Search

Background: The accumulation of ectopic fats is related to metabolic syndromes with insulin resistance, which is considered as the first hit in obesity-related diseases. However, systematic understanding of the occurrence of ectopic fats is limited, since organisms are capable of orchestrating complicated intracellular signaling pathways to ensure that the correct nutritional components reach the tissues where they are needed. Interestingly, tissue-specific mechanisms lead to different consequences of fat metabolism with different insulin sensitivities. Aim of Review: To summarize the mechanisms of fat deposition in different tissues including adipose tissue, subcutis, liver, muscle and intestines, in an attempt to elucidate interactive mechanisms involving insulin actions and establish a potential reference for the rational uptake of fat. Key Scientific Concepts of Review: Tissue-specific fat metabolism serves as a trigger for developing abnormal fat metabolism or as a compensatory agent for regulating normal fat metabolism. Outcomes of de novo lipogenesis and adipogenesis differ in the subcutaneous adipose tissue (SAT), liver and muscle, with the participation of insulin actions. Overload of lipid metabolic capability results in SAT fat expansion, and ectopic fat accumulation implicates impaired lipo-/adipogenesis in SAT. Regulating insulin actions may be a key measure on fat deposition and metabolism in individuals.

ABSTRACTGut microbiota–diet interaction has been identified as a key factor of metabolic associated fatty liver disease (MAFLD). Recent studies suggested that dietary polyphenols may protect against MAFLD by regulating gut microbiota; however, the underlying mechanisms remain elusive. We first investigated the effects of cyanidin 3-glucoside and its phenolic metabolites on high-fat diet induced MAFLD in C57BL/6J mice, and protocatechuic acid (PCA) showed a significant positive effect. Next, regulation of PCA on lipid metabolism and gut microbiota were explored by MAFLD mouse model and fecal microbiota transplantation (FMT) experiment. Dietary PCA reduced intraperitoneal and hepatic fat deposition with lower levels of transaminases (AST & ALT) and inflammatory cytokines (IL-1β, IL-2, IL-6, TNF-α & MCP-1), but higher HDL-c/LDL-c ratio. Characterization of gut microbiota indicated that PCA decreased the Firmicutes/Bacteroidetes ratio mainly by reducing the relative abundance of genus Enterococcus, which was positively correlated with the levels of LDL-c, AST, ALT and most of the up-regulated hepatic lipids by lipidomics analysis. FMT experiments showed that Enterococcus faecalis caused hepatic inflammation, fat deposition and insulin resistance with decreased expression of carnitine palmitoyltransferase-1 alpha (CPT1α), which can be reversed by PCA through inhibiting Enterococcus faecalis. Transcriptomics analysis suggested that Enterococcus faecalis caused a significant decrease in the expression of fibroblast growth factor 1 (Fgf1), and PCA recovered the expression of Fgf1 with insulin-like growth factor binding protein 2 (Igfbp2), insulin receptor substrate 1 (Irs1) and insulin receptor substrate 2 (Irs2). These results demonstrated that high proportion of gut Enterococcus faecalis accelerates MAFLD with decreased expression of CPT1α and Fgf1, which can be prevented by dietary supplementation of PCA.

Ferulic acid (FA) and vanillic acid (VA) are considered as major phenolic metabolites of cyanidin 3-glucoside, a polyphenol that widely exists in plants that possess a protective effect against oxidative stress and inflammation in our previous study. This study aimed to investigate the effect of FA and VA on inflammation, gut barrier function, and growth performance in a weaned piglet model challenged with lipopolysaccharide (LPS). Thirty-six piglets (PIC 337 × C48, 28 d of age) were randomly allocated into 3 treatments with 6 replicate pens (2 piglets per pen). They were fed with a basal diet or a diet containing 4,000 mg/kg of FA or VA. Dietary supplementation of VA significantly increased average daily gain (ADG) (P

