Annotated Graph Research Articles

Thanos: An R Package for the Gene-Centric Analysis of Functional Potential in Metagenomic Samples.

As the amount of metagenomic sequencing continues to increase, there is a growing need for tools that help biologists make sense of the data. Specifically, researchers are often interested in the potential of a microbial community to carry out a metabolic reaction, but this analysis requires knitting together multiple software tools into a complex pipeline. Thanos offers a user-friendly R package designed for the pathway-centric analysis and visualization of the functions encoded within metagenomic samples. It allows researchers to go beyond taxonomic profiles and find out, quantitatively, which pathways are prevalent in an environment, as well as comparing different environments in terms of their functional potential. The analysis is based on the sequencing depth of the genes of interest, either in the metagenome-assembled genomes (MAGs) or in the assembled reads (contigs), using a normalization strategy that enables comparison across samples. The package can import the data from multiple formats and offers functions for the visualization of the results as bar plots of the functional profile, box plots of compare functions across samples, and annotated pathway graphs. By streamlining the analysis of the functional potential encoded in microbial communities, Thanos can enable impactful discoveries in all the fields touched by metagenomics, from human health to the environmental sciences.

ServiceAnomaly: An anomaly detection approach in microservices using distributed traces and profiling metrics

Anomaly detection is an essential activity for identifying abnormal behaviours in microservice-based systems. A common approach is to model the system behaviour during normal operation using either distributed traces or profiling metrics. The model is then used to detect anomalies during system operation. In this paper, we present a new anomaly detection approach, called ServiceAnomaly, for anomaly detection in microservice systems that combines distributed traces and six profiling metrics to build an annotated directed acyclic graph that characterizes the normal behaviour of the system. Unlike existing techniques, our approach captures the context propagation provided by distributed traces as a graph that is annotated with functions characterizing both linear and non-linear relationships between profiling metrics. The final annotated graph is used to detect abnormal executions during system operation. The results of applying our approach to two open-source benchmarks show that our approach detects anomalies with an F1-score up to 86%. We also show how developers can use the annotated graph to reason about the causes of anomalies

Nlive: an R package to facilitate the application of the sigmoidal and random changepoint mixed models

BackgroundThe use of mixed effect models with a specific functional form such as the Sigmoidal Mixed Model and the Piecewise Mixed Model (or Changepoint Mixed Model) with abrupt or smooth random change allows the interpretation of the defined parameters to understand longitudinal trajectories. Currently, there are no interface R packages that can easily fit the Sigmoidal Mixed Model allowing the inclusion of covariates or incorporating recent developments to fit the Piecewise Mixed Model with random change.ResultsTo facilitate the modeling of the Sigmoidal Mixed Model, and Piecewise Mixed Model with abrupt or smooth random change, we have created an R package called nlive. All needed pieces such as functions, covariance matrices, and initials generation were programmed. The package was implemented with recent developments such as the polynomial smooth transition of the piecewise mixed model with improved properties over Bacon-Watts, and the stochastic approximation expectation-maximization (SAEM) for efficient estimation. It was designed to help interpretation of the output by providing features such as annotated output, warnings, and graphs. Functionality, including time and convergence, was tested using simulations. We provided a data example to illustrate the package use and output features and interpretation. The package implemented in the R software is available from the Comprehensive R Archive Network (CRAN) at https://CRAN.R-project.org/package=nlive.ConclusionsThe nlive package for R fits the Sigmoidal Mixed Model and the Piecewise Mixed: abrupt and smooth. The nlive allows fitting these models with only five mandatory arguments that are intuitive enough to the less sophisticated users.

Accurate and fast graph-based pangenome annotation and clustering with ggCaller.

