terminal
main_analysis.py
Python 3.9 Kernel Ready
1
2
3
4
5
6
7
8
9
10
11
12
13
2
3
4
5
6
7
8
9
10
11
12
13
import scanpy as sc
import pandas as pd
# Load dataset configuration
DATA_PATH = 's3://bloom-data/lung_atlas_v2.h5ad'
# Initialize analysis object
adata = sc.read_h5ad(DATA_PATH)
# Preprocessing: Normalize and log transform
sc.pp.normalize_total(adata, target_sum=1e4)
sc.pp.log1p(adata)
# Attempt neighborhood graph construction
error
sc.pp.neighbors(adata, n_neighbors=10, n_pcs=40)
sc.tl.umap(adata)
TERMINAL
OUTPUT
DEBUG CONSOLE
close
➜ workspace git:(main) python main_analysis.py
Loading dataset 'lung_atlas_v2.h5ad'... Done (2.4s)
Normalizing counts... Done (0.8s)
Computing neighbors...
RuntimeError: Matrix alignment failed.
File "main_analysis.py", line 12, in <module>
sc.pp.neighbors(adata, n_neighbors=10, n_pcs=40)
Principal components do not match reference integration. Batch effect detected across samples.
File "main_analysis.py", line 12, in <module>
sc.pp.neighbors(adata, n_neighbors=10, n_pcs=40)
Principal components do not match reference integration. Batch effect detected across samples.
Harmony Integration Required
psychology
It looks like your matrices are unaligned. Standard neighborhood calculation failed due to significant batch effects in the lung_atlas_v2 dataset.
school
Learn about: Batch Effects, Harmony Method
Data Alignment Preview
Recommended Fix
Python
# Use Harmony for batch correction
import scanpy.external as sce
sce.pp.harmony_integrate(adata, key='batch')
sc.pp.neighbors(adata, use_rep='X_pca_harmony')