Proteochemometric modeling (PCM) combines ligand information as well as target information in order to predict an output variable of interest (e.g. activity of a compound). The big advantage of PCM compared to conventional Quantitative Structure-Activity Relationship (QSAR) modeling is, that by creating a single model one can not only predict the affinity of a diverse set of compounds to a diverse set of targets, but also extrapolate the specific ligand-protein interactions that might be relevant for binding. Moreover, by combining different datasets also targets with sparse data-availability can be included and modelled. Since PCM has already been successfully applied to SLC and ABC transporters, we wanted to investigate whether PCM is a potential new method to predict the activity of neurotransmitter transporter such as the four GABA transporters (GAT1-3, BGT1).<br/>First, we compiled a dataset by collecting bioactivities for all four GABA transporters from the ChEMBL25 database and PubChem. After rigorous curation of the data, we obtained a dataset of 317 unique compounds that were tested at least in one of the four transporters in a [3H]GABA uptake assay (85 compounds were tested in all transporters). For model building, 25 physicochemical RDKit descriptors as well as Z3-scales and Z5-scales descriptors for the orthosteric binding pocket of the GABA transporters were calculated. Subsequently, regression models by applying machine learning techniques such as partial-least-square(PLS) and random forest were derived. Finally, we compared the performance of the PCM models to conventional QSAR models. Overall, we observed that PCM models showed similar performance as the QSAR models for an external test set. Remarkably, by analyzing the importance of the descriptors used in the PCM models, we identified residues as relevant for binding that already had been confirmed in mutational studies. Thus, PCM is a new approach that not only helps to identify new active molecules on the GABA transporters, but also is capable to shed light on the possible binding modes of these compounds.

Proteochemometric modeling of GABA transporters

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.