• AI-enabled physics-based multiscale models power digital twin simulators for in silico oncology and nanomedicine applications.
  • AI-enabled physics-based multiscale models power digital twin simulators for in silico oncology and nanomedicine applications.

The goal of the Radhakrishnan Lab is to Create Digital Twin Models in Biomedical Engineering for Cancer Treatment and Next Generation Therapeutics using Nanomedicine. The lab specializes in several computational algorithms spanning the molecular and cellular scales in conjunction with the theoretical formalisms of statistical mechanics, applied machine learning, and high-performance scientific computing in parallel architectures. The lab has forged successful and funded collaborations with pharmacologists, cell biologists, biophysical chemists, anaesthesiologists, and oncologists, primarily through grants from the US National Science Foundation, the US National Institutes of Health, US Department of Energy and the European Research Council. The Lab is also supported by various foundations and through sponsored research from several companies including Corning, Sanofi, Amgen, Siemens Healthineers etc.

Intracellular Trafficking

Intracellular Trafficking

Biological membranes are ubiquitous in every aspect of cell biology and play the key roles of barrier, carrier, host, and mediators of communication. Using computational techniques encompassing nano to micron length scales, we investigate the chemical and physical properties of membranes in order to elucidate their role in a biological process of Intracellular Trafficking.
Read More
Computational Structural Biology

Computational Structural Biology

Mutations in receptor tyrosine kinases have been implicated in a number of cancers. We utilize an array of quantum mechanics, molecular dynamics, free energy, and bioinformatics methods together with machine learning to explore mechanisms in cancer-driving mutations and help discriminate them from passenger mutations. Specifically, we are examining the molecular mechanisms of mutation-driven constitutive kinase activation and drug resistance and developing efficient computational methods for predicting the oncogenic potential of novel mutations.
Read More
Insilico Oncology

Insilico Oncology

The heterogeneous mutational landscape of cancer results from the varying response of the different signaling pathways in the tissue microenvironment. We adopt a AI-enabled multiscale modeling approach to develop digital twins that can be employed in diagnosis and therapy in the context of personalized medicine.
Read More
Targeted Drug Delivery

Targeted Drug Delivery

Targeted drug delivery systems utilize the unique signatures expressed by malignant cells to deliver a nano-sized therapeutic cargo to infected sites. Our ML-enabled modeling framework focuses on tissue as well as vascular transport with the hope to build next-generation pharmacodynamic models which guide the design and optimization of drug delivery vehicles in the clinical context.
Read More