Network-based prediction of protein interactions

State of the interactomes: an evaluation of molecular networks for generating biological insights

Advancements in genomic and proteomic technologies have powered the creation of large gene and protein networks ("interactomes") for understanding biological systems. However, the proliferation of interactomes complicates the selection of networks for specific applications. Here, we present a comprehensive evaluation of 45 current human interactomes, encompassing protein-protein interactions as well as gene regulatory, signaling, colocalization, and genetic interaction networks. Our analysis shows that large composite networks such as HumanNet, STRING, and FunCoup are most effective for identifying disease genes, while smaller networks such as DIP, Reactome, and SIGNOR demonstrate stronger performance in interaction prediction. Our study provides a benchmark for interactomes across diverse biological applications and clarifies factors that influence network performance. Furthermore, our evaluation pipeline paves the way for continued assessment of emerging and updated interaction networks in the future.

Heterogeneous network approaches to protein pathway prediction

Understanding protein-protein interactions (PPIs) and the pathways they comprise is essential for comprehending cellular functions and their links to specific phenotypes. Despite the prevalence of molecular data generated by high-throughput sequencing technologies, a significant gap remains in translating this data into functional information regarding the series of interactions that underlie phenotypic differences. In this review, we present an in-depth analysis of heterogeneous network methodologies for modeling protein pathways, highlighting the critical role of integrating multifaceted biological data. It outlines the process of constructing these networks, from data representation to machine learning-driven predictions and evaluations. The work underscores the potential of heterogeneous networks in capturing the complexity of proteomic interactions, thereby offering enhanced accuracy in pathway prediction. This approach not only deepens our understanding of cellular processes but also opens up new possibilities in disease treatment and drug discovery by leveraging the predictive power of comprehensive proteomic data analysis.

RIscoper 2.0: A deep learning tool to extract RNA biomedical relation sentences from literature

RNA plays an extensive role in a multi-dimensional regulatory system, and its biomedical relationships are scattered across numerous biological studies. However, text mining works dedicated to the extraction of RNA biomedical relations remain limited. In this study, we established a comprehensive and reliable corpus of RNA biomedical relations, recruiting over 30,000 sentences manually curated from more than 15,000 biomedical literature. We also updated RIscoper 2.0, a BERT-based deep learning tool to extract RNA biomedical relation sentences from literature. Benefiting from approximately 100,000 annotated named entities, we integrated the text classification and named entity recognition tasks in this tool. Additionally, RIscoper 2.0 outperformed the original tool in both tasks and can discover new RNA biomedical relations. Additionally, we provided a user-friendly online search tool that enables rapid scanning of RNA biomedical relationships using local and online resources. Both the online tools and data resources of RIscoper 2.0 are available at http://www.rnainter.org/riscoper.

Cross-modal embedding integrator for disease-gene/protein association prediction using a multi-head attention mechanism

Knowledge graphs, powerful tools that explicitly transfer knowledge to machines, have significantly advanced new knowledge inferences. Discovering unknown relationships between diseases and genes/proteins in biomedical knowledge graphs can lead to the identification of disease development mechanisms and new treatment targets. Generating high-quality representations of biomedical entities is essential for successfully predicting disease-gene/protein associations. We developed a computational model that predicts disease-gene/protein associations using the Precision Medicine Knowledge Graph, a biomedical knowledge graph. Embeddings of biomedical entities were generated using two different methods-a large language model (LLM) and the knowledge graph embedding (KGE) algorithm. The LLM utilizes information obtained from massive amounts of text data, whereas the KGE algorithm relies on graph structures. We developed a disease-gene/protein association prediction model, "Cross-Modal Embedding Integrator (CMEI)," by integrating embeddings from different modalities using a multi-head attention mechanism. The area under the receiver operating characteristic curve of CMEI was 0.9662 (± 0.0002) in predicting disease-gene/protein associations. In conclusion, we developed a computational model that effectively predicts disease-gene/protein associations. CMEI may contribute to the identification of disease development mechanisms and new treatment targets.

Graph-based machine learning model for weight prediction in protein-protein networks

Proteins interact with each other in complex ways to perform significant biological functions. These interactions, known as protein-protein interactions (PPIs), can be depicted as a graph where proteins are nodes and their interactions are edges. The development of high-throughput experimental technologies allows for the generation of numerous data which permits increasing the sophistication of PPI models. However, despite significant progress, current PPI networks remain incomplete. Discovering missing interactions through experimental techniques can be costly, time-consuming, and challenging. Therefore, computational approaches have emerged as valuable tools for predicting missing interactions. In PPI networks, a graph is usually used to model the interactions between proteins. An edge between two proteins indicates a known interaction, while the absence of an edge means the interaction is not known or missed. However, this binary representation overlooks the reliability of known interactions when predicting new ones. To address this challenge, we propose a novel approach for link prediction in weighted protein-protein networks, where interaction weights denote confidence scores. By leveraging data from the yeast Saccharomyces cerevisiae obtained from the STRING database, we introduce a new model that combines similarity-based algorithms and aggregated confidence score weights for accurate link prediction purposes. Our model significantly improves prediction accuracy, surpassing traditional approaches in terms of Mean Absolute Error, Mean Relative Absolute Error, and Root Mean Square Error. Our proposed approach holds the potential for improved accuracy in predicting PPIs, which is crucial for better understanding the underlying biological processes.