Placental function is vital to the fetal growth of sows, and resveratrol (RES) can protect cells against oxidative stress, which is one of the major factors impairing placental function. This study aimed to investigate the effect of dietary resveratrol (RES) on placental function and reproductive performance during late pregnancy in a sow model from the aspects of oxidative stress, insulin resistance, and gut microbiota. A total of 26 hybrid pregnant sows (Landrace × Yorkshire) with similar parity were randomly allocated into two groups (n = 13) and fed with a basal diet or a diet containing 200 mg/kg of resveratrol from day 85 of gestation until parturition. The dietary supplementation of RES increased the litter weight at parturition by 12.53% (p = 0.145), with ameliorated insulin resistance (HOMA-IR), increased triglyceride (TG) levels, and decreased interleukin (IL)-1β and IL-6 levels in serum (p < 0.05). Moreover, resveratrol increased the placental vascular density (p < 0.05) with the enhanced expression of nutrient transporter genes (SLC2A1 and SLC2A3) and antioxidant genes, such as superoxide dismutase 2 (SOD2) and heme oxygenase-1 (HO-1) but declined the expression of inflammatory genes, such as IL-1β and IL-6 (p < 0.05). The characterization of the fecal microbiota revealed that resveratrol decreased the relative abundance of the Christensensllaceae R-7 group and Ruminococcaceae UCG-008 (p < 0.05), which had a positive linear correlation with the expression of IL-1β and IL-6 (p < 0.05), but had a negative linear correlation with the expression of SOD2, HO-1, SLC2A1, and SCL2A3 genes (p < 0.05). These data demonstrated that dietary supplementation with resveratrol can improve placental function with ameliorated insulin resistance, oxidative stress, and inflammation potentially by regulating Ruminococcaceae UCG-008 and the Christensensllaceae R-7 group in sows.

Eucommia ulmoides bark has been traditionally used as a Chinese medicine to attenuate stress, but the leaf, which is rich in polyphenols and polysaccharides, has been rarely used. This study aimed to investigate the effect of Eucommia ulmoides leaf extracts (EULEs) on oxidative stress and meat quality of broilers. A total of 252 broilers were randomly divided into 3 treatments and fed with a control basal diet (CON), or a diet containing 250 mg/kg or 1,000 mg/kg of EULE for 51 days. Results showed that dietary supplementation of 250 mg/kg EULE increased significantly the average daily gain of broilers in the early stage (1–21 days), while 250 mg/kg or 1,000 mg/kg of EULE decreased the feed conversion ratio in the whole period (P < 0.05). Supplementation of 250 mg/kg EULE reduced the level of MDA in the liver (P < 0.05), while 1,000 mg/kg EULE decreased the serum level of MDA (P < 0.05), and the HDL level in serum was increased by 250 mg/kg or 1,000 mg/kg EULE (P < 0.05). Additionally, 250 mg/kg EULE decreased abdominal fat ratio and serum triglyceride (TC) level in broilers, while 250 or 1,000 mg/kg of EULE reduced drip loss in breast muscle (P < 0.05), and 1,000 mg/kg EULE reduced the cooking loss in thigh muscle (P < 0.05). In conclusion, dietary supplementation of 250 mg/kg of EULE could attenuate oxidative stress and improve the growth performance and meat quality in broilers.

ObjectiveThis study aimed to evaluate the effect of an antibiotic cocktail on gut microbiota and provide a reference for establishing an available mouse model for fecal microbiota transplantation (FMT) of specific microbes.DesignC57BL/6J mice (n = 24) had free access to an antibiotic cocktail containing vancomycin (0.5 g/L), ampicillin (1 g/L), neomycin (1 g/L), and metronidazole (1 g/L) in drinking water for 3 weeks. Fecal microbiota was characterized by 16S rDNA gene sequencing at the beginning, 1st week, and 3rd week, respectively. The mice were then treated with fecal microbiota from normal mice for 1 week to verify the efficiency of FMT.ResultsThe diversity of microbiota including chao1, observed species, phylogenetic diversity (PD) whole tree, and Shannon index were decreased significantly (P < 0.05) after being treated with the antibiotic cocktail for 1 or 3 weeks. The relative abundance of Bacteroidetes, Actinobacteria, and Verrucomicrobia was decreased by 99.94, 92.09, and 100%, respectively, while Firmicutes dominated the microbiota at the phylum level after 3 weeks of treatment. Meanwhile, Lactococcus, a genus belonging to the phylum of Firmicutes dominated the microbiota at the genus level with a relative abundance of 80.63%. Further FMT experiment indicated that the fecal microbiota from the receptor mice had a similar composition to the donor mice after 1 week.ConclusionThe antibiotic cocktail containing vancomycin, ampicillin, neomycin, and metronidazole eliminates microbes belonging to Bacteroidetes, Actinobacteria, and Verrucomicrobia, which can be recovered by FMT in mice.

