Cancer is a group of diseases causing abnormal cell growth, altering the genome, and invading or spreading to other parts of the body. Among therapeutic peptide drugs, anticancer peptides (ACPs) have been considered to target and kill cancer cells because cancer cells have unique characteristics such as a high negative charge and abundance of microvilli in the cell membrane when compared to a normal cell. ACPs have several advantages, such as high specificity, cost-effectiveness, low immunogenicity, minimal toxicity, and high tolerance under normal physiological conditions. However, the development and identification of ACPs are time-consuming and expensive in traditional wet-lab-based approaches. Thus, the application of artificial intelligence on the approaches can save time and reduce the cost to identify candidate ACPs. Recently, machine learning (ML), deep learning (DL), and hybrid learning (ML combined DL) have emerged into the development of ACPs without experimental analysis, owing to advances in computer power and big data from the power system. Additionally, we suggest that combination therapy with classical approaches and ACPs might be one of the impactful approaches to increase the efficiency of cancer therapy.

Parkinson’s disease (PD) and multiple system atrophy (MSA) belong to the neurodegenerative group of synucleinopathies; differential diagnosis between PD and MSA is difficult, especially at early stages, owing to their clinical and biological similarities. Thus, there is a pressing need to identify metabolic biomarkers for these diseases. The metabolic profile of the cerebrospinal fluid (CSF) is reported to be altered in PD and MSA; however, the altered metabolites remain unclear. We created a single network with altered metabolites in PD and MSA based on the literature and assessed biological functions, including metabolic disorders of the nervous system, inflammation, concentration of ATP, and neurological disorder, through bioinformatics methods. Our in-silico prediction-based metabolic networks are consistent with Parkinsonism events. Although metabolomics approaches provide a more quantitative understanding of biochemical events underlying the symptoms of PD and MSA, limitations persist in covering molecules related to neurodegenerative disease pathways. Thus, omics data, such as proteomics and microRNA, help understand the altered metabolomes mechanism. In particular, integrated omics and machine learning approaches will be helpful to elucidate the pathological mechanisms of PD and MSA. This review discusses the altered metabolites between PD and MSA in the CSF and omics approaches to discover diagnostic biomarkers.

Parkinson’s disease (PD) is a common neurodegenerative disorder characterized by the loss of dopaminergic neurons in the substantia nigra. Recent studies have highlighted the significant role of cerebrospinal fluid (CSF) in reflecting pathophysiological PD brain conditions by analyzing the components of CSF. Based on the published literature, we created a single network with altered metabolites in the CSF of patients with PD. We analyzed biological functions related to the transmembrane of mitochondria, respiration of mitochondria, neurodegeneration, and PD using a bioinformatics tool. As the proteome reflects phenotypes, we collected proteome data based on published papers, and the biological function of the single network showed similarities with that of the metabolomic network. Then, we analyzed the single network of integrated metabolome and proteome. In silico predictions based on the single network with integrated metabolomics and proteomics showed that neurodegeneration and PD were predicted to be activated. In contrast, mitochondrial transmembrane activity and respiration were predicted to be suppressed in the CSF of patients with PD. This review underscores the importance of integrated omics analyses in deciphering PD’s complex biochemical networks underlying neurodegeneration.

Neurodegenerative diseases (NDDs), which are chronic and progressive diseases, are a growing health concern. Among the therapeutic methods, stem-cell-based therapy is an attractive approach to NDD treatment owing to stem cells’ characteristics such as their angiogenic ability, anti-inflammatory, paracrine, and anti-apoptotic effects, and homing ability to the damaged brain region. Human bone-marrow-derived mesenchymal stem cells (hBM-MSCs) are attractive NDD therapeutic agents owing to their widespread availability, easy attainability and in vitro manipulation and the lack of ethical issues. Ex vivo hBM-MSC expansion before transplantation is essential because of the low cell numbers in bone marrow aspirates. However, hBM-MSC quality decreases over time after detachment from culture dishes, and the ability of hBM-MSCs to differentiate after detachment from culture dishes remains poorly understood. Conventional analysis of hBM-MSCs characteristics before transplantation into the brain has several limitations. However, omics analyses provide more comprehensive molecular profiling of multifactorial biological systems. Omics and machine learning approaches can handle big data and provide more detailed characterization of hBM-MSCs. Here, we provide a brief review on the application of hBM-MSCs in the treatment of NDDs and an overview of integrated omics analysis of the quality and differentiation ability of hBM-MSCs detached from culture dishes for successful stem cell therapy.

Cell-penetrating peptides (CPPs) have gained significant attention for biomedical applications, including drug delivery and therapeutic development, due to their ability to penetrate cell membranes. The accurate prediction of CPPs is critical for accelerating the design and development of novel peptide-based therapies. Approaches for CPP prediction primarily depend on either peptide characteristic-based conventional features or one or two protein language models (PLMs), but these methods often fail to fully leverage the potential of combining diverse features. To address this limitation, we propose CPPpred-En, a prediction model that evaluates multiple conventional and PLM-based features across various machine learning classifiers, selects high-performing feature-classifier combinations, and integrates them through ensemble learning. The CPPpred-En model, which was trained on both the CPP924 and MLCPP 2.0 datasets, outperformed existing state-of-the-art predictors, achieving an accuracy (Acc) of 97.27 % and a matthews correlation coefficient (MCC) of 0.964 on the CPP924 dataset and an Acc of 96.10 % and an MCC of 0.707 on the MLCPP 2.0 dataset. The ensemble-based strategy demonstrated robustness across different datasets, highlighting the strong ability of the model to generalise. The combination of conventional and PLM features in an ensemble framework is promising approach for improving peptide-based therapeutics. The CPPpred-En model is a highly accurate and reliable tool for the identification of CPPs and their application in drug delivery and targeted therapy.

Multiple system atrophy (MSA) is a progressive neurodegenerative synucleinopathy. Differentiating MSA from other synucleinopathies, especially in the early stages, is challenging because of its overlapping symptoms with other forms of Parkinsonism. Thus, there is a pressing need to clarify the underlying biological mechanisms and identify specific biomarkers for MSA. The metabolic profile of cerebrospinal fluid (CSF) is known to be altered in MSA. To further investigate the biological mechanisms behind the metabolic changes, we created a network of altered CSF metabolites in patients with MSA and analysed these changes using bioinformatic software. Acknowledging the limitations of metabolomics, we incorporated proteomic data to improve the overall comprehensiveness of the study. Our in silico predictions showed elevated ROS, cytoplasmic inclusions, white matter demyelination, ataxia, and neurodegeneration, with ATP concentration, neurotransmitter release, and oligodendrocyte count predicted to be suppressed in MSA CSF samples. Machine learning and dimension reduction are important multi-omics approaches as they handle large amounts of data, identify patterns, and make predictions while reducing variance without information loss and generating easily visualised plots that help identify clusters, patterns, or outliers. Thus, integrated multiomics and machine learning approaches are essential for elucidating neurodegenerative mechanisms and identifying potential diagnostic biomarkers of MSA.