Hierarchical Structure Information Research Articles

Discovery of Highly Bioactive Peptides through Hierarchical Structural Information and Molecular Dynamics Simulations.

Peptide drugs play an essential role in modern therapeutics, but the computational design of these molecules is hindered by several challenges. Traditional methods like molecular docking and molecular dynamics (MD) simulation, as well as recent deep learning approaches, often face limitations related to computational resource demands, complex binding affinity assessments, extensive data requirements, and poor model interpretability. Here, we introduce PepHiRe, an innovative methodology that utilizes the hierarchical structural information in peptide sequences and employs a novel strategy called Ladderpath, rooted in algorithmic information theory, to rapidly generate and enhance the efficiency and clarity of novel peptide design. We applied PepHiRe to develop BH3-like peptide inhibitors targeting myeloid cell leukemia-1, a protein associated with various cancers. By analyzing just eight known bioactive BH3 peptide sequences, PepHiRe effectively derived a hierarchy of subsequences used to create new BH3-like peptides. These peptides underwent screening through MD simulations, leading to the selection of five candidates for synthesis and subsequent in vitro testing. Experimental results demonstrated that these five peptides possess high inhibitory activity, with IC50 values ranging from 28.13 ± 7.93 to 167.42 ± 22.15 nM. Our study explores a white-box model driven technique and a structured screening pipeline for identifying and generating novel peptides with potential bioactivity.

A study of extractive summarization of long documents incorporating local topic and hierarchical information

In recent years, the transformer-based language models have achieved remarkable success in the field of extractive text summarization. However, there are still some limitations in this kind of research. First, the transformer language model usually regards the text as a linear sequence, ignoring the inherent hierarchical structure information of the text. Second, for long text data, traditional extractive models often focus on global topic information, which poses challenges in how they capturing and integrating local contextual information within topic segments. To address these issues, we propose a long text extractive summarization model that employs a local topic information extraction module and a text hierarchical extraction module to capture the local topic information and document's hierarchical structure information of the original text. Our approach enhances the ability to determine whether a sentence belongs to the summary. In this experiment, ROUGE score is used as the experimental evaluation index, and evaluates the model on three large public datasets. Through experimental validation, the model demonstrates superior performance in terms of ROUGE-1, ROUGE-2, and ROUGE-L scores compared to current mainstream summarization models, affirming the effectiveness of incorporating local topic information and document hierarchical structure into the model.

Online streaming feature selection based on hierarchical structure information

SummaryHierarchical classification learning aims to exploit the hierarchical relationship between data categories. The high dimensionality and dynamic of the data feature space are the main challenges of this research. Hierarchical feature selection uses a hierarchical structure to divide large‐scale tasks into multiple small tasks, which can more effectively improve the training speed and prediction accuracy of classification models. To present, existing online feature selection methods ignore the hierarchical structure of data. In addition, the dependency relationships in the hierarchical structure can serve as auxiliary knowledge to aid feature selection. Based on this, this paper proposes an online streaming hierarchical feature selection method based on kernelized fuzzy rough sets (OFS‐HNFRS). First, we use the prior knowledge of the hierarchical structure to divide the sample set into multiple subsets. Second, the dependency relationship of hierarchical structure is extended to kernelized fuzzy rough sets, and hierarchical category dependency based on kernelized fuzzy rough sets is defined. Finally, a new online feature selection framework is proposed, which is used to evaluate the relevance, significance, and redundancy of features. We verify the effectiveness of the proposed algorithm on six hierarchical datasets and eight flat datasets.