Inconsistency among evaluation metrics in link prediction

Link prediction is a paradigmatic and challenging problem in network science, which aims to predict missing links, future links, and temporal links based on known topology. Along with the increasing number of link prediction algorithms, a critical yet previously ignored risk is that the evaluation metrics for algorithm performance are usually chosen at will. This paper implements extensive experiments on hundreds of real networks and 26 well-known algorithms, revealing significant inconsistency among evaluation metrics, namely different metrics probably produce remarkably different rankings of algorithms. Therefore, we conclude that any single metric cannot comprehensively or credibly evaluate algorithm performance. In terms of information content, we suggest the usage of at least two metrics: one is the area under the receiver operating characteristic curve, and the other is one of the following three candidates, say the area under the precision-recall curve, the area under the precision curve, and the normalized discounted cumulative gain. When the data are imbalanced, say the number of negative samples significantly outweighs the number of positive samples, the area under the generalized Receiver Operating Characteristic curve should also be used. In addition, as we have proved the essential equivalence of threshold-dependent metrics, if in a link prediction task, some specific thresholds are meaningful, we can consider any one threshold-dependent metric with those thresholds. This work completes a missing part in the landscape of link prediction, and provides a starting point toward a well-accepted criterion or standard to select proper evaluation metrics for link prediction.

Temperature-jump microscopy and interaction of Hsp70 heat shock protein with a client protein in vivo

Biomolecular processes such as protein-protein interactions can depend strongly on cell type and even vary within a single cell type. Here we develop a microscope with a Peltier-controlled temperature stage, a laser temperature jump to induce heat stress, and an autofocusing feature to mitigate temperature drift during experiments, to study a protein-protein interaction in a selected cell type within a live organism, the zebrafish larva. As an application of the instrument, we show that there is considerable cell-to-cell variation of the heat shock protein Hsp70 binding to one of its clients, phosphoglycerate kinase in vivo. We adapt a key feature from our previous folding study, rare transformation of cells within the larva, so that individual cells can be imaged and differentiated for cell-to-cell response. Our approach can be extended to other organisms and cell types than the ones demonstrated in this work.

NADPHnet: a novel strategy to predict compounds for regulation of NADPH metabolism via network-based methods

Identification of compounds to modulate NADPH metabolism is crucial for understanding complex diseases and developing effective therapies. However, the complex nature of NADPH metabolism poses challenges in achieving this goal. In this study, we proposed a novel strategy named NADPHnet to predict key proteins and drug-target interactions related to NADPH metabolism via network-based methods. Different from traditional approaches only focusing on one single protein, NADPHnet could screen compounds to modulate NADPH metabolism from a comprehensive view. Specifically, NADPHnet identified key proteins involved in regulation of NADPH metabolism using network-based methods, and characterized the impact of natural products on NADPH metabolism using a combined score, NADPH-Score. NADPHnet demonstrated a broader applicability domain and improved accuracy in the external validation set. This approach was further employed along with molecular docking to identify 27 compounds from a natural product library, 6 of which exhibited concentration-dependent changes of cellular NADPH level within 100 μM, with Oxyberberine showing promising effects even at 10 μM. Mechanistic and pathological analyses of Oxyberberine suggest potential novel mechanisms to affect diabetes and cancer. Overall, NADPHnet offers a promising method for prediction of NADPH metabolism modulation and advances drug discovery for complex diseases.

Exploring the evolutionary trajectory and functional landscape of cannabinoid receptors: A comprehensive bioinformatic analysis

The bioinformatic analysis of cannabinoid receptors (CBRs) CB1 and CB2 reveals a detailed picture of their structure, evolution, and physiological significance within the endocannabinoid system (ECS). The study highlights the evolutionary conservation of these receptors evidenced by sequence alignments across diverse species including humans, amphibians, and fish. Both CBRs share a structural hallmark of seven transmembrane (TM) helices, characteristic of class A G-protein-coupled receptors (GPCRs), which are critical for their signalling functions. The study reports a similarity of 44.58 % between both CBR sequences, which suggests that while their evolutionary paths and physiological roles may differ, there is considerable conservation in their structures. Pathway databases like KEGG, Reactome, and WikiPathways were employed to determine the involvement of the receptors in various signalling pathways. The pathway analyses integrated within this study offer a detailed view of the CBRs interactions within a complex network of cannabinoid-related signalling pathways. High-resolution crystal structures (PDB ID: 5U09 for CB1 and 5ZTY for CB2) provided accurate structural information, showing the binding pocket volume and surface area of the receptors, essential for ligand interaction. The comparison between these receptors' natural sequences and their engineered pseudo-CBRs (p-CBRs) showed a high degree of sequence identity, confirming the validity of using p-CBRs in receptor-ligand interaction studies. This comprehensive analysis enhances the understanding of the structural and functional dynamics of cannabinoid receptors, highlighting their physiological roles and their potential as therapeutic targets within the ECS.

