Deep Structural Information Research Articles

Seismic probing of buried ancient terrane boundaries - insight into Fennoscandia’s Palaeoproterozoic continental formation

Terrane boundaries are usually mapped from structures, lithologies and ages of the bedrock geology. Geophysical studies occasionally used to image terrane boundaries at depth typically yield localised information. In this contribution we demonstrate that it is possible to map Palaeoproterozoic terrane boundaries over large areas in northwest Fennoscandia through modelling of the crustal structure using receiver function inversion. Our new model suggests the existence of three “arms” of thick crust interpreted as deep expressions of Palaeoproterozoic terrane boundaries. We also observe previously unknown high velocity lower crust that we relate to Palaeoproterozoic rifting. The deep structural information shows that crustal structures can be preserved over billions of years and yields a three-dimensional crustal terrane model. This model improves our understanding of Palaeoproterozoic tectonics and continent formation processes.

Exploring geothermal resources using electromagnetic methods in coastal areas of volcanic islands: Challenges of nearshore and land 3D controlled-source electromagnetic data

Three-dimensional geophysical exploration is essential in identifying favorable areas and derisking high-temperature geothermal projects. In particular, electrical resistivity imaging plays a key role in this exploration due to its sensitivity to the presence of alteration products, geothermal fluid circulation, and temperature. As 3D seismic exploration is rarely effective in volcanic environments, resistivity methods such as magnetotellurics (MTs) are often used to extract deep structural information. However, deep electromagnetic (EM) imaging in coastal areas of volcanic islands with MT can be challenging due to anthropogenic noise induced by urbanized areas concentrated around the coast. The use of active EM sources, such as airborne EM (AEM) and controlled-source EM (CSEM), as a complement to MT is a solution for overcoming anthropogenic noise. However, applying these methods in this context is still challenging due to the proximity to the sea/land interface, large variations in topography and nearshore bathymetry, and the heterogeneity of the near surface. Our approach outlines the challenges of acquiring, processing, and inverting nearshore and land 3D CSEM data in such complex environments. The CSEM data are part of a multimethod geothermal exploration on the island of Martinique in the French West Indies, and its 3D inversion result is compared with the previous regional 3D MT and AEM inversion results. In addition to MT, CSEM may highlight the location of a potential high-temperature paleo-reservoir at shallow depths under the urbanized area of Petite-Anse covered by a paleo-clay cap ranging from a few meters to several hundred meters in thickness. We conclude by proposing possible improvements for CSEM and multimethod methodologies to obtain more reliable exploratory models.

A Rumor Detection Model Incorporating Propagation Path Contextual Semantics and User Information.

Currently, social media is full of rumors. To stop rumors from spreading further, rumor detection has received increasing attention. Recent rumor detection methods treat all propagation paths and all nodes on the paths as equally important, resulting in models that fail to extract the key features. In addition, most methods ignore user features, leading to limitations in the performance improvement of rumor detection. To address these problems, we propose a Dual-Attention Network model on propagation Tree structures named DAN-Tree, where a node-and-path dual-attention mechanism is designed to organically fuse deep structure and semantic information on the propagation structures of rumors, and path oversampling and structural embedding are employed to enhance the learning of deep structures. Finally, we deeply integrate user profiles into the propagation trees in DAN-Tree, thus proposing the DAN-Tree++ model to further improve performance. Empirical studies on four rumor datasets have shown that DAN-Tree outperforms the state-of-the-art rumor detection models learning on propagation structures, and the results on two datasets with user information validate the superior performance of DAN-Tree++ over other models using both user profiles and propagation structures. What's more, DAN-Tree, especially DAN-Tree++, has achieved the best performance on early detection tasks.

GCNPCA: miRNA-Disease Associations Prediction Algorithm Based on Graph Convolutional Neural Networks.