Abstract Background Weaning is one of the major factors that cause stress and intestinal disease in piglets. Protocatechuic acid (PCA) is an active plant phenolic acid which exists in Chinese herb, Duzhong (Eucommia ulmoides Oliver), and is also considered as the main bioactive metabolite of polyphenol against oxidative stress and inflammation. This study aimed to investigate the effect of PCA on growth performance, intestinal barrier function, and gut microbiota in a weaned piglet model challenged with lipopolysaccharide (LPS). Methods Thirty-six piglets (Pig Improvement Company line 337 × C48, 28 d of age, 8.87 kg ± 0.11 kg BW) were randomly allocated into 3 treatments and fed with a basal diet (CTL), a diet added 50 mg/kg of aureomycin (AUR), or a diet supplemented with 4000 mg/kg of PCA, respectively. The piglets were challenged with LPS (10 μg/kg BW) on d 14 and d 21 by intraperitoneal injection during the 21-d experiment. Animals (n = 6 from each group) were sacrificed after being anesthetized by sodium pentobarbital at 2 h after the last injection of LPS. The serum was collected for antioxidant indices and inflammatory cytokines analysis, the ileum was harvested for detecting mRNA and protein levels of tight junction proteins by PCR and immunohistochemical staining, and the cecum chyme was collected for intestinal flora analysis using 16S rRNA gene sequencing. Results Dietary supplementation of PCA or AUR significantly increased the expression of tight junction proteins including ZO-1 and claudin-1 in intestinal mucosa, and decreased the serum levels of thiobarbituric acid reactive substances (TBARS) and IL-6, as compared with CTL group. In addition, PCA also decreased the serum levels of IL-2 and TNF-α (P

Blue honeysuckle is rich in polyphenols, and recently receiving attention because of its potential antioxidant and anti-inflammatory properties. Nonalcoholic fatty liver disease (NAFLD) is the leading cause of chronic liver disease that develops hepatic inflammation and metabolic syndrome. The present study aims to study the effect of blue honeysuckle extract (BHE) on fat deposition and hepatic lipid peroxidation in a high-fat-diet (HFD)-induced mouse model. Mice were fed a normal diet (ND) or a HFD containing 0.5% or 1% of BHE or not for 45 d. Liver sections were stained by hematoxylin-eosin staining. Serum lipids were measured by a clinical analyzer. Insulin was examined by ELISA, and hepatic proteins were detected by Western blotting. Dietary supplementation of BHE dose-dependently suppressed HFD-induced obesity and hepatic fat deposition. Moreover, BHE improved glucose metabolism by increasing insulin sensitivity and attenuated oxidative stress potentially by up-regulating nuclear factor (erythroid-derived 2)-like 2 (Nrf2)-mediated pathway. Keywords: Blue honeysuckle, Polyphenols, Fatty liver, Lipid peroxidation, Antioxidant

Cyanidin-3-glucoside (C3G) is a well-known natural anthocyanin and possesses antioxidant and anti-inflammatory properties. The catabolism of C3G in the gastrointestinal tract could produce bioactive phenolic metabolites, such as protocatechuic acid, phloroglucinaldehyde, vanillic acid, and ferulic acid, which enhance C3G bioavailability and contribute to both mucosal barrier and microbiota. To get an overview of the function and mechanisms of C3G and its phenolic metabolites, we review the accumulated data of the absorption and catabolism of C3G in the gastrointestine, and attempt to give crosstalk between the phenolic metabolites, gut microbiota, and mucosal innate immune signaling pathways.

