Unified Python SDK for OpenFDA, PubMed, and ClinicalTrials.gov with clinical intelligence, interaction detection, and research tools.

A Django web application to search for medicinal products basing on criteria specified by the user. The app scrapes a website and saves the downloaded data into its own database, allowing you to search for the desired drug and visualize its interactions with other drugs. It also implements the functionality of a thematic internet forum.

Web application for checking drug interactions in Estonian.

Production-ready healthcare AI agent with 9 LangChain tools, 5-layer verification, and 100-case eval dataset. Integrates with OpenEMR.

drug interactions with 2 drugs

ML training pipelines with RunPod serverless GPU infrastructure. Includes DDI drug interaction classifier using Bio_ClinicalBERT on 176K DrugBank samples.

Drug interaction checker & pharmaceutical compliance

End-to-end pharmaceutical data pipeline for active ingredient validation, OpenFDA label enrichment, and systematic drug–drug interaction detection.

ML-driven platform for Glioblastoma drug recommendation using GDSC data. Features multi-model prediction (RF, XGBoost, NN, SVM, KNN), molecular similarity analysis (Tanimoto, MCS, GCN), pathway enrichment, drug interaction checking, and combination therapy optimization with interactive dashboard.

Full-stack web application that analyzes drug interactions using FDA's OpenFDA API. Built with Python/Flask, featuring real-time drug label search, interaction detection, and user-friendly interface for healthcare safety information.

🧠 SafeMeds is an intelligent LangGraph-based medical assistant that checks drug interactions, recognizes medicines from images, and answers health-related questions.

MediLyze – Flutter app for safe polypharmacy: medication tracking + interaction warnings (PL market).

Heterogeneous GAT with temporal attention for drug-drug interaction prediction. Multi-task learning (interaction + metabolite pathway + temporal dynamics) on Tox21 molecular data. 99.9% interaction accuracy, 0.875 temporal correlation.

Predicting Drug-Drug Interactions (DDI) using Machine Learning and molecular features (Morgan/RDKit)

A machine learning system for predicting potential drug-food interactions using ensemble methods and explainable AI techniques. This project implements multiple classification algorithms to identify interaction risks and provides interpretable predictions through SHAP and LIME analysis.