gRNAde: A Geometric Deep Learning Pipeline for 3D RNA Inverse Design.

Fundamental to the diverse biological functions of RNA are its 3D structure and conformational flexibility, which enable single sequences to adopt a variety of distinct 3D states. Currently, computational RNA design tasks are often posed as inverse problems, where sequences are designed based on adopting a single desired secondary structure without considering 3D geometry and conformational diversity. In this tutorial, we present gRNAde, a geometric RNA design pipeline operating on sets of 3D RNA backbone structures to design sequences that explicitly account for RNA 3D structure and dynamics. gRNAde is a graph neural network that uses an SE (3) equivariant encoder-decoder framework for generating RNA sequences conditioned on backbone structures where the identities of the bases are unknown. We demonstrate the utility of gRNAde for fixed-backbone re-design of existing RNA structures of interest from the PDB, including riboswitches, aptamers, and ribozymes. gRNAde is more accurate in terms of native sequence recovery while being significantly faster compared to existing physics-based tools for 3D RNA inverse design, such as Rosetta.

Application of a single-cell-RNA-based biological-inspired graph neural network in diagnosis of primary liver tumors.

Single-cell technology depicts integrated tumor profiles including both tumor cells and tumor microenvironments, which theoretically enables more robust diagnosis than traditional diagnostic standards based on only pathology. However, the inherent challenges of single-cell RNA sequencing (scRNA-seq) data, such as high dimensionality, low signal-to-noise ratio (SNR), sparse and non-Euclidean nature, pose significant obstacles for traditional diagnostic approaches. The diagnostic value of single-cell technology has been largely unexplored despite the potential advantages. Here, we present a graph neural network-based framework tailored for molecular diagnosis of primary liver tumors using scRNA-seq data. Our approach capitalizes on the biological plausibility inherent in the intercellular communication networks within tumor samples. By integrating pathway activation features within cell clusters and modeling unidirectional inter-cellular communication, we achieve robust discrimination between malignant tumors (including hepatocellular carcinoma, HCC, and intrahepatic cholangiocarcinoma, iCCA) and benign tumors (focal nodular hyperplasia, FNH) by scRNA data of all tissue cells and immunocytes only. The efficacy to distinguish iCCA from HCC was further validated on public datasets. Through extending the application of high-throughput scRNA-seq data into diagnosis approaches focusing on integrated tumor microenvironment profiles rather than a few tumor markers, this framework also sheds light on minimal-invasive diagnostic methods based on migrating/circulating immunocytes.

The effect of chess on cognition: a graph theory study on cognitive data.

Objectives: We aimed to advance our understanding of the effect of chess on cognition by expanding previous univariate studies with the use of graph theory on cognitive data. Specifically, we investigated the cognitive connectome of adult chess players. Method: We included 19 chess players and 19 controls with ages between 39 and 69 years. Univariate analysis and graph theory included 27 cognitive measures representing multiple cognitive domains and subdomains. Graph analysis included global and nodal measures of integration, segregation, and centrality. We also performed an analysis of community structures to gain an additional understanding of the cognitive architecture of chess players. Results: The analysis of global graph measures showed that chess players had a higher local efficiency than controls at the cost of a lower global efficiency, which did not permeate segregation aspects of their connectome. The nodal graph measures showed that executive/attention/processing speed and visuoconstructive nodes had a central role in the connectome of chess players. The analysis of communities showed that chess players had a slightly reorganized cognitive architecture into three modules. These graph theory findings were in the context of better cognitive performance in chess players than controls in visuospatial abilities. Conclusion: We conclude that the cognitive architecture of chess players is slightly reorganized into functionally and anatomically coherent modules reflecting a distinction between visual, verbal, and executive/attention/processing speed-related functions, perhaps reminiscent of right hemisphere and left hemisphere subnetworks orchestrated by the frontal lobe and its white matter connections.

Predicting microbe-disease association based on graph autoencoder and inductive matrix completion with multi-similarities fusion.