Readdressing the Localization of Apolipoprotein E (APOE) in Mitochondria-Associated Endoplasmic Reticulum (ER) Membranes (MAMs): An Investigation of the Hepatic Protein-Protein Interactions of APOE with the Mitochondrial Proteins Lon Protease (LONP1), Mitochondrial Import Receptor Subunit TOM40 (TOMM40) and Voltage-Dependent Anion-Selective Channel 1 (VDAC1)

As a component of circulating lipoproteins, APOE binds to cell surface receptors mediating lipoprotein metabolism and cholesterol transport. A growing body of evidence, including the identification of a broad variety of cellular proteins interacting with APOE, suggests additional independent functions. Investigating cellular localization and protein-protein interactions in cultured human hepatocytes, we aimed to contribute to the elucidation of hitherto unnoted cellular functions of APOE. We observed a strong accumulation of APOE in MAMs, equally evident for the two major isoforms APOE3 and APOE4. Using mass spectrometry proteome analyses, novel and previously noted APOE interactors were identified, including the mitochondrial proteins TOMM40, LONP1 and VDAC1. All three interactors were present in MAM fractions, which we think initially facilitates interactions with APOE. LONP1 is a protease with chaperone activity, which migrated to MAMs in response to ER stress, displaying a reinforced interaction with APOE. We therefore hypothesize that APOE may help in the unfolded protein response (UPR) by acting as a co-chaperone in cooperation with LONP1 at the interface of mitochondria and ER membranes. The interaction of APOE with the integral proteins TOMM40 and VDAC1 may point to the formation of bridging complexes connecting mitochondria with other organelles.

Knowledge Graphs for drug repurposing: a review of databases and methods

Drug repurposing has emerged as a effective and efficient strategy to identify new treatments for a variety of diseases. One of the most effective approaches for discovering potential new drug candidates involves the utilization of Knowledge Graphs (KGs). This review comprehensively explores some of the most prominent KGs, detailing their structure, data sources, and how they facilitate the repurposing of drugs. In addition to KGs, this paper delves into various artificial intelligence techniques that enhance the process of drug repurposing. These methods not only accelerate the identification of viable drug candidates but also improve the precision of predictions by leveraging complex datasets and advanced algorithms. Furthermore, the importance of explainability in drug repurposing is emphasized. Explainability methods are crucial as they provide insights into the reasoning behind AI-generated predictions, thereby increasing the trustworthiness and transparency of the repurposing process. We will discuss several techniques that can be employed to validate these predictions, ensuring that they are both reliable and understandable.

Current approaches and outstanding challenges of functional annotation of metabolites: a comprehensive review

Metabolite profiling is a powerful approach for the clinical diagnosis of complex diseases, ranging from cardiometabolic diseases, cancer, and cognitive disorders to respiratory pathologies and conditions that involve dysregulated metabolism. Because of the importance of systems-level interpretation, many methods have been developed to identify biologically significant pathways using metabolomics data. In this review, we first describe a complete metabolomics workflow (sample preparation, data acquisition, pre-processing, downstream analysis, etc.). We then comprehensively review 24 approaches capable of performing functional analysis, including those that combine metabolomics data with other types of data to investigate the disease-relevant changes at multiple omics layers. We discuss their availability, implementation, capability for pre-processing and quality control, supported omics types, embedded databases, pathway analysis methodologies, and integration techniques. We also provide a rating and evaluation of each software, focusing on their key technique, software accessibility, documentation, and user-friendliness. Following our guideline, life scientists can easily choose a suitable method depending on method rating, available data, input format, and method category. More importantly, we highlight outstanding challenges and potential solutions that need to be addressed by future research. To further assist users in executing the reviewed methods, we provide wrappers of the software packages at https://github.com/tinnlab/metabolite-pathway-review-docker.

Exploring the Knowledge of an Outstanding Protein to Protein Interaction Transformer

Protein-to-protein interaction (PPI) prediction aims to predict whether two given proteins interact or not. Compared with traditional experimental methods of high cost and low efficiency, the current deep learning based approach makes it possible to discover massive potential PPIs from large-scale databases. However, deep PPI prediction models perform poorly on unseen species, as their proteins are not in the training set. Targetting on this issue, the paper first proposes PPITrans, a Transformer based PPI prediction model that exploits a language model pre-trained on proteins to conduct binary PPI prediction. To validate the effectiveness on unseen species, PPITrans is trained with Human PPIs and tested on PPIs of other species. Experimental results show that PPITrans significantly outperforms the previous state-of-the-art on various metrics, especially on PPIs of unseen species. For example, the AUPR improves 0.339 absolutely on Fly PPIs. Aiming to explore the knowledge learned by PPITrans from PPI data, this paper also designs a series of probes belonging to three categories. Their results reveal several interesting findings, like that although PPITrans cannot capture the spatial structure of proteins, it can obtain knowledge of PPI type and binding affinity, learning more than binary PPI.

Graph Representation Learning Based on Specific Subgraphs for Biomedical Interaction Prediction

Discovering the novel associations of biomedical entities is of great significance and can facilitate not only the identification of network biomarkers of disease but also the search for putative drug targets.Graph representation learning (GRL) has incredible potential to efficiently predict the interactions from biomedical networks by modeling the robust representation for each node.> However, the current GRL-based methods learn the representation of nodes by aggregating the features of their neighbors with equal weights. Furthermore, they also fail to identify which features of higher-order neighbors are integrated into the representation of the central node. In this work, we propose a novel graph representation learning framework: a multi-order graph neural network based on reconstructed specific subgraphs (MGRS) for biomedical interaction prediction. In the MGRS, we apply the multi-order graph aggregation module (MOGA) to learn the wide-view representation by integrating the multi-hop neighbor features. Besides, we propose a subgraph selection module (SGSM) to reconstruct the specific subgraph with adaptive edge weights for each node. SGSM can clearly explore the dependency of the node representation on the neighbor features and learn the subgraph-based representation based on the reconstructed weighted subgraphs. Extensive experimental results on four public biomedical networks demonstrate that the MGRS performs better and is more robust than the latest baselines.

