 'X_EMB' in adata.obsm:
if 'X_emb' in adata.obsm:
print(
'overwriting existing `adata.obsm["X_emb"] in the adata object'
)
adata.obsm['X_emb'] = adata.obsm['X_EMB']
del adata.obsm['X_EMB']
return (adata)
def normalize(adata, min_mean=0.1, log=True, precluster=True, sparsify=True):
checkAdata(adata)
# Check for 0 count cells
if np.any(adata.X.sum(axis=1) == 0):
raise ValueError('found 0 count cells in the AnnData object.'
' Please filter these from your dataset.')
# Check for 0 count genes
if np.any(adata.X.sum(axis=0) == 0):
raise ValueError('found 0 count genes in the AnnData object.'
' Please filter these from your dataset.')
if sparsify:
# massive speedup when working with sparse matrix
if not sparse.issparse(
adata.X): # quick fix: HVG doesn't work on dense matrix
adata.X = sparse.csr_matrix(adata.X)
anndata2ri.activate()
ro.r('library("scran")')
# keep raw counts
adata.layers["counts"] = adata.X.copy()
is_sparse = False
X = adata.X.T
# convert to CSC if possible. See https://github.com/MarioniLab/scran/issues/70
if sparse.issparse(X):
is_sparse = True
if X.nnz > 2**31 - 1:
X = X.tocoo()
else:
X = X.tocsc()
ro.globalenv['data_mat'] = X
if precluster:
# Preliminary clustering for differentiated normalisation
adata_pp = adata.copy()
sc.pp.normalize_per_cell(adata_pp, counts_per_cell_after=1e6)
sc.pp.log1p(adata_pp)
sc.pp.pca(adata_pp, n_comps=15, svd_solver='arpack')
sc.pp.neighbors(adata_pp)
sc.tl.louvain(adata_pp, key_added='groups', resolution=0.5)
ro.globalenv['input_groups'] = adata_pp.obs['groups']
size_factors = ro.r(
'sizeFactors(computeSumFactors(SingleCellExperiment('
'list(counts=data_mat)), clusters = input_groups,'
f' min.mean = {min_mean}))')
del adata_pp
else:
size_factors = ro.r(
'sizeFactors(computeSumFactors(SingleCellExperiment('
f'list(counts=data_mat)), min.mean = {min_mean}))')
# modify adata
adata.obs['size_factors'] = size_factors
adata.X /= adata.obs['size_factors'].values[:, None]
if log:
print("Note! Performing log1p-transformation after normalization.")
sc.pp.log1p(adata)
else:
print("No log-transformation performed after normalization.")
if is_sparse:
# convert to sparse, bc operation always converts to dense
adata.X = sparse.csr_matrix(adata.X)
adata.raw = adata # Store the full data set in 'raw' as log-normalised data for statistical testing
# Free memory in R
ro.r('rm(list=ls())')
ro.r(
'lapply(names(sessionInfo()$loadedOnly), require, character.only = TRUE)'
)
ro.r(
'invisible(lapply(paste0("package:", names(sessionInfo()$otherPkgs)), '
'detach, character.only=TRUE, unload=TRUE))')
ro.r('gc()')
anndata2ri.deactivate()
