Improving Crystal Property Prediction from a Multiplex Graph Perspective

Graph neural networks (GNNs) have proven to be effective tools for the rapid and accurate prediction of crystal properties. While most existing methods focus on enriching representations of crystal structures, they do not deeply explore the characteristics of crystal graphs and leverage their intrinsic information from a data science perspective. In this work, we propose the potential multiplex crystal graph neural network (PMCGNN) for crystal property prediction. Based on the characteristics of crystal graphs, we reconstruct the crystal graph into a multiplex graph that includes two views: a global crystal graph embodying infinite potentials and a local crystal graph capturing local atomic interactions. We employ graph transformers (GTs) and message passing neural networks (MPNNs) architectures to learn the atomic representations of these two perspectives. Specifically, we augment the GT by incorporating positional encodings and structural encodings from the local crystal graph. This approach promotes interaction between the two perspectives, enabling the model to learn both node positional and graph structural information from different viewpoints through an attention mechanism. As a result, it enhances the model's ability to learn crystal representations. We conduct comprehensive experiments on the JARVIS and the Materials Project data sets for evaluation. Results show that PMCGNN presents superior performance in 9 crystal prediction tasks while maintaining reasonable computational expense.

Morphogenic Modeling of Corrosion Reveals Complex Effects of Intermetallic Particles

Corrosion processes are often discussed as stochastic events. Here, it is shown that some of these seemingly random processes are not driven by nanoscopic fluctuations but rather by the spatial distribution of micrometer-scale heterogeneities that trigger fast reactions associated with corrosion. Using a novel excitable reaction-diffusion model, corrosion waves traveling over the metal surface and the associated material loss are described. This resulting nonuniform corrosion penetration, seen as a height loss in modeling, exposes buried intermetallic particles, which depending on the local electrochemical state of the surface trigger or block new waves. Informed by quantitative experimental data for the Mg-Al-Zn alloy AZ31B, wave speeds, wave widths, and average material loss are accurately captured. Morphogenic mitigation based on wave-breaking microparticles is also simulated. While AZ31B corrosion is identified as a process driven by rare-wave events, this study predicts several other corrosion regimes that proceed via spots or patchy patterns, opening the door for new protection, design, and prediction strategies.

Detection of distant relatedness in biobanks to identify undiagnosed cases of Mendelian disease as applied to Long QT syndrome

Rare genetic diseases are typically studied in referral populations, resulting in underdiagnosis and biased assessment of penetrance and phenotype. To address this, we develop a generalizable method of genotype inference based on distant relatedness and deploy this to identify undiagnosed Type 5 Long QT Syndrome (LQT5) rare variant carriers in a non-referral population. We identify 9 LQT5 families referred to a single specialty clinic, each carrying p.Asp76Asn, the most common LQT5 variant. We uncover recent common ancestry and a single shared haplotype among probands. Application to a non-referral population of 69,819 BioVU biobank subjects identifies 22 additional subjects sharing this haplotype, which we confirm to carry p.Asp76Asn. Referral and non-referral carriers have prolonged QT interval corrected for heart rate (QTc) compared to controls, and, among carriers, the QTc polygenic score is independently associated with QTc prolongation. Thus, our innovative analysis of shared chromosomal segments identifies undiagnosed cases of genetic disease and refines the understanding of LQT5 penetrance and phenotype.

Disease gene prioritization with quantum walks

MOTIVATION

Disease gene prioritization methods assign scores to genes or proteins according to their likely relevance for a given disease based on a provided set of seed genes. This scoring can be used to find new biologically relevant genes or proteins for many diseases. Although methods based on classical random walks have proven to yield competitive results, quantum walk methods have not been explored to this end.

RESULTS

We propose a new algorithm for disease gene prioritization based on continuous-time quantum walks using the adjacency matrix of a protein-protein interaction (PPI) network. We demonstrate the success of our proposed quantum walk method by comparing it to several well-known gene prioritization methods on three disease sets, across seven different PPI networks. In order to compare these methods, we use cross-validation and examine the mean reciprocal ranks of recall and average precision values. We further validate our method by performing an enrichment analysis of the predicted genes for coronary artery disease.

AVAILABILITY AND IMPLEMENTATION

The data and code for the methods can be accessed at https://github.com/markgolds/qdgp.

Attributed Graph Force Learning

In numerous network analysis tasks, feature representation plays an imperative role. Due to the intrinsic nature of networks being discrete, enormous challenges are imposed on their effective usage. There has been a significant amount of attention on network feature learning in recent times that has the potential of mapping discrete features into a continuous feature space. The methods, however, lack preserving the structural information owing to the utilization of random negative sampling during the training phase. The ability to effectively join attribute information to embedding feature space is also compromised. To address the shortcomings identified, a novel attribute force-based graph (AGForce) learning model is proposed that keeps the structural information intact along with adaptively joining attribute information to the node's features. To demonstrate the effectiveness of the proposed framework, comprehensive experiments on benchmark datasets are performed. AGForce based on the spring-electrical model extends opportunities to simulate node interaction for graph learning.

