def _write_scp_expression(unidata: UnimodalData, output_name: str, is_sparse: bool, precision: int = 2) -> None:
""" Only write the main matrix X
"""
try:
from pegasusio.cylib.io import write_mtx, write_dense
except ModuleNotFoundError:
print("No module named 'pegasusio.cylib.io'")
matrix = unidata.get_matrix("X")
if is_sparse:
barcode_file = f"{output_name}.scp.barcodes.tsv"
with open(barcode_file, "w") as fout:
fout.write("\n".join(unidata.obs_names) + "\n")
logger.info(f"Barcode file {barcode_file} is written.")
feature_file = f"{output_name}.scp.features.tsv"
gene_names = unidata.var_names.values
gene_ids = unidata.var["featureid"].values if "featureid" in unidata.var else (unidata.var["gene_ids"] if "gene_ids" in unidata.var else gene_names)
df = pd.DataFrame({"gene_names": gene_names, "gene_ids": gene_ids})[["gene_ids", "gene_names"]]
df.to_csv(feature_file, sep="\t", header=False, index=False)
logger.info(f"Feature file {feature_file} is written.")
mtx_file = f"{output_name}.scp.matrix.mtx"
write_mtx(mtx_file, matrix.data, matrix.indices, matrix.indptr, matrix.shape[0], matrix.shape[1], precision = precision) # matrix is cell x gene csr_matrix, will write as gene x cell
logger.info(f"Matrix file {mtx_file} is written.")
else:
expr_file = f"{output_name}.scp.expr.txt"
matrix = matrix.T.tocsr() # convert to gene x cell
write_dense(expr_file, unidata.obs_names.values, unidata.var_names.values, matrix.data, matrix.indices, matrix.indptr, matrix.shape[0], matrix.shape[1], precision = precision)
logger.info(f"Dense expression file {expr_file} is written.")
def deseq2(
pseudobulk: UnimodalData,
design: str,
contrast: Tuple[str, str, str],
de_key: str = "deseq2",
replaceOutliers: bool = True,
) -> None:
"""Perform Differential Expression (DE) Analysis using DESeq2 on pseduobulk data. This function calls R package DESeq2, requiring DESeq2 in R installed.
DE analysis will be performed on all pseudo-bulk matrices in pseudobulk.
Parameters
----------
pseudobulk: ``UnimodalData``
Pseudobulk data with rows for samples and columns for genes. If pseudobulk contains multiple matrices, DESeq2 will apply to all matrices.
design: ``str``
Design formula that will be passed to DESeq2
contrast: ``Tuple[str, str, str]``
A tuple of three elements passing to DESeq2: a factor in design formula, a level in the factor as numeritor of fold change, and a level as denominator of fold change.
de_key: ``str``, optional, default: ``"deseq2"``
Key name of DE analysis results stored. For cluster.X, stored key will be cluster.de_key
replaceOutliers: ``bool``, optional, default: ``True``
If execute DESeq2's replaceOutliers step. If set to ``False``, we will set minReplicatesForReplace=Inf in ``DESeq`` function and set cooksCutoff=False in ``results`` function.
Returns
-------
``None``
Update ``pseudobulk.varm``:
``pseudobulk.varm[de_key]``: DE analysis result for pseudo-bulk count matrix.
``pseudobulk.varm[cluster.de_key]``: DE results for cluster-specific pseudo-bulk count matrices.
Examples
--------
>>> pg.deseq2(pseudobulk, '~gender', ('gender', 'female', 'male'))
"""
try:
import rpy2.robjects as ro
from rpy2.robjects import pandas2ri, numpy2ri, Formula
from rpy2.robjects.packages import importr
from rpy2.robjects.conversion import localconverter
except ModuleNotFoundError as e:
import sys
logger.error(f"{e}\nNeed rpy2! Try 'pip install rpy2'.")
