MiMeNet: Exploring microbiome-metabolome relationships using neural networks

The advance in microbiome and metabolome studies has generated rich omics data revealing the involvement of the microbial community in host disease pathogenesis through interactions with their host at a metabolic level. However, the computational tools to uncover these relationships are just emerging. Here, we present MiMeNet, a neural network framework for modeling microbe-metabolite relationships. Using ten iterations of 10-fold cross-validation on three paired microbiome-metabolome datasets, we show that MiMeNet more accurately predicts metabolite abundances (mean Spearman correlation coefficients increase from 0.108 to 0.309, 0.276 to 0.457, and -0.272 to 0.264) and identifies more well-predicted metabolites (increase in the number of well-predicted metabolites from 198 to 366, 104 to 143, and 4 to 29) compared to state-of-art linear models for individual metabolite predictions. Additionally, we demonstrate that MiMeNet can group microbes and metabolites with similar interaction patterns and functions to illuminate the underlying structure of the microbe-metabolite interaction network, which could potentially shed light on uncharacterized metabolites through “Guilt by Association”. Our results demonstrated that MiMeNet is a powerful tool to provide insights into the causes of metabolic dysregulation in disease, facilitating future hypothesis generation at the interface of the microbiome and metabolomics.     

Joint Microbial and Metabolomic Network Estimation with the Censored Gaussian Graphical Model

Joint analysis of microbiome and metabolomic data represents an imperative objective as the field moves beyond basic microbiome association studies and turns towards mechanistic and translational investigations. We present a censored Gaussian graphical model framework, where the metabolomic data are treated as continuous and the microbiome data as censored at zero, to identify direct interactions (defined as conditional dependence relationships) between microbial species and metabolites. Simulated examples show that our method metaMint performs favorably compared to the existing ones. metaMint also provides interpretable microbe-metabolite interactions when applied to a bacterial vaginosis data set. R implementation of metaMint is available on GitHub.

     

Integrated mass spectrometry imaging and omics workflows on the same tissue section using grid-aided,parafilm-assisted microdissection

BackgroundIn spite of the number of applications describing the use of MALDI MSI, one of its major drawbacks is the limited capability of identifying multiple compound classes directly on the same tissue section.MethodsWe demonstrate the use of grid-aided, parafilm-assisted microdissection to perform MALDI MS imaging and shotgun proteomics and metabolomics in a combined workflow and using only a single tissue section. The grid is generated by microspotting acid dye 25 using a piezoelectric microspotter, and this grid was used as a guide to locate regions of interest and as an aid during manual microdissection. Subjecting the dissected pieces to the modified Folch method allows to separate the metabolites from proteins. The proteins can then be subjected to digestion under controlled conditions to improve protein identification yields.ResultsThe proof of concept experiment on rat brain generated 162 and 140 metabolite assignments from three ROIs (cerebellum, hippocampus and midbrain/hypothalamus) in positive and negative modes, respectively, and 890, 1303 and 1059 unique proteins. Integrated metabolite and protein overrepresentation analysis identified pathways associated with the biological functions of each ROI, most of which were not identified when looking at the protein and metabolite lists individually.ConclusionsThis combined MALDI MS imaging and multi-omics approach further extends the amount of information that can be generated from single tissue sections.General significanceTo the best of our knowledge, this is the first report combining both imaging and multi-omics analyses in the same workflow and on the same tissue section.     

Fecal Microbiota,Fecal Metabolome,and Colorectal Cancer Interrelations

Background and Aims

Investigation of microbe-metabolite relationships in the gut is needed to understand and potentially reduce colorectal cancer (CRC) risk.

Methods

Microbiota and metabolomics profiling were performed on lyophilized feces from 42 CRC cases and 89 matched controls. Multivariable logistic regression was used to identify statistically independent associations with CRC. First principal coordinate-component pair (PCo1-PC1) and false discovery rate (0.05)-corrected P-values were calculated for 116,000 Pearson correlations between 530 metabolites and 220 microbes in a sex*case/control meta-analysis.

