All Projects Bioinformatics · ML · NGS

Genomics NGS Pipeline

A full bioinformatics research pipeline built to demonstrate production-grade genomics engineering. Simulates realistic population-stratified genotype data using the Balding-Nichols model, processes variants through a Snakemake workflow, and applies both classical population genetics statistics and supervised ML classification. Includes an interactive Tableau dashboard and LLM-powered variant reporter.

Public View on GitHub ↗
Problem

Classifying population ancestry from simulated genomic variation.

Approach

Built an end-to-end NGS (next-generation sequencing) workflow that takes raw DNA sequencing reads all the way through alignment, variant calling, and ML classification.

Tools
Python Biopython Scikit-Learn Snakemake GATK BWA-MEM Tableau Pandas NumPy Jupyter
Result

Achieved 79% accuracy and 0.96 macro ROC-AUC on a four-population simulated cohort.

Why It Matters

Demonstrates applied genomics, reproducible bioinformatics workflows, variant analysis, and machine learning evaluation — the core skill set behind population genetics research and clinical genomics products.

Project Highlights

  • Simulated 450 samples × 500 SNPs across 4 populations (Fst ≈ 0.015) using Balding-Nichols model
  • Snakemake NGS workflow: FASTQ → BWA-MEM alignment → GATK variant calling → VCF
  • Random Forest ancestry classifier: 79% accuracy, AUC 0.96 on held-out test set
  • Biopython nucleotide diversity analysis: π, Watterson's θ, Tajima's D per population
  • Interactive Tableau dashboard (5 sheets) for variant exploration and population comparison
  • LLM variant reporter generating natural-language summaries from top SNPs
  • CI/CD pipeline running full workflow on every push via GitHub Actions

Tech Stack

Python Biopython Scikit-Learn Snakemake GATK BWA-MEM Tableau Pandas NumPy Jupyter

Domain Tags

Bioinformatics Machine Learning NGS Population Genetics

Infographics

NGS Pipeline: Read Alignment and Variant Calling

NGS Pipeline: Read Alignment and Variant Calling

NGS Pipeline: Population Genetics Analysis

NGS Pipeline: Population Genetics Analysis

NGS Pipeline: ML Classification

NGS Pipeline: ML Classification

NGS Pipeline: Visualization and Reporting

NGS Pipeline: Visualization and Reporting

Screenshots & Outputs

Confusion matrix: Random Forest ancestry classifier

Confusion matrix: Random Forest ancestry classifier

PCA scatter: 450 samples across 4 populations

PCA scatter: 450 samples across 4 populations

Nucleotide diversity panel (π, θ, Tajima's D)

Nucleotide diversity panel (π, θ, Tajima's D)

Interactive Tableau dashboard

Interactive Tableau dashboard

Pipeline Overview

Balding-Nichols Simulation (450 samples × 500 SNPs)
  ↓
VCF Generation → MAF QC Filtering
  ↓
BWA-MEM Alignment → GATK Variant Calling
  ↓
PCA Dimensionality Reduction + Random Forest Ancestry Classifier
  ↓
Biopython Nucleotide Diversity (π · θ · Tajima's D)
  ↓
Tableau Dashboard + LLM Variant Reporter + CI/CD