Current and future directions in network biology

Summary

Network biology is an interdisciplinary field bridging computational and biological sciences that has proved pivotal in advancing the understanding of cellular functions and diseases across biological systems and scales. Although the field has been around for two decades, it remains nascent. It has witnessed rapid evolution, accompanied by emerging challenges. These stem from various factors, notably the growing complexity and volume of data together with the increased diversity of data types describing different tiers of biological organization. We discuss prevailing research directions in network biology, focusing on molecular/cellular networks but also on other biological network types such as biomedical knowledge graphs, patient similarity networks, brain networks, and social/contact networks relevant to disease spread. In more detail, we highlight areas of inference and comparison of biological networks, multimodal data integration and heterogeneous networks, higher-order network analysis, machine learning on networks, and network-based personalized medicine. Following the overview of recent breakthroughs across these five areas, we offer a perspective on future directions of network biology. Additionally, we discuss scientific communities, educational initiatives, and the importance of fostering diversity within the field. This article establishes a roadmap for an immediate and long-term vision for network biology.

Availability and implementation

Not applicable.

Computational Approaches to Drug Repurposing: Methods, Challenges, and Opportunities

Drug repurposing refers to the inference of therapeutic relationships between a clinical indication and existing compounds. As an emerging paradigm in drug development, drug repurposing enables more efficient treatment of rare diseases, stratified patient populations, and urgent threats to public health. However, prioritizing well-suited drug candidates from among a nearly infinite number of repurposing options continues to represent a significant challenge in drug development. Over the past decade, advances in genomic profiling, database curation, and machine learning techniques have enabled more accurate identification of drug repurposing candidates for subsequent clinical evaluation. This review outlines the major methodologic classes that these approaches comprise, which rely on (a) protein structure, (b) genomic signatures, (c) biological networks, and (d) real-world clinical data. We propose that realizing the full impact of drug repurposing methodologies requires a multidisciplinary understanding of each method's advantages and limitations with respect to clinical practice.

Link prediction in protein-protein interaction network: A similarity multiplied similarity algorithm with paths of length three

Protein-protein interactions (PPIs) are crucial for various biological processes, and predicting PPIs is a major challenge. To solve this issue, the most common method is link prediction. Currently, the link prediction methods based on network Paths of Length Three (L3) have been proven to be highly effective. In this paper, we propose a novel link prediction algorithm, named SMS, which is based on L3 and protein similarities. We first design a mixed similarity that combines the topological structure and attribute features of nodes. Then, we compute the predicted value by summing the product of all similarities along the L3. Furthermore, we propose the Max Similarity Multiplied Similarity (maxSMS) algorithm from the perspective of maximum impact. Our computational prediction results show that on six datasets, including S. cerevisiae, H. sapiens, and others, the maxSMS algorithm improves the precision of the top 500, area under the precision-recall curve, and normalized discounted cumulative gain by an average of 26.99%, 53.67%, and 6.7%, respectively, compared to other optimal methods.

Contextual AI models for single-cell protein biology

Understanding protein function and developing molecular therapies require deciphering the cell types in which proteins act as well as the interactions between proteins. However, modeling protein interactions across biological contexts remains challenging for existing algorithms. Here, we introduce Pinnacle, a geometric deep learning approach that generates context-aware protein representations. Leveraging a multi-organ single-cell atlas, Pinnacle learns on contextualized protein interaction networks to produce 394,760 protein representations from 156 cell type contexts across 24 tissues. Pinnacle's embedding space reflects cellular and tissue organization, enabling zero-shot retrieval of the tissue hierarchy. Pretrained protein representations can be adapted for downstream tasks: enhancing 3D structure-based representations for resolving immuno-oncological protein interactions, and investigating drugs' effects across cell types. Pinnacle outperforms state-of-the-art models in nominating therapeutic targets for rheumatoid arthritis and inflammatory bowel diseases, and pinpoints cell type contexts with higher predictive capability than context-free models. Pinnacle's ability to adjust its outputs based on the context in which it operates paves way for large-scale context-specific predictions in biology.

A deep learning framework for predicting disease-gene associations with functional modules and graph augmentation

BACKGROUND

The exploration of gene-disease associations is crucial for understanding the mechanisms underlying disease onset and progression, with significant implications for prevention and treatment strategies. Advances in high-throughput biotechnology have generated a wealth of data linking diseases to specific genes. While graph representation learning has recently introduced groundbreaking approaches for predicting novel associations, existing studies always overlooked the cumulative impact of functional modules such as protein complexes and the incompletion of some important data such as protein interactions, which limits the detection performance.

RESULTS

Addressing these limitations, here we introduce a deep learning framework called ModulePred for predicting disease-gene associations. ModulePred performs graph augmentation on the protein interaction network using L3 link prediction algorithms. It builds a heterogeneous module network by integrating disease-gene associations, protein complexes and augmented protein interactions, and develops a novel graph embedding for the heterogeneous module network. Subsequently, a graph neural network is constructed to learn node representations by collectively aggregating information from topological structure, and gene prioritization is carried out by the disease and gene embeddings obtained from the graph neural network. Experimental results underscore the superiority of ModulePred, showcasing the effectiveness of incorporating functional modules and graph augmentation in predicting disease-gene associations. This research introduces innovative ideas and directions, enhancing the understanding and prediction of gene-disease relationships.