Results

Overall microbe-metabolite PCo1-PC1 was more strongly correlated in cases than in controls (Rho 0.606 vs 0.201, P = 0.01). CRC was independently associated with lower levels of Clostridia, Lachnospiraceae, p-aminobenzoate and conjugated linoleate, and with higher levels of Fusobacterium, Porphyromonas, p-hydroxy-benzaldehyde, and palmitoyl-sphingomyelin. Through postulated effects on cell shedding (palmitoyl-sphingomyelin), inflammation (conjugated linoleate), and innate immunity (p-aminobenzoate), metabolites mediated the CRC association with Fusobacterium and Porphyromonas by 29% and 34%, respectively. Overall, palmitoyl-sphingomyelin correlated directly with abundances of Enterobacteriaceae (Gammaproteobacteria), three Actinobacteria and five Firmicutes. Only Parabacteroides correlated inversely with palmitoyl-sphingomyelin. Other lipids correlated inversely with Alcaligenaceae (Betaproteobacteria). Six Bonferroni-significant correlations were found, including low indolepropionate and threnoylvaline with Actinobacteria and high erythronate and an uncharacterized metabolite with Enterobacteriaceae.

Conclusions

Feces from CRC cases had very strong microbe-metabolite correlations that were predominated by Enterobacteriaceae and Actinobacteria. Metabolites mediated a direct CRC association with Fusobacterium and Porphyromonas, but not an inverse association with Clostridia and Lachnospiraceae. This study identifies complex microbe-metabolite networks that may provide insights on neoplasia and targets for intervention.     

Interpretation of network-based integration from multi-omics longitudinal data

Multi-omics integration is key to fully understand complex biological processes in an holistic manner. Furthermore, multi-omics combined with new longitudinal experimental design can unreveal dynamic relationships between omics layers and identify key players or interactions in system development or complex phenotypes. However, integration methods have to address various experimental designs and do not guarantee interpretable biological results. The new challenge of multi-omics integration is to solve interpretation and unlock the hidden knowledge within the multi-omics data. In this paper, we go beyond integration and propose a generic approach to face the interpretation problem. From multi-omics longitudinal data, this approach builds and explores hybrid multi-omics networks composed of both inferred and known relationships within and between omics layers. With smart node labelling and propagation analysis, this approach predicts regulation mechanisms and multi-omics functional modules. We applied the method on 3 case studies with various multi-omics designs and identified new multi-layer interactions involved in key biological functions that could not be revealed with single omics analysis. Moreover, we highlighted interplay in the kinetics that could help identify novel biological mechanisms. This method is available as an R package netOmics to readily suit any application.     

ENIGMA: an enterotype-like unigram mixture model for microbial association analysis

Background

One of the major challenges in microbial studies is detecting associations between microbial communities and a specific disease. A specialized feature of microbiome count data is that intestinal bacterial communities form clusters called as “enterotype”, which are characterized by differences in specific bacterial taxa, making it difficult to analyze these data under health and disease conditions. Traditional probabilistic modeling cannot distinguish between the bacterial differences derived from enterotype and those related to a specific disease.

Results

We propose a new probabilistic model, named as ENIGMA (Enterotype-like uNIGram mixture model for Microbial Association analysis), which can be used to address these problems. ENIGMA enabled simultaneous estimation of enterotype-like clusters characterized by the abundances of signature bacterial genera and the parameters of environmental effects associated with the disease.

Conclusion

In the simulation study, we evaluated the accuracy of parameter estimation. Furthermore, by analyzing the real-world data, we detected the bacteria related to Parkinson’s disease. ENIGMA is implemented in R and is available from GitHub (https://github.com/abikoushi/enigma).