Bacterial genomes differ in both gene content and sequence mutations, which underlie extensive phenotypic diversity, including variation in susceptibility to antimicrobials or vaccine-induced immunity. To identify and quantify important variants, all genes within a population must be predicted, functionally annotated, and clustered, representing the "pangenome." Despite the volume of genome data available, gene prediction and annotation are currently conducted in isolation on individual genomes, which is computationally inefficient and frequently inconsistent across genomes. Here, we introduce the open-source software graph-gene-caller (ggCaller). ggCaller combines gene prediction, functional annotation, and clustering into a single workflow using population-wide de Bruijn graphs, removing redundancy in gene annotation and resulting in more accurate gene predictions and orthologue clustering. We applied ggCaller to simulated and real-world bacterial data sets containing hundreds or thousands of genomes, comparing it to current state-of-the-art tools. ggCaller has considerable speed-ups with equivalent or greater accuracy, particularly with data sets containing complex sources of error, such as assembly contamination or fragmentation. ggCaller is also an important extension to bacterial genome-wide association studies, enabling querying of annotated graphs for functional analyses. We highlight this application by functionally annotating DNA sequences with significant associations to tetracycline and macrolide resistance in Streptococcus pneumoniae, identifying key resistance determinants that were missed when using only a single reference genome. ggCaller is a novel bacterial genome analysis tool with applications in bacterial evolution and epidemiology.

Knowledge Graph Embeddings for ICU readmission prediction

BackgroundIntensive Care Unit (ICU) readmissions represent both a health risk for patients,with increased mortality rates and overall health deterioration, and a financial burden for healthcare facilities. As healthcare became more data-driven with the introduction of Electronic Health Records (EHR), machine learning methods have been applied to predict ICU readmission risk. However, these methods disregard the meaning and relationships of data objects and work blindly over clinical data without taking into account scientific knowledge and context. Ontologies and Knowledge Graphs can help bridge this gap between data and scientific context, as they are computational artefacts that represent the entities of a domain and their relationships to each other in a formalized way.Methods and resultsWe have developed an approach that enriches EHR data with semantic annotations to ontologies to build a Knowledge Graph. A patient’s ICU stay is represented by Knowledge Graph embeddings in a contextualized manner, which are used by machine learning models to predict 30-days ICU readmissions. This approach is based on several contributions: (1) an enrichment of the MIMIC-III dataset with patient-oriented annotations to various biomedical ontologies; (2) a Knowledge Graph that defines patient data with biomedical ontologies; (3) a predictive model of ICU readmission risk that uses Knowledge Graph embeddings; (4) a variant of the predictive model that targets different time points during an ICU stay. Our predictive approaches outperformed both a baseline and state-of-the-art works achieving a mean Area Under the Receiver Operating Characteristic Curve of 0.827 and an Area Under the Precision-Recall Curve of 0.691. The application of this novel approach to help clinicians decide whether a patient can be discharged has the potential to prevent the readmission of 40% of Intensive Care Unit patients, without unnecessarily prolonging the stay of those who would not require it.ConclusionThe coupling of semantic annotation and Knowledge Graph embeddings affords two clear advantages: they consider scientific context and they are able to build representations of EHR information of different types in a common format. This work demonstrates the potential for impact that integrating ontologies and Knowledge Graphs into clinical machine learning applications can have.

Calliope-Net: Automatic Generation of Graph Data Facts via Annotated Node-Link Diagrams.

Graph or network data are widely studied in both data mining and visualization communities to review the relationship among different entities and groups. The data facts derived from graph visual analysis are important to help understand the social structures of complex data, especially for data journalism. However, it is challenging for data journalists to discover graph data facts and manually organize correlated facts around a meaningful topic due to the complexity of graph data and the difficulty to interpret graph narratives. Therefore, we present an automatic graph facts generation system, Calliope-Net, which consists of a fact discovery module, a fact organization module, and a visualization module. It creates annotated node-link diagrams with facts automatically discovered and organized from network data. A novel layout algorithm is designed to present meaningful and visually appealing annotated graphs. We evaluate the proposed system with two case studies and an in-lab user study. The results show that Calliope-Net can benefit users in discovering and understanding graph data facts with visually pleasing annotated visualizations.

Lossless indexing with counting de Bruijn graphs.

