🧬 How to use ADMET-AI Online

Use ADMET-AI online for multi-property ADMET screening of small-molecule libraries.

ADMET-AI is a graph-neural-network platform for predicting absorption, distribution, metabolism, excretion, and toxicity endpoints across large compound libraries. The Bioinformatics paper describes a Chemprop-RDKit model family trained on 41 Therapeutics Data Commons datasets, with predictions contextualized against approved drugs.

On Neurosnap, you submit one or many Input Molecules and receive a table of ADMET endpoints that is better suited to medicinal-chemistry triage than single-endpoint calculators. The service is designed for early filtering, analog comparison, and library prioritization.

How ADMET-AI Works

ADMET-AI combines learned molecular graph representations with RDKit-derived features so it can capture both connectivity patterns and traditional physicochemical signals. Rather than producing one generic score, the model reports a panel of endpoint-level predictions spanning permeability, clearance, toxicity, and other developability-relevant properties.

On Neurosnap, that makes the tool useful early in screening when you want to eliminate obviously problematic compounds, compare analog series, or prioritize molecules for synthesis or docking follow-up. The results page is centered on sortable property tables so chemists can move from raw predictions to rank-ordering decisions quickly.

What is Neurosnap?

Neurosnap is the leading platform for bioinformatics and computational science focused on expanding access to powerful modeling and simulation tools. Because many state-of-the-art machine learning systems remain complex to install, configure, and scale, Neurosnap offers a clean, browser-based workspace that removes the burden of infrastructure management, dependency conflicts, and command-line tooling.

Built for biologists, chemists, and cross-disciplinary scientists, the platform enables advanced computational workflows without requiring expertise in software engineering or cloud architecture. Researchers can launch analyses through an intuitive interface, connect programmatically through a comprehensive API, and rely on automated resource management to scale workloads efficiently. By taking care of the underlying compute and operational complexity, Neurosnap allows teams to devote their energy to scientific progress and faster iteration. Security and data protection remain foundational principles, with clear safeguards outlined in our Terms of Use and Privacy Policy to ensure your work stays protected.

Advancing Discovery with ADMET-AI on Neurosnap

Using ADMET-AI on Neurosnap could drastically accelerate multi-property ADMET screening and medicinal-chemistry triage from input molecules.

Study-fit inputs: ADMET-AI accepts batches of molecules, making it practical for library-level triage rather than one-compound-at-a-time inspection.
Multi-endpoint view: The model reports a broad ADMET panel instead of a single score, which is much closer to how medicinal chemistry decisions are actually made.
Strong training basis: The platform is built on Chemprop-RDKit models trained across 41 Therapeutics Data Commons datasets for broad endpoint coverage.
Readable evidence: Sortable ADMET tables make it easy to compare analogs, spot liabilities, and prioritize compounds for downstream work.
Faster iteration: Managed execution on Neurosnap removes infrastructure overhead so teams can focus on decision-making rather than local property-prediction tooling.

How to Use ADMET-AI on Neurosnap

To harness the capabilities of ADMET-AI, researchers can follow this streamlined workflow within Neurosnap:

Access Neurosnap: Start by logging in to the Neurosnap website.
Select Tool: From the list of available tools, choose ADMET-AI.
Provide Inputs: Provide all the inputs specified within the submission panel and optionally configure the tool as desired.
Run Tool: Submit the ADMET-AI job and Neurosnap will execute it in the cloud, automatically notifying you as soon as your results are ready.
Review Output: Explore your results through rich visualizations, including figures, plots, and interactive views designed to help you analyze findings with clarity and confidence.

Similar Services

Explore related tools that support similar research workflows:

ChemBounce

eTox Drug Toxicity Prediction

Free Wilson Analysis

Mordred Molecular Descriptor Calculator

Proudly supporting 50,000+ scientists worldwide, including 7,000+ leading biotech and global biopharma organizations.