     

AUTOMATIC ACOUSTIC IDENTIFICATION OF SINGING INSECTS

ABSTRACT

We report on our research efforts towards developing efficient equipment for the automatic recognition of insects using only the acoustic modality. Specifically, we deal with three groups of insects, namely the crickets, cicadas and katydids. Inspired by well-documented tactics of speech processing, the signal processing employed in the present work is elaborated further with respect to the sound production mechanisms of insects. In order to improve the practical efficacy of our equipment, we adopt a score-level fusion of classifiers with non-parametric (probabilistic neural network) and parametric (Gaussian mixture models) estimation of the probability density function. An efficient hierarchic classification scheme is introduced, where the identification of unlabelled input takes place at various levels of hierarchy, such as suborder, family, subfamily, genus and species. We evaluate the practical significance of our approach on a large and well-documented catalogue of recordings of crickets, cicadas and katydids. For the hierarchic classification scheme, we report identification accuracy that exceeds 99% at suborder and family levels. In the straight classification scheme, we report accuracy of 90% for 307 species.     

A novel algorithm based on bi-random walks to identify disease-related lncRNAs

Background

It’s a very urgent task to identify cancer genes that enables us to understand the mechanisms of biochemical processes at a biomolecular level and facilitates the development of bioinformatics. Although a large number of methods have been proposed to identify cancer genes at recent times, the biological data utilized by most of these methods is still quite less, which reflects an insufficient consideration of the relationship between genes and diseases from a variety of factors.

Results

In this paper, we propose a two-rounds random walk algorithm to identify cancer genes based on multiple biological data (TRWR-MB), including protein-protein interaction (PPI) network, pathway network, microRNA similarity network, lncRNA similarity network, cancer similarity network and protein complexes. In the first-round random walk, all cancer nodes, cancer-related genes, cancer-related microRNAs and cancer-related lncRNAs, being associated with all the cancer, are used as seed nodes, and then a random walker walks on a quadruple layer heterogeneous network constructed by multiple biological data. The first-round random walk aims to select the top score k of potential cancer genes. Then in the second-round random walk, genes, microRNAs and lncRNAs, being associated with a certain special cancer in corresponding cancer class, are regarded as seed nodes, and then the walker walks on a new quadruple layer heterogeneous network constructed by lncRNAs, microRNAs, cancer and selected potential cancer genes. After the above walks finish, we combine the results of two-rounds RWR as ranking score for experimental analysis. As a result, a higher value of area under the receiver operating characteristic curve (AUC) is obtained. Besides, cases studies for identifying new cancer genes are performed in corresponding section.

Conclusion

In summary, TRWR-MB integrates multiple biological data to identify cancer genes by analyzing the relationship between genes and cancer from a variety of biological molecular perspective.

     

Multi-scale inference of genetic trait architecture using biologically annotated neural networks

In this article, we present Biologically Annotated Neural Networks (BANNs), a nonlinear probabilistic framework for association mapping in genome-wide association (GWA) studies. BANNs are feedforward models with partially connected architectures that are based on biological annotations. This setup yields a fully interpretable neural network where the input layer encodes SNP-level effects, and the hidden layer models the aggregated effects among SNP-sets. We treat the weights and connections of the network as random variables with prior distributions that reflect how genetic effects manifest at different genomic scales. The BANNs software uses variational inference to provide posterior summaries which allow researchers to simultaneously perform (i) mapping with SNPs and (ii) enrichment analyses with SNP-sets on complex traits. Through simulations, we show that our method improves upon state-of-the-art association mapping and enrichment approaches across a wide range of genetic architectures. We then further illustrate the benefits of BANNs by analyzing real GWA data assayed in approximately 2,000 heterogenous stock of mice from the Wellcome Trust Centre for Human Genetics and approximately 7,000 individuals from the Framingham Heart Study. Lastly, using a random subset of individuals of European ancestry from the UK Biobank, we show that BANNs is able to replicate known associations in high and low-density lipoprotein cholesterol content.     

