import scanpy as sc
import numpy as np

# Calculate mitochondrial gene percentage
adata.var['mt'] = adata.var_names.str.startswith('MT-')
sc.pp.calculate_qc_metrics(adata, qc_vars=['mt'], percent_top=None, log1p=False, inplace=True)

# Key metrics added to adata.obs:
# - n_genes_by_counts: genes detected per cell
# - total_counts: total UMI counts per cell
# - pct_counts_mt: percentage mitochondrial

import matplotlib.pyplot as plt

sc.pl.violin(adata, ['n_genes_by_counts', 'total_counts', 'pct_counts_mt'], jitter=0.4, multi_panel=True)
sc.pl.scatter(adata, x='total_counts', y='pct_counts_mt')
sc.pl.scatter(adata, x='total_counts', y='n_genes_by_counts')

# Filter cells by QC metrics
sc.pp.filter_cells(adata, min_genes=200)
sc.pp.filter_cells(adata, max_genes=5000)

# Filter by mitochondrial percentage
adata = adata[adata.obs['pct_counts_mt'] < 20, :].copy()

# Filter genes
sc.pp.filter_genes(adata, min_cells=3)

print(f'After filtering: {adata.n_obs} cells, {adata.n_vars} genes')

# Store raw counts before normalization
adata.raw = adata.copy()
# Or use layers
adata.layers['counts'] = adata.X.copy()

# Library size normalization (normalize to 10,000 counts per cell)
sc.pp.normalize_total(adata, target_sum=1e4)

# Log transform
sc.pp.log1p(adata)

# Identify highly variable genes (default: top 2000)
sc.pp.highly_variable_genes(adata, n_top_genes=2000, flavor='seurat_v3', layer='counts')

# Visualize
sc.pl.highly_variable_genes(adata)

# Check results
print(f'Highly variable genes: {adata.var.highly_variable.sum()}')

# Keep only highly variable genes for downstream analysis
adata_hvg = adata[:, adata.var.highly_variable].copy()

# Scale to unit variance and zero mean
sc.pp.scale(adata, max_value=10)

# Regress out unwanted variation (e.g., cell cycle, mitochondrial)
sc.pp.regress_out(adata, ['total_counts', 'pct_counts_mt'])

import scanpy as sc

adata = sc.read_10x_mtx('filtered_feature_bc_matrix/')

# QC
adata.var['mt'] = adata.var_names.str.startswith('MT-')
sc.pp.calculate_qc_metrics(adata, qc_vars=['mt'], inplace=True)

# Filter
sc.pp.filter_cells(adata, min_genes=200)
sc.pp.filter_genes(adata, min_cells=3)
adata = adata[adata.obs['pct_counts_mt'] < 20, :].copy()

# Store raw
adata.raw = adata.copy()

# Normalize
sc.pp.normalize_total(adata, target_sum=1e4)
sc.pp.log1p(adata)

# HVGs
sc.pp.highly_variable_genes(adata, n_top_genes=2000)

# Scale
adata = adata[:, adata.var.highly_variable].copy()
sc.pp.scale(adata, max_value=10)

library(Seurat)
library(ggplot2)

# Calculate mitochondrial percentage
seurat_obj[['percent.mt']] <- PercentageFeatureSet(seurat_obj, pattern = '^MT-')

# View QC metrics
head(seurat_obj@meta.data)

# Violin plots
VlnPlot(seurat_obj, features = c('nFeature_RNA', 'nCount_RNA', 'percent.mt'), ncol = 3)

# Scatter plots
plot1 <- FeatureScatter(seurat_obj, feature1 = 'nCount_RNA', feature2 = 'percent.mt')
plot2 <- FeatureScatter(seurat_obj, feature1 = 'nCount_RNA', feature2 = 'nFeature_RNA')
plot1 + plot2

# Filter by QC metrics
seurat_obj <- subset(seurat_obj,
    subset = nFeature_RNA > 200 &
             nFeature_RNA < 5000 &
             percent.mt < 20)

cat('After filtering:', ncol(seurat_obj), 'cells\n')

# Standard log normalization
seurat_obj <- NormalizeData(seurat_obj, normalization.method = 'LogNormalize', scale.factor = 10000)

# SCTransform - recommended for most workflows
# Combines normalization, scaling, and HVG selection
seurat_obj <- SCTransform(seurat_obj, vars.to.regress = 'percent.mt', verbose = FALSE)

# Identify highly variable features (if not using SCTransform)
seurat_obj <- FindVariableFeatures(seurat_obj, selection.method = 'vst', nfeatures = 2000)

# Visualize
top10 <- head(VariableFeatures(seurat_obj), 10)
plot1 <- VariableFeaturePlot(seurat_obj)
plot2 <- LabelPoints(plot = plot1, points = top10, repel = TRUE)
plot2

# Scale data (if not using SCTransform)
all.genes <- rownames(seurat_obj)
seurat_obj <- ScaleData(seurat_obj, features = all.genes)

# Or scale only variable features (faster)
seurat_obj <- ScaleData(seurat_obj)

# Regress out unwanted variation during scaling
seurat_obj <- ScaleData(seurat_obj, vars.to.regress = c('percent.mt', 'nCount_RNA'))

library(Seurat)

counts <- Read10X(data.dir = 'filtered_feature_bc_matrix/')
seurat_obj <- CreateSeuratObject(counts = counts, min.cells = 3, min.features = 200)

# QC
seurat_obj[['percent.mt']] <- PercentageFeatureSet(seurat_obj, pattern = '^MT-')

# Filter
seurat_obj <- subset(seurat_obj,
    subset = nFeature_RNA > 200 & nFeature_RNA < 5000 & percent.mt < 20)

# Normalize
seurat_obj <- NormalizeData(seurat_obj)

# HVGs
seurat_obj <- FindVariableFeatures(seurat_obj, nfeatures = 2000)

# Scale
seurat_obj <- ScaleData(seurat_obj)

library(Seurat)

counts <- Read10X(data.dir = 'filtered_feature_bc_matrix/')
seurat_obj <- CreateSeuratObject(counts = counts, min.cells = 3, min.features = 200)

# QC
seurat_obj[['percent.mt']] <- PercentageFeatureSet(seurat_obj, pattern = '^MT-')

# Filter
seurat_obj <- subset(seurat_obj,
    subset = nFeature_RNA > 200 & nFeature_RNA < 5000 & percent.mt < 20)

# SCTransform (does normalization, HVG, and scaling)
seurat_obj <- SCTransform(seurat_obj, vars.to.regress = 'percent.mt', verbose = FALSE)