Background: Clinical studies have demonstrated that microbes play a crucial role in human health and disease. The identification of microbe-disease interactions can provide insights into the pathogenesis and promote the diagnosis, treatment, and prevention of disease. Although a large number of computational methods are designed to screen novel microbe-disease associations, the accurate and efficient methods are still lacking due to data inconsistence, underutilization of prior information, and model performance. Methods: In this study, we proposed an improved deep learning-based framework, named GIMMDA, to identify latent microbe-disease associations, which is based on graph autoencoder and inductive matrix completion. By co-training the information from microbe and disease space, the new representations of microbes and diseases are used to reconstruct microbe-disease association in the end-to-end framework. In particular, a similarity fusion strategy is conducted to improve prediction performance. Results: The experimental results show that the performance of GIMMDA is competitive with that of existing state-of-the-art methods on 3 datasets (i.e., HMDAD, Disbiome, and multiMDA). In particular, it performs best with the area under the receiver operating characteristic curve (AUC) of 0.9735, 0.9156, 0.9396 on abovementioned 3 datasets, respectively. And the result also confirms that different similarity fusions can improve the prediction performance. Furthermore, case studies on two diseases, i.e., asthma and obesity, validate the effectiveness and reliability of our proposed model. Conclusion: The proposed GIMMDA model show a strong capability in predicting microbe-disease associations. We expect that GPUDMDA will help identify potential microbe-related diseases in the future.

Reorganization of structural connectivity in the brain supports preservation of cognitive ability in healthy aging.

The global population is aging rapidly, and a research question of critical importance is why some older adults suffer tremendous cognitive decline while others are mostly spared. Past aging research has shown that older adults with spared cognitive ability have better local short-range information processing while global long-range processing is less efficient. We took this research a step further to investigate whether the underlying structural connections, measured in vivo using diffusion magnetic resonance imaging (dMRI), show a similar shift to support cognitive ability. We analyzed the structural connectivity streamline probability (representing the probability of connection between regions) and nodal efficiency and local efficiency regional graph theory metrics to determine whether age and cognitive ability are related to structural network differences. We found that the relationship between structural connectivity and cognitive ability with age was nuanced, with some differences with age that were associated with poorer cognitive outcomes, but other reorganizations that were associated with spared cognitive ability. These positive changes included strengthened local intrahemispheric connectivity and increased nodal efficiency of the ventral occipital-temporal stream, nucleus accumbens, and hippocampus for older adults, and widespread local efficiency primarily for middle-aged individuals.

We utilized network neuroscience methods to investigate why some older adults suffer tremendous cognitive decline while others are mostly spared. Past functional research found that older adults with spared cognitive ability have better local short-range information processing while global long-range processing is less efficient. We took this research a step further to investigate whether structural connectivity reorganizes to preserve cognitive ability. We analyzed age and fluid intelligence as a function of structural connectivity and regional graph theory measures using partial least squares. Some differences with age were associated with poorer cognitive outcomes, but other reorganizations spared cognitive ability. Beneficial reorganizations included strengthened local intrahemispheric connectivity and increased nodal efficiency of focal regions for older adults, as well as widespread increased local efficiency for middle-aged individuals.

NecroGlobalGCN: Integrating micronecrosis information in HCC prognosis prediction via graph convolutional neural networks.

BACKGROUND AND OBJECTIVE: Hepatocellular carcinoma (HCC) ranks fourth in cancer mortality, underscoring the importance of accurate prognostic predictions to improve postoperative survival rates in patients. Although micronecrosis has been shown to have high prognostic value in HCC, its application in clinical prognosis prediction requires specialized knowledge and complex calculations, which poses challenges for clinicians. It would be of interest to develop a model to help clinicians make full use of micronecrosis to assess patient survival. METHODS: To address these challenges, we propose a HCC prognosis prediction model that integrates pathological micronecrosis information through Graph Convolutional Neural Networks (GCN). This approach enables GCN to utilize micronecrosis, which has been shown to be highly correlated with prognosis, thereby significantly enhancing prognostic stratification quality. We developed our model using 3622 slides from 752 patients with primary HCC from the FAH-ZJUMS dataset and conducted internal and external validations on the FAH-ZJUMS and TCGA-LIHC datasets, respectively. RESULTS: Our method outperformed the baseline by 8.18% in internal validation and 9.02% in external validations. Overall, this paper presents a deep learning research paradigm that integrates HCC micronecrosis, enhancing both the accuracy and interpretability of prognostic predictions, with potential applicability to other pathological prognostic markers. CONCLUSIONS: This study proposes a composite GCN prognostic model that integrates information on HCC micronecrosis, collecting large dataset of HCC histopathological images. This approach could assist clinicians in analyzing HCC patient survival and precisely locating and visualizing necrotic tissues that affect prognosis. Following the research paradigm outlined in this paper, other prognostic biomarker integration models with GCN could be developed, significantly enhancing the predictive performance and interpretability of prognostic model.