In recent years, nonsteroidal anti-inflammatory drug (NSAIDs), which are considered to affect the prognosis of spinal surgery, have been widely used in perioperative analgesia in spinal surgery, but the relationship between these two factors remains unclear. The purpose of this study was to explore the effect of perioperative use of NSAIDs on the prognosis of patients treated with spinal surgery. We systematically searched PubMed, Embase, and Cochrane Library for relevant articles published on or before July 14, 2023. We used a random-effect model for the meta-analysis to calculate the standardized mean difference (SMD) with a 95% confidence interval (CI). Sensitivity analyses were conducted to analyze stability. A total of 23 randomized clinical trials including 1457 participants met the inclusion criteria. Meta-analysis showed that NSAIDs were significantly associated with postoperative morphine use (mg) (SMD = -0.90, 95% CI -1.12 to -0.68) and postoperative pain (SMD = -0.71, 95% CI -0.85 to -0.58). These results were further confirmed by the trim-and-fill procedure and leave-one-out sensitivity analyses. The current study shows that perioperative use of NSAIDs appears to be an important factor in reducing postoperative pain and morphine use in patients undergoing spinal surgery. However, well-designed, high-quality randomized controlled trials (RCTs) are still required. [ABSTRACT FROM AUTHOR]

Early dental caries detection by endoscope can prevent complications, such as pulpitis and apical infection. However, automatically identifying dental caries remains challenging due to the uncertainty in size, contrast, low saliency, and high interclass similarity of dental caries. To address these problems, we propose the Global Feature Detector (GFDet) that integrates the proposed Feature Selection Pyramid Network (FSPN) and Adaptive Assignment-Balanced Mechanism (AABM). Specifically, FSPN performs upsampling with the semantic information of adjacent feature layers to mitigate the semantic information loss due to sharp channel reduction and enhance discriminative features by aggregating fine-grained details and high-level semantics. In addition, a new label assignment mechanism is proposed that enables the model to select more high-quality samples as positive samples, which can address the problem of easily ignored small objects. Meanwhile, we have built an endoscopic dataset for caries detection, consisting of 1318 images labeled by five dentists. For experiments on the collected dataset, the F1-score of our model is 75.6%, which out-performances the state-of-the-art models by 7.1%.

Prediction of enhancer-promoter interactions (EPIs) is key to regulating gene expression and diagnosing genetic diseases. Due to limited resolution, biological experiments perform not as well as expected while precisely identifying specific interactions, giving rise to computational biology approaches. Many EPI predictors have been developed, but their prediction accuracy still needs to be enhanced. Here, we design a new model named EPIMR to identify enhancer-promoter interactions. First, Hilbert Curve is utilized to represent sequences to images to preserve the position and spatial information. Second, a multi-scale residual neural network (ResNet) is used to learn the distinguishing features of different abstraction levels. Finally, matching heuristics are adopted to concatenate the learned features of enhancers and promoters, which pays attention to their potential interaction information. Experimental results on six cell lines indicate that EPIMR performs better than existing methods, with higher area under the precision-recall curve (AUPR) and area under the receiver operating characteristic (AUROC) results on benchmark and under-sampling datasets. Furthermore, our model is pre-trained on all cell lines, which improves not only the transferability of cross-cell line prediction, but also cell line-specific prediction ability. In conclusion, our method serves as a valuable technical tool for predicting enhancer-promoter interactions, contributing to the understanding of gene transcription mechanisms. Our code and results are available at https://github.com/guofei-tju/EPIMR.