Research and application of the global positioning system (GPS) clustering algorithm based on multilevel functions

With the rapid development and widespread adoption of wearable technology, a new type of lifelog data is being collected and used in numerous studies. We refer to these data as informative lifelog which usually contain GPS, images, videos, text, etc. GPS trajectory data in lifelogs is typically categorized into continuous and discrete trajectories. Finding a point of interest (POI) from discrete trajectories is a challenging task to do and has caught little attention so far. This paper suggests an LP-DBSCAN model for mining personal trajectories from discrete GPS trajectory data. It makes use of the hierarchical structure information implied in GPS trajectory data and it is suggested a variable-levels, variable-parameters clustering method (LP-DBSCAN) based on the DBSCAN algorithm to increase the precision of finding POI information. Finally, the Liu lifelog dataset is subjected to a systematic evaluation. In terms of GPS data that are not evenly distributed geographically, the experimental results demonstrated that the proposed algorithm could more accurately identify POI information and address the adverse effects caused by the global parameters of the traditional DBSCAN algorithm.

Convergence of polarized self-attention with consistent rank Chinese text classification

Utilizing the powerful feature extraction capabilities of deep learning, a text classification algorithm with multi-dimensional and high-domain adaptability is designed in this study. This method enhances the models understanding of topics and content by incorporating the Polarized Self-Attention (PSA) module, which strengthens the spatial structure and semantic features of textual information. The loss function is redesigned to assign smaller losses to misclassifications of neighboring categories, allowing the model to optimize classification accuracy while learning hierarchical structural information between categories. Finally, experimental verification is conducted on a publicly available news dataset, demonstrating improved results in text classification achieved by the proposed algorithm.

Snowflake: visualizing microbiome abundance tables as multivariate bipartite graphs.

Current visualizations in microbiome research rely on aggregations in taxonomic classifications or do not show less abundant taxa. We introduce Snowflake: a new visualization method that creates a clear overview of the microbiome composition in collected samples without losing any information due to classification or neglecting less abundant reads. Snowflake displays every observed OTU/ASV in the microbiome abundance table and provides a solution to include the data's hierarchical structure and additional information obtained from downstream analysis (e.g., alpha- and beta-diversity) and metadata. Based on the value-driven ICE-T evaluation methodology, Snowflake was positively received. Experts in microbiome research found the visualizations to be user-friendly and detailed and liked the possibility of including and relating additional information to the microbiome's composition. Exploring the topological structure of the microbiome abundance table allows them to quickly identify which taxa are unique to specific samples and which are shared among multiple samples (i.e., separating sample-specific taxa from the core microbiome), and see the compositional differences between samples. An R package for constructing and visualizing Snowflake microbiome composition graphs is available at https://gitlab.com/vda-lab/snowflake.

Neighboring Envelope Embedded Stacked Autoencoder for Deep Learning on Hierarchically Structured Samples

A stacked autoencoder (SAE) is a widely used deep network. However, existing deep SAEs focus on original samples without considering the hierarchical structural information between samples. This limits the accuracy of the SAE. In recent years, state-of-the-art SAEs have suggested improvements in network structure, cost function, parameter optimization, and thereby the accuracy has been enhanced. However, the problem mentioned above is still not solved. Therefore, this paper is concerned with how to design a SAE that can conduct deep learning on hierarchically structured samples. This proposed SAE - neighboring envelope embedded stacked autoencoder (NE_ESAE) mainly consists of two parts. The first is the neighboring sample envelope learning mechanism (NSELM) that constructs sample-pairs by combining neighboring samples. In addition, the NSELM constructs multilayer sample spaces by multilayer iterative mean clustering, which considers similar samples and generates layers of envelope samples with hierarchical structural information. The second is an embedded stacked autoencoder (ESAE) to consider the original samples during training and in network structure, thereby finding the relationship of the samples with original features and deep features in a better manner. The experimental results show that our method has significantly better performance than some representative methods. Different from existing SAEs, the proposed NE_ESAE realizes deep learning on hierarchical structured samples, and makes SAE able to conduct cooperative deep sample and feature learning. The advantage that has been gained can be applied to other deep neural networks.

