opencode-skills-collection 4.1.15 → 4.1.16

package/bundled-skills/scanpy/assets/analysis_template.py

@@ -0,0 +1,295 @@
+#!/usr/bin/env python3
+"""
+Complete Single-Cell Analysis Template
+
+This template provides a complete workflow for single-cell RNA-seq analysis
+using scanpy, from data loading through clustering and cell type annotation.
+
+Customize the parameters and sections as needed for your specific dataset.
+"""
+
+import scanpy as sc
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+
+# ============================================================================
+# CONFIGURATION
+# ============================================================================
+
+# File paths
+INPUT_FILE = 'data/raw_counts.h5ad'  # Change to your input file
+OUTPUT_DIR = 'results/'
+FIGURES_DIR = 'figures/'
+
+# QC parameters
+MIN_GENES = 200          # Minimum genes per cell
+MIN_CELLS = 3            # Minimum cells per gene
+MT_THRESHOLD = 5         # Maximum mitochondrial percentage
+
+# Analysis parameters
+N_TOP_GENES = 2000       # Number of highly variable genes
+N_PCS = 40               # Number of principal components
+N_NEIGHBORS = 10         # Number of neighbors for graph
+LEIDEN_RESOLUTION = 0.5  # Clustering resolution
+
+# Scanpy settings
+sc.settings.verbosity = 3
+sc.settings.set_figure_params(dpi=80, facecolor='white')
+sc.settings.figdir = FIGURES_DIR
+
+# ============================================================================
+# 1. LOAD DATA
+# ============================================================================
+
+print("=" * 80)
+print("LOADING DATA")
+print("=" * 80)
+
+# Load data (adjust based on your file format)
+adata = sc.read_h5ad(INPUT_FILE)
+# adata = sc.read_10x_mtx('data/filtered_gene_bc_matrices/')  # For 10X data
+# adata = sc.read_csv('data/counts.csv')  # For CSV data
+
+print(f"Loaded: {adata.n_obs} cells x {adata.n_vars} genes")
+
+# ============================================================================
+# 2. QUALITY CONTROL
+# ============================================================================
+
+print("\n" + "=" * 80)
+print("QUALITY CONTROL")
+print("=" * 80)
+
+# Identify mitochondrial genes
+adata.var['mt'] = adata.var_names.str.startswith('MT-')
+
+# Calculate QC metrics
+sc.pp.calculate_qc_metrics(adata, qc_vars=['mt'], percent_top=None,
+                            log1p=False, inplace=True)
+
+# Visualize QC metrics before filtering
+sc.pl.violin(adata, ['n_genes_by_counts', 'total_counts', 'pct_counts_mt'],
+             jitter=0.4, multi_panel=True, save='_qc_before_filtering')
+
+sc.pl.scatter(adata, x='total_counts', y='pct_counts_mt', save='_qc_mt')
+sc.pl.scatter(adata, x='total_counts', y='n_genes_by_counts', save='_qc_genes')
+
+# Filter cells and genes
+print(f"\nBefore filtering: {adata.n_obs} cells, {adata.n_vars} genes")
+
+sc.pp.filter_cells(adata, min_genes=MIN_GENES)
+sc.pp.filter_genes(adata, min_cells=MIN_CELLS)
+adata = adata[adata.obs.pct_counts_mt < MT_THRESHOLD, :]
+
+print(f"After filtering: {adata.n_obs} cells, {adata.n_vars} genes")
+
+# ============================================================================
+# 3. NORMALIZATION
+# ============================================================================
+
+print("\n" + "=" * 80)
+print("NORMALIZATION")
+print("=" * 80)
+
+# Normalize to 10,000 counts per cell