Post-quantum distributed ledger technology: a systematic survey

Blockchain technology finds widespread application across various fields due to its key features such as immutability, reduced costs, decentralization, and transparency. The security of blockchain relies on elements like hashing, digital signatures, and cryptography. However, the emergence of quantum computers and supporting algorithms poses a threat to blockchain security. These quantum algorithms pose a significant threat to both public-key cryptography and hash functions, compelling the redesign of blockchain architectures. This paper investigates the status quo of the post-quantum, quantum-safe, or quantum-resistant cryptosystems within the framework of blockchain. This study starts with a fundamental overview of both blockchain and quantum computing, examining their reciprocal influence and evolution. Subsequently, a comprehensive literature review is conducted focusing on Post-Quantum Distributed Ledger Technology (PQDLT). This research emphasizes the practical implementation of these protocols and algorithms providing extensive comparisons of characteristics and performance. This work will help to foster further research at the intersection of post-quantum cryptography and blockchain systems and give prospective directions for future PQDLT researchers and developers.

Coined quantum walks on the line: Disorder, entanglement, and localization

Disorder in coined quantum walks generally leads to localization. We investigate the influence of the localization on the entanglement properties of coined quantum walks. Specifically, we consider quantum walks on the line and explore the effects of quenched disorder in the coin operations. After confirming that our choice of disorder localizes the walker, we study how the localization affects the properties of the coined quantum walk. We find that the mixing properties of the walk are altered nontrivially with mixing being improved at short time scales. Special focus is given to the influence of coin disorder on the properties of the quantum state and the coin-walker entanglement. We find that disorder alters the quantum state significantly even when the walker probability distribution is still close to the nondisordered case. We observe that, generically, coin disorder decreases the coin-walker entanglement and that the localization leaves distinct traces in the entanglement entropy and the entanglement negativity of the coined quantum walk.

When to Pre-Train Graph Neural Networks? From Data Generation Perspective!

In recent years, graph pre-training has gained significant attention, focusing on acquiring transferable knowledge from unlabeled graph data to improve downstream performance. Despite these recent endeavors, the problem of negative transfer remains a major concern when utilizing graph pre-trained models to downstream tasks. Previous studies made great efforts on the issue of what to pre-train and how to pre-train by designing a variety of graph pre-training and fine-tuning strategies. However, there are cases where even the most advanced "pre-train and fine-tune" paradigms fail to yield distinct benefits. This paper introduces a generic framework W2PGNN to answer the crucial question of when to pre-train (i.e., in what situations could we take advantage of graph pre-training) before performing effortful pre-training or fine-tuning. We start from a new perspective to explore the complex generative mechanisms from the pre-training data to downstream data. In particular, W2PGNN first fits the pre-training data into graphon bases, each element of graphon basis (i.e., a graphon) identifies a fundamental transferable pattern shared by a collection of pre-training graphs. All convex combinations of graphon bases give rise to a generator space, from which graphs generated form the solution space for those downstream data that can benefit from pre-training. In this manner, the feasibility of pre-training can be quantified as the generation probability of the downstream data from any generator in the generator space. W2PGNN offers three broad applications: providing the application scope of graph pre-trained models, quantifying the feasibility of pre-training, and assistance in selecting pre-training data to enhance downstream performance. We provide a theoretically sound solution for the first application and extensive empirical justifications for the latter two applications.

Discrete-time quantum walk dispersion control through long-range correlations

We investigate the evolution dynamics of inhomogeneous discrete-time one-dimensional quantum walks displaying long-range correlations in both space and time. The associated quantum coin operators of internal states are built to exhibit random inhomogeneity distribution of long-range correlations embedded in the time evolution protocol through a fractional Brownian motion with spectrum following a power-law behavior, S(k)∼1/k^{ν}. From extensive numerical simulations with averages over a large number of independent realizations of the phases of quantum coins, the power-law correlated disorder encoded in the coin phases is shown to give rise to a wide variety of spreading patterns of the qubit states, from localized to subdiffusive, diffusive, and superdiffusive (including ballistic) behavior, depending on the relative strength of the parameters driving the correlation degree. Dispersion control is possible in one-dimensional discrete-time quantum walks by tuning the long-range correlation properties assigned to the inhomogeneous quantum coin operator.