The influence of sentence focus on motor system activity in language comprehension and its temporal dynamics: Preliminary evidence from sEMG

Previous research has shown that individual experiences and experimental tasks can influence the occurrence of mental simulation during sentence comprehension. However, little research has focused on the effect of sentence focus on mental simulation and its temporal dynamics. Sentence focus refers to the hierarchical structure of information within a sentence, where focused information represents the most prominent and essential information. In contrast, nonfocused information provides a background for the focused information. The present study investigated whether sentence focus would affect the activity of the motor system in language comprehension and at which stage the effect of sentence focus occurred. We measured spontaneous arm muscle electrical activity by surface electromyography (sEMG) while participants read action-focused, nonaction-focused, and control sentences. We observed greater spontaneous muscle electrical activity in the flexor common muscle of the fingers when participants read action-focused sentences compared to nonaction-focused and control sentences. Additionally, there was an interactive trend between sentence type and time, spontaneous muscle electrical activity while reading action-focused sentences was observed in both early (1 ms to 300 ms after the presentation of the action phrase) and late time windows (901 ms to 1500 ms after the action phrase). The findings suggest that the motor system exhibits flexible engagement during language comprehension and the impact of sentence focus on motor system activity may be throughout both the lexical-semantic retrieval and sentence-meaning integration stages.

Hierarchical Consensus Hashing for Cross-Modal Retrieval

Cross-modal hashing (CMH) has gained much attention due to its effectiveness and efficiency in facilitating efficient retrieval between different modalities. Whereas, most existing methods unconsciously ignore the hierarchical structural information of the data, and often learn a single-layer hash function to directly transform cross-modal data into common low-dimensional hash codes in one step. This sudden drop of dimension and the huge semantic gap can cause the discriminative information loss. To this end, we adopt a coarse-to-fine progressive mechanism and propose a novel Hierarchical Consensus Cross-Modal Hashing (HCCH). Specifically, to mitigate the loss of important discriminative information, we propose a coarse-to-fine hierarchical hashing scheme that utilizes a two-layer hash function to refine the beneficial discriminative information gradually. And then, the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\ell _{2,1}$</tex-math></inline-formula> -norm is imposed on the layer-wise hash function to alleviate the effects of redundant and corrupted features. Finally, we present consensus learning to effectively encode data into a consensus space in such a progressive way, thereby reducing the semantic gap progressively. Through extensive contrast experiments with some advanced CMH methods, the effectiveness and efficiency of our HCCH method are demonstrated on four benchmark datasets. We have released the source code at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/sunyuan-cs</uri> .

HTPosum:Heterogeneous Tree Structure augmented with Triplet Positions for extractive Summarization of scientific papers

Currently, many summarization models are based on Transformer architectures, which regard text as a connected graph of words and tokens, thus fail to fully leverage the text’s hierarchical structure. However, hierarchical structural information is crucial in understanding long documents, especially scientific papers. To exploit the structural information, we propose a Heterogeneous Tree structure augmented with Triplet Positions for extractive Summarization of scientific papers (HTPosum). The proposed model constructs a heterogeneous tree for each document, introducing section nodes and a global node to capture the documents’ structural information. The tree is then augmented with a novel triplet position, which consists of three values that represent the depth, parent width position, and sibling width position of each node in a tree. The triplet position provides a unified view of the document structure . Experimental results show that the proposed model achieves state-of-the-art extractive performance on the PubMed and arXiv datasets compared with the latest scientific paper summarization models.

