Toward Reducing hERG Affinities for DAT Inhibitors with a Combined Machine Learning and Molecular Modeling Approach

Unlocking the Potential of High-Quality Dopamine Transporter Pharmacological Data: Advancing Robust Machine Learning-Based QSAR Modeling

The dopamine transporter (DAT) plays a critical role in the central nervous system and has been implicated in numerous psychiatric disorders. The ligand-based approaches are instrumental to decipher the structure-activity relationship (SAR) of DAT ligands, especially the quantitative SAR (QSAR) modeling. By gathering and analyzing data from literature and databases, we systematically assemble a diverse range of ligands binding to DAT, aiming to discern the general features of DAT ligands and uncover the chemical space for potential novel DAT ligand scaffolds. The aggregation of DAT pharmacological activity data, particularly from databases like ChEMBL, provides a foundation for constructing robust QSAR models. The compilation and meticulous filtering of these data, establishing high-quality training datasets with specific divisions of pharmacological assays and data types, along with the application of QSAR modeling, prove to be a promising strategy for navigating the pertinent chemical space. Through a systematic comparison of DAT QSAR models using training datasets from various ChEMBL releases, we underscore the positive impact of enhanced data set quality and increased data set size on the predictive power of DAT QSAR models.

Series of (([1,1'-Biphenyl]-2-yl)methyl)sulfinylalkyl Alicyclic Amines as Novel and High Affinity Atypical Dopamine Transporter Inhibitors with Reduced hERG Activity

Currently, there are no FDA-approved medications for the treatment of psychostimulant use disorders (PSUD). We have previously discovered "atypical" dopamine transporter (DAT) inhibitors that do not display psychostimulant-like behaviors and may be useful as medications to treat PSUD. Lead candidates (e.g., JJC8-091, 1) have shown promising in vivo profiles in rodents; however, reducing hERG (human ether-à-go-go-related gene) activity, a predictor of cardiotoxicity, has remained a challenge. Herein, a series of 30 (([1,1'-biphenyl]-2-yl)methyl)sulfinylalkyl alicyclic amines was synthesized and evaluated for DAT and serotonin transporter (SERT) binding affinities. A subset of analogues was tested for hERG activity, and the IC50 values were compared to those predicted by our hERG QSAR models, which showed robust predictive power. Multiparameter optimization scores (MPO > 3) indicated central nervous system (CNS) penetrability. Finally, comparison of affinities in human DAT and its Y156F and Y335A mutants suggested that several compounds prefer an inward facing conformation indicating an atypical DAT inhibitor profile.

hERG agonists pose challenges to web-based machine learning methods for prediction of drug-hERG channel interaction

Pharmacological blockade of the IKr channel (hERG) by diverse drugs in clinical use is associated with the Long QT Syndrome that can lead to life threatening arrhythmia. Various computational tools including machine learning models (MLM) for the prediction of hERG inhibition have been developed to facilitate the throughput screening of drugs in development and optimise thus the prediction of hERG liabilities. The use of MLM relies on large libraries of training compounds for the quantitative structure-activity relationship (QSAR) modelling of hERG inhibition. The focus on inhibition omits potential effects of hERG channel agonist molecules and their associated QT shortening risk. It is instructive, therefore, to consider how known hERG agonists are handled by MLM. Here, two highly developed online computational tools for the prediction of hERG liability, Pred-hERG and HergSPred were probed for their ability to detect hERG activator drug molecules as hERG interactors. In total, 73 hERG blockers were tested with both computational tools giving overall good predictions for hERG blockers with reported IC50s below Pred-hERG and HergSPred cut-off threshold for hERG inhibition. However, for compounds with reported IC50s above this threshold such as disopyramide or sotalol discrepancies were observed. HergSPred identified all 20 hERG agonists selected as interacting with the hERG channel. Further studies are warranted to improve online MLM prediction of hERG related cardiotoxicity, by explicitly taking into account channel agonism as well as inhibition.

