AI molecular property prediction for Parkinson's Disease reveals potential repurposing drug candidates based on the increase of the expression of PINK1.

BACKGROUND AND OBJECTIVE: Parkinson's Disease (PD), a common neurodegenerative disorder and one of the major current challenges in neuroscience and pharmacology, may potentially be tackled by the modern AI techniques employed in drug discovery based on molecular property prediction. The aim of our study was to explore the application of a machine learning setup for the identification of the best potential drug candidates among FDA approved drugs, based on their predicted PINK1 expression-enhancing activity. METHODS: Our study relies on supervised machine learning paradigm exploiting in vitro data and utilizing the scaffold splits methodology in order to assess model's capability to extract molecular patterns and generalize from them to new, unseen molecular representations. Models' predictions are combined in a meta-ensemble setup for finding new pharmacotherapies based on the predicted expression of PINK1. RESULTS: The proposed machine learning setup can be used for discovering new drugs for PD based on the predicted increase of expression of PINK1. Our study identified nitazoxanide as well as representatives of imidazolidines, trifluoromethylbenzenes, anilides, nitriles, stilbenes and steroid esters as the best potential drug candidates for PD with PINK1 expression-enhancing activity on or inside the cell's mitochondria. CONCLUSIONS: The applied methodology allows to reveal new potential drug candidates against PD. Next to novel indications, it allows also to confirm the utility of already known antiparkinson drugs, in the new context of PINK1 expression, and indicates the potential for simultaneous utilization of different mechanisms of action.

Machine learning enabled identification of potential SARS-CoV-2 3CLpro inhibitors based on fixed molecular fingerprints and Graph-CNN neural representations.

AIM: Rapidly developing AI and machine learning (ML) technologies can expedite therapeutic development and in the time of current pandemic their merits are particularly in focus. The purpose of this study was to explore various ML approaches for molecular property prediction and illustrate their utility for identifying potential SARS-CoV-2 3CLpro inhibitors. MATERIALS AND METHODS: We perform a series of drug discovery screenings based on supervised ML models operating in different ways on molecular representations, encompassing shallow learning methods based on fixed molecular fingerprints, Graph Convolutional Neural Network (Graph-CNN) with its self-learned molecular representations, as well as ML methods based on combining fixed and Graph-CNN learned representations. RESULTS: Results of our ML models are compared both with respect to the aggregated predictive performance in terms of ROC-AUC based on the scaffold splits, as well as on the granular level of individual predictions, corresponding to the top ranked repurposing candidates. This comparison reveals both certain characteristic homogeneity regarding chemical and pharmacological classification, with a prevalence of sulfonamides and anticancer drugs, as well as identifies novel groups of potential drug candidates against COVID-19. CONCLUSIONS: A series of ML approaches for molecular property prediction enables drug discovery screenings, illustrating the utility for COVID-19. We show that the obtained results correspond well with the already published research on COVID-19 treatment, as well as provide novel insights on potential antiviral characteristics inferred from in vitro data.

AI drug discovery screening for COVID-19 reveals zafirlukast as a repurposing candidate.

AIMS: Over the past few years, AI has been considered as potential important area for improving drug development and in the current urgent need to fight the global COVID-19 pandemic new technologies are even more in focus with the hope to speed up this process. The purpose of our study was to identify the best repurposing candidates among FDA-approved drugs, based on their predicted antiviral activity against SARS-CoV-2. MATERIALS AND METHODS: This article describes a drug discovery screening based on a supervised machine learning model, trained on in vitro data encoded in chemical fingerprints, representing particular molecular substructures. Predictive performance of our model has been evaluated using so-called scaffold splits offering a state-of-the-art setup for assessing model's ability to generalize to new chemical spaces, critical for drug repurposing applications. KEY FINDINGS: Our study identified zafirlukast as the best repurposing candidate for COVID-19. SIGNIFICANCE: Zafirlukast could be potent against COVID-19 both due to its predicted antiviral properties and its ability to attenuate the so called cytokine storm. Thus, these two critical mechanisms of action may be combined in one drug as a novel and promising pharmacotherapy in the current pandemic.