Meta-Information Fusion of Hierarchical Semantics Dependency and Graph Structure for Structured Text Classification

Structured text with plentiful hierarchical structure information is an important part in real-world complex texts. Structured text classification is attracting more attention in natural language processing due to the increasing complexity of application scenarios. Most existing methods treat structured text from a local hierarchy perspective, focusing on the semantics dependency and the graph structure of the structured text independently. However, structured text has global hierarchical structures with sophisticated dependency when compared to unstructured text. According to the variety of structured texts, it is not appropriate to use the existing methods directly. The function of distinction information within semantics dependency and graph structure for structured text, referred to as meta-information, should be stated more precisely. In this article, we propose HGMETA, a novel meta-information embedding frame network for structured text classification, to obtain the fusion embedding of hierarchical semantics dependency and graph structure in a structured text, and to distill the meta-information from fusion characteristics. To integrate the global hierarchical features with fused structured text information, we design a hierarchical LDA module and a structured text embedding module. Specially, we employ a multi-hop message passing mechanism to explicitly incorporate complex dependency into a meta-graph. The meta-information is constructed from meta-graph via neighborhood-based propagation to distill redundant information. Furthermore, using an attention-based network, we investigate the complementarity of semantics dependency and graph structure based on global hierarchical characteristics and meta-information. Finally, the fusion embedding and the meta-information can be straightforwardly incorporated for structured text classification. Experiments conducted on three real-world datasets show the effectiveness of meta-information and demonstrate the superiority of our method.

A novel algorithm for identifying influential nodes in complex networks based on local propagation probability model

Identifying influential nodes in complex networks is an essential research issue in network science since it may attribute to understand network structure and function. Majority of existing methods have been established by considering topological characteristics of networks. In this paper, we put forward a novel algorithm based on the Local Propagation Probability (LPP) model for identifying influential nodes in complex networks. The core idea of LPP algorithm is that the nodal influence is measured by total comprehensive scores of neighbor nodes within its three level neighborhood. Specially, the comprehensive score is calculated from three dimensions, namely the propagation influence score between different order neighbors, the propagation influence score in the same order neighbors and the hierarchical structure information of nodes. To validate the performance and applicability of the proposed algorithm, LPP is compared with eight state-of-the-art and competitive algorithms on nine real-world networks. Experimental results demonstrate that LPP performs better in terms of ranking accuracy, effectiveness, top-k nodes and distinguishing ability. The low time complexity allows LPP to be applied to large-scale sparse networks.

Efficient recognition of dynamic user emotions based on deep neural networks

The key issue at this stage is how to mine the large amount of valuable user sentiment information from the massive amount of web text and create a suitable dynamic user text sentiment analysis technique. Hence, this study offers a writing feature abstraction process based on ON-LSTM and attention mechanism to address the problem that syntactic information is ignored in emotional text feature extraction. The study found that the Att-ON-LSTM improved the micro-average F1 value by 2.27% and the macro-average F value by 1.7% compared to the Bi-LSTM model with the added attentivity mechanisms. It is demonstrated that it can perform better extraction of semantic information and hierarchical structure information in emotional text and obtain more comprehensive emotional text features. In addition, the ON-LSTM-LS, a sentiment analysis model based on ON-LSTM and tag semantics, is planned to address the problem that tag semantics is ignored in the process of text sentiment analysis. The experimental consequences exposed that the accuracy of the ON-LSTM and labeled semantic sentiment analysis model on the test set is improved by 0.78% with the addition of labeled word directions compared to the model Att-ON-LSTM without the addition of labeled semantic information. The macro-averaged F1 value improved by 1.04%, which indicates that the sentiment analysis process based on ON-LSTM and tag semantics can effectively perform the text sentiment analysis task and improve the sentiment classification effect to some extent. In conclusion, deep learning models for dynamic user sentiment analysis possess high application capabilities.

Hierarchical lifelong topic modeling using rules extracted from network communities.

Topic models extract latent concepts from texts in the form of topics. Lifelong topic models extend topic models by learning topics continuously based on accumulated knowledge from the past which is updated continuously as new information becomes available. Hierarchical topic modeling extends topic modeling by extracting topics and organizing them into a hierarchical structure. In this study, we combine the two and introduce hierarchical lifelong topic models. Hierarchical lifelong topic models not only allow to examine the topics at different levels of granularity but also allows to continuously adjust the granularity of the topics as more information becomes available. A fundamental issue in hierarchical lifelong topic modeling is the extraction of rules that are used to preserve the hierarchical structural information among the rules and will continuously update based on new information. To address this issue, we introduce a network communities based rule mining approach for hierarchical lifelong topic models (NHLTM). The proposed approach extracts hierarchical structural information among the rules by representing textual documents as graphs and analyzing the underlying communities in the graph. Experimental results indicate improvement of the hierarchical topic structures in terms of topic coherence that increases from general to specific topics.

