Research

Multimodal Deep Learning & Spatial Analysis in Ovarian Cancer

Overview This project focused on the development of a comprehensive computational pathology framework to investigate molecular signatures in ovarian cancer. The objective was to bridge the gap between unstructured histological data and patient-level clinical endpoints. The solution involved an automated pipeline for registering serial tissue sections (H&E and IHC) and a downstream analysis workflow utilizing foundation models to correlate morphological features with molecular data, including Response, Mismatch Repair (MMR) status, and Tumor Mutational Burden (TMB).

Read More

Single-cell sample-level embedding

Overview Developed a novel sample-wise similarity metric to enable high-level embedding of scRNA-seq data, allowing researchers to compare entire patient cohorts rather than just individual cells.

Read More

PDAC Spatial Transcriptomics Analysis

Overview Analyzed the intersection of nerves and tumor cells in Pancreatic Ductal Adenocarcinoma (PDAC) to understand how the microenvironment facilitates perineural invasion.

Read More

Prognostic Marker Discovery Pipeline

Overview Developed a semi-automated pipeline to standardize heterogeneous public single-cell datasets, enabling the discovery of prognostic markers across multiple tissue types.

Read More

Antimicrobial Peptide Generator

Overview This project leverages deep learning to address the critical issue of antibiotic resistance. By integrating Reinforcement Learning (RL) into a Generative Adversarial Network (GAN) framework, we developed a model capable of de novo design of Antimicrobial Peptides (AMPs). The core innovation lies in embedding a Monte Carlo search within the generator to optimize sequence generation through policy gradients.

Read More

Deep Forest for Antitubercular Peptides

Overview Developed a machine learning framework using a deep forest architecture to predict antitubercular peptides, addressing the global challenge of antibiotic resistance.

Read More