+sc.pp.normalize_total(adata, target_sum=1e4)
+
+# Log-transform
+sc.pp.log1p(adata)
+
+# Store normalized data
+adata.raw = adata
+
+# ============================================================================
+# 4. FEATURE SELECTION
+# ============================================================================
+
+print("\n" + "=" * 80)
+print("FEATURE SELECTION")
+print("=" * 80)
+
+# Identify highly variable genes
+sc.pp.highly_variable_genes(adata, n_top_genes=N_TOP_GENES)
+
+# Visualize
+sc.pl.highly_variable_genes(adata, save='_hvg')
+
+print(f"Selected {sum(adata.var.highly_variable)} highly variable genes")
+
+# Subset to highly variable genes
+adata = adata[:, adata.var.highly_variable]
+
+# ============================================================================
+# 5. SCALING AND REGRESSION
+# ============================================================================
+
+print("\n" + "=" * 80)
+print("SCALING AND REGRESSION")
+print("=" * 80)
+
+# Regress out unwanted sources of variation
+sc.pp.regress_out(adata, ['total_counts', 'pct_counts_mt'])
+
+# Scale data
+sc.pp.scale(adata, max_value=10)
+
+# ============================================================================
+# 6. DIMENSIONALITY REDUCTION
+# ============================================================================
+
+print("\n" + "=" * 80)
+print("DIMENSIONALITY REDUCTION")
+print("=" * 80)
+
+# PCA
+sc.tl.pca(adata, svd_solver='arpack')
+sc.pl.pca_variance_ratio(adata, log=True, save='_pca_variance')
+
+# Compute neighborhood graph
+sc.pp.neighbors(adata, n_neighbors=N_NEIGHBORS, n_pcs=N_PCS)
+
+# UMAP
+sc.tl.umap(adata)
+
+# ============================================================================
+# 7. CLUSTERING
+# ============================================================================
+
+print("\n" + "=" * 80)
+print("CLUSTERING")
+print("=" * 80)
+
+# Leiden clustering
+sc.tl.leiden(adata, resolution=LEIDEN_RESOLUTION)
+
+# Visualize
+sc.pl.umap(adata, color='leiden', legend_loc='on data', save='_leiden')
+
+print(f"Identified {len(adata.obs['leiden'].unique())} clusters")
+
+# ============================================================================
+# 8. MARKER GENE IDENTIFICATION
+# ============================================================================
+
+print("\n" + "=" * 80)
+print("MARKER GENE IDENTIFICATION")
+print("=" * 80)
+
+# Find marker genes
+sc.tl.rank_genes_groups(adata, 'leiden', method='wilcoxon')
+
+# Visualize top markers
+sc.pl.rank_genes_groups(adata, n_genes=25, sharey=False, save='_markers')
+sc.pl.rank_genes_groups_heatmap(adata, n_genes=10, save='_markers_heatmap')
+sc.pl.rank_genes_groups_dotplot(adata, n_genes=5, save='_markers_dotplot')
+
+# Get top markers for each cluster
+for cluster in adata.obs['leiden'].unique():
+    print(f"\nCluster {cluster} top markers:")
+    markers = sc.get.rank_genes_groups_df(adata, group=cluster).head(10)
+    print(markers[['names', 'scores', 'pvals_adj']].to_string(index=False))
+
+# ============================================================================
+# 9. CELL TYPE ANNOTATION (CUSTOMIZE THIS SECTION)
+# ============================================================================
+
+print("\n" + "=" * 80)
+print("CELL TYPE ANNOTATION")
+print("=" * 80)
+
+# Example marker genes for common cell types (customize for your data)
