Research
Computational Biology, AI, and Materials Informatics
Areas of Focus
Research Directions
Genome-Scale Metabolic Modeling
Development and analysis of genome-scale metabolic models (GEMs) for Gram-negative bacteria and other organisms. Integration of multi-omics datasets to simulate thousands of biochemical reactions, validate metabolic reconstructions, and support metabolic engineering and bioprocess design. Application of optimization frameworks (e.g., Gurobi) to resolve thermodynamically infeasible cycles (Optrecon).
AI for Drug Discovery & Repurposing
Data-driven workflows for drug repurposing targeting immune-system-related diseases. In silico screening of 19,000+ small molecules, AI-based drug-response prediction, pharmacometric modeling (PK/PD), and integration of transcriptomic and metabolomic data to identify disease-specific metabolic signatures. Contributions to U.S. DoD / NSRI-associated medical countermeasure research.
Digital Twin Systems for Biology
Multi-scale computational digital twins for immune-response modeling, chemical reaction engineering, and polymer systems. Coupling mechanistic models with machine-learning surrogates to enable process optimization, drug-response simulation, and predictive toxicology. Projects include PolyForm, SpadeTwin, and immune-response digital twins. Invention disclosures submitted to NUtech Ventures.
Polymer & Materials Informatics
Machine-learning and deep-learning workflows for polymer copolymer reactivity-ratio prediction (CopolPred, CopolPred 2), solid-state electrolyte property prediction, and ionic conductivity modeling. Graph neural network (GNN) and graph attention network (GAT) approaches for copolymer sequence-property prediction. AutoML clustering and formula featurization pipelines (Molytics).
Multi-omics Integration
Integration of RNA-seq, ATAC-seq, metabolomics, and proteomics data to study immune-metabolic interactions, disease phenotypes, and drug responses across 50+ patient and experimental datasets. Tools include DESeq2, edgeR, Seurat, Scanpy, GSEA, DAVID, Enrichr, and KEGG Mapper. Published in the COMO pipeline (Briefings in Bioinformatics, 2023).
Microbial Community Modeling (NSF MICRA)
Community-based modeling of soil microbial ecosystems, focusing on Bacillus subtilis secondary-metabolite interactions to study microbial community structure, nutrient cycling, and drought-resilience mechanisms. Funded by NSF MICRA (2024–Present, 2025). Presented at MICRA Symposium and UNL Research Days.
High-Performance Scientific Computing
Development and deployment of large-scale computational pipelines using SLURM on Linux HPC environments, PySpark, Hadoop, Hive, Docker, and Git. Automated model validation workflows to support reproducibility across research teams.
All Research Interests
Experience
Research & Professional Experience
Graduate Research Assistant, Materials Informatics and Machine Learning
University of Nebraska-Lincoln, Lincoln, NE
- Developed machine-learning and deep-learning workflows for copolymer reactivity-ratio prediction, monomer-pair representation, and sequence-aware polymer property modeling.
- Built materials-informatics pipelines for solid-state electrolyte and polymer-property prediction, integrating composition featurization, dimensionality reduction, clustering, local regression, unseen-data routing, and confidence-aware evaluation.
- Evaluated LSTM, Siamese neural-network, graph-neural-network, and graph-attention architectures for copolymerization modeling and structure-property prediction.
- Contributed to materials-discovery studies spanning polymer informatics, solid-state electrolyte prediction, and chemically informed machine-learning model development.
Graduate Research Scientist / Computational Biology Researcher
University of Nebraska-Lincoln, Lincoln, NE
- Led development of a genome-scale metabolic model for Gram-negative bacteria by integrating multi-omics datasets and curating a reaction network containing more than 2,000 biochemical reactions.
- Developed optimization-based methods to identify and resolve thermodynamically infeasible cycles in genome-scale metabolic reconstructions.
- Automated model-validation workflows to improve reproducibility, reduce manual curation effort, and support cross-team model evaluation.
- Contributed computational modeling and machine-learning workflows for metabolic engineering, bio-based product design, and sustainable bioprocess analysis.
Digital Twin / Computational Biology Research Assistant
University of Nebraska-Lincoln, Lincoln, NE
- Developed computational and digital-twin workflows for immune-system disease modeling, drug-response prediction, pharmacometric analysis, and multi-scale biological simulation.