sys.exit(-1)
try:
deseq2 = importr('DESeq2')
except ModuleNotFoundError:
import sys
text = """Please install DESeq2 in order to run this function.\n
To install this package, start R and enter:\n
if (!require("BiocManager", quietly = TRUE))
install.packages("BiocManager")
BiocManager::install("DESeq2")"""
logger.error(text)
sys.exit(-1)
import math
to_dataframe = ro.r('function(x) data.frame(x)')
for mat_key in pseudobulk.list_keys():
with localconverter(ro.default_converter + numpy2ri.converter +
pandas2ri.converter):
dds = deseq2.DESeqDataSetFromMatrix(
countData=pseudobulk.get_matrix(mat_key).T,
colData=pseudobulk.obs,
design=Formula(design))
if replaceOutliers:
dds = deseq2.DESeq(dds)
res = deseq2.results(dds, contrast=ro.StrVector(contrast))
else:
dds = deseq2.DESeq(dds, minReplicatesForReplace=math.inf)
res = deseq2.results(dds,
contrast=ro.StrVector(contrast),
cooksCutoff=False)
with localconverter(ro.default_converter + pandas2ri.converter):
res_df = ro.conversion.rpy2py(to_dataframe(res))
res_df.fillna(
{
'log2FoldChange': 0.0,
'lfcSE': 0.0,
'stat': 0.0,
'pvalue': 1.0,
'padj': 1.0
},
inplace=True)
de_res_key = de_key if mat_key.find(
'.') < 0 else f"{mat_key.partition('.')[0]}.{de_key}"
pseudobulk.varm[de_res_key] = res_df.to_records(index=False)
def analyze_one_modality(unidata: UnimodalData, output_name: str, is_raw: bool,
append_data: UnimodalData, **kwargs) -> None:
print()
logger.info(f"Begin to analyze UnimodalData {unidata.get_uid()}.")
if is_raw:
# normailize counts and then transform to log space
tools.log_norm(unidata, kwargs["norm_count"])
# select highly variable features
standardize = False # if no select HVF, False
if kwargs["select_hvf"]:
if unidata.shape[1] <= kwargs["hvf_ngenes"]:
logger.warning(
f"Number of genes {unidata.shape[1]} is no greater than the target number of highly variable features {kwargs['hvf_ngenes']}. HVF selection is omitted."
)
else:
standardize = True
tools.highly_variable_features(
unidata,
kwargs["batch_attr"]
if kwargs["batch_correction"] else None,
flavor=kwargs["hvf_flavor"],
n_top=kwargs["hvf_ngenes"],
n_jobs=kwargs["n_jobs"],
)
if kwargs["hvf_flavor"] == "pegasus":
if kwargs["plot_hvf"] is not None:
from pegasus.plotting import hvfplot
fig = hvfplot(unidata, return_fig=True)
fig.savefig(f"{kwargs['plot_hvf']}.hvf.pdf")
n_pc = min(kwargs["pca_n"], unidata.shape[0], unidata.shape[1])
if n_pc < kwargs["pca_n"]:
logger.warning(
f"UnimodalData {unidata.get_uid()} has either dimension ({unidata.shape[0]}, {unidata.shape[1]}) less than the specified number of PCs {kwargs['pca_n']}. Reduce the number of PCs to {n_pc}."
)
# Run PCA irrespect of which batch correction method would apply
tools.pca(
unidata,
n_components=n_pc,
features="highly_variable_features",
standardize=standardize,
n_jobs=kwargs["n_jobs"],
random_state=kwargs["random_state"],
)
dim_key = "pca"
if kwargs["nmf"] or (kwargs["batch_correction"]
and kwargs["correction_method"] == "inmf"):
n_nmf = min(kwargs["nmf_n"], unidata.shape[0], unidata.shape[1])
if n_nmf < kwargs["nmf_n"]:
logger.warning(
f"UnimodalData {unidata.get_uid()} has either dimension ({unidata.shape[0]}, {unidata.shape[1]}) less than the specified number of NMF components {kwargs['nmf_n']}. Reduce the number of NMF components to {n_nmf}."