TIDAL: Topology-Inferred Drug Addiction Learning

Drug addiction is a global public health crisis, and the design of antiaddiction drugs remains a major challenge due to intricate mechanisms. Since experimental drug screening and optimization are too time-consuming and expensive, there is urgent need to develop innovative artificial intelligence (AI) methods for addressing the challenge. We tackle this challenge by topology-inferred drug addiction learning (TIDAL) built from integrating multiscale topological Laplacians, deep bidirectional transformer, and ensemble-assisted neural networks (EANNs). Multiscale topological Laplacians are a novel class of algebraic topology tools that embed molecular topological invariants and algebraic invariants into its harmonic spectra and nonharmonic spectra, respectively. These invariants complement sequence information extracted from a bidirectional transformer. We validate the proposed TIDAL framework on 22 drug addiction related, 4 hERG, and 12 DAT data sets, which suggests that the proposed TIDAL is a state-of-the-art framework for the modeling and analysis of drug addiction data. We carry out cross-target analysis of the current drug addiction candidates to alert their side effects and identify their repurposing potentials. Our analysis reveals drug-mediated linear and bilinear target correlations. Finally, TIDAL is applied to shed light on relative efficacy, repurposing potential, and potential side effects of 12 existing antiaddiction medications. Our results suggest that TIDAL provides a new computational strategy for pressingly needed antisubstance addiction drug development.

Machine Learning Analysis of Cocaine Addiction Informed by DAT, SERT, and NET-Based Interactome Networks

Cocaine addiction is a psychosocial disorder induced by the chronic use of cocaine and causes a large number of deaths around the world. Despite decades of effort, no drugs have been approved by the Food and Drug Administration (FDA) for the treatment of cocaine dependence. Cocaine dependence is neurological and involves many interacting proteins in the interactome. Among them, the dopamine (DAT), serotonin (SERT), and norepinephrine (NET) transporters are three major targets. Each of these targets has a large protein-protein interaction (PPI) network, which must be considered in the anticocaine addiction drug discovery. This work presents DAT, SERT, and NET interactome network-informed machine learning/deep learning (ML/DL) studies of cocaine addiction. We collected and analyzed 61 protein targets out of 460 proteins in the DAT, SERT, and NET PPI networks that have sufficiently large existing inhibitor datasets. Utilizing autoencoder (AE) and other ML/DL algorithms, including gradient boosting decision tree (GBDT) and multitask deep neural network (MT-DNN), we built predictive models for these targets with 115 407 inhibitors to predict drug repurposing potential and possible side effects. We further screened their absorption, distribution, metabolism, and excretion, and toxicity (ADMET) properties to search for leads having potential for developing treatments for cocaine addiction. Our approach offers a new systematic protocol for artificial intelligence (AI)-based anticocaine addiction lead discovery.

Limited power of dopamine transporter mRNA mapping for predicting dopamine transporter availability

Dopamine transporters (DAT) are transmembrane proteins that translocate dopamine from the extracellular space into presynaptic neurons. We aimed to investigate the predictive power of DAT mRNA for DAT protein expression, measured using positron emission tomography (PET). We performed ¹⁸ F-FP-CIT PET scans in 35 healthy individuals. Binding potentials (BP_ND ) from the ventral striatum, caudate nucleus, putamen, and middle frontal, orbitofrontal, cingulate, parietal, and temporal cortices were measured. DAT gene expression data were obtained from the freely available Allen Human Brain Atlas derived from six healthy donors. The auto-correlation of PET-derived BP_ND s for DAT was intermediate (mean ρ² = 0.66) with ρ² ranging from 0.0811 to 1. However, the auto-correlation of mRNA expression was weak across the probes with a mean ρ² of 0.09-0.23. Cross-correlations between PET-derived BP_ND s and mRNA expression were weak with a mean ρ² ranging from 0 to 0.22 across the probes. In conclusion, we observed weak associations between DAT mRNA expression and DAT availability in human brains. Therefore, DAT mRNA mapping may have only limited predictive power for DAT availability in humans. However, the difference in distribution of DAT mRNA and DAT protein may influence this limitation. This article is protected by copyright. All rights reserved.

Cocculus hirsutus ameliorates gastric and lung injuries by suppressing Src/Syk

BACKGROUND

Cocculus hirsutus (L.) W. Thedo., a traditionally well-known plant, has confirmed antitumor properties as well as acute and chronic diuretic effects. However, little is known about its inflammatory activities and the potential effect on inflammatory disease treatment.

