Dataset Information

Blood-brain barrier penetration prediction enhanced by uncertainty estimation.

ABSTRACT: Blood-brain barrier is a pivotal factor to be considered in the process of central nervous system (CNS) drug development, and it is of great significance to rapidly explore the blood-brain barrier permeability (BBBp) of compounds in silico in early drug discovery process. Here, we focus on whether and how uncertainty estimation methods improve in silico BBBp models. We briefly surveyed the current state of in silico BBBp prediction and uncertainty estimation methods of deep learning models, and curated an independent dataset to determine the reliability of the state-of-the-art algorithms. The results exhibit that, despite the comparable performance on BBBp prediction between graph neural networks-based deep learning models and conventional physicochemical-based machine learning models, the GROVER-BBBp model shows greatly improvement when using uncertainty estimations. In particular, the strategy combined Entropy and MC-dropout can increase the accuracy of distinguishing BBB + from BBB - to above 99% by extracting predictions with high confidence level (uncertainty score < 0.1). Case studies on preclinical/clinical drugs for Alzheimer' s disease and marketed antitumor drugs that verified by literature proved the application value of uncertainty estimation enhanced BBBp prediction model, that may facilitate the drug discovery in the field of CNS diseases and metastatic brain tumors.

SUBMITTER: Tong X

PROVIDER: S-EPMC9264551 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Autoimmune encephalitis (AE) is a severe neurological disease. The brain of the AE patient is attacked by a dysregulated immune system, which is caused by the excessive production of autoantibodies against neuronal receptors and synaptic proteins. AE is also characterized by the uncontrolled B lymphocyte infiltration through the blood-brain barrier (BBB) layer, and the investigation of the underlying mechanism involved in this infiltration may facilitate the discovery of novel therapies for AE. However, few AE-related studies have focused on this issue. In this study, we aimed to identify the factors involved in B lymphocyte infiltration in AE. For this purpose, we first enrolled four healthy control and five AE subjects, collecting their serum and/or total white blood cell samples. The white blood cell samples were further used for collecting RNA and DNA. Then, we simulated the in vivo B lymphocyte infiltration with an in vitro leukocyte transendothelial migration model. It turned out that AE serum treatment significantly and specifically promoted B cells to penetrate the BBB endothelial layer without affecting neutrophils. Next, through genome-wide DNA methylation assays on bisulfite-conversion DNA samples, we identified S100A6 and S100A11 as potential hypo-methylated disease genes in the AE samples. Further qPCR assays demonstrated their upregulation in AE samples, reflecting the negative correlations between gene expression and DNA methylation. Finally, recombinant S100A6 protein treatment significantly increased B lymphocyte infiltration through the BBB endothelial layer, which partially recapitulated the effect of AE serum. In summary, by using an in vitro leukocyte transendothelial migration model, we confirmed that S100A6 promoted B lymphocyte to penetrate the BBB endothelial layer, which is similar to the in vivo clinical manifestations of AE. Therefore, further studies on how the S100A6 protein facilitates B lymphocyte infiltration and on whether other factors in serum also contribute to this phenomenon are likely to improve our understanding of AE and hopefully to reveal novel therapeutic targets for this emerging treatable neurological disorder.

Dataset Information

Blood-brain barrier penetration prediction enhanced by uncertainty estimation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets