Publications

Sep, 2026

Conference Paper

CAHS: Context-Aware Homology Search

Protein homology search is foundational to bioinformatics: it supports annotation transfer, structure/function inference, and evolutionary analysis over rapidly expanding sequence repositories (e.g., UniProtKB). Profile hidden Markov models (pHMMs), as implemented in HMMER, remain the most widely trusted approach because they provide statistically calibrated E-values; howe…

Jul, 2026

Journal

EvoDiffMol: evolutionary diffusion framework for 3D molecular design with optimized properties

Designing molecules with specific target properties remains a fundamental challenge in computational chemistry. While existing approaches show promise, most rely on simplified representations like SMILES strings or 2D graphs that lack essential three-dimensional geometric information. We present EvoDiffMol, a computational framework that integrates evolutionary algorithms…

Jun, 2026

Journal

Actinium–DOTA coordination in water from hybrid ML/MM: Structure, free energies, and water-exchange pathways

Quantitative simulation of trivalent 𝑓-block chelates in water remains challenging because bonded and nonbonded force-field models make different approximations for coordination structure, exchange dynamics, and ion–ligand interactions in highly charged systems. Here, we develop a hybrid machine-learning/molecularmechanics (ML/MM) framework for Ac3+–DOTA in explicit solven…

Jun, 2026

Book Chapter

Aging as Meta-Disease: A Comprehensive Framework Integrating Set Theory with Cellular Senescence as Causal Nexus

Whether aging should be classified as a disease remains contentious. We propose a conceptual synthesis: aging is a meta-disease – a universal, upstream pathological condition that gives rise to the full spectrum of age-related disorders, as well as the structural and cosmetic changes historically dismissed as “normal aging.” This framework reflects a Hegelian dialectic, in…

Jan, 2026

Journal

RLMolLM: Reinforcement Learning-Enhanced Language Model Framework for Inverse Molecular Design

Inverse molecular design faces significant challenges due to vast chemical space and complex property requirements. While language models show promise for molecular generation, they struggle with validity, multi-property optimization, and structural constraints. This work presents RLMolLM, a reinforcement learning framework combining Proximal Policy Optimization (PPO) with…

Jan, 2026

Journal

Leveraging Natural Language Processing and Generative Models in Molecular Chemistry: Property Prediction and Novel Compound Generation

The accurate prediction of molecular properties is important for the rational design and the advancement of green chemistry and sustainable materials research. However, the predictive power of traditional computational chemistry methods is limited due to computational restrictions. Here, we examine an alternative approach to the accurate prediction of properties of organic…

Mar, 2024

Journal

Enhancing molecular design efficiency: Uniting language models and generative networks with genetic algorithms

This study examines the effectiveness of generative models in drug discovery, material science, and polymer science, aiming to overcome constraints associated with traditional inverse design methods relying on heuristic rules. Generative models generate synthetic data resembling real data, enabling deep learning model training without extensive labeled datasets. They prove…

Jan, 2024

Journal

Transferring a Molecular Foundation Model for Polymer Property Predictions

Transformer-based large language models have remarkable potential to accelerate design optimization for applications such as drug development and material discovery. Self-supervised pretraining of transformer models requires large-scale data sets, which are often sparsely populated in topical areas such as polymer science. State-of-the-art approaches for polymers conduct d…

Dec, 2023

Journal

Influence of molecular shape on self-diffusion under severe confinement: A molecular dynamics study

We have investigated the effect of molecular shape and charge asymmetry on the translation dynamics of confined hydrocarbon molecules having different shapes but similar kinetic diameters, inside ZSM-5 pores using molecular dynamics simulations. The mean square displacement of propane, acetonitrile, acetaldehyde, and acetone in ZSM-5 exhibit two different regimes – ballist…

Dec, 2023

Journal

Effect of molecular shape on rotation under severe confinement

Orientational structure and dynamics of molecules is known to be affected by confinement in space comparable in size to the molecule itself. ZSM-5 with porous channels of ≈≈0.55 nm is such a porous medium, which offers a strict spatial confinement on low molecular weight hydrocarbons. An important factor that determines these properties is the shape of the confined molecul…

Dec, 2023

Conference Paper

Building an edge computing infrastructure for rapid multi-dimensional electron microscopy

Dec, 2023

Journal

Deep learning workflow for the inverse design of molecules with specific optoelectronic properties

The inverse design of novel molecules with a desirable optoelectronic property requires consideration of the vast chemical spaces associated with varying chemical composition and molecular size. First principles-based property predictions have become increasingly helpful for assisting the selection of promising candidate chemical species for subsequent experimental validat…