The efficient removal of antibiotic residues from water has become a significant concern in environmental management. This study addresses the low tetracycline removal efficiency of MIL-125(Ti) due to its limited adsorption capacity and weak ultraviolet light absorption. To enhance the photocatalytic performance of MIL-125(Ti), Co3O4 with a suitable band gap was selected for designing and preparing the heterojunction catalyst. By leveraging the porous nature of metal–organic frameworks, Co3O4 was derived from ZIF-67(Co) to provide additional adsorption sites. Notably, the addition of just 0.5 % Co3O4, which exhibits negligible photocatalytic activity on its own, enabled MIL-125(Ti) to form a visible-light responsive Z-scheme heterojunction with superior adsorption capacity. The adsorption of tetracycline increased from 18.1 % for MIL-125(Ti) to 34.3 % for the MIL-125(Ti)/Co3O4 composite. Furthermore, the photocatalytic degradation rate of tetracycline increased from 41.1 % for MIL-125(Ti) to 57.6 % for MIL-125(Ti)/Co3O4, resulting in a remarkable overall tetracycline removal efficiency of 91.9 % due to the combined effects of adsorption and photocatalysis. The Z-scheme heterojunction demonstrated excellent stability and reusability after undergoing five cycles. This study provides new insights into the design of MIL-125(Ti)-based composites for efficient synergistic adsorption and photocatalysis.

Abstract Prior research has shown that the deconvolution of cell-free RNA can uncover the tissue origin. The conventional deconvolution approaches rely on constructing a reference tissue-specific gene panel, which cannot capture the inherent variation present in actual data. To address this, we have developed a novel method that utilizes a neural network framework to leverage the entire training dataset. Our approach involved training a model that incorporated 15 distinct tissue types. Through one semi-independent and two complete independent validations, including deconvolution using a semi in silico dataset, deconvolution with a custom normal tissue mixture RNA-seq data, and deconvolution of longitudinal circulating tumor cell RNA-seq (ctcRNA) data from a cancer patient with metastatic tumors, we demonstrate the efficacy and advantages of the deep-learning approach which were exerted by effectively capturing the inherent variability present in the dataset, thus leading to enhanced accuracy. Sensitivity analyses reveal that neural network models are less susceptible to the presence of missing data, making them more suitable for real-world applications. Moreover, by leveraging the concept of organotropism, we applied our approach to trace the migration of circulating tumor cell-derived RNA (ctcRNA) in a cancer patient with metastatic tumors, thereby highlighting the potential clinical significance of early detection of cancer metastasis.

Abstract Plant phenotypic characteristics, especially leaf morphology of leaves, are an important indicator for species identification. However, leaf shape can be extraordinarily complex in some species, such as oaks. The great variation in leaf morphology and difficulty of species identification in oaks have attracted the attention of scientists since Charles Darwin. Recent advances in discrimination technology have provided opportunities to understand leaf morphology variation in oaks. Here, we aimed to compare the accuracy and efficiency of species identification in two closely related deciduous oaks by geometric morphometric method (GMM) and deep learning using preliminary identification of simple sequence repeats (nSSRs) as a prior. A total of 538 Asian deciduous oak trees, 16 Q. aliena and 23 Q. dentata populations, were firstly assigned by nSSRs Bayesian clustering analysis to one of the two species or admixture and this grouping served as a priori identification of these trees. Then we analyzed the shapes of 2328 leaves from the 538 trees in terms of 13 characters (landmarks) by GMM. Finally, we trained and classified 2221 leaf‐scanned images with Xception architecture using deep learning. The two species can be identified by GMM and deep learning using genetic analysis as a priori. Deep learning is the most cost‐efficient method in terms of time‐consuming, while GMM can confirm the admixture individuals' leaf shape. These various methods provide high classification accuracy, highlight the application in plant classification research, and are ready to be applied to other morphology analysis.

DNA data storage is a rapidly developing technology with great potential due to its high density, long-term durability, and low maintenance cost. Here the authors present a strand assembly algorithm (DBGPS) using de Bruijn graph and greedy path search.

Core-shell thermally expandable microspheres (TEMs) were prepared via Pickering suspension polymerization. Acrylonitrile (AN), methacrylic acid (MAA) and N,N-dimethylacrylamide (DMAA) were used as the comonomers, the 2,2′-azobisisobutyronitrile (AIBN) was used as the initiator and the ethyleneglycol dimethacrylate (EGDMA) was used as the crosslinker. The effects of initiator concentration, cross-linking agent concentration and modified monomer type on the morphology, thermal properties and encapsulation content of TEMs were investigated. The results show that the small change in initiator concentration had a significant effect on the properties of TEMs. When the initiator concentration was 0.55%, the microspheres showed core-shell structure and the maximum expansion ratio was 3.06 times. According to the scanning electron microscope (SEM) image, the heat resistance of the microspheres increased with the increase of the content of crosslinking agent. The lower the water solubility of the modified monomer, the more stable the foaming of the TEMs. When methyl acrylate (MA) was used as a modified monomer, the initial expansion temperature of the microspheres was 163.2°C, the maximum expansion temperature was 223.5 °C, and the encapsulation content of the blowing agent was 14.70%.

