Predicting Membrane Permeability

Rowan's membrane permeability prediction workflow predicts the permeability of small molecules across cell membranes using either a graph neural network (GNN-MTL) or a physics-based method (PyPermm).

To create a new membrane permeability prediction, find your way to this screen in Rowan:

Click on "Membrane permeability prediction" to create the workflow.

Add a molecule

The membrane permeability workflow only takes in individual 2D structures. You can add these by inputting SMILES strings, using our 2D editor, or by adding a 3D molecule through a file or the editor then clicking the "Convert to SMILES" icon to the right of the charge and multiplicity selectors.

Selecting a method

Membrane permeability can be predicted using the graph neural network GNN-MTL or the physics-based method PyPerMM. Click on the dropdown to select a method.

Submitting your workflow

Once you have added a molecule and selected a method, click "Submit permeability" to begin the workflow.