How to use Permeability and Efflux Prediction Online

Predict Caco-2 and MDCK permeability and efflux for small molecules.

This service uses the published GNN-MTL model from Ivers Ohlsson and colleagues to estimate four experimental assay endpoints from a small molecule's structure. The outputs are Caco-2 efflux ratio, Caco-2 apparent permeability (×10⁻⁶ cm/s), MDCK efflux ratio, and NIH-MDCK efflux ratio. Submit SMILES, SDF, or CCD molecules in a batch to compare analogs in one table. The released model runs without extra pKa or LogD predictions.

How Permeability and Efflux Prediction Works

Chemprop converts each molecule into a graph and applies the published multitask neural network. One forward pass returns the four endpoints in the order specified by the model authors. Efflux ratios are unitless; Caco-2 Papp uses ×10⁻⁶ cm/s. These values estimate assay outcomes and should be interpreted in the context of assay conditions, the model's training domain, and experimental follow-up. Compare compounds within the same endpoint rather than treating the four columns as interchangeable scores.

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 Permeability and Efflux Prediction on Neurosnap

Using Permeability and Efflux Prediction on Neurosnap could drastically accelerate batch prediction of epithelial permeability and efflux assay endpoints from molecular structure.

Four linked assays: Inspect Caco-2 permeability and three efflux ratios together.
Simple input: Provide SMILES, SDF, or CCD molecules without separate descriptor models.
Batch comparison: Compare candidate molecules in one sortable table and export the CSV for further analysis.
Published checkpoint: Predictions use the authors' released Chemprop v2.1.0 GNN-MTL weights.

How to Use Permeability and Efflux Prediction on Neurosnap

To harness the capabilities of Permeability and Efflux Prediction, 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 Permeability and Efflux Prediction.
Provide Inputs: Provide all the inputs specified within the submission panel and optionally configure the tool as desired.
Run Tool: Submit the Permeability and Efflux Prediction 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.

Citations

Please cite the original work when using Permeability and Efflux Prediction in publications or research outputs.

Ivers Ohlsson P, Ghiandoni GM, Winiwarter S, Mercado R, Subramanian V. Prediction of Permeability and Efflux Using Multitask Learning. ACS Omega. 2025;10(45):54148-54159. https://doi.org/10.1021/acsomega.5c04861

Ivers Ohlsson P, et al. GNN-MTL permeability model. Zenodo. 2025. https://doi.org/10.5281/zenodo.16948542

Neurosnap Inc. (2022). Neurosnap: An online platform for computational biology and chemistry. Available at: https://neurosnap.ai/

Similar Services

Explore related tools that support similar research workflows:

Admetica

ChemBounce

PyPermM Membrane Permeability

ADMET-AI

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