CureLens AI is an AI-powered medication safety platform designed to help healthcare professionals and patients make safer medication decisions. The platform uses machine learning models to predict potential drug-drug interactions, assess personalized medication risks based on patient profiles, and recommend safer alternative medications.

Exploration of vanilla GIN, GIN with edge heuristics in prediction head, Heuristics weighted Edge-GNN for link prediction in ogbl-ddi dataset

DrugDoseFinder: A Python tool that uses fuzzy name matching and RDF graphs to search for drugs and retrieve their dosage information. Designed for accurate querying and easy integration with personalized medical RDF datasets.

Drug interaction prediction using deep learning leverages neural networks to identify harmful combinations by analyzing biomedical and molecular data. This enhances patient safety and supports smarter drug development.

Towards Interpretable Drug-Drug Interaction Prediction: A Graph-Based Approach with Molecular and Network-Level Explanations

Thesis research on open cross domain transfer learning in Graph Isomorphism Networks.

Graph Embedding Evaluation / Code and Datasets for "Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations"

Multi-task GNN predicting inhibition of 5 major cytochrome P450 enzymes (CYP1A2, CYP2C9, CYP2C19, CYP2D6, CYP3A4) for drug-drug interaction assessment.

Extraction of Drug-Drug Interactions from Biomedical Texts

Web App that checks if any of the added medications have interactions with each other. Created as portfolio project for Web Dev course.

app for drug drivers to log drug use to determine when they can legally drive again

Official Implementation of ADEP paper.

Data and code of CADGL: Context-Aware Deep Graph Learning for Predicting Drug-Drug Interactions

Molormer:A Lightweight Self-Attention-Based Method Focused on Spatial Structure of Molecular Graph for Drug-Drug Interactions Prediction

Code for my Master thesis on "Intelligent Drug-Drug Interaction Extraction: A Natural Language Processing Approach to Biomedical Text Analysis".

PyTorch code for an effective way of making a Molecular Graph Dataset in Torch Geometric involving a pair of graphs from chemical SMILE strings

AushadhiNet-GATv2-128 is GNN Model to Predict Multiple Drug Pair Interaction

💊 Drug Annotation from Regulatory Texts (DART) is a structured dataset of Italian drug product leaflets ("Riassunti delle Caratteristiche del Prodotto", or RCPs), curated for Clinical NLP applications.