Projects

My projects

WSI to ST

WSI to ST

Predicting Spatial Transcriptomics (ST) using Whole Slide Images (WSI).

AI Research Open Source
Genome Comparison

Genome Comparison

Genetic differences between the Cockatiel (Nymphicus hollandicus) and a biological control species, the Chicken (Gallus gallus).

Open Source
A Custom MPI

A Custom MPI

A Custom Message Passing Interface (MPI) with Remote Direct Memory Access (RDMA).

RDMA Open Source
Drug-Target Interaction

Drug-Target Interaction

Affinity (pKd) regression using Deep Neural Networks

AI Research Open Source Drug-Target Interaction
DermGemma

DermGemma

A multi-agent, multimodal RAG, AI dermatological assistant.

AI Research Open Source Agentic AI
BRCA Integrated Gradients

BRCA Integrated Gradients

This 5-layer model predicts five clinical outcomes: histological, vital, and receptor status by concatenating 1,936 multi-omics features per patient node and using an LSTM unit to prevent GCN oversmoothing. Integrated Gradients provide explainability.

AI Research Open Source
KEGG Pathway Enrichment Analysis

KEGG Pathway Enrichment Analysis

KEGG Pathway Enrichment Analysis using R and clusterProfiler.

AI Research Open Source
Histopathologic CapsuleNet

Histopathologic CapsuleNet

Histopathologic CapsuleNet for cancer classification.

AI Research Open Source
Genetic Algorithm Mona Lisa

Genetic Algorithm Mona Lisa

This Python script implements a genetic algorithm that recreates a target image (the Mona Lisa) by iteratively evolving a population of 500 semi-transparent circles through processes of selection, crossover, and mutation to minimize the visual difference between the generated art and the original.

AI Research Open Source
Multimodal Histopathology & Multi-omics Fusion

Multimodal Histopathology & Multi-omics Fusion

A multimodal model that combines histopathology image data and multi-omics data to classify breast cancer subtypes. It uses mamba, GNNs, and a pretrained ConvNext model.

AI Research Open Source
HINN

HINN PyTorch implementation

PyTorch implementation of the paper: HINN: Hierarchical Input Neural Network identifies multi-omics biomarker for cognitive decline.

AI Research Open Source
IGCN Optimized

IGCN Optimized

Improved the IGCN paper’s performance on the TCGA-BRCA dataset by replacing threshold-based adjacency with k-nearest neighbors and implementing k-fold cross-validation. Reduced runtime from 206 to 60 seconds.

AI Research Open Source
BRCA-multi-omics

BRCA-multi-omics

A graph neural network (GNN) pipeline for binary survival classification.

AI Research Optimization Open Source
SegDICOM

SegDICOM

A web-based application for manual segmentation of DICOM medical images. Upload files, annotate via brush, assign labels, and export segmentation maps.

AI Tools Open Source
Medical Vision Transformer

Spatial-attention ConvMixer

A new technique for gastrointestinal image classification.

AI Research Medical Imaging TensorFlow Open Source