Multi-relational graph contrastive learning with learnable graph augmentation.

Multi-relational graph learning aims to embed entities and relations in knowledge graphs into low-dimensional representations, which has been successfully applied to various multi-relationship prediction tasks, such as information retrieval, question answering, and etc. Recently, contrastive learning has shown remarkable performance in multi-relational graph learning by data augmentation mechanisms to deal with highly sparse data. In this paper, we present a Multi-Relational Graph Contrastive Learning architecture (MRGCL) for multi-relational graph learning. More specifically, our MRGCL first proposes a Multi-relational Graph Hierarchical Attention Networks (MGHAN) to identify the importance between entities, which can learn the importance at different levels between entities for extracting the local graph dependency. Then, two graph augmented views with adaptive topology are automatically learned by the variant MGHAN, which can automatically adapt for different multi-relational graph datasets from diverse domains. Moreover, a subgraph contrastive loss is designed, which generates positives per anchor by calculating strongly connected subgraph embeddings of the anchor as the supervised signals. Comprehensive experiments on multi-relational datasets from three application domains indicate the superiority of our MRGCL over various state-of-the-art methods. Our datasets and source code are published at https://github.com/Legendary-L/MRGCL.

Interaction-knowledge semantic alignment for recommendation.

In order to alleviate the issue of data sparsity, knowledge graphs are introduced into recommender systems because they contain diverse information about items. The existing knowledge graph enhanced recommender systems utilize both user-item interaction data and knowledge graph, but those methods ignore the semantic difference between interaction data and knowledge graph. On the other hand, for the item representations obtained from two kinds of graph structure data respectively, the existing methods of fusing representations only consider the item representations themselves, without considering the personalized preference of users. In order to overcome the limitations mentioned above, we present a recommendation method named Interaction-Knowledge Semantic Alignment for Recommendation (IKSAR). By introducing a semantic alignment module, the semantic difference between the interaction bipartite graph and the knowledge graph is reduced. The representation of user is integrated during the fusion of representations of item, which improves the quality of the fused representation of item. To validate the efficacy of the proposed approach, we perform comprehensive experiments on three datasets. The experimental results demonstrate that the IKSAR is superior to the existing methods, showcasing notable improvement.

Deep learning-derived optimal aviation strategies to control pandemics.

The COVID-19 pandemic affected countries across the globe, demanding drastic public health policies to mitigate the spread of infection, which led to economic crises as a collateral damage. In this work, we investigate the impact of human mobility, described via international commercial flights, on COVID-19 infection dynamics on a global scale. We developed a graph neural network (GNN)-based framework called Dynamic Weighted GraphSAGE (DWSAGE), which operates over spatiotemporal graphs and is well-suited for dynamically changing flight information updated daily. This architecture is designed to be structurally sensitive, capable of learning the relationships between edge features and node features. To gain insights into the influence of air traffic on infection spread, we conducted local sensitivity analysis on our model through perturbation experiments. Our analyses identified Western Europe, the Middle East, and North America as leading regions in fueling the pandemic due to the high volume of air traffic originating or transiting through these areas. We used these observations to propose air traffic reduction strategies that can significantly impact controlling the pandemic with minimal disruption to human mobility. Our work provides a robust deep learning-based tool to study global pandemics and is of key relevance to policymakers for making informed decisions regarding air traffic restrictions during future outbreaks.

Functional connectivity compensation in Parkinson's disease with freezing of gait.