Sequencing data are rapidly accumulating in public repositories. Making this resource accessible for interactive analysis at scale requires efficient approaches for its storage and indexing. There have recently been remarkable advances in building compressed representations of annotated (or colored) de Bruijn graphs for efficiently indexing k-mer sets. However, approaches for representing quantitative attributes such as gene expression or genome positions in a general manner have remained underexplored. In this work, we propose counting de Bruijn graphs, a notion generalizing annotated de Bruijn graphs by supplementing each node-label relation with one or many attributes (e.g., a k-mer count or its positions). Counting de Bruijn graphs index k-mer abundances from 2652 human RNA-seq samples in over eightfold smaller representations compared with state-of-the-art bioinformatics tools and is faster to construct and query. Furthermore, counting de Bruijn graphs with positional annotations losslessly represent entire reads in indexes on average 27% smaller than the input compressed with gzip for human Illumina RNA-seq and 57% smaller for Pacific Biosciences (PacBio) HiFi sequencing of viral samples. A complete searchable index of all viral PacBio SMRT reads from NCBI's Sequence Read Archive (SRA) (152,884 samples, 875 Gbp) comprises only 178 GB. Finally, on the full RefSeq collection, we generate a lossless and fully queryable index that is 4.6-fold smaller than the MegaBLAST index. The techniques proposed in this work naturally complement existing methods and tools using de Bruijn graphs, and significantly broaden their applicability: from indexing k-mer counts and genome positions to implementing novel sequence alignment algorithms on top of highly compressed graph-based sequence indexes.

Audio–visual annotation graphs for guiding lens-based scene exploration

We introduce a novel approach for guiding users in the exploration of annotated 2D models using interactive visualization lenses. Information on the interesting areas of the model is encoded in an annotation graph generated at authoring time. Each graph node contains an annotation, in the form of a visual and audio markup of the area of interest, as well as the optimal lens parameters that should be used to explore the annotated area and a scalar representing the annotation importance. Directed graph edges are used, instead, to represent preferred ordering relations in the presentation of annotations, by having each node point to the set of nodes that should be seen before presenting its associated annotation. A scalar associated to each edge determines the strength of this constraint. At run-time, users explore the scene with the lens, and the graph is exploited to select the annotations that have to be presented at a given time. The selection is based on the current view and lens parameters, the graph content and structure, and the navigation history. The best annotation under the lens is presented by playing the associated audio clip and showing the visual markup in overlay. When the user releases control, requests guidance, opts for automatic touring, or when no available annotations are under the lens, the system guides the user towards the next best annotation using glyphs, and potentially moves the lens towards it if the user remains inactive. This approach supports the seamless blending of an automatic tour of the data with interactive lens-based exploration. The approach is tested and discussed in the context of the exploration of multi-layer relightable models.

AAPFE: Aligned Assembly Pre-Training Function Embedding for Malware Analysis

The use of natural language processing to analyze binary data is a popular research topic in malware analysis. Embedding binary code into a vector is an important basis for building a binary analysis neural network model. Current solutions focus on embedding instructions or basic block sequences into vectors with recurrent neural network models or utilizing a graph algorithm on control flow graphs or annotated control flow graphs to generate binary representation vectors. In malware analysis, most of these studies only focus on the single structural information of the binary and rely on one corpus. It is difficult for vectors to effectively represent the semantics and functionality of binary code. Therefore, this study proposes aligned assembly pre-training function embedding, a function embedding scheme based on a pre-training aligned assembly. The scheme creatively applies data augmentation and a triplet network structure to the embedding model training. Each sub-network extracts instruction sequence information using the self-attention mechanism and basic block graph structure information with the graph convolution network model. An embedding model is pre-trained with the produced aligned assembly triplet function dataset and is subsequently evaluated against a series of comparative experiments and application evaluations. The results show that the model is superior to the state-of-the-art methods in terms of precision, precision ranking at top N (p@N), and the area under the curve, verifying the effectiveness of the aligned assembly pre-training and multi-level information extraction methods.

Identification, Quantification, and Testing of Alternative Splicing Events from RNA-Seq Data Using SplAdder.

Alternative splicing (AS) is a regulatory process during mRNA maturation that shapes higher eukaryotes' complex transcriptomes. High-throughput sequencing of RNA (RNA-Seq) allows for measurements of AS transcripts at an unprecedented depth and diversity. The ever-expanding catalog of known AS events provides biological insights into gene regulation, population genetics, or in the context of disease. Here, we present an overview on the usage of SplAdder, a graph-based alternative splicing toolbox, which can integrate an arbitrarily large number of RNA-Seq alignments and a given annotation file to augment the shared annotation based on RNA-Seq evidence. The shared augmented annotation graph is then used to identify, quantify, and confirm alternative splicing events based on the RNA-Seq data. Splice graphs for individual alignments can also be tested for significant quantitative differences between other samples or groups of samples.