A neural network-based method for exhaustive cell label assignment using single cell RNA-seq data

The fast-advancing single cell RNA sequencing (scRNA-seq) technology enables researchers to study the transcriptome of heterogeneous tissues at a single cell level. The initial important step of analyzing scRNA-seq data is usually to accurately annotate cells. The traditional approach of annotating cell types based on unsupervised clustering and marker genes is time-consuming and laborious. Taking advantage of the numerous existing scRNA-seq databases, many supervised label assignment methods have been developed. One feature that many label assignment methods shares is to label cells with low confidence as “unassigned.” These unassigned cells can be the result of assignment difficulties due to highly similar cell types or caused by the presence of unknown cell types. However, when unknown cell types are not expected, existing methods still label a considerable number of cells as unassigned, which is not desirable. In this work, we develop a neural network-based cell annotation method called NeuCA (Neural network-based Cell Annotation) for scRNA-seq data obtained from well-studied tissues. NeuCA can utilize the hierarchical structure information of the cell types to improve the annotation accuracy, which is especially helpful when data contain closely correlated cell types. We show that NeuCA can achieve more accurate cell annotation results compared with existing methods. Additionally, the applications on eight real datasets show that NeuCA has stable performance for intra- and inter-study annotation, as well as cross-condition annotation. NeuCA is freely available as an R/Bioconductor package at https://bioconductor.org/packages/NeuCA.

MeSIN: Multilevel selective and interactive network for medication recommendation

Recommending medications for patients using electronic health records (EHRs) is a crucial data mining task for an intelligent healthcare system. EHRs data, which comprise multiple temporal sequences (e.g., lab, diagnosis, and treatment sequences), encompass multilevel structure information, including flat structure information (e.g., sequential medical codes and their relationships) in each sequence and hierarchical structure information between sequences (e.g., information flow from lab sequence to diagnosis sequence or hierarchical codes relationships), which implicitly reflects a physician’s decision process. However, existing studies focus on mining flat structure information, which is incomplete and hence biased. Therefore, to realize more accurate medication recommendations, this paper proposes a multilevel selective and interactive network (MeSIN) that exploits complete structure information of EHR data; in particular, at the core of our framework is an interactive long short-term memory network (InLSTM), which is developed to model the temporal dependencies in each flat-structured sequence via a recurrent mechanism and capture the hierarchical relationships of different sequences via a reinforced interactive network. Moreover, to reduce the impact of irrelevant information on the multilevel interaction process, an attentional selective module (ASM) is introduced to filter out noisy information and thereby focus on important sequence information at each timestamp. Finally, a global selective fusion module (GSFM) is proposed to infuse multisourced information embeddings into multilevel structural relationship-aware patient representation. Experimental results on a practical clinical dataset show that our framework consistently outperformed all baseline models in the medication recommendation task.

An extended spatiotemporal exposure index for urban racial segregation

ABSTRACT The Segregation Index quantifies the degree of segregation of social groups or classes. Because of the increasing use of fine-grained spatiotemporal activity and flow data, the conventional segregation measurements’ inclusiveness is challenged. We add population flow to the conventional place-based spatial exposure index to identify spatiotemporal segregation changes. Specifically, we considered the population-flow network, hierarchical structure, and time. In Chicago’s demonstration case study, we first used the time-dependent Twitter Origin-Destination flow matrices and their hierarchical structure information to estimate interactions between areal units at the neighborhood level. Then we computed the new population composition of units based on their interactions with other units and estimated the proposed spatiotemporal exposure index for different times. Finally, we systematically compared their differences with the conventional indices at global and local scales to see how population-flow patterns affect the exposure index. The results show that the population-flow patterns reflect valuable information in neighborhood interactions in temporal and spatial dimensions, but it is missing information in the conventional segregation computations. Furthermore, we emphasize that the hierarchical structures of flow patterns and the choice of appropriate parameters are also important factors for a rational segregation evaluation.

