Vivek Ruhela

Vivek Ruhela

he / him / his

Genome Decoding × AI × Complex Disease

Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

SAGA (Simplified Association Genomewide Analyses): a user-friendly Pipeline to Democratize Genome-Wide Association Studies

Published in BioRxiv, 2025

SAGA — a framework that unravels complex multi-omics associations to pinpoint key disease biomarkers.

Recommended citation: Cieza, B., Pandey, N., Ruhela, V., Ali, S. and Tosto, G., 2025. SAGA (Simplified Association Genomewide Analyses): a user-friendly Pipeline to Democratize Genome-Wide Association Studies. bioRxiv, pp.2025-08.
Download Paper | Download Slides | Download Bibtex

A comprehensive targeted panel of 295 genes: Unveiling key disease initiating and transformative biomarkers in multiple myeloma

Published in Computers in Biology and Medicine, 2025

Can AI map the molecular code of cancer? In our study, we built BIO-DGI, a bio-inspired graph learning model that deciphers how genes interact to drive Multiple Myeloma (MM) progression from its precursor stage MGUS. By integrating SNVs, CNVs, and SVs from genomic data with network-based AI insights, we identified a clinically validated 295-gene panel strongly linked to MM-related pathways. Curious how graph intelligence can reveal cancer’s hidden blueprints? Check out our paper to learn more!

Recommended citation: Vivek Ruhela and Ritu Gupta and Rupin Oberoi and Anubha Gupta, 2025. A comprehensive targeted panel of 295 genes: Unveiling key disease initiating and transformative biomarkers in multiple myeloma. Computers in Biology and Medicine, 196, p.110619.
Download Paper | Download Slides | Download Bibtex

A Unified Computational Framework for a Robust, Reliable, and Reproducible Identification of Novel miRNAs From the RNA Sequencing Data

Published in Frontiers in Bioinformatics, 2022

Meet miRPipe — our end-to-end framework that accurately detects and quantifies known and novel miRNAs and piRNAs from small-RNA sequencing data. By combining seed-based clustering and novel sequence analysis, miRPipe outperforms existing tools, revealing more cancer-linked small RNAs across CLL, lung, and breast cancer datasets.

Recommended citation: Ruhela, V., Gupta, A., Sriram, K., Ahuja, G., Kaur, G. and Gupta, R., 2022. A Unified Computational Framework for a Robust, Reliable, and Reproducible Identification of Novel miRNAs From the RNA Sequencing Data. Frontiers in Bioinformatics, 2, p.842051.
Download Paper | Download Slides | Download Bibtex

Characterizing the mutational landscape of MM and its precursor MGUS

Published in American Journal of Cancer Research, 2022

Can mutation patterns predict cancer outcomes? In this study, we explored how the mutational burden and signatures evolve as MGUS progresses to Multiple Myeloma (MM) — and how they relate to patient survival. Analyzing genomic data from over 1,000 MM and 61 MGUS cases, we found that hypermutators had poorer survival, with distinct increases in C>A and C>T substitutions and APOBEC activity. Want to know how mutation dynamics can forecast cancer progression and prognosis? Check out our paper to find out!

Recommended citation: Ruhela, V., Jena, L., Kaur, G., Gupta, R. and Gupta, A., 2023. mm-mutatiion-landscape: A Bio-inspired DL model for the identification of altered Signaling Pathways in Multiple Myeloma using WES data. American Journal of Cancer Research, 13(4), p.1155, 10(1), p.6.
Download Paper | Download Slides | Download Bibtex

BDL-SP: A Bio-inspired DL model for the identification of altered Signaling Pathways in Multiple Myeloma using WES data

Published in American Journal of Cancer Research, 2020

Using our Bio-inspired Deep Learning model (BDL-SP), we explored how Multiple Myeloma (MM) emerges from its precancerous stage MGUS. By integrating gene-gene networks and whole-exome data from over 1,200 patients, BDL-SP uncovered key oncogenes, tumor suppressors, and dysregulated pathways driving this transition — outperforming traditional machine-learning models in biological insight. Check out our paper to see how AI is revealing the hidden genomic signatures behind MM progression!

Recommended citation: Ruhela, V., Jena, L., Kaur, G., Gupta, R. and Gupta, A., 2023. BDL-SP: A Bio-inspired DL model for the identification of altered Signaling Pathways in Multiple Myeloma using WES data. American Journal of Cancer Research, 13(4), p.1155, 10(1), p.6.
Download Paper | Download Slides | Download Bibtex

RNA-Seq profiling of deregulated miRs in CLL and their impact on clinical outcome

Published in Blood Cancer Journal Nature, 2020

Our study uncovered eight small RNAs (including miR-155, let-7e, and miR-744) that show striking expression changes in Chronic Lymphocytic Leukemia (CLL) — some promoting disease progression, others offering protective effects. Curious how these small molecules could transform risk prediction and treatment strategies in CLL? 👉 Check out our paper to find out more!

