RADGenT helps design and evaluate new chemical entities (NCEs) — from target identification through virtual hits, lead optimisation, and clinical evidence.
Modular apps that assist at every stage of drug discovery — from statistical analysis to ADMET prediction, docking, and beyond.
Classical biostatistics for medical and pharmacological research: t-tests, ANOVA, Chi-square, regression, survival analysis and more.
Predict drug-likeness and ADMET descriptors from Name + SMILES input.
Structure-based virtual screening with Vina and cavity-aware scoring.
A central library of virtual and experimental candidates with docking, ADMET and ML scores in one place.
QSAR and deep learning (GNN) models to predict potency, selectivity and ADMET from structure.
Estimate environmental risk of drugs and metabolites: persistence, bioaccumulation, ecotoxicity.
MCQ practice tool covering pharmacokinetics, adverse drug reactions, and clinical trial phases.
RADGenT tools support each stage of the journey.
Select disease pathways and biological targets. Validate using in-vitro and in-vivo experiments.
Use RADock, RAlib and ML models to generate new chemical entities that interact with the target.
Optimise potency and ADMET with RADPT and ML. Analyse preclinical data statistically using STMS.
Design and analyse clinical trials, compile evidence for regulators, and move NCEs toward market approval.
Enter candidate molecules (Name + SMILES) to evaluate key drug-likeness and ADMET-related properties.
Collaborate on AI-powered drug discovery.
Researchers, clinicians, chemists and developers are welcome.