Freezing of gait (FOG) is a disabling motor symptom prevalent in patients with Parkinson's disease (PD); however, its pathophysiological mechanisms are poorly understood. This study aimed to investigate whole-brain functional connectivity (FC) pattern alterations in PD patients with FOG. A total of 18 PD patients, 10 with FOG (PD-FOG) and 8 without FOG (PD-nFOG), and 10 healthy controls were enrolled. High-resolution 3D T1-weighted and resting-state functional MRI (rs-fMRI) data were obtained from all participants. The groups' internetwork connectivity differences were explored with rs-fMRI FC using seed-based analysis and graph theory. Multiple linear regression analysis estimated the relationship between FC changes and clinical measurements. Rs-fMRI analysis demonstrated alterations in FC in various brain regions between the three groups. Freezing of Gait Questionnaire severity was correlated with decreased brain functional connection between Vermis12 and the left temporal occipital fusiform cortex (r = -0.82, P < .001). Graph theory topological metrics indicated a decreased clustering coefficient in the right superior temporal gyrus in the PD-nFOG group. PD-FOG patients exhibited a compensatory increase in connectivity between the left inferior frontal gyrus language network and the postcentral gyrus compared to PD-nFOG patients. Further, the decreased connection between Vermis 12 and the left temporal occipital fusiform cortex may serve as a potential neuroimaging biomarker for tracking PD-FOG and distinguishing between PD subtypes.

Investigating Material Interface Diffusion Phenomena through Graph Neural Networks in Applied Materials.

Understanding and predicting interface diffusion phenomena in materials is crucial for various industrial applications, including semiconductor manufacturing, battery technology, and catalysis. In this study, we propose a novel approach utilizing Graph Neural Networks (GNNs) to investigate and model material interface diffusion. We begin by collecting experimental and simulated data on diffusion coefficients, concentration gradients, and other relevant parameters from diverse material systems. The data are preprocessed, and key features influencing interface diffusion are extracted. Subsequently, we construct a GNN model tailored to the diffusion problem, with a graph representation capturing the atomic structure of materials. The model architecture includes multiple graph convolutional layers for feature aggregation and update, as well as optional graph attention layers to capture complex relationships between atoms. We train and validate the GNN model using the preprocessed data, achieving accurate predictions of diffusion coefficients, diffusion rates, concentration profiles, and potential diffusion pathways. Our approach offers insights into the underlying mechanisms of interface diffusion and provides a valuable tool for optimizing material design and engineering. Additionally, our method offers possible strategies to solve the longstanding problems related to materials interface diffusion.

Reconfiguring Shortest Paths in Graphs.

Reconfiguring two shortest paths in a graph means modifying one shortest path to the other by changing one vertex at a time so that all the intermediate paths are also shortest paths. This problem has several natural applications, namely: (a) repaving road networks, (b) rerouting data packets in a synchronous multiprocessing setting, (c) the shipping container stowage problem, and (d) the train marshalling problem. When modelled as graph problems, (a) is the most general case while (b), (c), (d) are restrictions to different graph classes. We show that (a) does not admit polynomial-time algorithms (assuming P ≠ NP ), even for relaxed variants of the problem (assuming P ≠ PSPACE ). For (b), (c), (d), we present polynomial-time algorithms to solve the respective problems. We also generalize the problem to when at most k (for a fixed integer k ≥ 2 ) contiguous vertices on a shortest path can be changed at a time.

AUV SLAM method based on SO-CFAR and ADT feature extraction.

Due to the exceptional detection capabilities, the forward-looking sonar could be adopted in simultaneous localization and mapping (SLAM) for autonomous underwater vehicle (AUVs). This paper primarily investigates the application of the factor graph optimization SLAM algorithm based on feature maps in AUV. It achieves this by combining the smallest of constant false alarm rate (SO-CFAR) and adaptive threshold (ADT) to filter noise from the forward-looking sonar and extract feature point clouds. Furthermore, a weighted iterative closest point (WICP) algorithm is employed for feature point registration, which is extracted from the sonar image. The experimental result based on field data demonstrates that the proposed method, with an 8.52% improvement in root mean square error (RMSE) compared with dead reckoning (DR).

CoNglyPred: Accurate Prediction of N-Linked Glycosylation Sites Using ESM-2 and Structural Features With Graph Network and Co-Attention.

