single-cell-rna-qc

Name: single-cell-rna-qc
Author: anthropics

1.7kinstalls2.7kforks

How to install single-cell-rna-qc?

anthropics/knowledge-work-plugins/single-cell-rna-qc

$npx -y skills add anthropics/knowledge-work-plugins --skill single-cell-rna-qc

Installs into the current project.

Summary

Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive visualizations. Use when users request QC analysis, filtering low-quality cells, assessing data quality, or following scverse/scanpy b

Files · 1

View on GitHub

SKILL.md

1	# Single-Cell RNA-seq Quality Control
2
3	Automated QC workflow for single-cell RNA-seq data following scverse best practices.
4
5	## When to Use This Skill
6
7	Use when users:
8	- Request quality control or QC on single-cell RNA-seq data
9	- Want to filter low-quality cells or assess data quality
10	- Need QC visualizations or metrics
11	- Ask to follow scverse/scanpy best practices
12	- Request MAD-based filtering or outlier detection
13
14	Supported input formats:
15	- `.h5ad` files (AnnData format from scanpy/Python workflows)
16	- `.h5` files (10X Genomics Cell Ranger output)
17
18	Default recommendation: Use Approach 1 (complete pipeline) unless the user has specific custom requirements or explicitly requests non-standard filtering logic.
19
20	## Approach 1: Complete QC Pipeline (Recommended for Standard Workflows)
21
22	For standard QC following scverse best practices, use the convenience script `scripts/qc_analysis.py`:
23
24	```bash
25	python3 scripts/qc_analysis.py input.h5ad
26	# or for 10X Genomics .h5 files:
27	python3 scripts/qc_analysis.py raw_feature_bc_matrix.h5
28	```
29
30	The script automatically detects the file format and loads it appropriately.
31
32	When to use this approach:
33	- Standard QC workflow with adjustable thresholds (all cells filtered the same way)
34	- Batch processing multiple datasets
35	- Quick exploratory analysis
36	- User wants the "just works" solution
37
38	Requirements: anndata, scanpy, scipy, matplotlib, seaborn, numpy
39
40	Parameters:
41
42	Customize filtering thresholds and gene patterns using command-line parameters:
43	- `--output-dir` - Output directory
44	- `--mad-counts`, `--mad-genes`, `--mad-mt` - MAD thresholds for counts/genes/MT%
45	- `--mt-threshold` - Hard mitochondrial % cutoff
46	- `--min-cells` - Gene filtering threshold
47	- `--mt-pattern`, `--ribo-pattern`, `--hb-pattern` - Gene name patterns for different species
48
49	Use `--help` to see current default values.
50
51	Outputs:
52
53	All files are saved to `<input_basename>_qc_results/` directory by default (or to the directory specified by `--output-dir`):
54	- `qc_metrics_before_filtering.png` - Pre-filtering visualizations
55	- `qc_filtering_thresholds.png` - MAD-based threshold overlays
56	- `qc_metrics_after_filtering.png` - Post-filtering quality metrics
57	- `<input_basename>_filtered.h5ad` - Clean, filtered dataset ready for downstream analysis
58	- `<input_basename>_with_qc.h5ad` - Original data with QC annotations preserved
59
60	If copying outputs for user access, copy individual files (not the entire directory) so users can preview them directly.
61
62	### Workflow Steps
63
64	The script performs the following steps:
65
66	1. Calculate QC metrics - Count depth, gene detection, mitochondrial/ribosomal/hemoglobin content
67	2. Apply MAD-based filtering - Permissive outlier detection using MAD thresholds for counts/genes/MT%
68	3. Filter genes - Remove genes detected in few cells
69	4. Generate visualizations - Comprehensive before/after plots with threshold overlays
70
71	## Approach 2: Modular Building Blocks (For Custom Workflows)
72
73	For custom analysis workflows or non-standard requirements, use the modular utility functions from `scripts/qc_core.py` and `scripts/qc_plotting.py`:
74
75	```python
76	# Run from scripts/ directory, or add scripts/ to sys.path if needed
77	import anndata as ad
78	from qc_core import calculate_qc_metrics, detect_outliers_mad, filter_cells
79	from qc_plotting import plot_qc_distributions # Only if visualization needed
80
81	adata = ad.read_h5ad('input.h5ad')
82	calculate_qc_metrics(adata, inplace=True)
83	# ... custom analysis logic here
84	```
85
86	When to use this approach:
87	- Different workflow needed (skip steps, change order, apply different thresholds to subsets)
88	- Conditional logic (e.g., filter neurons differently than other cells)
89	- Partial execution (only metrics/visualization, no filtering)
90	- Integration with other analysis steps in a larger pipeline
91	- Custom filtering criteria beyond what command-line params support
92
93	Available utility functions:
94
95	From `qc_core.py` (core QC operations):
96	- `calculate_qc_metrics(adata, mt_pattern, ribo_pattern, hb_pattern, inplace=True)` - Calculate QC metrics and annotate adata
97	- `detect_outliers_mad(adata, metric, n_mads, verbose=True)` - MAD-based outlier detection, returns boolean mask
98	- `apply_hard_threshold(adata, metric, threshold, operator='>', verbose=True)` - Apply hard cutoffs, returns boolean mask
99	- `filter_cells(adata, mask, inplace=False)` - Apply boolean mask to filter cells
100	- `filter_genes(adata, min_cells=20, min_counts=None, inplace=True)` - Filter genes by detection
101	- `print_qc_summary(adata, label='')` - Print summary statistics
102
103	From `qc_plotting.py` (visualization):
104	- `plot_qc_distributions(a