Functional Metabolic Map of Faecalibacterium prausnitzii,a Beneficial Human Gut Microbe

The human gut microbiota plays a central role in human well-being and disease. In this study, we present an integrated, iterative approach of computational modeling, in vitro experiments, metabolomics, and genomic analysis to accelerate the identification of metabolic capabilities for poorly characterized (anaerobic) microorganisms. We demonstrate this approach for the beneficial human gut microbe Faecalibacterium prausnitzii strain A2-165. We generated an automated draft reconstruction, which we curated against the limited biochemical data. This reconstruction modeling was used to develop in silico and in vitro a chemically defined medium (CDM), which was validated experimentally. Subsequent metabolomic analysis of the spent medium for growth on CDM was performed. We refined our metabolic reconstruction according to in vitro observed metabolite consumption and secretion and propose improvements to the current genome annotation of F. prausnitzii A2-165. We then used the reconstruction to systematically characterize its metabolic properties. Novel carbon source utilization capabilities and inabilities were predicted based on metabolic modeling and validated experimentally. This study resulted in a functional metabolic map of F. prausnitzii, which is available for further applications. The presented workflow can be readily extended to other poorly characterized and uncharacterized organisms to yield novel biochemical insights about the target organism.     

MR microscopy of the human fetal upper extremity – a proof-of-principle study

Background

Bone morphogenetic proteins regulate multiple processes in embryonic development, including early dorso-ventral patterning and neural crest development. BMPs activate heteromeric receptor complexes consisting of type I and type II receptor-serine/threonine kinases. BMP receptors Ia and Ib, also known as ALK3 and ALK6 respectively, are the most common type I receptors that likely mediate most BMP signaling events. Since early expression patterns and functions in Xenopus laevis development have not been described, we have addressed these questions in the present study.

Results

Here we have analyzed the temporal and spatial expression patterns of ALK3 and ALK6; we have also carried out loss-of-function studies to define the function of these receptors in early Xenopus development. We detected both redundant and non-redundant roles of ALK3 and ALK6 in dorso-ventral patterning. From late gastrula stages onwards, their expression patterns diverged, which correlated with a specific, non-redundant requirement of ALK6 in post-gastrula neural crest cells. ALK6 was essential for induction of neural crest cell fate and further development of the neural crest and its derivatives.

Conclusions

ALK3 and ALK6 both contribute to the gene regulatory network that regulates dorso-ventral patterning; they play partially overlapping and partially non-redundant roles in this process. ALK3 and ALK6 are independently required for the spatially restricted activation of BMP signaling and msx2 upregulation at the neural plate border, whereas in post-gastrula development ALK6 exerts a highly specific, conserved function in neural crest development.

     

Applications and Challenges of Machine Learning Methods in Alzheimer's Disease Multi-Source Data Analysis

BackgroundRecent development in neuroimaging and genetic testing technologies have made it possible to measure pathological features associated with Alzheimer''s disease (AD) in vivo. Mining potential molecular markers of AD from high-dimensional, multi-modal neuroimaging and omics data will provide a new basis for early diagnosis and intervention in AD. In order to discover the real pathogenic mutation and even understand the pathogenic mechanism of AD, lots of machine learning methods have been designed and successfully applied to the analysis and processing of large-scale AD biomedical data.ObjectiveTo introduce and summarize the applications and challenges of machine learning methods in Alzheimer''s disease multi-source data analysis.MethodsThe literature selected in the review is obtained from Google Scholar, PubMed, and Web of Science. The keywords of literature retrieval include Alzheimer''s disease, bioinformatics, image genetics, genome-wide association research, molecular interaction network, multi-omics data integration, and so on.ConclusionThis study comprehensively introduces machine learning-based processing techniques for AD neuroimaging data and then shows the progress of computational analysis methods in omics data, such as the genome, proteome, and so on. Subsequently, machine learning methods for AD imaging analysis are also summarized. Finally, we elaborate on the current emerging technology of multi-modal neuroimaging, multi-omics data joint analysis, and present some outstanding issues and future research directions.     

