Insight-driven Decision Support for Teams That Design and Synthesize New Chemical Entities with Percepta Platform | What's new in the Latest Version
ACD Labs Logo
MENU

What's New in Percepta

Version 2018.1

LogP GALAS

The built-in training database of experimental logP values has been expanded by >1700 drug-like compounds from novel congeneric series (representing a 12% increase in size of the training set) resulting in improved accuracy and reliability of prediction for novel entities—logP is predicted within 0.5 log units for 85 % of those compounds in v2018.1 (see Figures 1 and 2).

Improvement in accuracy of logP prediction for the new set of 1724 compounds with the logP GALAS prediction model
Improvement in accuracy of logP prediction for the new set of 1724 compounds with the logP GALAS prediction model

Improvement in accuracy of logP prediction for the new set of 1724 compounds with the logP GALAS prediction model

Improvements in logP prediction accuracy for the new set of 1724 compound from v2017.1 to v2018.1

Improvements in logP prediction accuracy for the new set of 1724 compound from v2017.1 to v2018.1—less than 2% compounds have a prediction error greater than 1 logP unit in v 2018.1 compared to 30% in v2017.1.

Impact on other prediction modules

In addition to improvements to the logP GALAS and Consensus models, enrichment of the logP database also results in enhancement in the prediction accuracy of the following Percepta prediction modules that use logP predictions in the background:

For further demonstration of the impact and improvements to logP predictions in v2018.1, read the poster 'A comprehensive evaluation of ACD/LogD on a pharmaceutical compound set'.

Mutagenicity/Ames Test

The Ames database in the Mutagenicity module has been expanded with experimental data from approximately 1700 compounds obtained from regulatory reports (a 20 % increase in the training set). Inclusion of this new data has resulted in improved prediction accuracy and reliability for novel marketed drugs, and for impurities and degradants of drug-like compounds (Figure 3).

Improvements in sensitivity, specificity, and accuracy of AMES test predictions for the new compounds used in expansion of the internal database in v2018.1

Improvements in sensitivity, specificity, and accuracy of AMES test predictions for the new compounds used in expansion of the internal database in v2018.1.

Volume of Distribution

The physicochemical model for Volume of Distribution (Vd) introduced in v2015 was updated with an improved description of hydrophobic retention processes to improve predictions for highly lipophilic chemical entities.

This module has also benefitted from accuracy enhancements as a result of the expansion of the GALAS LogP training set.

Absolv equations

The database of Abraham-type solvation equations has been significantly revised and expanded with the addition of ~150 new equations (for a total of >250) and updates to existing equations with newly published parameter coefficients. The new equations enable calculation of a variety of solvent/water and gas/water partition coefficients, as well as partitioning processes in biological systems, and non-specific toxicities to aquatic organisms.​

The database of Abraham-type solvation equations has been significantly revised and expanded

These improvements are applied in desktop prediction modules and Batch (for Windows OS only). Contact us at info@acdlabs.com to enquire about the upcoming LINUX release.

Want to learn more?

Contact Us