People who liked this also viewed

6 picks

Type

single-cell-rna-qc

1.7kinstalls2.7kforks

View on GitHub

How to install single-cell-rna-qc?

anthropics/knowledge-work-plugins/single-cell-rna-qc

$npx -y skills add anthropics/knowledge-work-plugins --skill single-cell-rna-qc

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Single-Cell RNA-seq Quality Control
2
3	Automated QC workflow for single-cell RNA-seq data following scverse best practices.
4
5	## When to Use This Skill
6
7	Use when users:
8	- Request quality control or QC on single-cell RNA-seq data
9	- Want to filter low-quality cells or assess data quality
10	- Need QC visualizations or metrics
11	- Ask to follow scverse/scanpy best practices
12	- Request MAD-based filtering or outlier detection
13
14	Supported input formats:
15	- `.h5ad` files (AnnData format from scanpy/Python workflows)
16	- `.h5` files (10X Genomics Cell Ranger output)
17
18	Default recommendation: Use Approach 1 (complete pipeline) unless the user has specific custom requirements or explicitly requests non-standard filtering logic.
19
20	## Approach 1: Complete QC Pipeline (Recommended for Standard Workflows)
21
22	For standard QC following scverse best practices, use the convenience script `scripts/qc_analysis.py`:
23
24	```bash
25	python3 scripts/qc_analysis.py input.h5ad
26	# or for 10X Genomics .h5 files:
27	python3 scripts/qc_analysis.py raw_feature_bc_matrix.h5
28	```
29
30	The script automatically detects the file format and loads it appropriately.
31
32	When to use this approach:
33	- Standard QC workflow with adjustable thresholds (all cells filtered the same way)
34	- Batch processing multiple datasets
35	- Quick exploratory analysis
36	- User wants the "just works" solution
37
38	Requirements: anndata, scanpy, scipy, matplotlib, seaborn, numpy
39
40	Parameters:
41
42	Customize filtering thresholds and gene patterns using command-line parameters:
43	- `--output-dir` - Output directory
44	- `--mad-counts`, `--mad-genes`, `--mad-mt` - MAD thresholds for counts/genes/MT%
45	- `--mt-threshold` - Hard mitochondrial % cutoff
46	- `--min-cells` - Gene filtering threshold
47	- `--mt-pattern`, `--ribo-pattern`, `--hb-pattern` - Gene name patterns for different species
48
49	Use `--help` to see current default values.
50
51	Outputs:
52
53	All files are saved to `<input_basename>_qc_results/` directory by default (or to the directory specified by `--output-dir`):
54	- `qc_metrics_before_filtering.png` - Pre-filtering visualizations
55	- `qc_filtering_thresholds.png` - MAD-based threshold overlays
56	- `qc_metrics_after_filtering.png` - Post-filtering quality metrics
57	- `<input_basename>_filtered.h5ad` - Clean, filtered dataset ready for downstream analysis
58	- `<input_basename>_with_qc.h5ad` - Original data with QC annotations preserved
59
60	If copying outputs for user access, copy individual files (not the entire directory) so users can preview them directly.
61
62	### Workflow Steps
63
64	The script performs the following steps:
65
66	1. Calculate QC metrics - Count depth, gene detection, mitochondrial/ribosomal/hemoglobin content
67	2. Apply MAD-based filtering - Permissive outlier detection using MAD thresholds for counts/genes/MT%
68	3. Filter genes - Remove genes detected in few cells
69	4. Generate visualizations - Comprehensive before/after plots with threshold overlays
70
71	## Approach 2: Modular Building Blocks (For Custom Workflows)
72
73	For custom analysis workflows or non-standard requirements, use the modular utility functions from `scripts/qc_core.py` and `scripts/qc_plotting.py`:
74
75	```python
76	# Run from scripts/ directory, or add scripts/ to sys.path if needed
77	import anndata as ad
78	from qc_core import calculate_qc_metrics, detect_outliers_mad, filter_cells
79	from qc_plotting import plot_qc_distributions # Only if visualization needed
80
81	adata = ad.read_h5ad('input.h5ad')
82	calculate_qc_metrics(adata, inplace=True)
83	# ... custom analysis logic here
84	```
85
86	When to use this approach:
87	- Different workflow needed (skip steps, change order, apply different thresholds to subsets)
88	- Conditional logic (e.g., filter neurons differently than other cells)
89	- Partial execution (only metrics/visualization, no filtering)
90	- Integration with other analysis steps in a larger pipeline
91	- Custom filtering criteria beyond what command-line params support
92
93	Available utility functions:
94
95	From `qc_core.py` (core QC operations):
96	- `calculate_qc_metrics(adata, mt_pattern, ribo_pattern, hb_pattern, inplace=True)` - Calculate QC metrics and annotate adata
97	- `detect_outliers_mad(adata, metric, n_mads, verbose=True)` - MAD-based outlier detection, returns boolean mask
98	- `apply_hard_threshold(adata, metric, threshold, operator='>', verbose=True)` - Apply hard cutoffs, returns boolean mask
99	- `filter_cells(adata, mask, inplace=False)` - Apply boolean mask to filter cells
100	- `filter_genes(adata, min_cells=20, min_counts=None, inplace=True)` - Filter genes by detection
101	- `print_qc_summary(adata, label='')` - Print summary statistics
102
103	From `qc_plotting.py` (visualization):
104	- `plot_qc_distributions(a

People who liked this also viewed

6 picks

Type