ACD/Percepta (Advanced Chemistry Development, Inc., Pharma Algorithms, Inc.) is a suite of comprehensive tools for the prediction of basic physico-chemical properties, ADME and toxicity endpoints.
Predictions are made from chemical structure and based upon large validated databases and QSAR models, in combination with expert knowledge of organic chemistry and toxicology.
The majority of ACD/Percepta models were developed using the GALAS modelling methodology (Global, Adjusted Locally According to Similarity), which consists in two parts:
- a global (baseline) statistical model based on PLS with multiple bootstrapping, using a predefined set of fragmental descriptors
- local correction to baseline prediction based on the analysis of model performance for similar compounds from the training set.
ACD/Percepta allows to evaluate the robustness of the prediction by examining compounds similar to the target from the training set, together with literature data and reference. ACD/Percepta models also provide an estimation of the reliability of the prediction by a reliability index (RI).
Estimation of the RI takes into account the following two aspects: similarity of the tested compound to the training set and the consistency of experimental values for similar compounds.