ACD/LogP DB
Use your own measurements and proprietary chemistry to improve logP prediction with ACD/LogP System Training and ACD/PhysChem Accuracy Extender (logP module)
A powerful feature in ACD/LogP DB is the ability to train the algorithm to improve logP prediction accuracy. Training is done in two different ways. The first option is to build a User Database containing representative compounds from the chemical classes of your interest. Such a database can be used not only to organize your experimental logP values, but also for algorithm training for special chemical classes.
The second training option is intended for advanced users. ACD/PhysChem Accuracy Extender (logP module) allows users to define their own new fragments and aromatic or aliphatic interactions, and assign corresponding values to these increments to dramatically increase the accuracy of prediction for specific classes.
Compare ACD/LogP System Training and ACD/PhysChem Accuracy Extender
| System Training | ACD/PhysChem Accuracy Extender |
|---|
| Easy-to-use | Powerful expert tool |
| Improves accuracy for similar compounds | Extends accuracy to diverse chemical space |
| No analysis required by user | Offers results analysis, statistics, and diagnostic ability |
| Ideal for small training data sets | Generally requires large training data sets |
|