Comparative Analysis of Unsupervised Protein Similarity Prediction Based on Graph Embedding.

The study of protein–protein interaction and the determination of protein functions are important parts of proteomics. Computational methods are used to study the similarity between proteins based on Gene Ontology (GO) to explore their functions and possible interactions. GO is a series of standardized terms that describe gene products from molecular functions, biological processes, and cell components. Previous studies on assessing the similarity of GO terms were primarily based on Information Content (IC) between GO terms to measure the similarity of proteins. However, these methods tend to ignore the structural information between GO terms. Therefore, considering the structural information of GO terms, we systematically analyze the performance of the GO graph and GO Annotation (GOA) graph in calculating the similarity of proteins using different graph embedding methods. When applied to the actual Human and Yeast datasets, the feature vectors of GO terms and proteins are learned based on different graph embedding methods. To measure the similarity of the proteins annotated by different GO numbers, we used Dynamic Time Warping (DTW) and cosine to calculate protein similarity in GO graph and GOA graph, respectively. Link prediction experiments were then performed to evaluate the reliability of protein similarity networks constructed by different methods. It is shown that graph embedding methods have obvious advantages over the traditional IC-based methods. We found that random walk graph embedding methods, in particular, showed excellent performance in calculating the similarity of proteins. By comparing link prediction experiment results from GO(DTW) and GOA(cosine) methods, it is shown that GO(DTW) features provide highly effective information for analyzing the similarity among proteins.

Graph-based open-ended survey on concerns related to COVID-19.

The COVID-19 pandemic is an unprecedented public health crisis with broad social and economic consequences. We conducted four surveys between April and August 2020 using the graph-based open-ended survey (GOS) framework, and investigated the most pressing concerns and issues for the general public in Japan. The GOS framework is a hybrid of the two traditional survey frameworks that allows respondents to post their opinions in a free-format style, which can subsequently serve as one of the choice items for other respondents, just as in a multiple-choice survey. As a result, this framework generates an opinion graph that relates opinions and respondents. We can also construct annotated opinion graphs to achieve a higher resolution. By clustering the annotated opinion graphs, we revealed the characteristic evolution of the response patterns as well as the interconnectedness and multi-faceted nature of opinions. Substantively, our notable finding is that “social pressure,” not “infection risk,” was one of the major concerns of our respondents. Social pressure refers to criticism and discrimination that they anticipate receiving from others should they contract COVID-19. It is possible that the collectivist nature of Japanese culture coupled with the government’s policy of relying on personal responsibility to combat COVID-19 explains some of the above findings, as the latter has led to the emergence of vigilantes. The presence of mutual surveillance can contribute to growing skepticism toward others as well as fear of ostracism, which may have negative consequences at both the societal and individual levels.

Crosslink: An R Package for Network Visualization of Grouped Nodes.

The demand for network visualization of relationships between nodes attributed to different categories grows in various biomedical research scenarios, such as gene regulatory networks, drug-target networks, ligand-receptor interactions and association networks of multi-omics elements. Elegantly visualizing the relationships between nodes with complex metadata of nodes and edges appended may inspire new insights. Here, we developed the crosslink R package, tailored for network visualization of grouped nodes, to provide a series of flexible functions for generating network diagrams. We first designed a CrossLink class for storage of metadata about nodes and edges and manipulation of node coordinates. Then affine transformation and function mapping transformation are implemented to perform fundamental node coordinates transformation by groups, based on which various network layouts can be defined easily. For convenience, we predefined several commonly used layouts, including row, column, arc, polygon and hive, which also can be combined in one layout. Finally, we designed a user-friendly wrapper function to draw network connections, aesthetic mappings of metadata and decoration with related annotation graphs in one interface by taking advantage of the powerful ggplot2 system. Overall, the crosslink R package is easy-to-use for achieving complex visualization of a network diagram of grouped nodes surrounded by associated annotation graphs.Availability and ImplementationCosslink is an open-source R package, freely available from github: https://github.com/zzwch/crosslink; A detailed user documentation can be found in https://zzwch.github.io/crosslink/.