+marker_genes = {
+    'T cells': ['CD3D', 'CD3E', 'CD3G'],
+    'B cells': ['MS4A1', 'CD79A', 'CD79B'],
+    'Monocytes': ['CD14', 'LYZ', 'S100A8'],
+    'NK cells': ['NKG7', 'GNLY', 'KLRD1'],
+    'Dendritic cells': ['FCER1A', 'CST3'],
+}
+
+# Visualize marker genes
+for cell_type, genes in marker_genes.items():
+    available_genes = [g for g in genes if g in adata.raw.var_names]
+    if available_genes:
+        sc.pl.umap(adata, color=available_genes, use_raw=True,
+                   save=f'_{cell_type.replace(" ", "_")}')
+
+# Manual annotation based on marker expression (customize this mapping)
+cluster_to_celltype = {
+    '0': 'CD4 T cells',
+    '1': 'CD14+ Monocytes',
+    '2': 'B cells',
+    '3': 'CD8 T cells',
+    '4': 'NK cells',
+    # Add more mappings based on your marker analysis
+}
+
+# Apply annotations
+adata.obs['cell_type'] = adata.obs['leiden'].map(cluster_to_celltype)
+adata.obs['cell_type'] = adata.obs['cell_type'].fillna('Unknown')
+
+# Visualize annotated cell types
+sc.pl.umap(adata, color='cell_type', legend_loc='on data', save='_celltypes')
+
+# ============================================================================
+# 10. ADDITIONAL ANALYSES (OPTIONAL)
+# ============================================================================
+
+print("\n" + "=" * 80)
+print("ADDITIONAL ANALYSES")
+print("=" * 80)
+
+# PAGA trajectory analysis (optional)
+sc.tl.paga(adata, groups='leiden')
+sc.pl.paga(adata, color='leiden', save='_paga')
+
+# Gene set scoring (optional)
+# example_gene_set = ['CD3D', 'CD3E', 'CD3G']
+# sc.tl.score_genes(adata, example_gene_set, score_name='T_cell_score')
+# sc.pl.umap(adata, color='T_cell_score', save='_gene_set_score')
+
+# ============================================================================
+# 11. SAVE RESULTS
+# ============================================================================
+
+print("\n" + "=" * 80)
+print("SAVING RESULTS")
+print("=" * 80)
+
+import os
+os.makedirs(OUTPUT_DIR, exist_ok=True)
+
+# Save processed AnnData object
+adata.write(f'{OUTPUT_DIR}/processed_data.h5ad')
+print(f"Saved processed data to {OUTPUT_DIR}/processed_data.h5ad")
+
+# Export metadata
+adata.obs.to_csv(f'{OUTPUT_DIR}/cell_metadata.csv')
+adata.var.to_csv(f'{OUTPUT_DIR}/gene_metadata.csv')
+print(f"Saved metadata to {OUTPUT_DIR}/")
+
+# Export marker genes
+for cluster in adata.obs['leiden'].unique():
+    markers = sc.get.rank_genes_groups_df(adata, group=cluster)
+    markers.to_csv(f'{OUTPUT_DIR}/markers_cluster_{cluster}.csv', index=False)
+print(f"Saved marker genes to {OUTPUT_DIR}/")
+
+# ============================================================================
+# 12. SUMMARY
+# ============================================================================
+
+print("\n" + "=" * 80)
+print("ANALYSIS SUMMARY")
+print("=" * 80)
+
+print(f"\nFinal dataset:")
+print(f"  Cells: {adata.n_obs}")
+print(f"  Genes: {adata.n_vars}")
+print(f"  Clusters: {len(adata.obs['leiden'].unique())}")
+
+print(f"\nCell type distribution:")
+print(adata.obs['cell_type'].value_counts())
+
+print("\n" + "=" * 80)
+print("ANALYSIS COMPLETE")
+print("=" * 80)

package/bundled-skills/scanpy/references/api_reference.md

@@ -0,0 +1,251 @@
+# Scanpy API Quick Reference
+
+Quick reference for commonly used scanpy functions organized by module.
