IET Systems Biology最新文献

Controlling tumour growth systems presents significant challenges due to the inherent restriction of positive input in biological systems, along with delays in system output and input measurements. Traditional control methods struggle to address these issues effectively, as they rely heavily on real-time feedback from system outputs. The delays in output measurements can lead to instability in closed-loop systems, whereas the inability of conventional approaches to manage the positive input constraint often results in ineffective control. In this study, the authors propose a novel control system designed to overcome these challenges. First, a system state prediction observer that utilises delayed output measurements was developed. Next, a backstepping technique was utilized to develop a feedback controller that ensures the control input stays positive, thereby guaranteeing the system's asymptotic stability. Furthermore, numerical comparisons with previous research validate the effectiveness of the proposed strategy. Overall, the approach offers a promising solution to the issues of delays and positive input constraints in tumour growth control systems.

Protein–protein interactions (PPIs) perform significant functions in many biological activities likewise gene regulation, metabolic pathways and signal transduction. The deregulation of PPIs may cause deadly diseases, such as cancer, autoimmune, pernicious anaemia etc. Detecting PPIs can aid in elucidating the cellular process's underlying molecular mechanisms and contribute to facilitating the discovery of new proteins for the development of novel drugs. Although high-throughput wet-lab technologies have been matured to identify large scale PPI identification; however, the traditional experimental methods are costly and slow and resource intensive. To support experimental techniques, numerous computational approaches have been emerged for identifying PPIs solely from protein sequences. However, the performance of available PPI tools are unsatisfactory and gaps remain for further improvement. In this study, a novel deep learning-based model, Deep_PPI, was developed for predicting multiple species PPIs. To extract the biological features, the authors used 21D vector representing 20 kinds' native and one special amino acid residue and implemented the Keras binary profile encoding technique to formulate each residue in proteins. The binary profile use the PaddVal strategy to equalise the length of positive and negative PPIs. After extracting the features, the authors fed them into one dimension convolutional neural network to build the final prediction model. The proposed Deep_PPI model, which consider the protein pairs into two convolutional heads. Finally, the authors concatenated the two outputs were concatenated from two branches concatenated by fully connected layer. The efficiency of the proposed predictor was demonstrated both on the cross validation and tested on various species datasets, for example, that is (Human, C. elegans, E. coli, and H. sapiens). The proposed model surpassed both the machine-learning models and existing state-of-the-art PPI methods. The proposed Deep_PPI will serve as valuable tool in the discovery of large-scale PPIs in particular and provide insights for drugs development in general.

Histone methylation is an important epigenetic modification process coordinated by histone methyltransferases, histone demethylases and histone methylation reader proteins and plays a key role in the occurrence and development of cancer. This study constructed a risk scoring model around histone methylation modification regulators and conducted a multidimensional comprehensive analysis to reveal its potential role in breast cancer prognosis and drug sensitivity. First, 144 histone methylation modification regulators (HMMRs) were subjected to differential analysis and univariate Cox regression analysis, and nine differentially expressed HMMRs associated with survival were screened out. Next, a risk scoring model consisting of eight HMMRs was constructed using the LASSO regression algorithm, exhibiting independent predictive values in training and validation cohorts. Then, immune analysis shows that patients in the high-risk group divided by the risk scoring model has weakened the immune response. In addition, through functional analysis of differentially expressed genes (DEGs) between high-risk and low-risk groups, we confirmed that the DEGs mainly affected the nucleoplasm and tumour microenvironment. Finally, drug sensitivity analysis demonstrated that our model could be useful for drug screening and identify potential drugs for treating BRCA patients. In conclusion, these eight HMMRs may be key factors in the prognosis and drug sensitivity of BRCA patients.

Single-cell sequencing (scRNA-seq) allows researchers to study cellular heterogeneity in individual cells. In single-cell transcriptomics analysis, identifying the cell type of individual cells is a key task. At present, single-cell datasets often face the challenges of high dimensionality, large number of samples, high sparsity and sample imbalance. The traditional methods of cell type recognition have been challenged. The authors propose a deep residual generation model based on semi-supervised learning (scRSSL) to address these challenges. ScRSSL creatively introduces residual networks into semi-supervised generative models. The authors take advantage of its semi-supervised learning to solve the problem of sample imbalance. During the training of the model, the authors use a residual neural network to accomplish the inference of cell types so that local features of single-cell data can be extracted. Because of the semi-supervised learning approach, it can automatically and accurately predict individual cell types in datasets, even with only a small number of cell labels. Experimentally, the authors’ method has proven to have better performance compared to other methods.

MicroRNAs (miRNAs) are crucial factors in gene regulation, and their dysregulation plays important roles in the immunity of gastric cancer (GC). However, finding specific and effective miRNA markers is still a great challenge for GC immunotherapy. In this study, we computed and analysed miRNA-seq, RNA-seq and clinical data of GC patients from the TCGA database. With the comparison of tumour and normal tissues in GC, we identified 2056 upregulated and 2311 downregulated protein-coding genes. Based on the miRNet database, more than 2600 miRNAs interact with these genes. Several key miRNAs, including hsa-mir-34a, hsa-mir-182 and hsa-mir-23b, were identified to potentially play important regulatory roles in the expression of most upregulated and downregulated genes in GC. Based on bioinformation approaches, the expressions of hsa-mir-34a and hsa-mir-182 were closely linked to the tumour stage, and high expression of hsa-mir-23b was correlated with poor survival in GC. Moreover, these three miRNAs are involved in immune cell infiltration (such as activated memory CD4 T cells and resting mast cells), particularly hsa-mir-182 and hsa-mir-23b. GSEA suggested that the changes in their expression may possibly activate/inhibit immune-related signal pathways, such as chemokine signalling pathway and CXCR4 pathway. These results will provide possible miRNA markers or targets for combined immunotherapy of GC.

