REDIRECTION: Generating drug repurposing hypotheses using link prediction with DISNET data

In recent years and due to COVID-19 pandemic, drug repurposing or repositioning has been placed in the spotlight. Giving new therapeutic uses to already existing drugs, this discipline allows to streamline the drug discovery process, reducing the costs and risks inherent to de novo development. Computational approaches have gained momentum, and emerging techniques from the machine learning domain have proved themselves as highly exploitable means for repurposing prediction. Against this backdrop, one can find that biomedical data can be represented in terms of graphs, which allow depicting in a very expressive manner the underlying structure of the information. Combining these graph data structures with deep learning models enhances the prediction of new links, such as potential disease-drug connections. In this paper, we present a new model named REDIRECTION, which aims to predict new disease-drug links in the context of drug repurposing. It has been trained with a part of the DISNET biomedical graph, formed by diseases, symptoms, drugs, and their relationships. The reserved testing graph for the evaluation has yielded to an AUROC of 0.93 and an AUPRC of 0.90. We have performed a secondary validation of REDIRECTION using RepoDB data as the testing set, which has led to an AUROC of 0.87 and a AUPRC of 0.83. In the light of these results, we believe that REDIRECTION can be a meaningful and promising tool to generate drug repurposing hypotheses. © 2022 IEEE.

Serum and CSF alpha-synuclein levels do not change in COVID-19 patients with neurological symptoms.

SARS-CoV-2 infection can associate diverse neurological manifestations. Several studies have provided proof to support the theory of neurotropic involvement of SARS-CoV-2. Alpha-synuclein has been described as a native antiviral factor within neurons, and upregulation of this protein can be seen in animals that suffered other neuroinvasive infections. To assess if increased expression of this protein takes place in COVID-19 patients with neurological symptoms, we analyzed serum total alpha-synuclein levels in three groups: seven COVID-19 patients with myoclonus, Parkinsonism and/or encephalopathy; thirteen age- and sex-matched COVID-19 patients without neurological involvement and eight age- and sex-matched healthy controls. We did not find differences among them. In a subset of four patients, the change in serum alpha-synuclein before and after the onset of neurological symptoms was not significant either. Cerebrospinal fluid alpha-synuclein levels were also similar between neurological COVID-19 and healthy controls. Overall, these results cannot support the hypothesis of alpha-synuclein upregulation in humans with neurological symptoms in COVID-19. Further research taking into account a larger group of COVID-19 patients including the whole spectrum of neurological manifestations and disease severity is needed.