)
if kwargs["nmf"]:
if kwargs["batch_correction"] and kwargs[
"correction_method"] == "inmf":
logger.warning(
"NMF is skipped because integrative NMF is run instead.")
else:
tools.nmf(
unidata,
n_components=n_nmf,
features="highly_variable_features",
n_jobs=kwargs["n_jobs"],
random_state=kwargs["random_state"],
)
if kwargs["batch_correction"]:
if kwargs["correction_method"] == "harmony":
dim_key = tools.run_harmony(
unidata,
batch=kwargs["batch_attr"],
rep="pca",
n_jobs=kwargs["n_jobs"],
n_clusters=kwargs["harmony_nclusters"],
random_state=kwargs["random_state"])
elif kwargs["correction_method"] == "inmf":
dim_key = tools.integrative_nmf(
unidata,
batch=kwargs["batch_attr"],
n_components=n_nmf,
features="highly_variable_features",
lam=kwargs["inmf_lambda"],
n_jobs=kwargs["n_jobs"],
random_state=kwargs["random_state"])
elif kwargs["correction_method"] == "scanorama":
dim_key = tools.run_scanorama(
unidata,
batch=kwargs["batch_attr"],
n_components=n_pc,
features="highly_variable_features",
standardize=standardize,
random_state=kwargs["random_state"])
else:
raise ValueError(
f"Unknown batch correction method {kwargs['correction_method']}!"
)
# Find K neighbors
tools.neighbors(
unidata,
K=kwargs["K"],
rep=dim_key,
n_jobs=kwargs["n_jobs"],
random_state=kwargs["random_state"],
full_speed=kwargs["full_speed"],
)
if kwargs["calc_sigscore"] is not None:
sig_files = kwargs["calc_sigscore"].split(",")
for sig_file in sig_files:
tools.calc_signature_score(unidata, sig_file)
# calculate diffmap
if (kwargs["fle"] or kwargs["net_fle"]):
if not kwargs["diffmap"]:
print("Turn on --diffmap option!")
kwargs["diffmap"] = True
if kwargs["diffmap"]:
tools.diffmap(
unidata,
n_components=kwargs["diffmap_ndc"],
rep=dim_key,
solver=kwargs["diffmap_solver"],
max_t=kwargs["diffmap_maxt"],
n_jobs=kwargs["n_jobs"],
random_state=kwargs["random_state"],
)
# calculate kBET
if ("kBET" in kwargs) and kwargs["kBET"]:
stat_mean, pvalue_mean, accept_rate = tools.calc_kBET(
unidata,
kwargs["kBET_batch"],
rep=dim_key,
K=kwargs["kBET_K"],
alpha=kwargs["kBET_alpha"],
n_jobs=kwargs["n_jobs"],
random_state=kwargs["random_state"])
print(
"kBET stat_mean = {:.2f}, pvalue_mean = {:.4f}, accept_rate = {:.2%}."
.format(stat_mean, pvalue_mean, accept_rate))
# clustering
if kwargs["spectral_louvain"]:
tools.cluster(
unidata,
algo="spectral_louvain",
rep=dim_key,
resolution=kwargs["spectral_louvain_resolution"],
rep_kmeans=kwargs["spectral_louvain_basis"],
n_clusters=kwargs["spectral_louvain_nclusters"],
n_clusters2=kwargs["spectral_louvain_nclusters2"],
n_init=kwargs["spectral_louvain_ninit"],
n_jobs=kwargs["n_jobs"],
random_state=kwargs["random_state"],
class_label="spectral_louvain_labels",
)
if kwargs["spectral_leiden"]:
tools.cluster(
unidata,
algo="spectral_leiden",
rep=dim_key,
resolution=kwargs["spectral_leiden_resolution"],
rep_kmeans=kwargs["spectral_leiden_basis"],
n_clusters=kwargs["spectral_leiden_nclusters"],
n_clusters2=kwargs["spectral_leiden_nclusters2"],
n_init=kwargs["spectral_leiden_ninit"],
n_jobs=kwargs["n_jobs"],
random_state=kwargs["random_state"],
class_label="spectral_leiden_labels",
)
if kwargs["louvain"]:
tools.cluster(
unidata,
algo="louvain",
rep=dim_key,
resolution=kwargs["louvain_resolution"],
random_state=kwargs["random_state"],
