I develop AI-driven approaches to advance discovery across complex biology — from molecules to medicine and sustainability.
I am currently a Postdoctoral Researcher at the University of Copenhagen (UCPH), Denmark. Building on a foundation in AI-driven bioinformatics and molecular modelling, I am actively seeking an Assistant Professorship with the clear objective of establishing an independent research group.
My research programme centres on the Translational Computational Pharmacology (TCP) Group. The core aim is to connect AI architectures with real-world clinical and environmental challenges—producing results that are mechanistically interpretable, reproducible, and experimentally actionable.
My expertise spans computational biology—from building AI predictive models (DrLungker, DeepEntXAI, LungXAI) and molecular simulations, to discovering PFAS-degrading enzymes. Trained at institutions across India, Finland, and Denmark, I am building towards leading an independent research group focused on therapeutic innovation. I am also an honorary alumnus of NIPER-Ahmedabad.
|
Recognised globally for citation impact in AI-driven drug discovery and computational genomics.
Identifying PFAS-degrading enzymes using AI strategies.
Predicting Colorectal Cancer susceptibility using artificial intelligence models.
AI-based Predictive Modelling and Molecular Enumeration against Lung Cancer.
Drug repurposing against COVID-19 using Machine Learning.
Core coursework in computational biology, structural bioinformatics, programming, and algorithms.
De novo assembly and genome-wide annotation of Ralstonia solanacearum.
Analysis of the whole genome and chloroplast genome of Vigna umbellata.
Comparative Genomics of Plasmodium spp.
Undergraduate study in plant sciences, physiology, chemistry, and genetics.
Conducted fungal culturing, seed sterilisation, microchemical tests, and botanical assays. DBC311 Fellowship (2015).
As an aspiring Assistant Professor, my goal is to establish the TCP Group at the intersection of AI, computational pharmacology, genomics, and sustainable biotechnology. The aim is to create models and workflows that do more than rank candidates: they explain mechanisms, support experimental decision-making, and generate outputs that are scientifically rigorous and practically useful.
This vision is portable and aligned with host institutions focused on precision medicine, biological data science, or environmental sustainability. It brings a recognisable signature: mechanism-aware AI, reproducible pipelines, and collaborative translation from prediction to biological insight.
Every computational result should be interpretable enough to guide validation, not just improve a benchmark.
The group should produce strong science while also training students to think across data, structure, and biology.
TCP should become a recognisable research home with clear themes, strong partnerships, and scalable mentoring.
The TCP group will not just be a hub for high-impact scientific output; it will be a dynamic, nurturing training ground. Having proudly mentored and guided numerous students globally, I am deeply committed to empowering the next generation of independent, ethical, and innovative researchers.
630+ Verified Peer Reviews on Web of Science