I am a Biotechnology Engineering graduate with a passion for decoding biological complexity using computational tools. My work bridges the gap between wet-lab biology and data science, focusing on Transcriptomics, Structure-based Drug Design, and Systems Biology.
- Languages: Python (Pandas, Scipy, NetworkX), R (Seurat, ClusterProfiler).
- Bioinformatics: scRNA-seq Analysis, Molecular Docking (AutoDock), Network Topology.
- Machine Learning: KNN, Classification, ROC Analysis, Feature Extraction.
- Tools: PyMOL, Discovery Studio, SwissADME, STRING DB.
Here is an overview of my key research projects, demonstrating my ability to analyze multi-omics data and develop therapeutic hypotheses.
Project: Drug Response Profiling of TNBC using scRNA-seq
- Objective: Dissected the tumor microenvironment of Triple-Negative Breast Cancer to understand resistance to chemo-immunotherapy.
- Key Skills: R, Seurat, Differential Gene Expression, Pathway Enrichment.
- Outcome: Identified IL1R2+ M2 Macrophages and FOXP3+ Tregs as drivers of resistance; proposed 3 novel therapeutic targets.
- View Repository »
Project: Multi-Target Drug Design for Alzheimer’s Disease
- Objective: Screened natural compounds to inhibit AChE and BACE1 enzymes and designed a hydrogel delivery system for BBB permeability.
- Key Skills: Molecular Docking (AutoDock), ADMET Profiling (SwissADME), Protein Validation.
- Outcome: Identified Withanolide A (-13.90 kcal/mol) as a high-affinity dual-inhibitor.
- View Repository »
Project: Host-Virus Interaction Network Analysis (SARS-CoV-2 & Influenza)
- Objective: Developed a Python pipeline to map conserved host dependency factors and "Bridge Proteins" connecting viral interactomes.
- Key Skills: Python, NetworkX, Graph Theory, Statistical Validation (Hypergeometric test).
- Outcome: Discovered a hidden PI3K/AKT signaling hub connecting both viruses; prioritized TCF12 as a broad-spectrum antiviral target.
- View Repository »
Project: Motor Imagery EEG Signal Classification
- Objective: Built a Machine Learning pipeline to classify left vs. right-hand movements from noisy EEG signals for BCI applications.
- Key Skills: Signal Processing (FFT), Feature Engineering (Frequency Domain), Cubic KNN.
- Outcome: Achieved 97.6% accuracy (Class 1) using a Cubic KNN classifier with Peak Frequency features.
- View Repository »
"Driven by data, inspired by biology."