Scalable robust graph and feature extraction for arbitrary vessel networks in large volumetric datasets

BackgroundRecent advances in 3D imaging technologies provide novel insights to researchers and reveal finer and more detail of examined specimen, especially in the biomedical domain, but also impose huge challenges regarding scalability for automated analysis algorithms due to rapidly increasing dataset sizes. In particular, existing research towards automated vessel network analysis does not always consider memory requirements of proposed algorithms and often generates a large number of spurious branches for structures consisting of many voxels. Additionally, very often these algorithms have further restrictions such as the limitation to tree topologies or relying on the properties of specific image modalities.ResultsWe propose a scalable iterative pipeline (in terms of computational cost, required main memory and robustness) that extracts an annotated abstract graph representation from the foreground segmentation of vessel networks of arbitrary topology and vessel shape. The novel iterative refinement process is controlled by a single, dimensionless, a-priori determinable parameter.ConclusionsWe are able to, for the first time, analyze the topology of volumes of roughly 1 TB on commodity hardware, using the proposed pipeline. We demonstrate improved robustness in terms of surface noise, vessel shape deviation and anisotropic resolution compared to the state of the art. An implementation of the presented pipeline is publicly available in version 5.1 of the volume rendering and processing engine Voreen.

Graph embeddings on gene ontology annotations for protein\u2013protein interaction prediction

BackgroundProtein–protein interaction (PPI) prediction is an important task towards the understanding of many bioinformatics functions and applications, such as predicting protein functions, gene-disease associations and disease-drug associations. However, many previous PPI prediction researches do not consider missing and spurious interactions inherent in PPI networks. To address these two issues, we define two corresponding tasks, namely missing PPI prediction and spurious PPI prediction, and propose a method that employs graph embeddings that learn vector representations from constructed Gene Ontology Annotation (GOA) graphs and then use embedded vectors to achieve the two tasks. Our method leverages on information from both term–term relations among GO terms and term-protein annotations between GO terms and proteins, and preserves properties of both local and global structural information of the GO annotation graph.ResultsWe compare our method with those methods that are based on information content (IC) and one method that is based on word embeddings, with experiments on three PPI datasets from STRING database. Experimental results demonstrate that our method is more effective than those compared methods.ConclusionOur experimental results demonstrate the effectiveness of using graph embeddings to learn vector representations from undirected GOA graphs for our defined missing and spurious PPI tasks.

NIMG-69. PERSONALIZED CONNECTOMIC SIGNATURES: BRIDGING THE GAP BETWEEN NEURO-ONCOLOGY AND CONNECTOMICS

Abstract PURPOSE Connectomics has led to significant neuroscientific findings within the last two decades, eventually making impact in the clinics. Neuro-oncology can benefit immensely from connectomics in evaluating structural connectivity of brains with tumor for pre- and post-treatment planning, as a tumor connectome along with derived network measures will make it possible to determine the cognitive effects of treatment and quantify the effect of surgery on quality of life. However, generating connectomes in the presence of tumor is a challenging task. Specifically, registration of an atlas to the brain, which is essential in parcellating the brain into regions of interest, fails around the tumor due to mass effect and infiltration related distortions which are not present in the atlas that comes from a healthy brain. We aim to tackle this problem by introducing a novel atlas registration method. METHOD Although tumor deforms the geometrical shape of its surrounding regions, it does not violate the connectivity of displaced cortical voxels to the rest of the brain. Leveraging this fact, we represent the brain as an annotated graph with nodes representing ROIs encoding geometric features of regions and weighted edges representing the connectivity between regions. In encoding the surroundings of the tumor into the graph, we subsample the region into smaller patches to represent the area with multiple nodes. We then calculate many-to-one graph matching between the graphs of a tumor patient and a healthy control to associate surroundings of tumor with healthy ROIs. OUTCOME A tumor connectome showing how the connectivity is morphed around the tumor, which can further be extended to creating connectomes of recurrence. CLINICAL IMPLICATIONS Use of connectomes can revolutionize neuro-oncology by helping surgeons in estimating structural, functional, and behavioral outcomes of resection prior to surgery and in predicting recovery after the surgery, potentially suggesting subject specific treatment plans.

