Advancing science through the integration of computational biology, artificial intelligence, bioinformatics, and pharmaceutical research — building solutions for the next era of medicine.
Core Research Areas
Our research spans the full computational drug discovery spectrum — from atomic-scale interactions to AI-driven therapeutic innovation.
Protein-ligand interaction studies and virtual screening to identify and rank lead compounds with high binding affinity against validated therapeutic targets.
All-atom MD simulations to study conformational stability, binding kinetics, and dynamic behaviour of biomolecular complexes over nanosecond-to-microsecond timescales.
Systems-level analysis of drug–target–disease interactions using graph theory and pathway enrichment, enabling multi-target therapeutic strategies.
Comprehensive genomics, proteomics, and transcriptomics pipelines — from sequence retrieval and homology modeling to multi-omics data integration.
Machine learning and deep learning models for QSAR, ADMET prediction, molecular property forecasting, and de novo drug design using graph neural networks.
Integrated hit-to-lead optimization combining docking, MD simulation, ADMET analysis, and AI-powered scaffold hopping for next-generation therapeutics.
Active Work
Integrating network pharmacology with molecular docking to identify flavonoid compounds capable of simultaneously inhibiting EGFR, AKT1, and TP53 pathways in NSCLC.
100 ns all-atom simulation assessing conformational stability of top-ranked docking hits against alpha-glucosidase, validated by MM-PBSA binding free energy calculations.
Structure prediction of unexplored antimicrobial resistance proteins using AlphaFold2, followed by cavity detection and AI-guided virtual screening for novel antibiotic scaffolds.
Developing GNN-based QSAR models trained on curated BBB permeability datasets to predict CNS drug penetration, accelerating neurological therapeutic discovery pipelines.
A comprehensive study integrating systems biology and molecular docking to reveal how curcumin-derived compounds modulate the TP53–AKT–VEGFA network in colorectal cancer, supported by 100 ns MD simulation for top candidates.
What's Next
Our roadmap towards precision medicine, AI-driven healthcare, and translational bioscience for global therapeutic impact.
Personalized therapeutic strategies using patient genomic data integrated with computational target profiling.
Near-termDe novo molecule generation using diffusion models and large language models trained on bioactive chemical space.
Mid-termFusing genomics, proteomics, metabolomics, and clinical data for holistic disease-network understanding.
Mid-termExploring quantum computing applications in molecular dynamics for unprecedented accuracy in binding predictions.
Long-termResearch Objectives
Every project we undertake is guided by a clear scientific objective and a commitment to translational impact.
Integrate AI, simulation, and bioinformatics to compress drug discovery timelines from years to months.
Ensure every computational finding is supported by rigorous literature evidence and peer-reviewed methodologies.
Build scalable, open-science solutions targeting neglected diseases, AMR, oncology, and neurological conditions.
Established core pipelines: docking, MD, network pharmacology, bioinformatics.
2024 · CompletedDeployed ML models for ADMET, QSAR, and bioactivity prediction using RDKit & DeepChem.
2025 · CompletedScaling to complex multi-target disease networks with integrated docking + MD validation.
2026 · In ProgressDe novo molecular design, patient-genomic integration, and clinical data fusion.
2027 · PlannedCollaborate With Us
We partner with researchers, academic institutions, and biotech companies to design and execute cutting-edge computational studies.