A growing number of studies have confirmed the important role of microRNAs (miRNAs) in human diseases and the aberrant expression of miRNAs affects the onset and progression of human diseases. The discovery of disease-associated miRNAs as new biomarkers promote the progress of disease pathology and clinical medicine. However, only a small proportion of miRNA-disease correlations have been validated by biological experiments. And identifying miRNA-disease associations through biological experiments is both expensive and inefficient. Therefore, it is important to develop efficient and highly accurate computational methods to predict miRNA-disease associations. A miRNA-disease associations prediction algorithm based on Graph Convolutional neural Networks and Principal Component Analysis (GCNPCA) is proposed in this paper. Specifically, the deep topological structure information is extracted from the heterogeneous network composed of miRNA and disease nodes by a Graph Convolutional neural Network (GCN) with an additional attention mechanism. The internal attribute information of the nodes is obtained by the Principal Component Analysis (PCA). Then, the topological structure information and the node attribute information are combined to construct comprehensive feature descriptors. Finally, the Random Forest (RF) is used to train and classify these feature descriptors. In the five-fold cross-validation experiment, the AUC and AUPR for the GCNPCA algorithm are 0.983 and 0.988 respectively.

Structural setting of the Zoujiashan-Julong’an region, Xiangshan volcanic basin, China, interpreted from modern CSAMT data

The Zoujiashan-Julong’an area is situated on the western side of the Xiangshan volcanic basin. The basin represents the central part of the Jiangxi Province and it is well endowed with uranium deposits. Ongoing brownfield exploration requires a better understanding of the deep-seated geological structures of the region so as to discover additional, but concealed, deposits at depth. Aiming at elucidating the deep structural and geological framework, 14 parallel controlled-source audio-frequency magnetotelluric (CSAMT) survey lines were conducted to document the relationships between lithological contacts, faults and uranium mineralization with a penetration depth of about 2 kms. By integrating the interpreted geological profiles with geological surface maps and drilling data, a 3D geological model was constructed by using GOCAD software. The 3D model illustrated the major lithological units, faults and concealed uranium mineralization, respectively. The obtained data show that: (1) The Ehuling Formation as well as the underlying metamorphic basement displays a medium-to-high resistivity, whereas the Daguding Formation has a low-resistivity. The unconformity surface between volcanic rocks and the metamorphic basement is represented by a distinct low-resistivity zone which is locally intersected by faults. The fault structure in the CSAMT inversed sections appears as a low resistivity zone or a high-low resistivity variation gradient zone cutting through different interfaces. (2) As is documented by the 3D geological model, the favorable sites for uranium mineralization are distributed in the depressions of the metamorphic rock basement, at the boundary of volcanic rock formations, and in the transitional zones between the depressions and uplifts, where the thickness of the strata increases (or decreases) and the composite faults exist. (3) The location and spatial distribution of the unexposed structures delineated by the 2D resistivity inversion results are consistent with the geological mapping results. The delineated interface between porphyritic lava and rhyodacite is basically consistent with the drilling data. The CSAMT detection results can provide reliable deep geological structure information for 3D geological mapping and deep metallogenic prediction in Xiangshan area.

A graph neural network framework based on preference-aware graph diffusion for recommendation.

Transforming user check-in data into graph structure data is a popular and powerful way to analyze users' behaviors in the field of recommendation. Graph-based deep learning methods such as graph embeddings and graph neural networks have shown promising performance on the task of point-of-interest recommendation in recent years. Despite effectiveness, existing methods fail to capture deep graph structural information, leading the suboptimal representations. In addition, they lack the ability of learning the influences of both global preference and user preference on the check-in behavior. To address the aforementioned issues, we propose a general framework based on preference-aware graph diffusion, named PGD. We first construct two types of graphs to represent the global preference and user preference. Then, we apply a graph diffusion process to capture the structural information of the generated graphs, resulting in weighted adjacency matrices. Finally, graph neural network-based backbones are introduced to learn the representations of users and POIs on weighted adjacency matrices. A learnable aggregation module is developed to learn the final representations from global preference and user preference adaptively. Extensive experiments on four real-world datasets demonstrate the superiority of PGD on POI recommendation, compared with the mainstream graph-based deep learning methods.

BioChemDDI: Predicting Drug-Drug Interactions by Fusing Biochemical and Structural Information through a Self-Attention Mechanism.