MD-MinerP: Interaction Profiling Bipartite Graph Mining for Malware-Control Domain Detection

Despite the efforts of information security experts, cybercrimes are still emerging at an alarming rate. Among the tools used by cybercriminals, malicious domains are indispensable and harm from the Internet has become a global problem. Malicious domains play an important role from SPAM and Cross-Site Scripting (XSS) threats to Botnet and Advanced Persistent Threat (APT) attacks at large scales. To ensure there is not a single point of failure or to prevent their detection and blocking, malware authors have employed domain generation algorithms (DGAs) and domain-flux techniques to generate a large number of domain names for malicious servers. As a result, malicious servers are difficult to detect and remove. Furthermore, the clues of cybercrime are stored in network traffic logs, but analyzing long-term big network traffic data is a challenge. To adapt the technology of cybercrimes and automatically detect unknown malicious threats, we previously proposed a system called MD-Miner. To improve its efficiency and accuracy, we propose the MD-MinerP here, which generates more features with identification capabilities in the feature extraction stage. Moreover, MD-MinerP adapts interaction profiling bipartite graphs instead of annotated bipartite graphs. The experimental results show that MD-MinerP has better area under curve (AUC) results and found new malicious domains that could not be recognized by other threat intelligence systems. The MD-MinerP exhibits both scalability and applicability, which has been experimentally validated on actual enterprise network traffic.

Scalable and Parallel Deep Bayesian Optimization on Attributed Graphs.

We propose a general and scalable global optimization framework directly operating on annotated graph data by introducing a Bayesian graph neural network to approximate the expensive-to-evaluate objectives. It prevents the cubical complexity of Gaussian processes and can scale linearly with the number of observations. Its parallelized variant makes it scalable. We provide strict theoretical support on its convergence. Intensive experiments conducted on both artificial and real-world problems, including molecular discovery and urban road network design, demonstrate the effectiveness of the proposed methods compared with the current state of the art.

Comparing Molecular Patterns Using the Example of SMARTS: Theory and Algorithms.

Molecular patterns are widely used for compound filtering in molecular design endeavors. They describe structural properties that are connected with unwanted physical or chemical properties like reactivity or toxicity. With filter sets comprising hundreds of structural filters, an analytic approach to compare those patterns is needed. Here we present a novel approach to solve the generic pattern comparison problem. We introduce chemically inspired fingerprints for pattern nodes and edges to derive an easy-to-compare pattern representation. On two annotated pattern graphs we apply a maximum common subgraph algorithm enabling the calculation of pattern inclusion and similarity. The resulting algorithm can be used in many different ways. We can automatically derive pattern hierarchies or search in large pattern collections for more general or more specific patterns. To the best of our knowledge, the presented algorithm is the first of its kind enabling these types of chemical pattern analytics. Our new tool named SMARTScompare is an implementation of the approach for the SMARTS language, which is the quasi-standard for structural filters. We demonstrate the capabilities of SMARTScompare on a large collection of SMARTS patterns from real applications.

ChopStitch: exon annotation and splice graph construction using transcriptome assembly and whole genome sequencing data.

MotivationSequencing studies on non-model organisms often interrogate both genomes and transcriptomes with massive amounts of short sequences. Such studies require de novo analysis tools and techniques, when the species and closely related species lack high quality reference resources. For certain applications such as de novo annotation, information on putative exons and alternative splicing may be desirable.ResultsHere we present ChopStitch, a new method for finding putative exons de novo and constructing splice graphs using an assembled transcriptome and whole genome shotgun sequencing (WGSS) data. ChopStitch identifies exon-exon boundaries in de novo assembled RNA-Seq data with the help of a Bloom filter that represents the k-mer spectrum of WGSS reads. The algorithm also accounts for base substitutions in transcript sequences that may be derived from sequencing or assembly errors, haplotype variations, or putative RNA editing events. The primary output of our tool is a FASTA file containing putative exons. Further, exon edges are interrogated for alternative exon-exon boundaries to detect transcript isoforms, which are represented as splice graphs in DOT output format.Availability and implementationChopStitch is written in Python and C++ and is released under the GPL license. It is freely available at https://github.com/bcgsc/ChopStitch.Supplementary information Supplementary data are available at Bioinformatics online.