Abstract Background Protein subcellular localization prediction plays an important role in biology research. Since traditional methods are laborious and time-consuming, many machine learning-based prediction methods have been proposed. However, most of the proposed methods ignore the evolution information of proteins. In order to improve the prediction accuracy, we present a deep learning-based method to predict protein subcellular locations. Results Our method utilizes not only amino acid compositions sequence but also evolution matrices of proteins. Our method uses a bidirectional long short-term memory network that processes the entire protein sequence and a convolutional neural network that extracts features from protein sequences. The position specific scoring matrix is used as a supplement to protein sequences. Our method was trained and tested on two benchmark datasets. The experiment results show that our method yields accurate results on the two datasets with an average precision of 0.7901, ranking loss of 0.0758 and coverage of 1.2848. Conclusion The experiment results show that our method outperforms five methods currently available. According to those experiments, we can see that our method is an acceptable alternative to predict protein subcellular location.

Abstract Background Identifying potential associations between genes and diseases via biomedical experiments must be the time-consuming and expensive research works. The computational technologies based on machine learning models have been widely utilized to explore genetic information related to complex diseases. Importantly, the gene-disease association detection can be defined as the link prediction problem in bipartite network. However, many existing methods do not utilize multiple sources of biological information; Additionally, they do not extract higher-order relationships among genes and diseases. Results In this study, we propose a novel method called Dual Hypergraph Regularized Least Squares (DHRLS) with Centered Kernel Alignment-based Multiple Kernel Learning (CKA-MKL), in order to detect all potential gene-disease associations. First, we construct multiple kernels based on various biological data sources in gene and disease spaces respectively. After that, we use CAK-MKL to obtain the optimal kernels in the two spaces respectively. To specific, hypergraph can be employed to establish higher-order relationships. Finally, our DHRLS model is solved by the Alternating Least squares algorithm (ALSA), for predicting gene-disease associations. Conclusion Comparing with many outstanding prediction tools, DHRLS achieves best performance on gene-disease associations network under two types of cross validation. To verify robustness, our proposed approach has excellent prediction performance on six real-world networks. Our research work can effectively discover potential disease-associated genes and provide guidance for the follow-up verification methods of complex diseases.

Abstract Background DNA-Binding Proteins (DBP) plays a pivotal role in biological system. A mounting number of researchers are studying the mechanism and detection methods. To detect DBP, the tradition experimental method is time-consuming and resource-consuming. In recent years, Machine Learning methods have been used to detect DBP. However, it is difficult to adequately describe the information of proteins in predicting DNA-binding proteins. In this study, we extract six features from protein sequence and use Multiple Kernel Learning-based on Centered Kernel Alignment to integrate these features. The integrated feature is fed into Support Vector Machine to build predictive model and detect new DBP. Results In our work, date sets of PDB1075 and PDB186 are employed to test our method. From the results, our model obtains better results (accuracy) than other existing methods on PDB1075 ( $$84.19\%$$ 84.19 % ) and PDB186 ( $$83.7\%$$ 83.7 % ), respectively. Conclusion Multiple kernel learning could fuse the complementary information between different features. Compared with existing methods, our method achieves comparable and best results on benchmark data sets.