N-Linked glycosylation is crucial for various biological processes such as protein folding, immune response, and cellular transport. Traditional experimental methods for determining N-linked glycosylation sites entail substantial time and labor investment, which has led to the development of computational approaches as a more efficient alternative. However, due to the limited availability of 3D structural data, existing prediction methods often struggle to fully utilize structural information and fall short in integrating sequence and structural information effectively. Motivated by the progress of protein pretrained language models (pLMs) and the breakthrough in protein structure prediction, we introduced a high-accuracy model called CoNglyPred. Having compared various pLMs, we opt for the large-scale pLM ESM-2 to extract sequence embeddings, thus mitigating certain limitations associated with manual feature extraction. Meanwhile, our approach employs a graph transformer network to process the 3D protein structures predicted by AlphaFold2. The final graph output and ESM-2 embedding are intricately integrated through a co-attention mechanism. Among a series of comprehensive experiments on the independent test dataset, CoNglyPred outperforms state-of-the-art models and demonstrates exceptional performance in case study. In addition, we are the first to report the uncertainty of N-linked glycosylation predictors using expected calibration error and expected uncertainty calibration error.

Graph neural pre-training based drug-target affinity prediction.

Computational drug-target affinity prediction has the potential to accelerate drug discovery. Currently, pre-training models have achieved significant success in various fields due to their ability to train the model using vast amounts of unlabeled data. However, given the scarcity of drug-target interaction data, pre-training models can only be trained separately on drug and target data, resulting in features that are insufficient for drug-target affinity prediction. To address this issue, in this paper, we design a graph neural pre-training-based drug-target affinity prediction method (GNPDTA). This approach comprises three stages. In the first stage, two pre-training models are utilized to extract low-level features from drug atom graphs and target residue graphs, leveraging a large number of unlabeled training samples. In the second stage, two 2D convolutional neural networks are employed to combine the extracted drug atom features and target residue features into high-level representations of drugs and targets. Finally, in the third stage, a predictor is used to predict the drug-target affinity. This approach fully utilizes both unlabeled and labeled training samples, enhancing the effectiveness of pre-training models for drug-target affinity prediction. In our experiments, GNPDTA outperforms other deep learning methods, validating the efficacy of our approach.

SpLitteR: diploid genome assembly using TELL-Seq linked-reads and assembly graphs.

Background: Recent advances in long-read sequencing technologies enabled accurate and contiguous de novo assemblies of large genomes and metagenomes. However, even long and accurate high-fidelity (HiFi) reads do not resolve repeats that are longer than the read lengths. This limitation negatively affects the contiguity of diploid genome assemblies since two haplomes share many long identical regions. To generate the telomere-to-telomere assemblies of diploid genomes, biologists now construct their HiFi-based phased assemblies and use additional experimental technologies to transform them into more contiguous diploid assemblies. The barcoded linked-reads, generated using an inexpensive TELL-Seq technology, provide an attractive way to bridge unresolved repeats in phased assemblies of diploid genomes. Results: We developed the SpLitteR tool for diploid genome assembly using linked-reads and assembly graphs and benchmarked it against state-of-the-art linked-read scaffolders ARKS and SLR-superscaffolder using human HG002 genome and sheep gut microbiome datasets. The benchmark showed that SpLitteR scaffolding results in 1.5-fold increase in NGA50 compared to the baseline LJA assembly and other scaffolders while introducing no additional misassemblies on the human dataset. Conclusion: We developed the SpLitteR tool for assembly graph phasing and scaffolding using barcoded linked-reads. We benchmarked SpLitteR on assembly graphs produced by various long-read assemblers and have demonstrated that TELL-Seq reads facilitate phasing and scaffolding in these graphs. This benchmarking demonstrates that SpLitteR improves upon the state-of-the-art linked-read scaffolders in the accuracy and contiguity metrics. SpLitteR is implemented in C++ as a part of the freely available SPAdes package and is available at https://github.com/ablab/spades/releases/tag/splitter-preprint.

An efficient water quality index forecasting and categorization using optimized Deep Capsule Crystal Edge Graph neural network.

