Projects
Explore our portfolio of active, ongoing, and completed projects across bioinformatics, time series analysis, and AI-driven materials design.
Showing 9 of 9 projects
A diffusion-based generative framework for de novo molecular design, enabling scaffold-aware generation of drug-like molecules with controllable structural and pharmacological properties.
2024
A structure-informed deep learning model for protein–ligand binding affinity prediction, combining 3D geometric features with sequence-level representations for cross-target generalization.
2024
An explainable AI toolkit for molecular property prediction, providing sub-structure attribution maps and counterfactual explanations to support medicinal chemistry decision-making.
2023
A general-purpose foundation model pre-trained on large-scale heterogeneous time series corpora, achieving strong zero-shot and few-shot performance across forecasting, classification, and anomaly detection.
2024
A retrieval-augmented generation approach for time series imputation that retrieves semantically similar historical patterns to guide missing value recovery in irregular multivariate signals.
2024
A visual representation framework that converts time series into structured image encodings, enabling vision transformers to perform competitive long-horizon forecasting with strong interpretability.
2023
AI-guided design of thermally adaptive composite materials for passive cooling of agricultural greenhouses, reducing peak internal temperature without active energy consumption.
2024
Generative models for spectrally selective surface coatings providing broadband camouflage across visible, near-infrared, and thermal infrared spectra for defense vehicle applications.
2023
A machine learning pipeline for the accelerated design of biocompatible sensing materials, jointly optimizing electrochemical sensitivity, analyte selectivity, and in-vitro biocompatibility.
2024