Abstract Background Biological functions of biomolecules rely on the cellular compartments where they are located in cells. Importantly, RNAs are assigned in specific locations of a cell, enabling the cell to implement diverse biochemical processes in the way of concurrency. However, lots of existing RNA subcellular localization classifiers only solve the problem of single-label classification. It is of great practical significance to expand RNA subcellular localization into multi-label classification problem. Results In this study, we extract multi-label classification datasets about RNA-associated subcellular localizations on various types of RNAs, and then construct subcellular localization datasets on four RNA categories. In order to study Homo sapiens, we further establish human RNA subcellular localization datasets. Furthermore, we utilize different nucleotide property composition models to extract effective features to adequately represent the important information of nucleotide sequences. In the most critical part, we achieve a major challenge that is to fuse the multivariate information through multiple kernel learning based on Hilbert-Schmidt independence criterion. The optimal combined kernel can be put into an integration support vector machine model for identifying multi-label RNA subcellular localizations. Our method obtained excellent results of 0.703, 0.757, 0.787, and 0.800, respectively on four RNA data sets on average precision. Conclusion To be specific, our novel method performs outstanding rather than other prediction tools on novel benchmark datasets. Moreover, we establish user-friendly web server with the implementation of our method.

Machine learning has been widely applied in the fields of biomedicine, computational biology, bioinformatics, image processing, and so on. The performance of machine learning methods mainly relies on feature representation that is the mapping from various types of raw data (i.e., image and genomic data) to a discriminant high-dimensional data space, bridging the raw data with the input of learning/inference algorithms. A good representation is often one that captures the discriminative information from the data and supports effective machine learning. However, over the last few decades, most representation learning approaches are labor-intensive and heavily dependent on the professional knowledge of researchers (dependent on handcrafted feature engineering). To conduct more novel applications in bioinformatics and biomedicine, the weakness of current learning algorithms should be overcome by developing novel feature representation learning algorithms, including supervised representation learning algorithms that are learning features from labeled data, unsupervised feature representation strategies that are learning feature representatives from unlabeled data, and deep feature representation learning algorithms that are learning representative features from data using deep learning architectures.

Abstract Background Reconstructing ancestral genomes is one of the central problems presented in genome rearrangement analysis since finding the most likely true ancestor is of significant importance in phylogenetic reconstruction. Large scale genome rearrangements can provide essential insights into evolutionary processes. However, when the genomes are large and distant, classical median solvers have failed to adequately address these challenges due to the exponential increase of the search space. Consequently, solving ancestral genome inference problems constitutes a task of paramount importance that continues to challenge the current methods used in this area, whose difficulty is further increased by the ongoing rapid accumulation of whole-genome data. Results In response to these challenges, we provide two contributions for ancestral genome inference. First, an improved discrete quantum-behaved particle swarm optimization algorithm (IDQPSO) by averaging two of the fitness values is proposed to address the discrete search space. Second, we incorporate DCJ sorting into the IDQPSO (IDQPSO-Median). In comparison with the other methods, when the genomes are large and distant, IDQPSO-Median has the lowest median score, the highest adjacency accuracy, and the closest distance to the true ancestor. In addition, we have integrated our IDQPSO-Median approach with the GRAPPA framework. Our experiments show that this new phylogenetic method is very accurate and effective by using IDQPSO-Median. Conclusions Our experimental results demonstrate the advantages of IDQPSO-Median approach over the other methods when the genomes are large and distant. When our experimental results are evaluated in a comprehensive manner, it is clear that the IDQPSO-Median approach we propose achieves better scalability compared to existing algorithms. Moreover, our experimental results by using simulated and real datasets confirm that the IDQPSO-Median, when integrated with the GRAPPA framework, outperforms other heuristics in terms of accuracy, while also continuing to infer phylogenies that were equivalent or close to the true trees within 5 days of computation, which is far beyond the difficulty level that can be handled by GRAPPA.

To address the large-scale discrete optimization problem,a cooperative optimization algorithm called IDQPSO-SA was proposed.First,a strategy by applying two selections on the averaging fitness values to update the mean best position was presented,which could overcome the deficiency that QPSO was not applicable for discrete problems.Second,the double cut joining (DCJ) sorting strategy was incorporated into IDQPSO-SA,since the DCJ sorting strategy could considerably reduce the search space.Finally,the probability jumping ability of simulated annealing (SA) was combined with the parallel search of QPSO,and the global search was carried out collaboratively.By comparing with existing algorithms,the experimental results show that IDQPSO-SA further improves the search efficiency and has a comparable performance when faced with large-scale discrete optimization problems.