Implementing Dual Base Stations within an IoT Network for Sustaining the Fault Tolerance of an IoT Network through an Efficient Path Finding Algorithm

The IoT networks for implementing mission-critical applications need a layer to effect remote communication between the cluster heads and the microcontrollers. Remote communication is affected through base stations using cellular technologies. Using a single base station in this layer is risky as the fault tolerance level of the network will be zero when the base stations break down. Generally, the cluster heads are within the base station spectrum, making seamless integration possible. Implementing a dual base station to cater for a breakdown of the first base station creates huge remoteness as the cluster heads are not within the spectrum of the second base station. Furthermore, using the remote base station involves huge latency affecting the performance of the IoT network. In this paper, a relay-based network is presented with intelligence to fetch the shortest path for communicating to reduce latency and sustain the fault tolerance capability of the IoT network. The results demonstrate that the technique improved the fault tolerance of the IoT network by 14.23%.

DTiGNN: Learning drug-target embedding from a heterogeneous biological network based on a two-level attention-based graph neural network

MOTIVATION

In vitro experiment-based drug-target interaction (DTI) exploration demands more human, financial and data resources. In silico approaches have been recommended for predicting DTIs to reduce time and cost. During the drug development process, one can analyze the therapeutic effect of the drug for a particular disease by identifying how the drug binds to the target for treating that disease. Hence, DTI plays a major role in drug discovery. Many computational methods have been developed for DTI prediction. However, the existing methods have limitations in terms of capturing the interactions via multiple semantics between drug and target nodes in a heterogeneous biological network (HBN).

METHODS

In this paper, we propose a DTiGNN framework for identifying unknown drug-target pairs. The DTiGNN first calculates the similarity between the drug and target from multiple perspectives. Then, the features of drugs and targets from each perspective are learned separately by using a novel method termed an information entropy-based random walk. Next, all of the learned features from different perspectives are integrated into a single drug and target similarity network by using a multi-view convolutional neural network. Using the integrated similarity networks, drug interactions, drug-disease associations, protein interactions and protein-disease association, the HBN is constructed. Next, a novel embedding algorithm called a meta-graph guided graph neural network is used to learn the embedding of drugs and targets. Then, a convolutional neural network is employed to infer new DTIs after balancing the sample using oversampling techniques.

RESULTS

The DTiGNN is applied to various datasets, and the result shows better performance in terms of the area under receiver operating characteristic curve (AUC) and area under precision-recall curve (AUPR), with scores of 0.98 and 0.99, respectively. There are 23,739 newly predicted DTI pairs in total.

Dynamics of stochastic-constrained particles

Prior studies have focused on the overall behavior of randomly moving particle swarms. However, the characteristics of the stochastic-constrained particles that form ubiquitously within these swarms remain oblivious. This study demonstrates a generalized diffusion equation for stochastic-constrained particles that considers the velocity and location aggregation effects observed from their parent particle swarm (i.e., a completely random particle swarm). This equation can be approximated as the form of Schrödinger equation in the microcosmic case (low relative density) and describe the dynamics of the total mass distribution in the macrocosmic case (high relative density). The predicted density distribution of the particle swarm in the stable aggregation state is consistent with the total mass distribution of massive, relaxed galaxy clusters (at least in the range of [Formula: see text]), preventing cuspy problems in the empirical Navarro-Frenk-White profile. This study opens a window to observe the dynamics of stochastic-constrained particles from a third perspective, from which the aggregation effect of particles without gravitation can be saw.

Graph Learning for Anomaly Analytics: Algorithms, Applications, and Challenges

Anomaly analytics is a popular and vital task in various research contexts, which has been studied for several decades. At the same time, deep learning has shown its capacity in solving many graph-based tasks like, node classification, link prediction, and graph classification. Recently, many studies are extending graph learning models for solving anomaly analytics problems, resulting in beneficial advances in graph-based anomaly analytics techniques. In this survey, we provide a comprehensive overview of graph learning methods for anomaly analytics tasks. We classify them into four categories based on their model architectures, namely graph convolutional network (GCN), graph attention network (GAT), graph autoencoder (GAE), and other graph learning models. The differences between these methods are also compared in a systematic manner. Furthermore, we outline several graph-based anomaly analytics applications across various domains in the real world. Finally, we discuss five potential future research directions in this rapidly growing field.

Topic-based influential user detection: a survey

Online Social networks have become an easy means of communication for users to share their opinion on various topics, including breaking news, public events, and products. The content posted by a user can influence or affect other users, and the users who could influence or affect a high number of users are called influential users. Identifying such influential users has a wide range of applications in the field of marketing, including product advertisement, recommendation, and brand evaluation. However, the users’ influence varies in different topics, and hence a tremendous interest has been shown towards identifying topic-based influential users over the past few years. Topic-level information in the content posted by the users can be used in various stages of the topic-based influential user detection (IUD) problem, including data gathering, construction of influence network, quantifying the influence between two users, and analyzing the impact of the detected influential user. This has opened up a wide range of opportunities to utilize the existing techniques to model and analyze the topic-level influence in online social networks. In this paper, we perform a comprehensive study of existing techniques used to infer the topic-based influential users in online social networks. We present a detailed review of these approaches in a taxonomy while highlighting the challenges and limitations associated with each technique. Moreover, we perform a detailed study of different evaluation techniques used in the literature to overcome the challenges that arise in evaluating topic-based IUD approaches. Furthermore, closely related research topics and open research questions in topic-based IUD are discussed to provide a deep understanding of the literature and future directions.