肿瘤亚型识别研究中智能算法的应用

目的:为解决肿瘤亚型识别过程中易出现的维数灾难和过拟合问题,提出了一种改进的粒子群BP神经网络集成算法。方法:算法采用欧式距离和互信息来初步过滤冗余基因,之后用Relief算法进一步处理,得到候选特征基因集合。采用BP神经网络作为基分类器,将特征基因提取与分类器训练相结合,改进的粒子群对其权值和阈值进行全局搜索优化。结果:当隐含层神经元个数为5时,候选特征基因个数为110时,QPSO/BP算法全局优化和搜索,此时的分类准确率最高。结论:该算法不但提高了肿瘤分型识别的准确率,而且降低了学习的复杂度。     

Dependency parsing of biomedical text with BERT

Background

Entity normalization is an important information extraction task which has gained renewed attention in the last decade, particularly in the biomedical and life science domains. In these domains, and more generally in all specialized domains, this task is still challenging for the latest machine learning-based approaches, which have difficulty handling highly multi-class and few-shot learning problems. To address this issue, we propose C-Norm, a new neural approach which synergistically combines standard and weak supervision, ontological knowledge integration and distributional semantics.

Results

Our approach greatly outperforms all methods evaluated on the Bacteria Biotope datasets of BioNLP Open Shared Tasks 2019, without integrating any manually-designed domain-specific rules.

Conclusions

Our results show that relatively shallow neural network methods can perform well in domains that present highly multi-class and few-shot learning problems.

     

基于BP神经网络与ETM+遥感数据的盐城滨海自然湿地覆被分类

高效而精确的湿地遥感分类是大范围湿地资源动态监测与管理的必要保障。本研究使用ETM 遥感数据,借助Matlab神经网络工具箱,构建了基于BP神经网络的滨海湿地覆被分类模型,并将其应用于江苏盐城沿海湿地珍禽国家级自然保护区的核心区的自然湿地覆被分类研究中。本研究选择3、4、7、8波段作为输入层变量,单隐藏层设为10个节点,输出层变量对应待划分的8种覆被类型,构建三层式BP神经网络滨海湿地覆被分类模型。结果显示,BP分类总精度为85.91%,Kappa系数为0.8328,与最小距离法和极大似然法的分类总精度相比,分别提高了7.99%和6.08%,Kappa系数也相比提高。研究结果表明,BP神经网络分类法是一种较为有效的湿地遥感影像分类技术,能够提高分类精度。     

Metabolic response of yellow mealworm larvae to two alternative rearing substrates

Introduction

Bitter melon (Momordica charantia, Cucurbitaceae) is a popular edible medicinal plant, which has been used as a botanical dietary supplement for the treatment of diabetes and obesity in Chinese folk medicine. Previously, our team has proved that cucurbitanes triterpenoid were involved in bitter melon’s anti-diabetic effects as well as on increasing energy expenditure. The triterpenoids composition can however be influenced by changes of varieties or habitats.

Objectives

To clarify the significance of bioactive metabolites diversity among different bitter melons and to provide a guideline for selection of bitter melon varieties, an exploratory study was carried out using a UHPLC-HRMS based metabolomic study to identify chemotypes.

Methods

Metabolites of 55 seed samples of bitter melon collected in different parts of China were profiled by UHPLC-HRMS. The profiling data were analysed with multivariate (MVA) statistical methods. Principle component analysis (PCA) and hierarchical cluster analysis (HCA) were applied for sample differentiation. Marker compounds were identified by comparing spectroscopic data with isolated compounds, and additional triterpenes were putatively identified by propagating annotations through a molecular network (MN) generated from UHPLC-HRMS & MS/MS metabolite profiling.

Results

PCA and HCA provided a good discrimination between bitter melon samples from various origins in China. This study revealed for the first time the existence of two chemotypes of bitter melon. Marker compounds of those two chemotypes were identified at different MSI levels. The combined results of MN and MVA demonstrated that the two chemotypes mainly differ in their richness in cucurbitane versus oleanane triterpenoid glycosides (CTGs vs. OTGs).

Conclusion

Our finding revealed a clear chemotype distribution of bioactive components across bitter melon varieties. While bioactivities of individual CTGs and OTGs still need to be investigated in more depth, our results could help in future the selection of bitter melon varieties with optimised metabolites profile for an improved management of diabetes with this popular edible Chinese folk medicine.

