PyDESeq2 Differential Expression

import pandas as pd
from pydeseq2.dds import DeseqDataSet
from pydeseq2.ds import DeseqStats

# 1. Load data
counts_df = pd.read_csv("counts.csv", index_col=0).T  # Transpose to samples × genes
metadata = pd.read_csv("metadata.csv", index_col=0)

# 2. Filter low-count genes
genes_to_keep = counts_df.columns[counts_df.sum(axis=0) >= 10]
counts_df = counts_df[genes_to_keep]

# 3. Initialize and fit DESeq2
dds = DeseqDataSet(
    counts=counts_df,
    metadata=metadata,
    design="~condition",
    refit_cooks=True
)
dds.deseq2()

# 4. Perform statistical testing
ds = DeseqStats(dds, contrast=["condition", "treated", "control"])
ds.summary()

# 5. Access results
results = ds.results_df
significant = results[results.padj < 0.05]
print(f"Found {len(significant)} significant genes")

# From CSV (typical format: genes × samples, needs transpose)
counts_df = pd.read_csv("counts.csv", index_col=0).T
metadata = pd.read_csv("metadata.csv", index_col=0)

# From TSV
counts_df = pd.read_csv("counts.tsv", sep="\t", index_col=0).T

# From AnnData
import anndata as ad
adata = ad.read_h5ad("data.h5ad")
counts_df = pd.DataFrame(adata.X, index=adata.obs_names, columns=adata.var_names)
metadata = adata.obs

# Remove low-count genes
genes_to_keep = counts_df.columns[counts_df.sum(axis=0) >= 10]
counts_df = counts_df[genes_to_keep]

# Remove samples with missing metadata
samples_to_keep = ~metadata.condition.isna()
counts_df = counts_df.loc[samples_to_keep]
metadata = metadata.loc[samples_to_keep]

design = "~condition"  # Simple two-group comparison

design = "~batch + condition"  # Control for batch effects
design = "~age + condition"     # Include continuous covariate
design = "~group + condition + group:condition"  # Interaction effects

from pydeseq2.dds import DeseqDataSet

dds = DeseqDataSet(
    counts=counts_df,
    metadata=metadata,
    design="~condition",
    refit_cooks=True,  # Refit after removing outliers
    n_cpus=1           # Parallel processing (adjust as needed)
)

# Run the complete DESeq2 pipeline
dds.deseq2()

from pydeseq2.ds import DeseqStats

ds = DeseqStats(
    dds,
    contrast=["condition", "treated", "control"],  # Test treated vs control
    alpha=0.05,                # Significance threshold
    cooks_filter=True,         # Filter outliers
    independent_filter=True    # Filter low-power tests
)

ds.summary()

ds.lfc_shrink()  # Applies apeGLM shrinkage

import pickle

# Export results as CSV
ds.results_df.to_csv("deseq2_results.csv")

# Save significant genes only
significant = ds.results_df[ds.results_df.padj < 0.05]
significant.to_csv("significant_genes.csv")

# Save DeseqDataSet for later use
with open("dds_result.pkl", "wb") as f:
    pickle.dump(dds.to_picklable_anndata(), f)

dds = DeseqDataSet(counts=counts_df, metadata=metadata, design="~condition")
dds.deseq2()

ds = DeseqStats(dds, contrast=["condition", "treated", "control"])
ds.summary()

results = ds.results_df
significant = results[results.padj < 0.05]

dds = DeseqDataSet(counts=counts_df, metadata=metadata, design="~condition")
dds.deseq2()

treatments = ["treatment_A", "treatment_B", "treatment_C"]
all_results = {}

for treatment in treatments:
    ds = DeseqStats(dds, contrast=["condition", treatment, "control"])
    ds.summary()
    all_results[treatment] = ds.results_df

    sig_count = len(ds.results_df[ds.results_df.padj < 0.05])
    print(f"{treatment}: {sig_count} significant genes")

# Include batch in design
dds = DeseqDataSet(counts=counts_df, metadata=metadata, design="~batch + condition")
dds.deseq2()

# Test condition while controlling for batch
ds = DeseqStats(dds, contrast=["condition", "treated", "control"])
ds.summary()