Code Clone Detection with Hierarchical Attentive Graph Embedding

Code clone serves as a typical programming manner that reuses the existing code to solve similar programming problems, which greatly facilitates software development but recurs program bugs and maintenance costs. Recently, deep learning-based detection approaches gradually present their effectiveness on feature representation and detection performance. Among them, deep learning approaches based on abstract syntax tree (AST) construct models relying on the node embedding technique. In AST, the semantic of nodes is obviously hierarchical, and the importance of nodes is quite different to determine whether the two code fragments are cloned or not. However, some approaches do not fully consider the hierarchical structure information of source code. Some approaches ignore the different importance of nodes when generating the features of source code. Thirdly, when the tree is very large and deep, many approaches are vulnerable to the gradient vanishing problem during training. In order to properly address these challenges, we propose a hierarchical attentive graph neural network embedding model-HAG for the code clone detection. Firstly, the attention mechanism is applied on nodes in AST to distinguish the importance of different nodes during the model training. In addition, the HAG adopts graph convolutional network (GCN) to propagate the code message on AST graph and then exploits a hierarchical differential pooling GCN to sufficiently capture the code semantics at different structure level. To evaluate the effectiveness of HAG, we conducted extensive experiments on public clone dataset and compared it with seven state-of-the-art clone detection models. The experimental results demonstrate that the HAG achieves superior detection performance compared with baseline models. Especially, in the detection of moderately Type-3 or Type-4 clones, the HAG particularly outperforms baselines, indicating the strong detection capability of HAG for semantic clones. Apart from that, the impacts of the hierarchical pooling, attention mechanism and critical model parameters are systematically discussed.

Joint extraction of entities and relations based on character graph convolutional network and Multi-Head Self-Attention Mechanism

ABSTRACT The traditional method of extracting entities and relations not only disregards the dependency between the two subtasks of entities and relations but also facilitates the cumulative propagation of errors. To solve these problems, a method – called MSBD – of joint extraction of entities and relations based on the Character Graph Convolutional Network (CGCN) and Multi-Head Self-Attention Mechanism (MS) is proposed. First, a new tagging scheme is used to tag the positions of entities and relations in the text. Second, to depict the hierarchical structure information between the entities and the relations in the text and the internal structure information of the entity, the CGCN is designed to obtain the character vector of the text. MS is introduced into the coding framework of Bidirectional Long Short-Term Memory (BiLSTM) to capture the relative position information between two entities in the text and represent the subspace information. The Dense Connected Convolutional Network (Dense Net) is embedded in the decoding framework to enhance the reuse and transmission of key information and achieve joint extraction of entities and relations in the text. The experimental results show that the P, R and F values are significantly improved for extracting entities and relations.

What could be My Next Job? Using Flat Information Structures to Generate Creative Future Career Ideas

AbstractIn a dynamic labor market, it is important to help people combine information and generate creative solutions to cope with complex career challenges. In the present research, we apply the theory of information structure to creative career idea generation and hypothesize that flat information structures—that is, structures in which the information is disorganized—are more conducive to creativity than hierarchical information structures—that is, structures in which information is organized in higher‐order categories. In two experimental studies, participants had to combine career information related to self and work preferences that was presented either in flat or hierarchical structures. We found that flat information structures, compared with hierarchical information structures, led to future career ideas that were more creative on average. Our results suggest that cognitive flexibility explains the effect of information structure on the creativity of career ideas. Theoretical implications and suggestions for career management practices are discussed.