Skip to content

🔥 add chromosome scaffold filtering #88

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mbuttner wants to merge 3 commits into
base: old
Choose a base branch
from
Open

🔥 add chromosome scaffold filtering #88

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
06a85be
:fire: add chromosome scaffold filtering
mbuttner Aug 22, 2023
c4bf818
:fire: concatenate fragment groups with pd.concat
mbuttner Aug 23, 2023
9e5aafb
Pandas bugfix
mbuttner Mar 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 13 additions & 1 deletion pycisTopic/pseudobulk_peak_calling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ def export_pseudobulk(
bed_path: str,
bigwig_path: str,
path_to_fragments: Optional[Dict[str, str]] = None,
chrom_filter: Optional[str] = None,
sample_id_col: Optional[str] = "sample_id",
n_cpu: Optional[int] = 1,
normalize_bigwig: Optional[bool] = True,
Expand Down Expand Up @@ -55,6 +56,9 @@ def export_pseudobulk(
A dictionary of character strings, with sample name as names indicating the path to the fragments file/s from which pseudobulk profiles have to
be created. If a :class:`CistopicObject` is provided as input it will be ignored, but if a cell metadata :class:`pd.DataFrame` is provided it
is necessary to provide it. The keys of the dictionary need to match with the sample_id tag added to the index names of the input data frame.
chrom_filter: str, optional
A regular expression to filter out scaffolds like GL/KI genes from the fragments list.
Example: `"GL|KI"`
sample_id_col: str, optional
Name of the column containing the sample name per barcode in the input :class:`CistopicObject.cell_data` or class:`pd.DataFrame`. Default: 'sample_id'.
n_cpu: int, optional
Expand Down Expand Up @@ -129,6 +133,12 @@ def export_pseudobulk(
prepare_tag_cells(cell_data.index.tolist(), split_pattern)
)
]
if chrom_filter is not None:
fragment_drop = fragments_df.Chromosome.str.contains(chrom_filter)
n_fragments_dropped = fragment_drop.sum()
log.info("Filtering out " + str(n_fragments_dropped) + " fragments.")
fragments_df.drop(fragments_df[fragment_drop].index, inplace=True)

fragments_df_dict[sample_id] = fragments_df

# Set groups
Expand Down Expand Up @@ -271,7 +281,7 @@ def export_pseudobulk_one_sample(
group_fragments_dict[list(group_fragments_dict.keys())[x]]
for x in range(len(fragments_df_dict))
]
group_fragments = group_fragments_list[0].append(group_fragments_list[1:])
group_fragments = pd.concat(group_fragments_list)

del group_fragments_dict
del group_fragments_list
Expand All @@ -280,6 +290,7 @@ def export_pseudobulk_one_sample(

group_pr = pr.PyRanges(group_fragments)
if isinstance(bigwig_path, str):
log.info("Creating bigwig file for " + str(group))
bigwig_path_group = os.path.join(bigwig_path, str(group) + ".bw")
if remove_duplicates:
group_pr.to_bigwig(
Expand All @@ -295,6 +306,7 @@ def export_pseudobulk_one_sample(
value_col="Score",
)
if isinstance(bed_path, str):
log.info("Creating bed file for " + str(group))
bed_path_group = os.path.join(bed_path, str(group) + ".bed.gz")
group_pr.to_bed(
path=bed_path_group, keep=False, compression="infer", chain=False
Expand Down