# Ensure continuous variable is numeric
metadata["age"] = pd.to_numeric(metadata["age"])

dds = DeseqDataSet(counts=counts_df, metadata=metadata, design="~age + condition")
dds.deseq2()

ds = DeseqStats(dds, contrast=["condition", "treated", "control"])
ds.summary()

# Basic usage
python scripts/run_deseq2_analysis.py \
  --counts counts.csv \
  --metadata metadata.csv \
  --design "~condition" \
  --contrast condition treated control \
  --output results/

# With additional options
python scripts/run_deseq2_analysis.py \
  --counts counts.csv \
  --metadata metadata.csv \
  --design "~batch + condition" \
  --contrast condition treated control \
  --output results/ \
  --min-counts 10 \
  --alpha 0.05 \
  --n-cpus 4 \
  --plots

# Filter by adjusted p-value
significant = ds.results_df[ds.results_df.padj < 0.05]

# Filter by both significance and effect size
sig_and_large = ds.results_df[
    (ds.results_df.padj < 0.05) &
    (abs(ds.results_df.log2FoldChange) > 1)
]

# Separate up- and down-regulated
upregulated = significant[significant.log2FoldChange > 0]
downregulated = significant[significant.log2FoldChange < 0]

print(f"Upregulated: {len(upregulated)}")
print(f"Downregulated: {len(downregulated)}")

# Sort by adjusted p-value
top_by_padj = ds.results_df.sort_values("padj").head(20)

# Sort by absolute fold change (use shrunk values)
ds.lfc_shrink()
ds.results_df["abs_lfc"] = abs(ds.results_df.log2FoldChange)
top_by_lfc = ds.results_df.sort_values("abs_lfc", ascending=False).head(20)

# Sort by a combined metric
ds.results_df["score"] = -np.log10(ds.results_df.padj) * abs(ds.results_df.log2FoldChange)
top_combined = ds.results_df.sort_values("score", ascending=False).head(20)

# Check normalization (size factors should be close to 1)
print("Size factors:", dds.obsm["size_factors"])

# Examine dispersion estimates
import matplotlib.pyplot as plt
plt.hist(dds.varm["dispersions"], bins=50)
plt.xlabel("Dispersion")
plt.ylabel("Frequency")
plt.title("Dispersion Distribution")
plt.show()

# Check p-value distribution (should be mostly flat with peak near 0)
plt.hist(ds.results_df.pvalue.dropna(), bins=50)
plt.xlabel("P-value")
plt.ylabel("Frequency")
plt.title("P-value Distribution")
plt.show()

import matplotlib.pyplot as plt
import numpy as np

results = ds.results_df.copy()
results["-log10(padj)"] = -np.log10(results.padj)

plt.figure(figsize=(10, 6))
significant = results.padj < 0.05

plt.scatter(
    results.loc[~significant, "log2FoldChange"],
    results.loc[~significant, "-log10(padj)"],
    alpha=0.3, s=10, c='gray', label='Not significant'
)
plt.scatter(
    results.loc[significant, "log2FoldChange"],
    results.loc[significant, "-log10(padj)"],
    alpha=0.6, s=10, c='red', label='padj < 0.05'
)

plt.axhline(-np.log10(0.05), color='blue', linestyle='--', alpha=0.5)
plt.xlabel("Log2 Fold Change")
plt.ylabel("-Log10(Adjusted P-value)")
plt.title("Volcano Plot")
plt.legend()
plt.savefig("volcano_plot.png", dpi=300)

plt.figure(figsize=(10, 6))

plt.scatter(
    np.log10(results.loc[~significant, "baseMean"] + 1),
    results.loc[~significant, "log2FoldChange"],
    alpha=0.3, s=10, c='gray'
)
plt.scatter(
    np.log10(results.loc[significant, "baseMean"] + 1),
    results.loc[significant, "log2FoldChange"],
    alpha=0.6, s=10, c='red'
)

plt.axhline(0, color='blue', linestyle='--', alpha=0.5)
plt.xlabel("Log10(Base Mean + 1)")
plt.ylabel("Log2 Fold Change")
plt.title("MA Plot")
plt.savefig("ma_plot.png", dpi=300)