A variational expectation-maximization framework for balanced multi-scale learning of protein and drug interactions

Protein functions are characterized by interactions with proteins, drugs, and other biomolecules. Understanding these interactions is essential for deciphering the molecular mechanisms underlying biological processes and developing new therapeutic strategies. Current computational methods mostly predict interactions based on either molecular network or structural information, without integrating them within a unified multi-scale framework. While a few multi-view learning methods are devoted to fusing the multi-scale information, these methods tend to rely intensively on a single scale and under-fitting the others, likely attributed to the imbalanced nature and inherent greediness of multi-scale learning. To alleviate the optimization imbalance, we present MUSE, a multi-scale representation learning framework based on a variant expectation maximization to optimize different scales in an alternating procedure over multiple iterations. This strategy efficiently fuses multi-scale information between atomic structure and molecular network scale through mutual supervision and iterative optimization. MUSE outperforms the current state-of-the-art models not only in molecular interaction (protein-protein, drug-protein, and drug-drug) tasks but also in protein interface prediction at the atomic structure scale. More importantly, the multi-scale learning framework shows potential for extension to other scales of computational drug discovery.

Protein features fusion using attributed network embedding for predicting protein-protein interaction

BACKGROUND

Protein-protein interactions (PPIs) hold significant importance in biology, with precise PPI prediction as a pivotal factor in comprehending cellular processes and facilitating drug design. However, experimental determination of PPIs is laborious, time-consuming, and often constrained by technical limitations.

METHODS

We introduce a new node representation method based on initial information fusion, called FFANE, which amalgamates PPI networks and protein sequence data to enhance the precision of PPIs' prediction. A Gaussian kernel similarity matrix is initially established by leveraging protein structural resemblances. Concurrently, protein sequence similarities are gauged using the Levenshtein distance, enabling the capture of diverse protein attributes. Subsequently, to construct an initial information matrix, these two feature matrices are merged by employing weighted fusion to achieve an organic amalgamation of structural and sequence details. To gain a more profound understanding of the amalgamated features, a Stacked Autoencoder (SAE) is employed for encoding learning, thereby yielding more representative feature representations. Ultimately, classification models are trained to predict PPIs by using the well-learned fusion feature.

RESULTS

When employing 5-fold cross-validation experiments on SVM, our proposed method achieved average accuracies of 94.28%, 97.69%, and 84.05% in terms of Saccharomyces cerevisiae, Homo sapiens, and Helicobacter pylori datasets, respectively.

CONCLUSION

Experimental findings across various authentic datasets validate the efficacy and superiority of this fusion feature representation approach, underscoring its potential value in bioinformatics.

Proper network randomization is key to assessing social balance

Social ties, either positive or negative, lead to signed network patterns, the subject of balance theory. For example, strong balance introduces cycles with even numbers of negative edges. The statistical significance of such patterns is routinely assessed by comparisons to null models. Yet, results in signed networks remain controversial. Here, we show that even if a network exhibits strong balance by construction, current null models can fail to identify it. Our results indicate that matching the signed degree preferences of the nodes is a critical step and so is the preservation of network topology in the null model. As a solution, we propose the STP null model, which integrates both constraints within a maximum entropy framework. STP randomization leads to qualitatively different results, with most social networks consistently demonstrating strong balance in three- and four-node patterns. On the basis our results, we present a potential wiring mechanism behind the observed signed patterns and outline further applications of STP randomization.

Computational drug repositioning with attention walking

Drug repositioning aims to identify new therapeutic indications for approved medications. Recently, the importance of computational drug repositioning has been highlighted because it can reduce the costs, development time, and risks compared to traditional drug discovery. Most approaches in this area use networks for systematic analysis. Inferring drug-disease associations is then defined as a link prediction problem in a heterogeneous network composed of drugs and diseases. In this article, we present a novel method of computational drug repositioning, named drug repositioning with attention walking (DRAW). DRAW proceeds as follows: first, a subgraph enclosing the target link for prediction is extracted. Second, a graph convolutional network captures the structural features of the labeled nodes in the subgraph. Third, the transition probabilities are computed using attention mechanisms and converted into random walk profiles. Finally, a multi-layer perceptron takes random walk profiles and predicts whether a target link exists. As an experiment, we constructed two heterogeneous networks with drug-drug similarities based on chemical structures and anatomical therapeutic chemical classification (ATC) codes. Using 10-fold cross-validation, DRAW achieved an area under the receiver operating characteristic (ROC) curve of 0.903 and outperformed state-of-the-art methods. Moreover, we demonstrated the results of case studies for selected drugs and diseases to further confirm the capability of DRAW to predict drug-disease associations.

Multi-level bioinformatics resources support drug target discovery of protein-protein interactions

Drug discovery often begins with a new target. Protein-protein interactions (PPIs) are crucial to multitudinous cellular processes and offer a promising avenue for drug-target discovery. PPIs are characterized by multi-level complexity: at the protein level, interaction networks can be used to identify potential targets, whereas at the residue level, the details of the interactions of individual PPIs can be used to examine a target's druggability. Much great progress has been made in target discovery through multi-level PPI-related computational approaches, but these resources have not been fully discussed. Here, we systematically survey bioinformatics tools for identifying and assessing potential drug targets, examining their characteristics, limitations and applications. This work will aid the integration of the broader protein-to-network context with the analysis of detailed binding mechanisms to support the discovery of drug targets.