- Built RNA-seq, pharmacometric, and multi-omics analysis pipelines to study immune-metabolic interactions across more than 50 patient and experimental datasets.
- Conducted in silico screening of more than 19,000 small molecules for drug-repurposing and candidate-prioritization studies.
- Supported machine-learning-based drug-response prediction workflows for prioritizing preclinical therapeutic candidates.
- Contributed computational analyses to U.S. Army / Department of Defense and National Strategic Research Institute-associated medical-countermeasure research activities.
Research Assistant
University of Nebraska-Lincoln, Lincoln, NE
- Built RNA-seq and pharmacometric analysis pipelines to investigate immune-metabolic interactions across large-scale patient datasets.
- Conducted computational screening of more than 19,000 small molecules for drug repurposing applications.
- Generated machine-learning-based drug-response predictions to support therapeutic candidate prioritization.
- Coordinated computational analyses with wet-lab collaborators to support immune-system-targeted therapeutic discovery.
Big Data Engineer Intern
Cognizant Technology Solutions, Remote / Noida, India
- Collaborated with American Express data teams to support high-throughput analytics pipelines for transaction and behavioral datasets exceeding 50 million records.
- Improved ETL and validation workflows for analytics, fraud-detection support, credit-risk reporting, and business-intelligence data quality.
- Supported scalable data-infrastructure, data-governance, and enterprise-analytics workflows in a production-oriented data environment.
Remote Summer Research Intern
Yale University, New Haven, CT / Remote
- Developed AI-assisted pharmacometric models for predicting drug efficacy and toxicity across oncology-related datasets.
- Integrated mechanistic pharmacokinetic modeling with data-driven learning methods to generate interpretable outputs for dosage and toxicity analysis.
Project Engineer Intern
Wipro Technologies, Remote / Noida, India
- Automated IRCTC train-search and Urban Ladder e-commerce workflows using software-testing and automation pipelines.
- Designed continuous-integration and regression-testing workflows using Maven, Jenkins, TestNG, Grid, and Cucumber.
- Authored test-case documentation and quality-assurance workflow guides used as cohort reference material.
Research Assistant
Amity University, Noida, Uttar Pradesh, India
- Conducted bioinformatics and systems-biology analyses to identify regulatory genes, pathways, and disease-associated molecular signatures.
- Applied network-analysis and machine-learning methods to biomolecular-interaction datasets, contributing to peer-reviewed publications in computational biology and biomedical data analysis.
Projects
Selected Research Projects
Molytics
Machine Learning / Materials Informatics
Developed a machine-learning and AutoML platform for materials and property prediction, integrating formula featurization, dimensionality reduction, clustering, cluster-specific regression, unseen-data routing, confidence analysis, and scientific visualization.
CopolPred
Deep Learning / Polymer Informatics
Developed an LSTM and Siamese neural-network framework to predict monomer-pair reactivity ratios in copolymerization systems using curated experimental data and chemical descriptors.
Polymer Copolymerization Prediction Using GAT-GNN
Graph Neural Networks / Polymer Informatics
Designed graph-attention and graph-neural-network workflows to model polymer/copolymer sequence, monomer-structure relationships, and copolymerization-property prediction tasks.
PolyForm: Polymer Digital Twin with Multiscale AI
Digital Twin / AI
Built a multiscale digital-twin platform connecting molecular descriptors, surrogate models, and process-scale prediction workflows for polymer systems.
SpadeTwin: Digital Twin for Chemical Reaction Engineering
Digital Twin / Chemical Engineering
Designed an AI-powered digital twin for chemical reaction engineering by coupling mechanistic reactor models with machine-learning surrogates for yield, selectivity, and process-optimization studies.
Community-Based Modeling / NSF MICRA
Systems Biology / Ecology
Modeled soil microbial ecosystems and Bacillus subtilis secondary-metabolite interactions to study microbial community structure, nutrient cycling, and drought-resilience mechanisms.
COMO Pipeline
Bioinformatics / Drug Discovery
Pipeline for multi-omics data integration in metabolic modeling and drug discovery, published in Briefings in Bioinformatics.
Optrecon
Metabolic Modeling / Optimization
Optimization-based framework for automated genome-scale model reconstruction upon resolving thermodynamically infeasible cycles.