RESUMO
Stakeholders of machine learning models desire explainable artificial intelligence (XAI) to produce human-understandable and consistent interpretations. In computational toxicity, augmentation of text-based molecular representations has been used successfully for transfer learning on downstream tasks. Augmentations of molecular representations can also be used at inference to compare differences between multiple representations of the same ground-truth. In this study, we investigate the robustness of eight XAI methods using test-time augmentation for a molecular-representation model in the field of computational toxicity prediction. We report significant differences between explanations for different representations of the same ground-truth, and show that randomized models have similar variance. We hypothesize that text-based molecular representations in this and past research reflect tokenization more than learned parameters. Furthermore, we see a greater variance between in-domain predictions than out-of-domain predictions, indicating XAI measures something other than learned parameters. Finally, we investigate the relative importance given to expert-derived structural alerts and find similar importance given irregardless of applicability domain, randomization and varying training procedures. We therefore caution future research to validate their methods using a similar comparison to human intuition without further investigation. SCIENTIFIC CONTRIBUTION: In this research we critically investigate XAI through test-time augmentation, contrasting previous assumptions about using expert validation and showing inconsistencies within models for identical representations. SMILES augmentation has been used to increase model accuracy, but was here adapted from the field of image test-time augmentation to be used as an independent indication of the consistency within SMILES-based molecular representation models.
RESUMO
Solute carriers (SLCs) are relatively underexplored compared to other prominent protein families such as kinases and G protein-coupled receptors. However, proteins from the SLC family play an essential role in various diseases. One such SLC is the high-affinity norepinephrine transporter (NET/SLC6A2). In contrast to most other SLCs, the NET has been relatively well studied. However, the chemical space of known ligands has a low chemical diversity, making it challenging to identify chemically novel ligands. Here, a computational screening pipeline was developed to find new NET inhibitors. The approach increases the chemical space to model for NETs using the chemical space of related proteins that were selected utilizing similarity networks. Prior proteochemometric models added data from related proteins, but here we use a data-driven approach to select the optimal proteins to add to the modeled data set. After optimizing the data set, the proteochemometric model was optimized using stepwise feature selection. The final model was created using a two-step approach combining several proteochemometric machine learning models through stacking. This model was applied to the extensive virtual compound database of Enamine, from which the top predicted 22,000 of the 600 million virtual compounds were clustered to end up with 46 chemically diverse candidates. A subselection of 32 candidates was synthesized and subsequently tested using an impedance-based assay. There were five hit compounds identified (hit rate 16%) with sub-micromolar inhibitory potencies toward NET, which are promising for follow-up experimental research. This study demonstrates a data-driven approach to diversify known chemical space to identify novel ligands and is to our knowledge the first to select this set based on the sequence similarity of related targets.
Assuntos
Proteínas da Membrana Plasmática de Transporte de Norepinefrina , Proteínas da Membrana Plasmática de Transporte de Norepinefrina/antagonistas & inibidores , Proteínas da Membrana Plasmática de Transporte de Norepinefrina/genética , Ligantes , Filogenia , Humanos , Linhagem Celular , Conjuntos de Dados como Assunto , Ligação Proteica , Modelos BiológicosRESUMO
The human norepinephrine transporter (NET) is an established drug target for a wide range of psychiatric disorders. Conventional methods that are used to functionally characterize NET inhibitors are based on the use of radiolabeled or fluorescent substrates. These methods are highly informative, but pose limitations to either high-throughput screening (HTS) adaptation or physiologically accurate representation of the endogenous uptake events. Recently, we developed a label-free functional assay based on the activation of G protein-coupled receptors by a transported substrate, termed the TRACT assay. In this study, the TRACT assay technology was applied to NET expressed in a doxycycline-inducible HEK 293 JumpIn cell line. Three endogenous substrates of NET-norepinephrine (NE), dopamine (DA) and epinephrine (EP)-were compared in the characterization of the reference NET inhibitor nisoxetine. The resulting assay, using NE as a substrate, was validated in a manual HTS set-up with a Z' = 0.55. The inhibitory potencies of several reported NET inhibitors from the TRACT assay showed positive correlation with those from an established fluorescent substrate uptake assay. These findings demonstrate the suitability of the TRACT assay for HTS characterization and screening of NET inhibitors and provide a basis for investigation of other solute carrier transporters with label-free biosensors.