+
+## Import Convention
+
+```python
+import scanpy as sc
+```
+
+## Reading and Writing Data (sc.read_*)
+
+### Reading Functions
+
+```python
+sc.read_10x_h5(filename)                    # Read 10X HDF5 file
+sc.read_10x_mtx(path)                       # Read 10X mtx directory
+sc.read_h5ad(filename)                      # Read h5ad (AnnData) file
+sc.read_csv(filename)                       # Read CSV file
+sc.read_excel(filename)                     # Read Excel file
+sc.read_loom(filename)                      # Read loom file
+sc.read_text(filename)                      # Read text file
+sc.read_visium(path)                        # Read Visium spatial data
+```
+
+### Writing Functions
+
+```python
+adata.write_h5ad(filename)                  # Write to h5ad format
+adata.write_csvs(dirname)                   # Write to CSV files
+adata.write_loom(filename)                  # Write to loom format
+adata.write_zarr(filename)                  # Write to zarr format
+```
+
+## Preprocessing (sc.pp.*)
+
+### Quality Control
+
+```python
+sc.pp.calculate_qc_metrics(adata, qc_vars=['mt'], inplace=True)
+sc.pp.filter_cells(adata, min_genes=200)
+sc.pp.filter_genes(adata, min_cells=3)
+```
+
+### Normalization and Transformation
+
+```python
+sc.pp.normalize_total(adata, target_sum=1e4)    # Normalize to target sum
+sc.pp.log1p(adata)                               # Log(x + 1) transformation
+sc.pp.sqrt(adata)                                # Square root transformation
+```
+
+### Feature Selection
+
+```python
+sc.pp.highly_variable_genes(adata, min_mean=0.0125, max_mean=3, min_disp=0.5)
+sc.pp.highly_variable_genes(adata, flavor='seurat_v3', n_top_genes=2000)
+```
+
+### Scaling and Regression
+
+```python
+sc.pp.scale(adata, max_value=10)                      # Scale to unit variance
+sc.pp.regress_out(adata, ['total_counts', 'pct_counts_mt'])  # Regress out unwanted variation
+```
+
+### Dimensionality Reduction (Preprocessing)
+
+```python
+sc.pp.pca(adata, n_comps=50)                     # Principal component analysis
+sc.pp.neighbors(adata, n_neighbors=10, n_pcs=40) # Compute neighborhood graph
+```
+
+### Batch Correction
+
+```python
+sc.pp.combat(adata, key='batch')                 # ComBat batch correction
+```
+
+## Tools (sc.tl.*)
+
+### Dimensionality Reduction
+
+```python
+sc.tl.pca(adata, svd_solver='arpack')            # PCA
+sc.tl.umap(adata)                                 # UMAP embedding
+sc.tl.tsne(adata)                                 # t-SNE embedding
+sc.tl.diffmap(adata)                              # Diffusion map
+sc.tl.draw_graph(adata, layout='fa')             # Force-directed graph
+```
+
+### Clustering
+
+```python
+sc.tl.leiden(adata, resolution=0.5)              # Leiden clustering (recommended)
+sc.tl.louvain(adata, resolution=0.5)             # Louvain clustering
+sc.tl.kmeans(adata, n_clusters=10)               # K-means clustering
+```
+
+### Marker Genes and Differential Expression
+
+```python
+sc.tl.rank_genes_groups(adata, groupby='leiden', method='wilcoxon')
+sc.tl.rank_genes_groups(adata, groupby='leiden', method='t-test')
+sc.tl.rank_genes_groups(adata, groupby='leiden', method='logreg')
+
+# Get results as dataframe
+sc.get.rank_genes_groups_df(adata, group='0')
+```
+
+### Trajectory Inference
+
+```python
+sc.tl.paga(adata, groups='leiden')               # PAGA trajectory
+sc.tl.dpt(adata)                                  # Diffusion pseudotime
+```
+
+### Gene Scoring
+
+```python
+sc.tl.score_genes(adata, gene_list, score_name='score')
+sc.tl.score_genes_cell_cycle(adata, s_genes, g2m_genes)
+```
+
+### Embeddings and Projections
+
+```python
+sc.tl.ingest(adata, adata_ref)                   # Map to reference
+sc.tl.embedding_density(adata, basis='umap', groupby='leiden')