The world's freshwater supply, predominantly sourced from rivers, faces significant contamination from various economic activities, confirming that the quality of river water is critical for public health, environmental sustainability, and effective pollution control. This research addresses the urgent need for accurate and reliable water quality monitoring by introducing a novel method for estimating the water quality index (WQI). The proposed approach combines cutting-edge optimization techniques with Deep Capsule Crystal Edge Graph neural networks, marking a significant advancement in the field. The innovation lies in the integration of a Hybrid Crested Porcupine Genghis Khan Shark Optimization Algorithm for precise feature selection, ensuring that the most relevant indicators of water quality (WQ) are utilized. Furthermore, the use of the Greylag Goose Optimization Algorithm to fine-tune the neural network's weight parameters enhances the model's predictive accuracy. This dual optimization framework significantly improves WQI prediction, achieving a remarkable mean squared error (MSE) of 6.7 and an accuracy of 99%. By providing a robust and highly accurate method for WQ assessment, this research offers a powerful tool for environmental authorities to proactively manage river WQ, prevent pollution, and evaluate the success of restoration efforts. PRACTITIONER POINTS: Novel method combines optimization and Deep Capsule Crystal Edge Graph for WQI estimation. Preprocessing includes data cleanup and feature selection using advanced algorithms. Deep Capsule Crystal Edge Graph neural network predicts WQI with high accuracy. Greylag Goose Optimization fine-tunes network parameters for precise forecasts. Proposed method achieves low MSE of 6.7 and high accuracy of 99%.

The Second Hyper-Zagreb Index and Coindex of Chemical Nanostructures in Drugs.

INTRODUCTION: Various dendrimer nanoparticles have properties like multivalency, controlled size, and surface functionality that make them promising nanocarriers for targeted drug delivery and other applications in pharmaceutical sciences. The precise tunability of dendrimers is an advantage over other nanoparticles. The topological descriptors can be used to predict the physicochemical properties of dendrimers and optimize their branching pattern for specific applications. The second hyper-Zagreb index and co-index are computed for various chemical structures, including dendrimers, to facilitate the correlation between their structure and biological activity. METHOD: In this study, the second Hyper-Zagreb index and second Hyper-Zagreb polynomials were calculated for various chemical structures, such as the molecular graph of poly(propyl) ether imine dendrimer PETIM, nanostar dendrimer (D3[p]), polypropylenimine octaamine dendrimer (NS1[p]) and (NS2[p]), polymer dendrimer (NS3[p]) and NS5[p]), fullerene dendrimer (NS4[p]), and other classes of dendrimers. RESULT: By computing formulae and analyzing data and figures, we obtained new insights into the features of structure-property connections for these types of compounds of nanostar dendrimers. CONCLUSION: The results can be used to optimize the properties of dendrimers for specific applications.

A Coupled Spatial-Network Model: A Mathematical Framework for Applications in Epidemiology.

There is extensive evidence that network structure (e.g., air transport, rivers, or roads) may significantly enhance the spread of epidemics into the surrounding geographical area. A new compartmental modeling framework is proposed which couples well-mixed (ODE in time) population centers at the vertices, 1D travel routes on the graph's edges, and a 2D continuum containing the rest of the population to simulate how an infection spreads through a population. The edge equations are coupled to the vertex ODEs through junction conditions, while the domain equations are coupled to the edges through boundary conditions. A numerical method based on spatial finite differences for the edges and finite elements in the 2D domain is described to approximate the model, and numerical verification of the method is provided. The model is illustrated on two simple and one complex example geometries, and a parameter study example is performed. The observed solutions exhibit exponential decay after a certain time has passed, and the cumulative infected population over the vertices, edges, and domain tends to a constant in time but varying in space, i.e., a steady state solution.

Graph Neural Networks for Carbon Dioxide Adsorption Prediction in Aluminum-Substituted Zeolites.

The ability to efficiently predict adsorption properties of zeolites can be of large benefit in accelerating the design process of novel materials. The existing configuration space for these materials is wide, while existing molecular simulation methods are computationally expensive. In this work, we propose a model which is 4 to 5 orders of magnitude faster at adsorption properties compared to molecular simulations. To validate the model, we generated data sets containing various aluminum configurations for the MOR, MFI, RHO and ITW zeolites along with their heat of adsorptions and Henry coefficients for CO2, obtained from Monte Carlo simulations. The predictions obtained from the Machine Learning model are in agreement with the values obtained from the Monte Carlo simulations, confirming that the model can be used for property prediction. Furthermore, we show that the model can be used for identifying adsorption sites. Finally, we evaluate the capability of our model for generating novel zeolite configurations by using it in combination with a genetic algorithm.