     

Backpropagation Neural Network for Processing of Missing Data in Breast Cancer Detection

BackgroundA complete dataset is essential for biomedical implementation. Due to the limitation of objective or subjective factors, missing data often occurs, which exerts uncertainty in the subsequent data processing. Commonly used methods of interpolation are interpolating substitute values that keep minimum error. Some applications of statistics are usually used for handling this problem.MethodsWe are trying to find a higher performance interpolation method compared with the usual statistic methods, by using artificial intelligence which is in full swing today. The prediction and classification of backpropagation neural network are used in this paper, describes a missing data interpolation method to propose the interpolation model that mines association rules in the data. In the experiment, depending on a multi-layer network structure, the model is trained and tested by sample data, constantly revises network weights and thresholds. The error function decreases along the negative gradient direction and approaches the expected real output. The model is validated on the breast cancer dataset, and we select real samples from the data set for validation, moreover, add four traditional methods as a control group.ResultsThe proposed method has great performance improvement in the interpolation of missing data. Experimental results show that the interpolation accuracy of our proposed method (84%) is higher than four traditional methods (1.33%, 74.67%, 73.33%, 77.33%) as mentioned in this paper, BPNN stays low in MSE evaluation. Finally, we analyze the performance of various methods in processing missing data.ConclusionsThe study in this paper has estimated missing data with high accuracy as much as possible to reduce the negative impact in the diagnosis of real life. At the same time, it can also assist in missing data processing in the biomedical field.     

基于高密度单核苷酸多态性的共祖远亲缘关系预测算法准确性研究

目的 研究构建基于共祖（identity-by-descent，IBD）片段算法预测远亲缘关系分析流程并评估预测准确性。方法 采用高密度单核苷酸多态性（single nucleotide polymorphism，SNP）芯片对253份家系样本进行检测，研究基于IBD片段算法的分析流程进行两两个体间亲缘关系预测，评估预测准确性。随机减少SNP位点，评估位点数对算法预测准确性的影响。结果 IBD片段算法预测1~7级亲缘关系平均置信区间准确率为94.72%，预测可信度为99.77%，6级及以上亲缘关系预测时出现假阴性。随着SNP数量减少，预测准确性会出现一定程度的下降。结论 IBD片段算法可用于7级以内亲缘关系的预测，该算法在群体遗传学、法医遗传学等领域有重要应用价值。     

Graph embedding ensemble methods based on the heterogeneous network for lncRNA-miRNA interaction prediction

Background

Researchers discover LncRNA–miRNA regulatory paradigms modulate gene expression patterns and drive major cellular processes. Identification of lncRNA-miRNA interactions (LMIs) is critical to reveal the mechanism of biological processes and complicated diseases. Because conventional wet experiments are time-consuming, labor-intensive and costly, a few computational methods have been proposed to expedite the identification of lncRNA-miRNA interactions. However, little attention has been paid to fully exploit the structural and topological information of the lncRNA-miRNA interaction network.

Results

In this paper, we propose novel lncRNA-miRNA prediction methods by using graph embedding and ensemble learning. First, we calculate lncRNA-lncRNA sequence similarity and miRNA-miRNA sequence similarity, and then we combine them with the known lncRNA-miRNA interactions to construct a heterogeneous network. Second, we adopt several graph embedding methods to learn embedded representations of lncRNAs and miRNAs from the heterogeneous network, and construct the ensemble models using two ensemble strategies. For the former, we consider individual graph embedding based models as base predictors and integrate their predictions, and develop a method, named GEEL-PI. For the latter, we construct a deep attention neural network (DANN) to integrate various graph embeddings, and present an ensemble method, named GEEL-FI. The experimental results demonstrate both GEEL-PI and GEEL-FI outperform other state-of-the-art methods. The effectiveness of two ensemble strategies is validated by further experiments. Moreover, the case studies show that GEEL-PI and GEEL-FI can find novel lncRNA-miRNA associations.

Conclusion

The study reveals that graph embedding and ensemble learning based method is efficient for integrating heterogeneous information derived from lncRNA-miRNA interaction network and can achieve better performance on LMI prediction task. In conclusion, GEEL-PI and GEEL-FI are promising for lncRNA-miRNA interaction prediction.