def maelstrom(args):
"""Run the maelstrom method."""
infile = args.inputfile
genome = args.genome
outdir = args.outdir
pfmfile = args.pfmfile
filter_redundant = args.filter_redundant
filter_cutoff = args.filter_cutoff
methods = args.methods
ncpus = args.ncpus
zscore = args.zscore
center = args.center
gc = args.gc
aggregation = args.aggregation
if not os.path.exists(infile):
raise ValueError("file {} does not exist".format(infile))
if methods:
methods = [x.strip() for x in methods.split(",")]
run_maelstrom(
infile,
genome,
outdir,
pfmfile,
filter_redundant=filter_redundant,
filter_cutoff=filter_cutoff,
methods=methods,
ncpus=ncpus,
zscore=zscore,
gc=gc,
center=center,
aggregation=aggregation,
)
def maelstrom(args):
"""Run the maelstrom method."""
infile = args.inputfile
genome = args.genome
outdir = args.outdir
pfmfile = args.pfmfile
methods = args.methods
ncpus = args.ncpus
zscore = args.zscore
gc = args.gc
if not os.path.exists(infile):
raise ValueError("file {} does not exist".format(infile))
if methods:
methods = [x.strip() for x in methods.split(",")]
run_maelstrom(
infile,
genome,
outdir,
pfmfile,
methods=methods,
ncpus=ncpus,
zscore=zscore,
gc=gc,
)
def test1_maelstrom(self):
""" Test Motif Activity by Ensemble Learning (maelstrom) """
run_maelstrom(self.clusters, "mm10", self.outdir,
score_table=self.score_table, count_table=self.count_table)
df = pd.read_table(self.outfile, index_col=0, comment="#")
self.assertEquals((623, 4), df.shape)
for fname in glob(os.path.join(self.outdir, "activity*")):
os.unlink(fname)
os.unlink(self.outfile)
def maelstrom(args):
infile = args.inputfile
genome = args.genome
outdir = args.outdir
if not os.path.exists(infile):
raise ValueError("file {} does not exist".format(infile))
check_genome(genome)
run_maelstrom(infile, genome, outdir)
def maelstrom(args):
infile = args.inputfile
genome = args.genome
outdir = args.outdir
if not os.path.exists(infile):
raise ValueError("file {} does not exist".format(infile))
check_genome(genome)
run_maelstrom(infile, genome, outdir)
def test1_maelstrom(self):
""" Test Motif Activity by Ensemble Learning (maelstrom) """
run_maelstrom(self.clusters,
"mm10",
self.outdir,
score_table=self.score_table,
count_table=self.count_table,
plot=False)
df = pd.read_table(self.outfile, index_col=0, comment="#")
self.assertEquals((623, 4), df.shape)
for fname in glob(os.path.join(self.outdir, "activity*")):
os.unlink(fname)
os.unlink(self.outfile)
def test1_maelstrom(self):
""" Test Motif Activity by Ensemble Learning (maelstrom) """
run_maelstrom(
self.clusters,
"mm10",
self.outdir,
filter_redundant=False,
score_table=self.score_table,
count_table=self.count_table,
plot=False,
)
df = pd.read_table(self.outfile, index_col=0, comment="#")
print(df.shape)
self.assertEquals((623, 8), df.shape)
# Filter redundant motifs
run_maelstrom(
self.clusters,
"mm10",
self.outdir,
filter_redundant=True,
score_table=self.score_table,
count_table=self.count_table,
plot=False,
)
df = pd.read_table(self.outfile, index_col=0, comment="#")
print(df.shape)
self.assertEquals((156, 8), df.shape)
for fname in glob(os.path.join(self.outdir, "activity*")):
os.unlink(fname)
for fname in glob(os.path.join(self.outdir, "gimme.verte*")):
os.unlink(fname)
os.unlink(self.outfile)
def infer_motifs(
adata: AnnData,
dataset: str,
cluster: Optional[str] = "louvain",
n_top_genes: Optional[int] = 1000,
max_cell_types: Optional[int] = 50,
pfm: Optional[str] = None,
min_annotated: Optional[int] = 50,
num_enhancers: Optional[int] = 10000,
maelstrom: Optional[bool] = False,
indirect: Optional[bool] = True,
n_sketch: Optional[int] = 2500,
n_permutations: Optional[int] = 100000,
) -> None:
"""Infer motif ativity for single cell RNA-seq data.
The adata object is modified with the following fields.
**X_cell_types** : `adata.obsm` field
Cell type coefficients.