class_label=kwargs["louvain_class_label"],
)
if kwargs["leiden"]:
tools.cluster(
unidata,
algo="leiden",
rep=dim_key,
resolution=kwargs["leiden_resolution"],
n_iter=kwargs["leiden_niter"],
random_state=kwargs["random_state"],
class_label=kwargs["leiden_class_label"],
)
# visualization
if kwargs["net_umap"]:
tools.net_umap(
unidata,
rep=dim_key,
n_jobs=kwargs["n_jobs"],
n_neighbors=kwargs["umap_K"],
min_dist=kwargs["umap_min_dist"],
spread=kwargs["umap_spread"],
random_state=kwargs["random_state"],
select_frac=kwargs["net_ds_frac"],
select_K=kwargs["net_ds_K"],
select_alpha=kwargs["net_ds_alpha"],
full_speed=kwargs["full_speed"],
net_alpha=kwargs["net_l2"],
polish_learning_rate=kwargs["net_umap_polish_learing_rate"],
polish_n_epochs=kwargs["net_umap_polish_nepochs"],
out_basis=kwargs["net_umap_basis"],
)
if kwargs["net_fle"]:
tools.net_fle(
unidata,
output_name,
n_jobs=kwargs["n_jobs"],
K=kwargs["fle_K"],
full_speed=kwargs["full_speed"],
target_change_per_node=kwargs["fle_target_change_per_node"],
target_steps=kwargs["fle_target_steps"],
is3d=False,
memory=kwargs["fle_memory"],
random_state=kwargs["random_state"],
select_frac=kwargs["net_ds_frac"],
select_K=kwargs["net_ds_K"],
select_alpha=kwargs["net_ds_alpha"],
net_alpha=kwargs["net_l2"],
polish_target_steps=kwargs["net_fle_polish_target_steps"],
out_basis=kwargs["net_fle_basis"],
)
if kwargs["tsne"]:
tools.tsne(
unidata,
rep=dim_key,
n_jobs=kwargs["n_jobs"],
perplexity=kwargs["tsne_perplexity"],
random_state=kwargs["random_state"],
initialization=kwargs["tsne_init"],
)
if kwargs["umap"]:
tools.umap(
unidata,
rep=dim_key,
n_neighbors=kwargs["umap_K"],
min_dist=kwargs["umap_min_dist"],
spread=kwargs["umap_spread"],
n_jobs=kwargs["n_jobs"],
full_speed=kwargs["full_speed"],
random_state=kwargs["random_state"],
)
if kwargs["fle"]:
tools.fle(
unidata,
output_name,
n_jobs=kwargs["n_jobs"],
K=kwargs["fle_K"],
full_speed=kwargs["full_speed"],
target_change_per_node=kwargs["fle_target_change_per_node"],
target_steps=kwargs["fle_target_steps"],
is3d=False,
memory=kwargs["fle_memory"],
random_state=kwargs["random_state"],
)
if kwargs["infer_doublets"]:
channel_attr = "Channel"
if (channel_attr not in unidata.obs) or (
unidata.obs["Channel"].cat.categories.size == 1):
channel_attr = None
clust_attr = kwargs["dbl_cluster_attr"]
if (clust_attr is None) or (clust_attr not in unidata.obs):
clust_attr = None
for value in [
"leiden_labels", "louvain_labels",
"spectral_leiden_labels", "spectral_louvain_labels"
]:
if value in unidata.obs:
clust_attr = value
break
if channel_attr is not None:
logger.info(f"For doublet inference, channel_attr={channel_attr}.")
if clust_attr is not None:
logger.info(f"For doublet inference, clust_attr={clust_attr}.")
tools.infer_doublets(
unidata,
channel_attr=channel_attr,
clust_attr=clust_attr,
expected_doublet_rate=kwargs["expected_doublet_rate"],
n_jobs=kwargs["n_jobs"],
random_state=kwargs["random_state"],
plot_hist=output_name)
dbl_clusts = None
if clust_attr is not None:
clusts = []
for idx, row in unidata.uns["pred_dbl_cluster"].iterrows():
if row["percentage"] >= 50.0:
logger.info(
f"Cluster {row['cluster']} (percentage={row['percentage']:.2f}%, q-value={row['qval']:.6g}) is identified as a doublet cluster."