Simple SummaryThroughout history, combining drugs has been a common method in the fight against complex diseases. However, potential drug–drug interactions could give rise to unknown toxicity issues, which requires the urgent proposal of efficient methods to identify potential interactions.We use computer technology and machine learning techniques to propose a novel computational framework to calculate scores of drug–drug interaction probability for simplifying the screening process. Additionally, we built an online prescreening tool for biological researchers to further verify possible interactions in the fields of biomedicine and pharmacology. Overall, our study can provide new insights and approaches for rapidly identifying potential drug–drug interactions.During the development of drug and clinical applications, due to the co-administration of different drugs that have a high risk of interfering with each other’s mechanisms of action, correctly identifying potential drug–drug interactions (DDIs) is important to avoid a reduction in drug therapeutic activities and serious injuries to the organism. Therefore, to explore potential DDIs, we develop a computational method of integrating multi-level information. Firstly, the information of chemical sequence is fully captured by the Natural Language Processing (NLP) algorithm, and multiple biological function similarity information is fused by Similarity Network Fusion (SNF). Secondly, we extract deep network structure information through Hierarchical Representation Learning for Networks (HARP). Then, a highly representative comprehensive feature descriptor is constructed through the self-attention module that efficiently integrates biochemical and network features. Finally, a deep neural network (DNN) is employed to generate the prediction results. Contrasted with the previous supervision model, BioChemDDI innovatively introduced graph collapse for extracting a network structure and utilized the biochemical information during the pre-training process. The prediction results of the benchmark dataset indicate that BioChemDDI outperforms other existing models. Moreover, the case studies related to three cancer diseases, including breast cancer, hepatocellular carcinoma and malignancies, were analyzed using BioChemDDI. As a result, 24, 18 and 20 out of the top 30 predicted cancer-related drugs were confirmed by the databases. These experimental results demonstrate that BioChemDDI is a useful model to predict DDIs and can provide reliable candidates for biological experiments. The web server of BioChemDDI predictor is freely available to conduct further studies.

GRACE Data Explore Moho Change Characteristics Beneath the South America Continent near the Chile Triple Junction

The internal and external mass migration and redistribution of the Earth system are usually accompanied by changes in the gravity field, and the Gravity Recovery and Climate Experiment (GRACE) has been proven to be able to effectively monitor and evaluate such changes. The Chile Triple Junction (CTJ) is the convergence point of the Nazca plate, the Antarctic plate and the South American plate. Subductions of different forms and rates in the north and south of the CTJ have varying degrees of impact on the surface and underground material changes of the South American plate. In this study, GRACE data are used in the estimation of the comprehensive mass changes in the South America Continent (SAC) Near the CTJ (~15° range). In addition, surface movement changes constrained by GNSS data cannot fully explain the GRACE results after deducting hydrological information, which indicates that residual signals might be attributed to mass changes beneath the crust, that is, the Moho interface deformation. After eliminating surface movement and hydrological signals from the comprehensive mass changes of GRACE, this study obtains the deep structural information and calculates the Moho changes of three significant regions with rates of −2.12 ± 0.67 cm/yr, 0.18 ± 0.19 cm/yr and −6.46 ± 1.31 cm/yr, respectively. Results have demonstrated that the subductions of the Nazca plate and the Antarctica plate have an effect on the uneven deformation of the Moho interface beneath the SAC. The Moho beneath the SAC mainly shows a deepening trend, but it is uplifted in some areas north of CTJ. On the whole, the rate of Moho changes is greater in the south than in the north. The relationship between Moho changes and surface changes also indicates that a longer timescale may be needed for maintaining isostatic balance.

SA-HAVE: A Self-Attention based Hierarchical VAEs Network for Abstractive Summarization

The abstractive automatic summarization task is to summarize the main content of the article with short sentences, which is an important research direction in natural language generation. Most abstractive summarization models are based on sequence-to-sequence neural networks. Specifically, they encode input text sequences by Bi-directional Long Short-Term Memory (bi-LSTM), and decode summaries word-by-word by LSTM. However, existing models usually did not consider both the self-attention dependence during the encoding process using bi-LSTM, and deep potential sentence structure information for the decoding process. To tackle these limitations, we propose a Self-Attention based word embedding and Hierarchical Variational AutoEncoders (SA-HVAE) model. The model first introduces self-attention into LSTM to alleviate information decay of encoding, and accomplish summarization with deep structure information inference through hierarchical VAEs. The experimental results on the Gigaword and CNN/Daily Mail datasets validate the superior performance of SA-HVAE, and our model has a significant improvement over the baseline model.

