The field of cancer neoantigen investigation has developed swiftly in the past decade. Predicting novel and true neoantigens derived from large multi-omics data became difficult but critical challenges. The rise of Artificial Intelligence (AI) or Machine Learning (ML) in biomedicine application has brought benefits to strengthen the current computational pipeline for neoantigen prediction. ML algorithms offer powerful tools to recognize the multidimensional nature of the omics data and therefore extract the key neoantigen features enabling a successful discovery of new neoantigens. The present review aims to outline the significant technology progress of machine learning approaches, especially the newly deep learning tools and pipelines, that were recently applied in neoantigen prediction. In this review article, we summarize the current state-of-the-art tools developed to predict neoantigens. The standard workflow includes calling genetic variants in paired tumor and blood samples, and rating the binding affinity between mutated peptide, MHC (I and II) and T cell receptor (TCR), followed by characterizing the immunogenicity of tumor epitopes. More specifically, we highlight the outstanding feature extraction tools and multi-layer neural network architectures in typical ML models. It is noted that more integrated neoantigen-predicting pipelines are constructed with hybrid or combined ML algorithms instead of conventional machine learning models. In addition, the trends and challenges in further optimizing and integrating the existing pipelines are discussed.
The aim of this study was to explore the relationships among gut microbiota disturbances and serum and spinal cord metabolic disorders in neuropathic pain. 16S rDNA amplicon sequencing and serum and spinal cord metabolomics were used to identify alterations in the microbiota and metabolite profiles in the sham rats and the chronic constriction injury (CCI) model rats. Correlations between the abundances of gut microbiota components at the genus level, the levels of serum metabolites, and pain-related behavioural parameters were analysed. Ingenuity pathway analysis (IPA) was applied to analyse the interaction networks of the differentially expressed serum metabolites. First, we found that the composition of the gut microbiota was different between rats with CCI-induced neuropathic pain and sham controls. At the genus level, the abundances of Helicobacter, Phascolarctobacterium, Christensenella, Blautia, Streptococcus, Rothia and Lactobacillus were significantly increased, whereas the abundances of Ignatzschineria, Butyricimonas, Escherichia, AF12, and Corynebacterium were significantly decreased. Additionally, 72 significantly differentially expressed serum metabolites and 17 significantly differentially expressed spinal cord metabolites were identified between the CCI rats and the sham rats. Finally, correlation analysis showed that changes in the gut microbiota was significantly correlated with changes in serum metabolite levels, suggesting that dysbiosis of the gut microbiota is an important factor in modulating metabolic disturbances in the context of neuropathic pain. In conclusion, our research provides a novel perspective on the potential roles of the gut microbiota and related metabolites in neuropathic pain.
In order to actively respond to the severe situation of the current African swine fever (ASF) epidemic, this paper proposed a double-quantitative decision rough set method over two universes. First, a double-quantitative decision rough set model over two universes based on compatibility relation is defined. Furthermore, the characteristics of ASF decision-making problems are fully considered, and the ASF decision-making process is transformed into a rough approximation decision problem. Then, we construct a double-quantitative decision rough set application method over two universes based on ASF decision-making problems. The upper and lower approximations of the ASF decision objects are calculated by the double quantification approximation space over two universes, and the positive region of the ASF decision object is given. The model proposes a method of ASF decision-making and the optimal decision rules based on the personal preference information of decision-makers. Finally, the theoretical model is applied to the ASF decision problem to illustrate the application process and its effectiveness of the model constructed in this paper. At the same time, the corresponding decision suggestions for dealing with the actual ASF problem are proposed based on the application results of numerical examples.
2 December 2021 in International Journal of Machine Learning and Cybernetics