)
clusts.append(row["cluster"])
if len(clusts) > 0:
dbl_clusts = f"{clust_attr}:{','.join(clusts)}"
tools.mark_doublets(unidata, dbl_clusts=dbl_clusts)
# calculate diffusion-based pseudotime from roots
if len(kwargs["pseudotime"]) > 0:
tools.calc_pseudotime(unidata, kwargs["pseudotime"])
genome = unidata.uns["genome"]
if append_data is not None:
locs = unidata.obs_names.get_indexer(append_data.obs_names)
idx = locs >= 0
locs = locs[idx]
Y = append_data.X[idx, :].tocoo(copy=False)
Z = coo_matrix((Y.data, (locs[Y.row], Y.col)),
shape=(unidata.shape[0], append_data.shape[1])).tocsr()
idy = Z.getnnz(axis=0) > 0
n_nonzero = idy.sum()
if n_nonzero > 0:
if n_nonzero < append_data.shape[1]:
Z = Z[:, idy]
append_df = append_data.feature_metadata.loc[idy, :]
else:
append_df = append_data.feature_metadata
if kwargs["citeseq"]:
append_df = append_df.copy()
append_df.index = append_df.index.map(lambda x: f"Ab-{x}")
rawX = hstack([unidata.get_matrix("counts"), Z], format="csr")
Zt = Z.astype(np.float32)
if not kwargs["citeseq"]:
Zt.data *= np.repeat(unidata.obs["scale"].values,
np.diff(Zt.indptr))
Zt.data = np.log1p(Zt.data)
else:
Zt.data = np.arcsinh(Zt.data / 5.0, dtype=np.float32)
X = hstack([unidata.get_matrix(unidata.current_matrix()), Zt],
format="csr")
new_genome = unidata.get_genome()
if new_genome != append_data.get_genome():
new_genome = f"{new_genome}_and_{append_data.get_genome()}"
feature_metadata = pd.concat([unidata.feature_metadata, append_df],
axis=0)
feature_metadata.reset_index(inplace=True)
_fillna(feature_metadata)
unidata = UnimodalData(
unidata.barcode_metadata, feature_metadata, {
unidata.current_matrix(): X,
"counts": rawX
}, unidata.uns.mapping, unidata.obsm.mapping,
unidata.varm.mapping
) # uns.mapping, obsm.mapping and varm.mapping are passed by reference
unidata.uns["genome"] = new_genome
if kwargs["citeseq"] and kwargs["citeseq_umap"]:
umap_index = append_df.index.difference(
[f"Ab-{x}" for x in kwargs["citeseq_umap_exclude"]])
unidata.obsm["X_citeseq"] = unidata.X[:,
unidata.var_names.
isin(umap_index
)].toarray()
tools.umap(
unidata,
rep="citeseq",
n_neighbors=kwargs["umap_K"],
min_dist=kwargs["umap_min_dist"],
spread=kwargs["umap_spread"],
n_jobs=kwargs["n_jobs"],
full_speed=kwargs["full_speed"],
random_state=kwargs["random_state"],
out_basis="citeseq_umap",
)
if kwargs["output_h5ad"]:
import time
start_time = time.perf_counter()
adata = unidata.to_anndata()
if "_tmp_fmat_highly_variable_features" in adata.uns:
adata.uns["scale.data"] = adata.uns.pop(
"_tmp_fmat_highly_variable_features") # assign by reference
adata.uns["scale.data.rownames"] = unidata.var_names[
unidata.var["highly_variable_features"] == True].values
adata.write(f"{output_name}.h5ad", compression="gzip")
del adata
end_time = time.perf_counter()
logger.info(
f"H5AD file {output_name}.h5ad is written. Time spent = {end_time - start_time:.2f}s."
