Skip to content

Base proportion of assigned reads on counts instead of transcripts table #123

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

Merged
LouisK92 merged 1 commit into from
Dec 13, 2025
Merged

Base proportion of assigned reads on counts instead of transcripts table #123

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
56 changes: 50 additions & 6 deletions src/metrics/quality/quality_metrics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
import numpy as np
import pandas as pd
import spatialdata as sd



def proportion_of_assigned_reads(
sdata: sd.SpatialData,
) -> [float, pd.Series]:
Expand All @@ -22,10 +22,8 @@ def proportion_of_assigned_reads(

"""

sdata['transcripts']['assigned'] = sdata['transcripts']['cell_id'] != 0

# Proportion of assigned reads
prop_of_assigned_reads = float(((sdata['transcripts']['assigned']).sum() / len(sdata['transcripts'])).compute())
prop_of_assigned_reads = float(sdata["counts"].layers["counts"].sum() / len(sdata['transcripts']))

# Proportion of assigned reads per gene
if prop_of_assigned_reads == 1.0:
Expand All @@ -39,10 +37,56 @@ def proportion_of_assigned_reads(
data=0.0
)
else:
df = pd.crosstab(sdata['transcripts']['feature_name'], sdata['transcripts']['assigned'])
prop_of_assigned_reads_per_gene = df[True] / (df[False] + df[True])
genes, counts = np.unique(sdata['transcripts']['feature_name'], return_counts=True)
df = pd.DataFrame(index=genes, data = {"fraction":0, "count":counts, "count_assigned":0})
df.loc[sdata["counts"].var_names, "count_assigned"] = np.array(sdata["counts"].layers["counts"].sum(axis=0))[0,:]
df["fraction"] = df["count_assigned"] / df["count"]
prop_of_assigned_reads_per_gene = df["fraction"]

return prop_of_assigned_reads, prop_of_assigned_reads_per_gene

# Previous version only based on transcripts table.
#
#def proportion_of_assigned_reads(
# sdata: sd.SpatialData,
#) -> [float, pd.Series]:
# """ Calculate the proportion of assigned reads
#
# Parameters
# ----------
# sdata : sd.SpatialData
# SpatialData object with sdata['transcripts'] including the column 'cell_id'
#
# Returns
# -------
# float
# Proportion of assigned reads
# pd.Series
# Proportion of assigned reads per gene
#
# """
#
# sdata['transcripts']['assigned'] = sdata['transcripts']['cell_id'] != 0
#
# # Proportion of assigned reads
# prop_of_assigned_reads = float(((sdata['transcripts']['assigned']).sum() / len(sdata['transcripts'])).compute())
#
# # Proportion of assigned reads per gene
# if prop_of_assigned_reads == 1.0:
# prop_of_assigned_reads_per_gene = pd.Series(
# index=sdata['transcripts']['feature_name'].unique().compute().values,
# data=1.0
# )
# elif prop_of_assigned_reads == 0.0:
# prop_of_assigned_reads_per_gene = pd.Series(
# index=sdata['transcripts']['feature_name'].unique().compute().values,
# data=0.0
# )
# else:
# df = pd.crosstab(sdata['transcripts']['feature_name'], sdata['transcripts']['assigned'])
# prop_of_assigned_reads_per_gene = df[True] / (df[False] + df[True])
#
# return prop_of_assigned_reads, prop_of_assigned_reads_per_gene



Expand Down