High-defined quantitative snapshots of the ganglioside lipidome using high resolution ion mobility SLIM assisted shotgun lipidomics

Defects in sphingolipid metabolism have emerged as a common link across neurodegenerative disorders, and a deeper understanding of the lipid content in preclinical models and patient specimens offers opportunities for development of new therapeutic targets and biomarkers. Sphingolipid metabolic pathways include the formation of glycosphingolipid species that branch into staggeringly complex structural heterogeneity within the globoside and ganglioside sub-lipidomes. Characterization of these sub-lipidomes has typically relied on liquid chromatography-mass spectrometry-based (LC-MS) approaches, but such assays are challenging and resource intensive due to the close structural heterogeneity, the presence of isobaric and isomeric species, and broad dynamic range of endogenous glycosphingolipids. Here, we apply Structures for Lossless Ion Manipulations (SLIM)-based High Resolution Ion Mobility (HRIM)-MS to enable rapid, repeatable, quantitative assays with deep structural information sufficient to resolve endogenous brain gangliosides at the level of individual molecular species. Analyses were performed using a prototype SLIM-MS instrument equipped with a 13-m serpentine path which enabled resolution of closely related isomeric analytes such as GD1a d36:1 and GD1b d36:1 based on recorded mass-to-charge (m/z) and arrival times. To demonstrate the power of our methodology, brain extracts derived from wild-type mice hemi-brains were analyzed by HRIM-MS using flow injection analyses (FIA) without the need for additional separation by liquid chromatography. Endogenous ganglioside species were readily resolved, identified, and quantified by FIA-SLIM-MS analyses within 2 min per sample. Thus, the FIA-SLIM-MS platform enables robust quantification across a broad range of lipid species in biological specimens in a standardized assay format that is readily scalable to support studies with large sample numbers.

Quasi-bound states in the continuum for deep subwavelength structural information retrieval for DUV nano-optical polarizers.

We demonstrate the retrieval of deep subwavelength structural information in nano-optical polarizers by scatterometry of quasi-bound states in the continuum (quasi-BICs). To this end, we investigate titanium dioxide wire grid polarizers for application wavelengths in the deep ultraviolet (DUV) spectral range fabricated with a self-aligned double-patterning process. In contrast to the time-consuming and elaborate measurement techniques like scanning electron microscopy, asymmetry induced quasi-BICs occurring in the near ultraviolet and visible spectral range provide an easily accessible and efficient probe mechanism. Thereby, dimensional parameters are retrieved with uncertainties in the sub-nanometer range. Our results show that BICs are a promising tool for process control in optics and semiconductor technology.

LncADeep: an ab initio lncRNA identification and functional annotation tool based on deep learning.

To characterize long non-coding RNAs (lncRNAs), both identifying and functionally annotating them are essential to be addressed. Moreover, a comprehensive construction for lncRNA annotation is desired to facilitate the research in the field. We present LncADeep, a novel lncRNA identification and functional annotation tool. For lncRNA identification, LncADeep integrates intrinsic and homology features into a deep belief network and constructs models targeting both full- and partial-length transcripts. For functional annotation, LncADeep predicts a lncRNA's interacting proteins based on deep neural networks, using both sequence and structure information. Furthermore, LncADeep integrates KEGG and Reactome pathway enrichment analysis and functional module detection with the predicted interacting proteins, and provides the enriched pathways and functional modules as functional annotations for lncRNAs. Test results show that LncADeep outperforms state-of-the-art tools, both for lncRNA identification and lncRNA-protein interaction prediction, and then presents a functional interpretation. We expect that LncADeep can contribute to identifying and annotating novel lncRNAs. LncADeep is freely available for academic use at http://cqb.pku.edu.cn/ZhuLab/lncadeep/ and https://github.com/cyang235/LncADeep/. Supplementary data are available at Bioinformatics online.

Understanding the Leitmotif: From Wagner to Hollywood Film Music By Matthew Bribitzer-Stull