State of the Interactomes: an evaluation of molecular networks for generating biological insights

Advancements in genomic and proteomic technologies have powered the use of gene and protein networks ("interactomes") for understanding genotype-phenotype translation. However, the proliferation of interactomes complicates the selection of networks for specific applications. Here, we present a comprehensive evaluation of 46 current human interactomes, encompassing protein-protein interactions as well as gene regulatory, signaling, colocalization, and genetic interaction networks. Our analysis shows that large composite networks such as HumanNet, STRING, and FunCoup are most effective for identifying disease genes, while smaller networks such as DIP and SIGNOR demonstrate strong interaction prediction performance. These findings provide a benchmark for interactomes across diverse network biology applications and clarify factors that influence network performance. Furthermore, our evaluation pipeline paves the way for continued assessment of emerging and updated interaction networks in the future.

Computational Approaches to Predict Protein-Protein Interactions in Crowded Cellular Environments

Investigating protein-protein interactions is crucial for understanding cellular biological processes because proteins often function within molecular complexes rather than in isolation. While experimental and computational methods have provided valuable insights into these interactions, they often overlook a critical factor: the crowded cellular environment. This environment significantly impacts protein behavior, including structural stability, diffusion, and ultimately the nature of binding. In this review, we discuss theoretical and computational approaches that allow the modeling of biological systems to guide and complement experiments and can thus significantly advance the investigation, and possibly the predictions, of protein-protein interactions in the crowded environment of cell cytoplasm. We explore topics such as statistical mechanics for lattice simulations, hydrodynamic interactions, diffusion processes in high-viscosity environments, and several methods based on molecular dynamics simulations. By synergistically leveraging methods from biophysics and computational biology, we review the state of the art of computational methods to study the impact of molecular crowding on protein-protein interactions and discuss its potential revolutionizing effects on the characterization of the human interactome.

A comprehensive review of protein-centric predictors for biomolecular interactions: from proteins to nucleic acids and beyond

Proteins interact with diverse ligands to perform a large number of biological functions, such as gene expression and signal transduction. Accurate identification of these protein-ligand interactions is crucial to the understanding of molecular mechanisms and the development of new drugs. However, traditional biological experiments are time-consuming and expensive. With the development of high-throughput technologies, an increasing amount of protein data is available. In the past decades, many computational methods have been developed to predict protein-ligand interactions. Here, we review a comprehensive set of over 160 protein-ligand interaction predictors, which cover protein-protein, protein-nucleic acid, protein-peptide and protein-other ligands (nucleotide, heme, ion) interactions. We have carried out a comprehensive analysis of the above four types of predictors from several significant perspectives, including their inputs, feature profiles, models, availability, etc. The current methods primarily rely on protein sequences, especially utilizing evolutionary information. The significant improvement in predictions is attributed to deep learning methods. Additionally, sequence-based pretrained models and structure-based approaches are emerging as new trends.

EPI-SF: essential protein identification in protein interaction networks using sequence features

Proteins are considered indispensable for facilitating an organism's viability, reproductive capabilities, and other fundamental physiological functions. Conventional biological assays are characterized by prolonged duration, extensive labor requirements, and financial expenses in order to identify essential proteins. Therefore, it is widely accepted that employing computational methods is the most expeditious and effective approach to successfully discerning essential proteins. Despite being a popular choice in machine learning (ML) applications, the deep learning (DL) method is not suggested for this specific research work based on sequence features due to the restricted availability of high-quality training sets of positive and negative samples. However, some DL works on limited availability of data are also executed at recent times which will be our future scope of work. Conventional ML techniques are thus utilized in this work due to their superior performance compared to DL methodologies. In consideration of the aforementioned, a technique called EPI-SF is proposed here, which employs ML to identify essential proteins within the protein-protein interaction network (PPIN). The protein sequence is the primary determinant of protein structure and function. So, initially, relevant protein sequence features are extracted from the proteins within the PPIN. These features are subsequently utilized as input for various machine learning models, including XGB Boost Classifier, AdaBoost Classifier, logistic regression (LR), support vector classification (SVM), Decision Tree model (DT), Random Forest model (RF), and Naïve Bayes model (NB). The objective is to detect the essential proteins within the PPIN. The primary investigation conducted on yeast examined the performance of various ML models for yeast PPIN. Among these models, the RF model technique had the highest level of effectiveness, as indicated by its precision, recall, F1-score, and AUC values of 0.703, 0.720, 0.711, and 0.745, respectively. It is also found to be better in performance when compared to the other state-of-arts based on traditional centrality like betweenness centrality (BC), closeness centrality (CC), etc. and deep learning methods as well like DeepEP, as emphasized in the result section. As a result of its favorable performance, EPI-SF is later employed for the prediction of novel essential proteins inside the human PPIN. Due to the tendency of viruses to selectively target essential proteins involved in the transmission of diseases within human PPIN, investigations are conducted to assess the probable involvement of these proteins in COVID-19 and other related severe diseases.