)
# write out results
if kwargs["output_loom"]:
write_output(unidata, f"{output_name}.loom")
# Change genome name back if append_data is True
if unidata.uns["genome"] != genome:
unidata.uns["genome"] = genome
# Eliminate objects starting with _tmp from uns
unidata.uns.pop("_tmp_fmat_highly_variable_features", None)
def analyze_one_modality(unidata: UnimodalData, output_name: str, is_raw: bool,
append_data: UnimodalData, **kwargs) -> None:
print()
logger.info(f"Begin to analyze UnimodalData {unidata.get_uid()}.")
if kwargs["channel_attr"] is not None:
unidata.obs["Channel"] = unidata.obs[kwargs["channel_attr"]]
if is_raw:
# normailize counts and then transform to log space
tools.log_norm(unidata, kwargs["norm_count"])
# set group attribute
if kwargs["batch_correction"] and kwargs["group_attribute"] is not None:
tools.set_group_attribute(unidata, kwargs["group_attribute"])
# select highly variable features
standardize = False # if no select HVF, False
if kwargs["select_hvf"]:
if unidata.shape[1] <= kwargs["hvf_ngenes"]:
logger.warning(
f"Number of genes {unidata.shape[1]} is no greater than the target number of highly variable features {kwargs['hvf_ngenes']}. HVF selection is omitted."
)
else:
standardize = True
tools.highly_variable_features(
unidata,
kwargs["batch_correction"],
flavor=kwargs["hvf_flavor"],
n_top=kwargs["hvf_ngenes"],
n_jobs=kwargs["n_jobs"],
)
if kwargs["hvf_flavor"] == "pegasus":
if kwargs["plot_hvf"] is not None:
from pegasus.plotting import hvfplot
fig = hvfplot(unidata, return_fig=True)
fig.savefig(f"{kwargs['plot_hvf']}.hvf.pdf")
# batch correction: L/S
if kwargs["batch_correction"] and kwargs["correction_method"] == "L/S":
tools.correct_batch(unidata, features="highly_variable_features")
if kwargs["calc_sigscore"] is not None:
sig_files = kwargs["calc_sigscore"].split(",")
for sig_file in sig_files:
tools.calc_signature_score(unidata, sig_file)
n_pc = min(kwargs["pca_n"], unidata.shape[0], unidata.shape[1])
if n_pc < kwargs["pca_n"]:
logger.warning(
f"UnimodalData {unidata.get_uid()} has either dimension ({unidata.shape[0]}, {unidata.shape[1]}) less than the specified number of PCs {kwargs['pca_n']}. Reduce the number of PCs to {n_pc}."
)
if kwargs["batch_correction"] and kwargs[
"correction_method"] == "scanorama":
pca_key = tools.run_scanorama(unidata,
n_components=n_pc,
features="highly_variable_features",
standardize=standardize,
random_state=kwargs["random_state"])
else:
# PCA
tools.pca(
unidata,
n_components=n_pc,
features="highly_variable_features",
standardize=standardize,
robust=kwargs["pca_robust"],
random_state=kwargs["random_state"],
)
pca_key = "pca"
# batch correction: Harmony
if kwargs["batch_correction"] and kwargs["correction_method"] == "harmony":
pca_key = tools.run_harmony(unidata,
rep="pca",
n_jobs=kwargs["n_jobs"],
n_clusters=kwargs["harmony_nclusters"],
random_state=kwargs["random_state"])
# Find K neighbors
tools.neighbors(
unidata,
K=kwargs["K"],
rep=pca_key,
n_jobs=kwargs["n_jobs"],
random_state=kwargs["random_state"],
full_speed=kwargs["full_speed"],
)
# calculate diffmap
if (kwargs["fle"] or kwargs["net_fle"]):
if not kwargs["diffmap"]:
print("Turn on --diffmap option!")
kwargs["diffmap"] = True
if kwargs["diffmap"]:
tools.diffmap(
unidata,
n_components=kwargs["diffmap_ndc"],
rep=pca_key,
solver=kwargs["diffmap_solver"],
random_state=kwargs["random_state"],
max_t=kwargs["diffmap_maxt"],
)
if kwargs["diffmap_to_3d"]:
tools.reduce_diffmap_to_3d(unidata,
random_state=kwargs["random_state"])
# calculate kBET
if ("kBET" in kwargs) and kwargs["kBET"]:
stat_mean, pvalue_mean, accept_rate = tools.calc_kBET(
unidata,
kwargs["kBET_batch"],
rep=pca_key,
K=kwargs["kBET_K"],
alpha=kwargs["kBET_alpha"],
n_jobs=kwargs["n_jobs"],
random_state=kwargs["random_state"])
print(
"kBET stat_mean = {:.2f}, pvalue_mean = {:.4f}, accept_rate = {:.2%}."
.format(stat_mean, pvalue_mean, accept_rate))
# clustering
if kwargs["spectral_louvain"]:
tools.cluster(
unidata,
algo="spectral_louvain",
rep=pca_key,
resolution=kwargs["spectral_louvain_resolution"],
rep_kmeans=kwargs["spectral_louvain_basis"],
n_clusters=kwargs["spectral_louvain_nclusters"],
n_clusters2=kwargs["spectral_louvain_nclusters2"],
n_init=kwargs["spectral_louvain_ninit"],
random_state=kwargs["random_state"],
class_label="spectral_louvain_labels",
)
if kwargs["spectral_leiden"]:
tools.cluster(
unidata,
algo="spectral_leiden",
rep=pca_key,
resolution=kwargs["spectral_leiden_resolution"],
rep_kmeans=kwargs["spectral_leiden_basis"],
n_clusters=kwargs["spectral_leiden_nclusters"],
n_clusters2=kwargs["spectral_leiden_nclusters2"],
n_init=kwargs["spectral_leiden_ninit"],
random_state=kwargs["random_state"],
class_label="spectral_leiden_labels",
)
if kwargs["louvain"]:
tools.cluster(
unidata,
algo="louvain",
rep=pca_key,
resolution=kwargs["louvain_resolution"],
random_state=kwargs["random_state"],
class_label=kwargs["louvain_class_label"],
)
if kwargs["leiden"]:
tools.cluster(
unidata,
algo="leiden",
rep=pca_key,
resolution=kwargs["leiden_resolution"],
n_iter=kwargs["leiden_niter"],
random_state=kwargs["random_state"],
class_label=kwargs["leiden_class_label"],
)
# visualization
if kwargs["net_tsne"]:
tools.net_tsne(
unidata,
rep=pca_key,
n_jobs=kwargs["n_jobs"],
perplexity=kwargs["tsne_perplexity"],
random_state=kwargs["random_state"],
select_frac=kwargs["net_ds_frac"],
select_K=kwargs["net_ds_K"],
select_alpha=kwargs["net_ds_alpha"],
net_alpha=kwargs["net_l2"],
polish_learning_frac=kwargs["net_tsne_polish_learing_frac"],
polish_n_iter=kwargs["net_tsne_polish_niter"],
out_basis=kwargs["net_tsne_basis"],
)
if kwargs["net_umap"]:
tools.net_umap(
unidata,
rep=pca_key,
n_jobs=kwargs["n_jobs"],
n_neighbors=kwargs["umap_K"],
min_dist=kwargs["umap_min_dist"],
spread=kwargs["umap_spread"],
random_state=kwargs["random_state"],
select_frac=kwargs["net_ds_frac"],
select_K=kwargs["net_ds_K"],
select_alpha=kwargs["net_ds_alpha"],
full_speed=kwargs["full_speed"],
net_alpha=kwargs["net_l2"],
polish_learning_rate=kwargs["net_umap_polish_learing_rate"],
polish_n_epochs=kwargs["net_umap_polish_nepochs"],
out_basis=kwargs["net_umap_basis"],
)
if kwargs["net_fle"]:
tools.net_fle(
unidata,
output_name,
n_jobs=kwargs["n_jobs"],
K=kwargs["fle_K"],
full_speed=kwargs["full_speed"],
target_change_per_node=kwargs["fle_target_change_per_node"],
target_steps=kwargs["fle_target_steps"],
is3d=False,
memory=kwargs["fle_memory"],
random_state=kwargs["random_state"],
select_frac=kwargs["net_ds_frac"],
select_K=kwargs["net_ds_K"],
select_alpha=kwargs["net_ds_alpha"],
net_alpha=kwargs["net_l2"],
polish_target_steps=kwargs["net_fle_polish_target_steps"],
out_basis=kwargs["net_fle_basis"],
)
if kwargs["tsne"]:
tools.tsne(
unidata,
