An in-silico approach to studying a very rare neurodegenerative disease using a disease with higher prevalence with shared pathways and genes: Cerebral adrenoleukodystrophy and Alzheimer's disease.

Cerebral adrenoleukodystrophy (cALD) is a rare neurodegenerative disease characterized by inflammatory demyelination in the central nervous system. Another neurodegenerative disease with a high prevalence, Alzheimer's disease (AD), shares many common features with cALD such as cognitive impairment and the alleviation of symptoms by erucic acid. We investigated cALD and AD in parallel to study the shared pathological pathways between a rare disease and a more common disease. The approach may expand the biological understandings and reveal novel therapeutic targets. Gene set enrichment analysis (GSEA) and weighted gene correlation network analysis (WGCNA) were conducted to identify both the resemblance in gene expression patterns and genes that are pathologically relevant in the two diseases. Within differentially expressed genes (DEGs), GSEA identified 266 common genes with similar up- or down-regulation patterns in cALD and AD. Among the interconnected genes in AD data, two gene sets containing 1,486 genes preserved in cALD data were selected by WGCNA that may significantly affect the development and progression of cALD. WGCNA results filtered by functional correlation via protein-protein interaction analysis overlapping with GSEA revealed four genes (annexin A5, beta-2-microglobulin, CD44 molecule, and fibroblast growth factor 2) that showed robust associations with the pathogeneses of cALD and AD, where they were highly involved in inflammation, apoptosis, and the mitogen-activated protein kinase pathway. This study provided an integrated strategy to provide new insights into a rare disease with scant publicly available data (cALD) using a more prevalent disorder with some pathological association (AD), which suggests novel druggable targets and drug candidates.

Prediction Models for Identifying Ion Channel-Modulating Peptides via Knowledge Transfer Approaches.

Ion channels, which can be modulated by peptides, are promising drug targets for neurological, metabolic, and cardiovascular disorders. Because it is expensive and labor-intensive to experimentally screen ion channel-modulating peptides (IMPs), in-silico approaches can serve as excellent alternatives. In this study, we present PrIMP, prediction models for screening IMPs that can target sodium, potassium, and calcium ion channels, as well as nicotine acetylcholine receptors (nAChRs). To overcome the data insufficiency of the IMPs, we utilized two types of knowledge transfer approaches: multi-task learning (MTL) and transfer learning (TL). MTL enabled model training for four target tasks simultaneously with hard parameter sharing, thereby increasing model generalization. TL transferred knowledge of pre-trained model weights from antimicrobial peptide data, which was a much larger, naturally-occurring functional peptide dataset that could potentially improve the model performance. MTL and TL successfully improved the prediction performance of prediction models. In addition, a hybrid approach by implementing deep learning along with traditional machine learning was utilized, with additional performance improvements. PrIMP achieved F1 scores of 0.924 (sodium ion channel), 0.937 (potassium ion channel), 0.898 (calcium ion channel), and 0.931 (nAChRs). The pre-processed dataset and proposed model are available at https://github.com/bzlee-bio/PrIMP.

A Deep Learning Approach with Data Augmentation to Predict Novel Spider Neurotoxic Peptides.

As major components of spider venoms, neurotoxic peptides exhibit structural diversity, target specificity, and have great pharmaceutical potential. Deep learning may be an alternative to the laborious and time-consuming methods for identifying these peptides. However, the major hurdle in developing a deep learning model is the limited data on neurotoxic peptides. Here, we present a peptide data augmentation method that improves the recognition of neurotoxic peptides via a convolutional neural network model. The neurotoxic peptides were augmented with the known neurotoxic peptides from UniProt database, and the models were trained using a training set with or without the generated sequences to verify the augmented data. The model trained with the augmented dataset outperformed the one with the unaugmented dataset, achieving accuracy of 0.9953, precision of 0.9922, recall of 0.9984, and F1 score of 0.9953 in simulation dataset. From the set of all RNA transcripts of Callobius koreanus spider, we discovered neurotoxic peptides via the model, resulting in 275 putative peptides of which 252 novel sequences and only 23 sequences showing homology with the known peptides by Basic Local Alignment Search Tool. Among these 275 peptides, four were selected and shown to have neuromodulatory effects on the human neuroblastoma cell line SH-SY5Y. The augmentation method presented here may be applied to the identification of other functional peptides from biological resources with insufficient data.