KERMT is a pretrained graph neural network model for molecular property prediction.

Accurate ADMET Prediction with XGBoost

A script using RDKit to reproduce the BBB score reported by Gupta.

Here I provide some code that enables users to calculate CNS MPO score for their molecules, based on the SMILES and known pKa values.

ADMET calculations from different research paper and a goal to make it memory efficent with ML implementations.

This repository contains code and documentation for participating in the OpenADMET + ExpansionRx Blind Challenge. The goal of this challenge is to develop machine learning models to predict various ADMET properties of small molecules using the provided dataset.

Claude Plugin for CompChem , Drug Discovery & Organic Chemistry reasoning

This project presents a web-based AI-driven platform designed to predict key ADMET (Absorption, Distribution, Metabolism, Excretion and Toxicity) properties of drug-like molecules.

Hackathon ADMET 2024 - evaluating the danger of the molecules for humans using ML.

AI campaign orchestrator for drug discovery that plans with OpenClaw and executes Refua MCP tools, including autonomous loops and portfolio ranking.

🤖 Use GitHub Actions and admetMesh to predict admet automatically per 30 minutes.

Reproducible R pipeline for network pharmacology analysis of plant extracts — from GC-MS data to pre-docking candidate prioritization

The open computational chemistry engine for drug discovery and materials science; MCP + REST + Workbench + Next.js dashboard, wrapping RDKit, GROMACS, AutoDock, OpenFold, Chai, Boltz, Gnina.

🧬 An open-source AI platform for molecular property prediction, QSAR modeling, and computational drug discovery using machine learning, cheminformatics, and molecular intelligence.

Multi-task learning (BBB + P-gp) for blood-brain barrier permeability prediction

A Drug Metabolite & Toxicity Property Predictor Based on Graph Neural Network

CNS-targeted virtual screening of TIMP2 modulators with ADMET and toxicity profiling.

Magnetic Laplacian based Hypergraph Contrastive Learning for Molecular ADMET Predictions

LigandForge is a modular ligand preparation and virtual screening pipeline for drug discovery that integrates ADMET filtering, 3D conformer generation, Meeko-based ligand preparation, and AutoDock Vina docking—with full provenance tracking, checkpointing, and clean restarts.

Contains relevant project files to publicly available Peptide Alkaloid database "Peptaloid"