Plink2 Gwas Analysis

# Skip install if already present
if command -v plink2 >/dev/null 2>&1; then
    echo "plink2 already installed: $(plink2 --version)"
else
    # Download PLINK2 pre-compiled binary (Linux)
    wget https://s3.amazonaws.com/plink2-assets/alpha6/plink2_linux_avx2_20241112.zip
    unzip plink2_linux_avx2_20241112.zip
    chmod +x plink2
    export PATH="$PWD:$PATH"

    # macOS
    # wget https://s3.amazonaws.com/plink2-assets/alpha6/plink2_mac_20241112.zip
    # unzip plink2_mac_20241112.zip

    plink2 --version
    # PLINK v2.00a6LM
fi

# Python for downstream analysis
pip install pandas numpy matplotlib scipy

# Run GWAS: linear regression for quantitative trait
plink2 \
    --bfile cohort_qc \
    --pheno phenotypes.txt \
    --covar covariates.txt \
    --linear hide-covar \
    --out results/gwas_result \
    --threads 8

# View top hits
head results/gwas_result.*.glm.linear | sort -k12,12g | head -20

# Convert VCF to PLINK binary
plink2 \
    --vcf cohort_genotyped.vcf.gz \
    --make-bed \
    --out cohort_plink \
    --threads 8

# Convert BGEN (imputed data from Michigan/TopMed imputation server)
plink2 \
    --bgen cohort_imputed.bgen ref-first \
    --sample cohort_imputed.sample \
    --make-bed \
    --out cohort_imputed_plink \
    --threads 8

echo "Files created:"
ls -lh cohort_plink.{bed,bim,fam}
echo "Samples: $(wc -l < cohort_plink.fam)"
echo "Variants: $(wc -l < cohort_plink.bim)"

# Compute per-sample and per-variant missingness
plink2 \
    --bfile cohort_plink \
    --missing \
    --out qc/sample_missingness \
    --threads 8

# Remove samples with > 2% missingness and variants with > 5% missing
plink2 \
    --bfile cohort_plink \
    --mind 0.02 \
    --geno 0.05 \
    --make-bed \
    --out cohort_sample_qc \
    --threads 8

echo "After sample QC:"
echo "Samples: $(wc -l < cohort_sample_qc.fam)"
echo "Variants: $(wc -l < cohort_sample_qc.bim)"

# Variant QC: MAF, HWE, missingness
plink2 \
    --bfile cohort_sample_qc \
    --maf 0.01 \
    --hwe 1e-6 \
    --geno 0.05 \
    --make-bed \
    --out cohort_variantqc \
    --threads 8

echo "After variant QC:"
echo "Variants remaining: $(wc -l < cohort_variantqc.bim)"

# For imputed data: also filter by INFO score (using VCF INFO field)
# plink2 --bfile cohort_variantqc --var-min-qual 0.8 --make-bed --out cohort_info_qc

# LD pruning: remove one variant from each pair with r² > 0.2
plink2 \
    --bfile cohort_variantqc \
    --indep-pairwise 50 5 0.2 \
    --out qc/ld_pruned \
    --threads 8

# Compute PCA on LD-pruned variants (top 20 PCs)
plink2 \
    --bfile cohort_variantqc \
    --extract qc/ld_pruned.prune.in \
    --pca 20 \
    --out pca/cohort_pca \
    --threads 8

echo "PCA files: pca/cohort_pca.eigenvec (PCs) and pca/cohort_pca.eigenval (variance)"
head pca/cohort_pca.eigenvec

# Case-control GWAS: logistic regression with covariates
plink2 \
    --bfile cohort_variantqc \
    --pheno phenotypes.txt \
    --1 \
    --covar covariates.txt \
    --covar-variance-standardize \
    --logistic hide-covar \
    --ci 0.95 \
    --out results/gwas_cc \
    --threads 8

# Quantitative trait GWAS: linear regression
plink2 \
    --bfile cohort_variantqc \
    --pheno phenotypes.txt \
    --covar covariates.txt \
    --covar-variance-standardize \
    --linear hide-covar \
    --ci 0.95 \
    --out results/gwas_qt \
    --threads 8

echo "GWAS complete. Files: results/gwas_*.glm.*"
wc -l results/gwas_qt.*.glm.linear

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import chi2

# Load GWAS results (PLINK2 linear output)
df = pd.read_csv("results/gwas_qt.PHENO1.glm.linear", sep="\t",
                 usecols=["#CHROM", "POS", "ID", "P"])
df.columns = ["CHR", "POS", "SNP", "P"]
df = df.dropna(subset=["P"])
df["P"] = pd.to_numeric(df["P"], errors="coerce")
df = df[df["P"] > 0].copy()
df["-log10P"] = -np.log10(df["P"])

print(f"Variants: {len(df)}")
print(f"Genome-wide significant (p<5e-8): {(df['P'] < 5e-8).sum()}")

# Manhattan plot
fig, ax = plt.subplots(figsize=(14, 4))
colors = plt.cm.Set1.colors
chrom_pos = 0
ticks = []
for chrom, group in df.groupby("CHR", sort=False):
    col = colors[int(chrom) % 2] if str(chrom).isdigit() else "gray"
    ax.scatter(group["POS"] + chrom_pos, group["-log10P"],
               c=[col], s=2, alpha=0.7)
    ticks.append((chrom_pos + group["POS"].mean(), str(chrom)))
    chrom_pos += group["POS"].max() + 1e7

ax.axhline(-np.log10(5e-8), color="red", linestyle="--", lw=1, label="p=5×10⁻⁸")
ax.set_xticks([t[0] for t in ticks[::2]])
ax.set_xticklabels([t[1] for t in ticks[::2]], fontsize=6)
ax.set_xlabel("Chromosome")
ax.set_ylabel("-log₁₀(p)")
ax.set_title("GWAS Manhattan Plot")
plt.tight_layout()
plt.savefig("manhattan.png", dpi=150)
print("Saved: manhattan.png")

# Compute kinship coefficients (King-robust estimator)
plink2 \
    --bfile cohort_variantqc \
    --extract qc/ld_pruned.prune.in \
    --king-cutoff 0.0625 \
    --out qc/kinship \
    --threads 8

# Remove related individuals (king-cutoff auto-generates exclusion list)
plink2 \
    --bfile cohort_variantqc \
    --remove qc/kinship.king.cutoff.out.id \
    --make-bed \
    --out cohort_unrelated \
    --threads 8

echo "After relatedness QC: $(wc -l < cohort_unrelated.fam) samples"

import pandas as pd
import numpy as np

def load_gwas_results(filepath: str, p_threshold: float = 5e-8) -> pd.DataFrame:
    """Load PLINK2 GWAS linear/logistic output and return genome-wide significant hits."""
    df = pd.read_csv(filepath, sep="\t",
                     usecols=["#CHROM", "POS", "ID", "REF", "ALT", "A1", "BETA", "SE", "P"])
    df.columns = ["CHR", "POS", "SNP", "REF", "ALT", "A1", "BETA", "SE", "P"]
    df = df.dropna(subset=["P"])
    df["P"] = pd.to_numeric(df["P"], errors="coerce")
    sig = df[df["P"] < p_threshold].sort_values("P")
    return sig

# Load results for one phenotype
hits = load_gwas_results("results/gwas_qt.PHENO1.glm.linear")
print(f"Genome-wide significant loci: {len(hits)}")
print(hits.head(10)[["CHR", "POS", "SNP", "BETA", "SE", "P"]])
hits.to_csv("gwas_top_hits.tsv", sep="\t", index=False)