Recommended citation: Kaur, G., Ruhela, V., Rani, L., Gupta, A., Sriram, K., Gogia, A., Sharma, A., Kumar, L. and Gupta, R., 2020. RNA-Seq profiling of deregulated miRs in CLL and their impact on clinical outcome. Blood cancer journal, 10(1), p.6.
Download Paper | Download Slides | Download Bibtex

Conference Papers

Genetic Colocalization of Expression Quantitative Trait Loci (eQTL) Mapping and GWAS in a multiethnic brain bank: An Insight into ancestry-specific Regulatory Architecture in Alzheimer’s disease

Published in Alzheimer's Association International Conference (AAIC), 2025

By integrating eQTL, GWAS, and colocalization analyses in Hispanic and Non-Hispanic White brains, this study advances precision genomics for Alzheimer’s research. BRAINscape reveals ancestry-specific genetic signals in Alzheimer’s disease — uncovering how variants in EHD1, TMEM68, and DEFA10P regulate gene expression differently across populations.

Recommended citation: Ruhela, V., Cieza, B., Mayeux, R., Reyes-Dumeyer, D., Teich, A.F. and Tosto, G., 2025, July. Genetic Colocalization of Expression Quantitative Trait Loci (eQTL) Mapping and GWAS in a multiethnic brain bank: An Insight into ancestry-specific Regulatory Architecture in Alzheimer’s disease. In Alzheimer's Association International Conference. ALZ. doi:10.5281/zenodo.6546356.
Download Paper | Download Slides | Download Bibtex

FINE MAPPING OF REGIONS OF HOMOZYGOSITY AND THEIR ROLE IN ALZHEIMER’S DISEASE: INSIGHTS FROM THE PERUVIAN AND MEXICAN POPULATIONS

Published in ADPD (Vienna), 2025

Runs of Homozygosity (ROH) reveal hidden ancestral signals linked to Alzheimer’s Disease in Peruvian and Mexican populations — uncovering shared genomic regions enriched with African ancestry. This study highlights the power of population-specific ROH and ancestry mapping in understanding the genetic roots of Alzheimer’s disease.

Recommended citation: Ruhela V., Pandey N., Cieza B., Barral S., Samper-Ternent R., Montesinos R., Soto-Añari M., Wong R., Custodio N., Tosto G. 2025 April,FINE MAPPING OF REGIONS OF HOMOZYGOSITY AND THEIR ROLE IN ALZHEIMER’S DISEASE: INSIGHTS FROM THE PERUVIAN AND MEXICAN POPULATIONS. In International Conference on Alzheimer's and Parkinson's Diseases and related neurological disorders (ADPD). http://dx.doi.org/10.13140/RG.2.2.15642.15048
Download Paper | Download Slides | Download Bibtex

Gene by Prenatal Alcohol Exposure Interaction Effects on Growth and Cognition in Mother- Child Dyads in a South African Birth Cohort

Published in American Society of Human Genetics Annual Meeting (ASHG), 2024

Mother–child genetic interactions reveal new insights into Fetal Alcohol Spectrum Disorders (FASD) — uncovering key risk genes linked to growth and neurodevelopment in South African cohorts. Genes in the methyl donor metabolism pathway (e.g., MTHFR, FADS1/2) suggest potential for nutrient-based interventions like choline to mitigate prenatal alcohol effects.

Recommended citation: Ruhela Vivek Zikun Yang, Sandra W. Jacobson, Joseph L. Jacobson, Ernesta M. Meintjes, Giuseppe Tosto, R C Carter. 2024 November,Gene by Prenatal Alcohol Exposure Interaction Effects on Growth and Cognition in Mother- Child Dyads in a South African Birth Cohort. In American Society of Human Genetics Annual Meeting (ASHG). http://dx.doi.org/10.13140/RG.2.2.17434.56006
Download Paper | Download Slides | Download Bibtex

AI-based models for the identification of critical genetic biomarkers to distinguish MM from MGUS using the WES data

Published in Clinical Lymphoma Myeloma and Leukemia, 2021

Machine learning decodes the genetic switch from MGUS to Multiple Myeloma (MM) — identifying key driver genes like HLA-DQB1, IRF1, and FGFR3 that distinguish the two stages with over 95% accuracy. This AI-powered approach reveals pivotal biomarkers shaping myeloma progression, offering clues for early detection and targeted intervention.

Recommended citation: Ruhela, V., Farswan, A., Gupta, A., Kaur, G. and Gupta, R., 2021. P-035: AI-based models for the identification of critical genetic biomarkers to distinguish MM from MGUS using the WES data. Clinical Lymphoma Myeloma and Leukemia, 21, p.S57. https://doi.org/10.1016/S2152-2650(21)02169-8
Download Paper | Download Slides | Download Bibtex