WORKS

Bioinformatic Projects

Bioinformatics projects focused on sequencing analysis, reproducible workflows, genomics pipelines, and data visualization.

Nextflow sequencing pipeline workflow

Multi-Assay Bulk Sequencing Pipeline

  • Designed modular Nextflow DSL2 workflows for RNA-seq, ATAC-seq, and ChIP-seq analysis.
  • Automated FASTQ QC, trimming, alignment, quantification, and organized output generation.
  • Supported both local and HPC execution for scalable and reproducible analysis.
Nextflow Docker HPC NGS Bulk Sequencing RNA-seq ATAC-seq ChIP-seq
View Project GitHub
ATAC-seq and RNA-seq project visualization

ATAC-seq & RNA-seq Analysis of TNBC

  • Integrated chromatin accessibility and gene expression data to study regulatory patterns in triple-negative breast cancer.
  • Identified 1,435 differentially accessible regions using statistical testing with FDR < 0.05.
  • Performed GO, KEGG, and GSEA enrichment analysis to interpret biological pathways.
R DESeq2 DiffBind ATAC-seq RNA-seq Functional Enrichment Analysis Gene-Set Enrichment Analysis
View Project GitHub
Breast cancer machine learning project

Breast Cancer Classification using KNN

  • Built a K-nearest-neighbors classifier using the Wisconsin Breast Cancer dataset.
  • Applied preprocessing, normalization, cross-validation, and model evaluation.
  • Achieved over 95% accuracy and reported results using confusion matrix and ROC curve.
R Machine Learning KNN Classification Supervised Learning Cross Validation Feature Scaling Confusion Matrix ROC Curve
View Project GitHub