Long non-coding RNAs (lncRNAs) are closely associated with the regulation of gene expression, whose promoters play a crucial role in comprehensively understanding lncRNA regulatory mechanisms, functions and their roles in diseases. Due to limitations of the current techniques, accurately identifying lncRNA promoters remains a challenge. To address this challenge, we propose a support vector machine (SVM)–based method for predicting lncRNA promoters, called SVM-LncRNAPro. This method uses position-specific trinucleotide propensity based on single-strand (PSTNPss) to encode the DNA sequences and employs an SVM as the learning algorithm. The SVM-LncRNAPro achieves state-of-the-art performance with reduced complexity. Additionally, experiments demonstrate that this method exhibits a strong generalisation ability. For the convenience of academic research, we have made the source code of SVM-LncRNAPro publicly available. Researchers can download the code and perform the prediction of the lncRNA promoter via the following link: https://github.com/TG0F7/Prom/tree/master.

Tumour necrosis factors (TNFs) are key players in processes such as inflammation, cancer development, and autoimmune diseases. However, accurately identifying TNFs remains challenging because of their complex interactions with other cytokines. Although existing machine learning models offer some potential, they often fall short in reliably distinguishing TNFs. To address this issue, the authors developed DEEP-TNFR, a more advanced model designed specifically to predict TNFR activity. The approach incorporates features such as relative and reverse positions, along with statistical moments, and is tested on a recognised benchmark dataset. The authors explored six different deep learning classifiers, including fully connected networks (FCN), convolutional neural networks (CNN), simple RNN (RNN), long short-term memory (LSTM), bidirectional LSTM (Bi-LSTM), and gated recurrent units (GRU). The model's effectiveness was evaluated through multiple methods: self-consistency, independent set testing, and 5- and 10-fold cross-validation, using metrics, such as accuracy, specificity, sensitivity, and Matthews correlation coefficient. Among these classifiers, LSTM proved to be the most effective, outperforming the others and setting a new standard compared to previous studies. DEEP-TNFR is poised to significantly support ongoing research by enhancing the accuracy of TNFR identification.

Antibiotic pollution in the environment can significantly impact soil microorganisms, such as altering the soil microbial community or emerging antibiotic-resistant bacteria. We propose three machine learning (ML) methods to investigate antibiotics' impact on microorganisms and predict microbial abundance. We examined the microbial abundances of various environmental soil samples treated with antibiotics. We developed 3 ML models: (Model 1) for predicting the most abundant bacterial classes in a specific treatment group; (Model 2) for predicting antibiotic treatment effects based on bacterial abundances; and (Model 3) for using data from short-term incubations to predict the data of community structure after stabilisation. In Model 1, the Random Forest model achieved the highest average accuracy, with a Coefficient of Variation mean of 0.05 and 0.14 in the training and test set. In Model 2, the accuracy of the random forest and SVM models have the highest accuracy (nearly 0.90). Model 3 demonstrates that the Random Forest can use data from short-term incubations to predict the abundance of bacterial communities after long-term stabilisation. This study highlights the potential of ML models as powerful tools for understanding microbial dynamics in response to antibiotic treatments. The code is publicly available at - https://github.com/DeweyYihengDu/ML_on_Microbiota.

Cancer is a serious and complex disease caused by uncontrolled cell growth and is becoming one of the leading causes of death worldwide. Anticancer peptides (ACPs), as a bioactive peptide with lower toxicity, emerge as a promising means of effectively treating cancer. Identifying ACPs is challenging due to the limitation of experimental conditions. To address this, we proposed a dual-channel-based deep learning method, termed ACP-DPE, for ACP prediction. The ACP-DPE consisted of two parallel channels: one was an embedding layer followed by the bi-directional gated recurrent unit (Bi-GRU) module, and the other was an adaptive embedding layer followed by the dilated convolution module. The Bi-GRU module captured the peptide sequence dependencies, whereas the dilated convolution module characterised the local relationship of amino acids. Experimental results show that ACP-DPE achieves an accuracy of 82.81% and a sensitivity of 86.63%, surpassing the state-of-the-art method by 3.86% and 5.1%, respectively. These findings demonstrate the effectiveness of ACP-DPE for ACP prediction and highlight its potential as a valuable tool in cancer treatment research.

Recently, many studies have proven that Piwi-interacting RNAs (piRNAs) play key roles in various biological processes and also associate with human complicated diseases. Therefore, in order to accelerate the traditional biomedical experimental methods for determining piRNA-disease associations, many computational approaches have been proposed. However, piRNA-disease associations can be classified into known and unknown associations, each of which may provide distinct types of information. Traditional graph convolutional networks (GCNs) typically treat all edges in a graph as identical, overlooking the fact that different edge types may carry different signals and influence the learning process in unique ways. In this study, we also provide a new piRNA-disease association prediction method, called PPDAMEGCN, based on a multi-edge type graph convolutional network. First, we calculate the piRNA sequence similarity based on the piRNA sequence information and Smith–Waterman method. The disease semantic similarity is also computed by disease ontology (DO). In addition, we calculate the Gaussian interaction profile (GIP) kernel similarities of piRNA and diseases through the known piRNA-disease associations. Then, we construct the piRNA similarity network by integrating the piRNA's sequence similarity and GIP similarity. We also construct the disease similarity network by integrating disease's semantic similarity and GIP similarity. Finally, we obtain the piRNA and disease embeddings by the multi-edge type graph convolutional network model on the heterogenous piRNA-disease association network. The piRNA-disease pair association probability score is calculated by a multilayer perceptron (MLP) with its concatenated embedding. We also compare PPDAMEGCN to other piRNA-disease prediction methods. The experimental results show that our method outperforms compared methods.