Advances in Computational Methods for Protein–Protein Interaction Prediction

Protein–protein interactions (PPIs) are pivotal in various physiological processes inside biological entities. Accurate identification of PPIs holds paramount significance for comprehending biological processes, deciphering disease mechanisms, and advancing medical research. Given the costly and labor-intensive nature of experimental approaches, a multitude of computational methods have been devised to enable swift and large-scale PPI prediction. This review offers a thorough examination of recent strides in computational methodologies for PPI prediction, with a particular focus on the utilization of deep learning techniques within this domain. Alongside a systematic classification and discussion of relevant databases, feature extraction strategies, and prominent computational approaches, we conclude with a thorough analysis of current challenges and prospects for the future of this field.

The maximum capability of a topological feature in link prediction

Networks offer a powerful approach to modeling complex systems by representing the underlying set of pairwise interactions. Link prediction is the task that predicts links of a network that are not directly visible, with profound applications in biological, social, and other complex systems. Despite intensive utilization of the topological feature in this task, it is unclear to what extent a feature can be leveraged to infer missing links. Here, we aim to unveil the capability of a topological feature in link prediction by identifying its prediction performance upper bound. We introduce a theoretical framework that is compatible with different indexes to gauge the feature, different prediction approaches to utilize the feature, and different metrics to quantify the prediction performance. The maximum capability of a topological feature follows a simple yet theoretically validated expression, which only depends on the extent to which the feature is held in missing and nonexistent links. Because a family of indexes based on the same feature shares the same upper bound, the potential of all others can be estimated from one single index. Furthermore, a feature's capability is lifted in the supervised prediction, which can be mathematically quantified, allowing us to estimate the benefit of applying machine learning algorithms. The universality of the pattern uncovered is empirically verified by 550 structurally diverse networks. The findings have applications in feature and method selection, and shed light on network characteristics that make a topological feature effective in link prediction.

On the complexity of quantum link prediction in complex networks

Link prediction methods use patterns in known network data to infer which connections may be missing. Previous work has shown that continuous-time quantum walks can be used to represent path-based link prediction, which we further study here to develop a more optimized quantum algorithm. Using a sampling framework for link prediction, we analyze the query access to the input network required to produce a certain number of prediction samples. Considering both well-known classical path-based algorithms using powers of the adjacency matrix as well as our proposed quantum algorithm for path-based link prediction, we argue that there is a polynomial quantum advantage on the dependence on N, the number of nodes in the network. We further argue that the complexity of our algorithm, although sub-linear in N, is limited by the complexity of performing a quantum simulation of the network's adjacency matrix, which may prove to be an important problem in the development of quantum algorithms for network science in general.

Network-Based Methods and Their Applications in Drug Discovery

Drug discovery is time-consuming, expensive, and predominantly follows the "one drug → one target → one disease" paradigm. With the rapid development of systems biology and network pharmacology, a novel drug discovery paradigm, "multidrug → multitarget → multidisease", has emerged. This new holistic paradigm of drug discovery aligns well with the essence of networks, leading to the emergence of network-based methods in the field of drug discovery. In this Perspective, we initially introduce the concept and data sources of networks and highlight classical methodologies employed in network-based methods. Subsequently, we focus on the practical applications of network-based methods across various areas of drug discovery, such as target prediction, virtual screening, prediction of drug therapeutic effects or adverse drug events, and elucidation of molecular mechanisms. In addition, we provide representative web servers for researchers to use network-based methods in specific applications. Finally, we discuss several challenges of network-based methods and the directions for future development. In a word, network-based methods could serve as powerful tools to accelerate drug discovery.

Functional selectivity of Receptor Tyrosine Kinases regulates distinct cellular outputs

Functional selectivity refers to the activation of differential signalling and cellular outputs downstream of the same membrane-bound receptor when activated by two or more different ligands. Functional selectivity has been described and extensively studied for G-protein Coupled Receptors (GPCRs), leading to specific therapeutic options for dysregulated GPCRs functions. However, studies regarding the functional selectivity of Receptor Tyrosine Kinases (RTKs) remain sparse. Here, we will summarize recent data about RTK functional selectivity focusing on how the nature and the amount of RTK ligands and the crosstalk of RTKs with other membrane proteins regulate the specificity of RTK signalling. In addition, we will discuss how structural changes in RTKs upon ligand binding affects selective signalling pathways. Much remains to be known about the integration of different signals affecting RTK signalling specificity to orchestrate long-term cellular outcomes. Recent advancements in omics, specifically quantitative phosphoproteomics, and in systems biology methods to study, model and integrate different types of large-scale omics data have increased our ability to compare several signals affecting RTK functional selectivity in a global, system-wide fashion. We will discuss how such methods facilitate the exploration of important signalling hubs and enable data-driven predictions aiming at improving the efficacy of therapeutics for diseases like cancer, where redundant RTK signalling pathways often compromise treatment efficacy.

Learning low-rank latent mesoscale structures in networks

Researchers in many fields use networks to represent interactions between entities in complex systems. To study the large-scale behavior of complex systems, it is useful to examine mesoscale structures in networks as building blocks that influence such behavior. In this paper, we present an approach to describe low-rank mesoscale structures in networks. We find that many real-world networks possess a small set of latent motifs that effectively approximate most subgraphs at a fixed mesoscale. Such low-rank mesoscale structures allow one to reconstruct networks by approximating subgraphs of a network using combinations of latent motifs. Employing subgraph sampling and nonnegative matrix factorization enables the discovery of these latent motifs. The ability to encode and reconstruct networks using a small set of latent motifs has many applications in network analysis, including network comparison, network denoising, and edge inference.