rep=pca_key,
n_jobs=kwargs["n_jobs"],
perplexity=kwargs["tsne_perplexity"],
random_state=kwargs["random_state"],
)
if kwargs["fitsne"]:
tools.fitsne(
unidata,
rep=pca_key,
n_jobs=kwargs["n_jobs"],
perplexity=kwargs["tsne_perplexity"],
random_state=kwargs["random_state"],
)
if kwargs["umap"]:
tools.umap(
unidata,
rep=pca_key,
n_neighbors=kwargs["umap_K"],
min_dist=kwargs["umap_min_dist"],
spread=kwargs["umap_spread"],
random_state=kwargs["random_state"],
)
if kwargs["fle"]:
tools.fle(
unidata,
output_name,
n_jobs=kwargs["n_jobs"],
K=kwargs["fle_K"],
full_speed=kwargs["full_speed"],
target_change_per_node=kwargs["fle_target_change_per_node"],
target_steps=kwargs["fle_target_steps"],
is3d=False,
memory=kwargs["fle_memory"],
random_state=kwargs["random_state"],
)
# calculate diffusion-based pseudotime from roots
if len(kwargs["pseudotime"]) > 0:
tools.calc_pseudotime(unidata, kwargs["pseudotime"])
genome = unidata.uns["genome"]
if append_data is not None:
locs = unidata.obs_names.get_indexer(append_data.obs_names)
idx = locs >= 0
locs = locs[idx]
Y = append_data.X[idx, :].tocoo(copy=False)
Z = coo_matrix((Y.data, (locs[Y.row], Y.col)),
shape=(unidata.shape[0], append_data.shape[1])).tocsr()
idy = Z.getnnz(axis=0) > 0
n_nonzero = idy.sum()
if n_nonzero > 0:
if n_nonzero < append_data.shape[1]:
Z = Z[:, idy]
append_df = append_data.feature_metadata.loc[idy, :]
else:
append_df = append_data.feature_metadata
rawX = hstack([unidata.get_matrix("raw.X"), Z], format="csr")
Zt = Z.astype(np.float32)
Zt.data *= np.repeat(unidata.obs["scale"].values,
np.diff(Zt.indptr))
Zt.data = np.log1p(Zt.data)
X = hstack([unidata.get_matrix("X"), Zt], format="csr")
new_genome = unidata.get_genome(
) + "_and_" + append_data.get_genome()
feature_metadata = pd.concat([unidata.feature_metadata, append_df],
axis=0)
feature_metadata.reset_index(inplace=True)
feature_metadata.fillna(value=_get_fillna_dict(
unidata.feature_metadata),
inplace=True)
unidata = UnimodalData(
unidata.barcode_metadata, feature_metadata, {
"X": X,
"raw.X": rawX
}, unidata.uns.mapping, unidata.obsm.mapping,
unidata.varm.mapping
) # uns.mapping, obsm.mapping and varm.mapping are passed by reference
unidata.uns["genome"] = new_genome
if kwargs["output_h5ad"]:
adata = unidata.to_anndata()
adata.uns["scale.data"] = adata.uns.pop(
"_tmp_fmat_highly_variable_features") # assign by reference
adata.uns["scale.data.rownames"] = unidata.var_names[
unidata.var["highly_variable_features"]].values
adata.write(f"{output_name}.h5ad", compression="gzip")
del adata
# write out results
if kwargs["output_loom"]:
write_output(unidata, f"{output_name}.loom")
# Change genome name back if append_data is True
if unidata.uns["genome"] != genome:
unidata.uns["genome"] = genome
# Eliminate objects starting with fmat_ from uns
unidata.uns.pop("_tmp_fmat_highly_variable_features", None)