De novo individualized disease modules reveal the synthetic penetrance of genes and inform personalized treatment regimens

Current understandings of individual disease etiology and therapeutics are limited despite great need. To fill the gap, we propose a novel computational pipeline that collects potent disease gene cooperative pathways to envision individualized disease etiology and therapies. Our algorithm constructs individualized disease modules de novo, which enables us to elucidate the importance of mutated genes in specific patients and to understand the synthetic penetrance of these genes across patients. We reveal that importance of the notorious cancer drivers TP53 and PIK3CA fluctuate widely across breast cancers and peak in tumors with distinct numbers of mutations and that rarely mutated genes such as XPO1 and PLEKHA1 have high disease module importance in specific individuals. Furthermore, individualized module disruption enables us to devise customized singular and combinatorial target therapies that were highly varied across patients, showing the need for precision therapeutics pipelines. As the first analysis of de novo individualized disease modules, we illustrate the power of individualized disease modules for precision medicine by providing deep novel insights on the activity of diseased genes in individuals.

Together Recognizing, Localizing and Summarizing Actions in Egocentric Videos

Analysis of egocentric video has recently drawn attention of researchers in the computer vision as well as multimedia communities. In this paper, we propose a weakly supervised superpixel level joint framework for localization, recognition and summarization of actions in an egocentric video. We first recognize and localize single as well as multiple action(s) in each frame of an egocentric video and then construct a summary of these detected actions. The superpixel level solution helps in precise localization of actions in addition to improving the recognition accuracy. Superpixels are extracted within the central regions of the egocentric video frames; these central regions being determined through a previously developed center-surround model. A sparse spatio-temporal video representation graph is constructed in the deep feature space with the superpixels as nodes. A weakly supervised solution using random walks yields action labels for each superpixel. After determining action label(s) for each frame from its constituent superpixels, we apply a fractional knapsack type formulation for obtaining a summary (of actions). Experimental comparisons on publicly available ADL, GTEA, EGTEA Gaze+, EgoGesture, and EPIC-Kitchens datasets show the effectiveness of the proposed solution.

Analysis of node2vec random walks on networks

Random walks have been proven to be useful for constructing various algorithms to gain information on networks. Algorithm node2vec employs biased random walks to realize embeddings of nodes into low-dimensional spaces, which can then be used for tasks such as multi-label classification and link prediction. The performance of the node2vec algorithm in these applications is considered to depend on properties of random walks that the algorithm uses. In the present study, we theoretically and numerically analyse random walks used by the node2vec. Those random walks are second-order Markov chains. We exploit the mapping of its transition rule to a transition probability matrix among directed edges to analyse the stationary probability, relaxation times in terms of the spectral gap of the transition probability matrix, and coalescence time. In particular, we show that node2vec random walk accelerates diffusion when walkers are designed to avoid both backtracking and visiting a neighbour of the previously visited node but do not avoid them completely.

Quantum walks with sequential aperiodic jumps

We analyze a set of discrete-time quantum walks for which the displacements on a chain follow binary aperiodic jumps according to three paradigmatic sequences: Fibonacci, Thue-Morse, and Rudin-Shapiro. We use a generalized Hadamard coin, C[over ̂]_{H}, as well as a generalized Fourier coin, C[over ̂]_{K}. We verify the QW experiences a slowdown of the wave packet spreading, σ^{2}(t)∼t^{α}, by the aperiodic jumps whose exponent, α, depends on the type of aperiodicity. Additional aperiodicity-induced effects also emerge, namely, (1) while the superdiffusive regime (1<α<2) is predominant, α displays an unusual sensibility with the type of coin operator where the more pronounced differences emerge for the Rudin-Shapiro and random protocols and (2) even though the angle θ of the coin operator is homogeneous in space and time, there is a nonmonotonic dependence of α with θ. Fingerprints of the aperiodicity in the hoppings are also found when distributional measures such as the Shannon and von Neumann entropies, the Inverse Participation Ratio, the Jensen-Shannon dissimilarity, and the kurtosis are computed, which allow assessing informational and delocalization features arising from these protocols and understanding the impact of linear and nonlinear correlations of the jump sequence in a quantum walk as well. Finally, we argue the spin-lattice entanglement is enhanced by aperiodic jumps.