+```
+
+## Plotting (sc.pl.*)
+
+### Basic Embeddings
+
+```python
+sc.pl.umap(adata, color='leiden')                # UMAP plot
+sc.pl.tsne(adata, color='gene_name')             # t-SNE plot
+sc.pl.pca(adata, color='leiden')                 # PCA plot
+sc.pl.diffmap(adata, color='leiden')             # Diffusion map plot
+```
+
+### Heatmaps and Dot Plots
+
+```python
+sc.pl.heatmap(adata, var_names=genes, groupby='leiden')
+sc.pl.dotplot(adata, var_names=genes, groupby='leiden')
+sc.pl.matrixplot(adata, var_names=genes, groupby='leiden')
+sc.pl.stacked_violin(adata, var_names=genes, groupby='leiden')
+```
+
+### Violin and Scatter Plots
+
+```python
+sc.pl.violin(adata, keys=['gene1', 'gene2'], groupby='leiden')
+sc.pl.scatter(adata, x='gene1', y='gene2', color='leiden')
+```
+
+### Marker Gene Visualization
+
+```python
+sc.pl.rank_genes_groups(adata, n_genes=25, sharey=False)
+sc.pl.rank_genes_groups_violin(adata, groups='0')
+sc.pl.rank_genes_groups_heatmap(adata, n_genes=10)
+sc.pl.rank_genes_groups_dotplot(adata, n_genes=5)
+```
+
+### Trajectory Visualization
+
+```python
+sc.pl.paga(adata, color='leiden')                # PAGA graph
+sc.pl.dpt_timeseries(adata)                      # DPT timeseries
+```
+
+### QC Plots
+
+```python
+sc.pl.highest_expr_genes(adata, n_top=20)
+sc.pl.violin(adata, ['n_genes_by_counts', 'total_counts', 'pct_counts_mt'])
+sc.pl.scatter(adata, x='total_counts', y='n_genes_by_counts')
+```
+
+### Advanced Plots
+
+```python
+sc.pl.dendrogram(adata, groupby='leiden')
+sc.pl.correlation_matrix(adata, groupby='leiden')
+sc.pl.tracksplot(adata, var_names=genes, groupby='leiden')
+```
+
+## Common Parameters
+
+### Color Parameters
+- `color`: Variable(s) to color by (gene name, obs column)
+- `use_raw`: Use `.raw` attribute of adata
+- `palette`: Color palette to use
+- `vmin`, `vmax`: Color scale limits
+
+### Layout Parameters
+- `basis`: Embedding basis ('umap', 'tsne', 'pca', etc.)
+- `legend_loc`: Legend location ('on data', 'right margin', etc.)
+- `size`: Point size
+- `alpha`: Point transparency
+
+### Saving Parameters
+- `save`: Filename to save plot
+- `show`: Whether to show plot
+
+## AnnData Structure
+
+```python
+adata.X                    # Expression matrix (cells × genes)
+adata.obs                  # Cell annotations (DataFrame)
+adata.var                  # Gene annotations (DataFrame)
+adata.uns                  # Unstructured annotations (dict)
+adata.obsm                 # Multi-dimensional cell annotations (e.g., PCA, UMAP)
+adata.varm                 # Multi-dimensional gene annotations
+adata.layers               # Additional data layers
+adata.raw                  # Raw data backup
+
+# Access
+adata.obs_names            # Cell barcodes
+adata.var_names            # Gene names
+adata.shape                # (n_cells, n_genes)
+
+# Slicing
+adata[cell_indices, gene_indices]
+adata[:, adata.var_names.isin(gene_list)]
+adata[adata.obs['leiden'] == '0', :]
+```
+
+## Settings
+
+```python
+sc.settings.verbosity = 3              # 0=error, 1=warning, 2=info, 3=hint
+sc.settings.set_figure_params(dpi=80, facecolor='white')
+sc.settings.autoshow = False           # Don't show plots automatically
+sc.settings.autosave = True            # Autosave figures
+sc.settings.figdir = './figures/'      # Figure directory
+sc.settings.cachedir = './cache/'      # Cache directory
+sc.settings.n_jobs = 8                 # Number of parallel jobs
+```
+
+## Useful Utilities
+
+```python
+sc.logging.print_versions()            # Print version information
+sc.logging.print_memory_usage()        # Print memory usage
+adata.copy()                           # Create a copy of AnnData object
+adata.concatenate([adata1, adata2])    # Concatenate AnnData objects
+```