PROGRAM MUSIC Understanding Leitmotif: From Wagner to Hollywood Film Music. By Matthew Bribitzer-Stull. Cambridge: Cambridge University Press, 2015. [xxiv, 331 p. ISBN 9781107098398 (hardcover), $120; ISBN 9781316161678 (e-book), Cambridge Books Online.] Music examples, illustrations, bibliography, index.Leitmotif is one of few terms in music's technical vocabulary to have left confines of its discipline and entered common parlance. Its ubiquity has come with trade-off, however, as original intentions and intendant nuances behind term attached to Richard Wagner since 1870s have become at best obscured, at worst unintentionally misused and intentionally abused. Recognizing that such phenomenon is an inherent property of any popular term, Matthew Bribitzer-Stull does not seek to return leitmotif to circumscribed environment of Wagnerian music drama. Rather, in Understanding Leitmotif: From Wagner to Hollywood Film Music, he explodes by showing how leitmotif-and, more accurately, leitmotivic procedures-has adapted to needs of established and new media over last one hundred fifty years. In doing so, he hopes to demonstrate that the idea of which Bribitzer-Stull believes has been debilitated by wave after wave of critical onslaught over last century, remains a valuable component of musical understanding (p. xix).Uncovering key features of Wagner's leitmotivic practice begins in chapter 1. Bribitzer-Stull emphasizes importance of accumulative association (p. 4; emphasis in original), which allows viewer not only to recall earlier themes, but also to track how those themes change according to various semantic, emotional, and dramatic cues. is, in fact, defining feature of leitmotif, which BribitzerStull also supplements with developmental (p. 14ff.) and structural (p. 18ff.) components. Given that these features are not unique to leitmotif, author concludes chapter by examining problematic ways in which scholars, especially beginning with Hans von Wolzogen in 1877, have applied them to Wagner's Der Ring des Nibelungen.Following taxonomy laid out in first chapter, Bribitzer-Stull divides his book into three parts: Musical Themes (chaps. 2-3), Musical Association (chaps. 4-6), and Leitmotifs in Context (chaps. 7-9). Chapter 2 continues methodology established earlier, in that attempts to arrive at leitmotivically-appropriate definition of by exclusion. A theme is not, according to Bribitzer-Stull, a unit of musical form (p. 41) like phrase, nor need have same linear basis that gives melody its singability (p. 44). And motives often convey important, deep structural information that themes-with their penchant for expressive, explicit extra-musical dramatic narrative-cannot (p. 50; emphasis in original).Chapter 3 sheds light on thematic identity by advancing model in which the listener, hearing multiple repetitions and variations of theme, forms an abstract prototype of it (p. 65). Bribitzer-Stull argues for prototype model, since works both at contingent and conceptual levels, and with this foundation he begins to move leitmotif out of territory of theme or motive by affirming its developmental nature. Chapter 4, drawing on understandings of expression, signification, referentiality, topic theory, and subjectivity (p. 83), tries to pinpoint leitmotif's level of associativity, which Bribitzer-Stull defines as the forging of connection between two separate ideas such that one may evoke or recall other (p. 100). Leitmotivic associativity is at its strongest when memory, emotion, and meaning align, as Bribitzer-Stull demonstrates in pregnant example from Gotterdammerung (p. 95ff.) that also conveniently foreshadows book's later forays into world of film. A fascinating discussion of hermeneutics of associativity follows (pp. …

Noise suppression for magnetotelluric sounding data based on signal subspace enhancement and endpoint detection

To retain useful information of magnetotelluric low frequency band and improve the capacity of magnetotelluric deep detection in ore concentration area with complex noises, the combined signal subspace enhancement with endpoint detection is proposed based on morphology filtering to secondary signal-to-noise separation processing. Firstly, aimed at noise contour extracted by morphology filtering, we use signal subspace enhancement to separate signal subspace and noise subspace for pretreatment. Secondly, the signal subspace is combined with reconstructed signal and the noise subspace is set to zero. Finally, endpoint detection for post-processing is carried out in order to identify the start and end points of the waveform mutation. Simulated results show that Cagniard resistivity curve in the low frequency band has been improved obviously, and the apparent resistivity value is relatively stable. The proposed method is better to offset the loss of low frequency useful information in the process of the morphological filtering, and the results can even more truly reflect the inherent deep structural information of low frequency components for the measured point itself.

Quantitative geometry

Rather than describing a traditional field of mathematics, “quantitative geometry” refers to a modern way of thinking about geometry and its applications that occur in a wide range of mathematical disciplines. The overarching theme here is that certain geometric problems can only be formulated after the introduction of auxiliary quantitative parameters and asking for their asymptotic or approximate behavior. This leads to meaningful questions that do not necessarily have counterparts in classical “qualitative” geometric investigations, a viewpoint that allows one to uncover deep and useful structural information that appears only in the quantitative regime. Quantitative reasoning allows one to tame complicated objects and phenomena that are unwieldy if one insists on exact measurements. It is often the case that a rich yet structured picture emerges only if one asks the correct questions by allowing for controlled errors.

