Hi, I’m Dr. Vivek Ruhela , a researcher passionate about unraveling the genetic and molecular architecture of complex diseases by integrating genetics, genomics, bioinformatics, and explainable artificial intelligence (XAI).

I currently work as a Postdoctoral Research Scientist in the GiusTo Lab, at Columbia University, where I investigate how genomic variation, gene- and pathway-level associations, and large-scale meta-analyses contribute to complex traits and neurodegenerative diseases. My work combines whole-genome sequencing, multi-omics (DNA/RNA/Single-Cell), and XAI to uncover hidden patterns of genetic influence across diverse populations. A key emphasis of my current research is designing interpretable, statistically grounded models that move beyond prediction to explain why certain genetic signals matter.

Before joining Columbia, I was part of the SBILab (Signal Processing and Biomedical Imaging Lab) at the Indraprastha Institute of Information Technology Delhi, where I explored the intersection of genomics and XAI. I developed bioinformatics workflows for RNA-seq analysis (e.g., miRPipe, miRSim) in Chronic Lymphocytic Leukemia (CLL), and created biologically inspired, AI-powered frameworks such as BDL-SP and BIO-DGI to decode the mutational landscape and identify key molecular drivers in Multiple Myeloma (MM). These projects were early efforts in what would evolve into a deeper interest in explainable and mechanistic AI, where computational models reflect the logic of biological systems rather than functioning as black boxes.

Research Interests

1. Genomics & Transcriptomics: Investigating how genomic variation and transcriptomic regulation contribute to complex traits and disease mechanisms across individuals and populations (e.g., miRPipe, miRSim).
2. XAI & Machine Learning in Biology: Designing interpretable, biologically inspired AI frameworks for multi-omics integration, biomarker discovery, and precision medicine applications.
3. Bioinformatics & Computational Pipelines: Developing scalable, GPU-accelerated workflows for large-scale genomics, transcriptomics, and variant analysis—ensuring reproducibility and high-throughput performance.
4. Statistical & Population Genetics: Conducting genome-wide association, gene-based, and ancestry-informed analyses to uncover genetic determinants of complex diseases in diverse populations.
5. Epidemiological & Meta-Analytic Studies: Integrating multi-cohort data using robust statistical and AI-assisted meta-analysis to identify consistent genetic and environmental risk patterns.
6. AI-driven Systems Biology: Leveraging deep learning and network-based modeling (e.g., BIO-DGI, BDL-SP) to map disease pathways and interpret high-dimensional biological data.

Beyond analysis and coding, I enjoy creating visual narratives that translate complex biological insights into accessible knowledge — blending science, storytelling, and design.

Reach Out

Let’s collaborate and Innovate together. If you are interested in discussing research ideas, potential collaborations, or AI-driven genomics projects, feel free to reach out using the form below.

Reach Out Form