PURPOSE

Our aim in this study was to explore additional beneficial properties of C. hirsutus ethanol extract (Ch-EE) such as anti-inflammatory activity in vitro and in vivo as well as its underlying mechanisms and to provide a theoretical basis for its role as a candidate natural drug in clinical gastritis and lung disease therapy.

STUDY DESIGN

RAW264.7 cells, HEK293T cells, peritoneal macrophages, and mouse models of acute gastritis and acute lung injury were used to assess the anti-inflammatory activity of Ch-EE.

METHODS

Decreases in LPS-induced nitric oxide (NO) production and cytokine expression by RAW264.7 cells after Ch-EE treatment were evaluated by Griess assays and PCR, respectively. Transcription factor activity was assessed through luciferase reporter gene assay, and protein expression was determined by Western blotting analysis. Overexpression assays and cellular thermal shift assays were executed in HEK293T cells. Our two in vivo models were an HCl/EtOH-induced gastritis model and an LPS-induced lung injury model. Changes in stomach lesions, lung edema, and lung histology were examined upon treatment with Ch-EE. Components of Ch-EE were determined by liquid chromatography-mass spectrometry.

RESULTS

LPS-induced nitric oxide production and Pam3CSK4- and L-NAME-induced NO production were inhibited by Ch-EE treatment of RAW264.7 cells. Furthermore, LPS-induced increases in transcript levels of iNOS, COX2, CCL12, and IL-1β were reduced by Ch-EE treatment. Ch-EE decreased both MyD88- and TRIF-induced NF-κB promotor activity. Proteins upstream of NF-κB, namely p-p50, p-p65, p-IκBα, p-AKT1, p-Src, and p-Syk, were all downregulated by Ch-EE. Moreover, Src and Syk were targets of Ch-EE. Ch-EE treatment reduced the size of inflammatory stomach lesions induced by HCl/EtOH, lung edema, and accumulation of activated neutrophils caused by LPS.

CONCLUSIONS

These results strongly suggest that Cocculus hirsutus can be developed as a promising anti-inflammatory remedy with Src- and Syk-inhibitory functions targeting diseases related to gastritis and lung injury.

Molecular mechanisms of action of stimulant novel psychoactive substances that target the high-affinity transporter for dopamine

Drug misuse is a significant social and public health problem worldwide. Misused substances exert their neurobehavioural effects through changing neural signalling within the brain, many of them leading to substance dependence and addiction in the longer term. Among drugs with addictive liability, there are illicit classical stimulants such as cocaine and amphetamine, and their more recently available counterparts known as novel psychoactive substances (NPS). Stimulants normally increase dopamine availability in the brain, including the pathway implicated in reward-related behaviour. This pattern is observed in both animal and human brain. The main biological target of stimulants, both classical and NPS, is the dopamine transporter (DAT) implicated in the dopamine-enhancing effects of these drugs. This article aims at reviewing research on the molecular mechanisms underpinning the interactions between stimulant NPS, such as benzofurans, cathinones or piperidine derivatives and DAT, to achieve a greater understanding of the core phenomena that decide about the addictive potential of stimulant NPS. As the methodology is essential in the process of experimental research in this area, we review the applications of in vitro, in vivo and in silico approaches. The latter, including molecular dynamics, attracts the focus of the present review as the method of choice in molecular and atomistic investigations of the mechanisms of addiction of stimulant NPS. Research of this kind is of interest to not only scientists but also health professionals as updated knowledge of NPS, their modes of action and health risks, is needed to tackle the challenges posed by NPS misuse.

Proteome-Informed Machine Learning Studies of Cocaine Addiction

No anti-cocaine addiction drugs have been approved by the Food and Drug Administration despite decades of effort. The main challenge is the intricate molecular mechanisms of cocaine addiction, involving synergistic interactions among proteins upstream and downstream of the dopamine transporter. However, it is difficult to study so many proteins with traditional experiments, highlighting the need for innovative strategies in the field. We propose a proteome-informed machine learning (ML) platform for discovering nearly optimal anti-cocaine addiction lead compounds. We analyze proteomic protein-protein interaction networks for cocaine dependence to identify 141 involved drug targets and build 32 ML models for cross-target analysis of more than 60,000 drug candidates or experimental drugs for side effects and repurposing potentials. We further predict their ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties. Our platform reveals that essentially all of the existing drug candidates fail in our cross-target and ADMET screenings but identifies several nearly optimal leads for further optimization.