Thioflavine-T and Congo Red Reveal the Polymorphism of Insulin Amyloid Fibrils When Probed by Polarization-Resolved Fluorescence Microscopy

Amyloid fibrils are protein misfolding structures that involve a β-sheet structure and are associated with the pathologies of various neurodegenerative diseases. Here we show that Thioflavine-T and Congo Red, two major dyes used to image fibrils by fluorescence assays, can provide deep structural information when probed by means of polarization-resolved fluorescence microscopy. Unlike fluorescence anisotropy or fluorescence detected linear dichroism imaging, this technique allows to retrieve simultaneously both mean orientation and orientation dispersion of the dye, used here as a reporter of the fibril structure. We have observed that insulin amyloid fibrils exhibit a homogeneous behavior over the fibrils' length, confirming their structural uniformity. In addition, these results reveal the existence of various structures among the observed fibrils' population, in spite of a similar aspect when imaged with conventional fluorescence microscopy. This optical nondestructive technique opens perspectives for in vivo structural analyses or high throughput screening.

Deep Mantle Seismic Modeling and Imaging

Detailed seismic modeling and imaging of Earth's deep interior is providing key information about lower-mantle structures and processes, including heat flow across the core-mantle boundary, the configuration of mantle upwellings and downwellings, phase equilibria and transport properties of deep mantle materials, and mechanisms of core-mantle coupling. Multichannel seismic wave analysis methods that provide the highest-resolution deep mantle structural information include network waveform modeling and stacking, array processing, and 3D migrations of P- and S-wave seismograms. These methods detect and identify weak signals from structures that cannot be resolved by global seismic tomography. Some methods are adapted from oil exploration seismology, but all are constrained by the source and receiver distributions, long travel paths, and strong attenuation experienced by seismic waves that penetrate to the deep mantle. Large- and small-scale structures, with velocity variations ranging from a fraction of a percent to tens of percent, have been detected and are guiding geophysicists to new perspectives of thermochemical mantle convection and evolution.

EXTRUCT

Users who are unfamiliar with database query languages can search XML data sets using keyword queries. Previous work has shown that current XML keyword search methods, although intuitive, do not effectively use the data's structural information and provide poor precision, recall, and ranking for most queries. Based on an extension of the concept of information theory, we have developed principled frameworks called normalized total correlation (NTC) and normalized term presence correlation (NTPC) to measure the relevance of candidate answers to keyword queries. We demonstrate EXTRUCT, an XML keyword search interface that uses NTC and NTPC. An extensive empirical evaluation over two real-world XML DBs has shown that EX-TRUCT has better precision and recall and provides better ranking than all previous approaches. We demonstrate EXTRUCT, along with seven other keyword search systems for four real-world XML data sets, using prepared queries as well as queries from the audience. The demonstration shows that using deep structural information increases the effectiveness of XML keyword search systems considerably.

Representation Theory of Finite Dimensional Algebras

Methods and results from the representation theory of finite di- mensional algebras have led to many interactions with other areas of mathe- matics. Such areas include the theory of Lie algebras and quantum groups, commutative algebra, algebraic geometry and topology, and in particular the new theory of cluster algebras. The aim of this workshop was to further de- velop such interactions and to stimulate progress in the representation theory of algebras.

Automatic Layout of UML Class Diagrams in Orthogonal Style

Unified modelling language (UML) diagrams have become increasingly important in engineering and re-engineering processes for software systems. Of particular interest are UML class diagrams whose purpose is to display generalizations, associations, aggregations, and compositions in one picture. The combination of directed and undirected relations poses a special challenge to a graph layout tool. Current approaches for the automatic layout of class diagrams are based on the layered graph drawing paradigm. These algorithms produce good results for class diagrams with large and deep structural information, that is, diagrams with a large and deep inheritance hierarchy. However, they do not perform satisfactorily in absence of this information. We suggest to use the topology-shape—metrics paradigm for automatic layout of class diagrams, which has been used very successfully for drawing undirected graphs in orthogonal style. Moreover, we introduce the algorithms UML-Kandinsky and GoVisual fitting into this paradigm. Both algorithms work for class diagrams with rich structural information as well as for class diagrams with few or no structural information. Therefore, they improve the existing algorithms significantly.