iKa

Small-molecule pK_a prediction using machine learning models

About iKa

Absorption, distribution, metabolism, excretion, and toxicity of drug molecules are significantly affected by the ionization states. iKa accurately predicts small molecule pK_a values using machine learning models trained on large experimental data sets. Models have been validated for kinase inhibitor-like small molecules and GPCR ligands.

This product is currently in development.

Key Features

Accuracy

Root mean square error of pK_a < 1.5 pH units for drug-like small molecules; recognizes acid or base

SMILES Only

Only SMILES strings for molecules are needed for training, validating, and predicting

Local Operation

Local data storage and computation; security guaranteed by your own environment

Self-Trainable

Can either predict using trained machine learning models or can train new models given experimental data

iKa