Parameters
----------
adata : :class:`~anndata.AnnData`
Annotated data matrix.
dataset : `str`
Name of reference data set or directory with reference data.
cluster : `str`, optional (default: "louvain")
Name of the clustering, can be either louvain or leiden.
n_top_genes : `int`, optional (default: 1000)
Number of variable genes that is used. If `n_top_genes` is greater than the
number of hypervariable genes in `adata` then all variable genes are
used.
max_cell_types : `int`, optional (default: 50)
Maximum number of cell types to select.
pfm : `str`, optional (default: None)
Name of motif file in PFM format. The GimmeMotifs default is used
if this parameter is not specified. This can be a filename, or a
pfm name support by GimmeMotifs such as `JASPAR2018_vertebrates`.
If a custom PFM file is specified, there should also be an associated
`.motif2factors.txt` file.
min_annotated : `int`, optional (default: 50)
Cells that are annotated with cell types less than this number will be
annotated as "other".
num_enhancers : `int`, optional (default: 10000)
Number of enhancers to use for motif activity analysis.
maelstrom : `boolean`, optional (default: False)
Use maelstrom instead of ridge regression for motif activity analysis.
"""
use_name = True
validate_adata(adata)
data = ScepiaDataset(dataset)
if "scepia" not in adata.uns:
adata.uns["scepia"] = {"version": __version__}
# Annotate each cell with H3K27ac reference
if "cell_annotation" not in adata.obs or "cluster_annotation" not in adata.obs:
annotate_cells(
adata,
dataset=dataset,
cluster=cluster,
n_top_genes=n_top_genes,
min_annotated=min_annotated,
max_cell_types=max_cell_types,
)
logger.info("Linking variable genes to differential enhancers.")
gene_map_file = data.gene_mapping
link_file = data.link_file
link = pd.read_feather(link_file)
if use_name:
ens2name = pd.read_csv(gene_map_file,
sep="\t",
index_col=0,
names=["identifier", "name"])
link = link.join(ens2name, on="gene").dropna()
link = link.set_index("name")
link.index = link.index.str.upper()
enh_genes = adata.var_names[adata.var_names.str.upper().isin(
link.index)].str.upper()
var_enhancers = change_region_size(link.loc[enh_genes, "loc"]).unique()
enhancer_df = data.load_reference_data(reftype="enhancer")
enhancer_df.index = change_region_size(enhancer_df.index)
enhancer_df = enhancer_df.loc[var_enhancers,
adata.uns["scepia"]["cell_types"]]
enhancer_df = enhancer_df.groupby(enhancer_df.columns, axis=1).mean()
enhancer_df.loc[:, :] = scale(enhancer_df)
# Select top most variable enhancers
enhancer_df = enhancer_df.loc[enhancer_df.var(1).sort_values().tail(
num_enhancers).index]
# Center by mean of the most import cell types
# Here we chose the majority cell type per cluster
cluster_cell_types = adata.obs["cluster_annotation"].unique()
mean_value = enhancer_df[cluster_cell_types].mean(1)
enhancer_df = enhancer_df.sub(mean_value, axis=0)
fname = NamedTemporaryFile(delete=False).name
enhancer_df.to_csv(fname, sep="\t")
logger.info("inferring motif activity")
pfm = pfmfile_location(pfm)
if maelstrom:
with TemporaryDirectory() as tmpdir:
run_maelstrom(
fname,
data.genome,
tmpdir,
center=False,
filter_redundant=True,
)
motif_act = pd.read_csv(
os.path.join(tmpdir, "final.out.txt"),
sep="\t",
comment="#",
index_col=0,
)
motif_act.columns = motif_act.columns.str.replace(
r"z-score\s+", "")
pfm = pfmfile_location(
os.path.join(tmpdir, "nonredundant.motifs.pfm"))
else:
logger.info(f"Activity based on genome {data.genome}")
motif_act = moap(
fname,
scoring="score",
genome=data.genome,
method="bayesianridge",
pfmfile=pfm,
ncpus=12,
)
adata.uns["scepia"]["pfm"] = pfm
adata.uns["scepia"]["motif_activity"] = motif_act[adata.uns["scepia"]
["cell_types"]]
logger.info("calculating cell-specific motif activity")
cell_motif_activity = (
adata.uns["scepia"]["motif_activity"] @ adata.obsm["X_cell_types"].T).T
cell_motif_activity.index = adata.obs_names
adata.obs = adata.obs.drop(
columns=cell_motif_activity.columns.intersection(adata.obs.columns))
adata.obs = adata.obs.join(cell_motif_activity)
correlate_tf_motifs(adata,
indirect=indirect,
n_sketch=n_sketch,
n_permutations=n_permutations)
add_activity(adata)
logger.info("Done with motif inference.")