Applying network link prediction in drug discovery: an overview of the literature

INTRODUCTION

Network representation can give a holistic view of relationships for biomedical entities through network topology. Link prediction estimates the probability of link formation between the pair of unconnected nodes. In the drug discovery process, the link prediction method not only enables the detection of connectivity patterns but also predicts the effects of one biomedical entity to multiple entities simultaneously and vice versa, which is useful for many applications.

AREAS COVERED

The authors provide a comprehensive overview of network link prediction in drug discovery. Link prediction methodologies such as similarity-based approaches, embedding-based approaches, probabilistic model-based approaches, and preprocessing methods are summarized with examples. In addition to describing their properties and limitations, the authors discuss the applications of link prediction in drug discovery based on the relationship between biomedical concepts.

EXPERT OPINION

Link prediction is a powerful method to infer the existence of novel relationships in drug discovery. However, link prediction has been hampered by the sparsity of data and the lack of negative links in biomedical networks. With preprocessing to balance positive and negative samples and the collection of more data, the authors believe it is possible to develop more reliable link prediction methods that can become invaluable tools for successful drug discovery.

Cross-Wired Memristive Crossbar Array for Effective Graph Data Analysis

Graphs adequately represent the enormous interconnections among numerous entities in big data, incurring high computational costs in analyzing them with conventional hardware. Physical graph representation (PGR) is an approach that replicates the graph within a physical system, allowing for efficient analysis. This study introduces a cross-wired crossbar array (cwCBA), uniquely connecting diagonal and non-diagonal components in a CBA by a cross-wiring process. The cross-wired diagonal cells enable cwCBA to achieve precise PGR and dynamic node state control. For this purpose, a cwCBA is fabricated using Pt/Ta2 O5 /HfO2 /TiN (PTHT) memristor with high on/off and self-rectifying characteristics. The structural and device benefits of PTHT cwCBA for enhanced PGR precision are highlighted, and the practical efficacy is demonstrated for two applications. First, it executes a dynamic path-finding algorithm, identifying the shortest paths in a dynamic graph. PTHT cwCBA shows a more accurate inferred distance and ≈1/3800 lower processing complexity than the conventional method. Second, it analyzes the protein-protein interaction (PPI) networks containing self-interacting proteins, which possess intricate characteristics compared to typical graphs. The PPI prediction results exhibit an average of 30.5% and 21.3% improvement in area under the curve and F1-score, respectively, compared to existing algorithms.

Embedding-based link predictions to explore latent comorbidity of chronic diseases

Purpose

Comorbidity is a term used to describe when a patient simultaneously has more than one chronic disease. Comorbidity is a significant health issue that affects people worldwide. This study aims to use machine learning and graph theory to predict the comorbidity of chronic diseases.

Methods

A patient-disease bipartite graph is constructed based on the administrative claim data. The bipartite graph projection approach was used to create the comorbidity network. For the link prediction task, three graph machine learning embedding-based models (node2vec, graph neural networks and hand-crafted approach) with different variants were used on the comorbidity network to compare their performance. This study also considered three commonly used similarity-based link prediction approaches (Jaccard coefficient, Adamic-Adar index and Resource allocation index) for performance comparison.

Results

The results showed that the embedding-based hand-crafted features technique achieved outstanding performance compared with the remaining similarity-based and embedding-based models. Especially, the hand-crafted technique with the extreme gradient boosting classifier achieved the highest accuracy (91.67%), followed by the same technique with the Logistic regression classifier (90.26%). For this shallow embedding method, the Jaccard coefficient and the degree centrality of the original chronic disease were the most important features for comorbidity prediction.

Conclusion

The proposed framework can be used to predict the comorbidity of chronic disease at an early stage of hospital admission. Thus, the prediction outcome could be valuable for medical practice, giving healthcare providers more control over their services and lowering expenses.

In silico protein function prediction: the rise of machine learning-based approaches

Proteins function as integral actors in essential life processes, rendering the realm of protein research a fundamental domain that possesses the potential to propel advancements in pharmaceuticals and disease investigation. Within the context of protein research, an imperious demand arises to uncover protein functionalities and untangle intricate mechanistic underpinnings. Due to the exorbitant costs and limited throughput inherent in experimental investigations, computational models offer a promising alternative to accelerate protein function annotation. In recent years, protein pre-training models have exhibited noteworthy advancement across multiple prediction tasks. This advancement highlights a notable prospect for effectively tackling the intricate downstream task associated with protein function prediction. In this review, we elucidate the historical evolution and research paradigms of computational methods for predicting protein function. Subsequently, we summarize the progress in protein and molecule representation as well as feature extraction techniques. Furthermore, we assess the performance of machine learning-based algorithms across various objectives in protein function prediction, thereby offering a comprehensive perspective on the progress within this field.

Constructing gene similarity networks using co-occurrence probabilities

Gene similarity networks play important role in unraveling the intricate associations within diverse cancer types. Conventionally, gauging the similarity between genes has been approached through experimental methodologies involving chemical and molecular analyses, or through the lens of mathematical techniques. However, in our work, we have pioneered a distinctive mathematical framework, one rooted in the co-occurrence of attribute values and single point mutations, thereby establishing a novel approach for quantifying the dissimilarity or similarity among genes. Central to our approach is the recognition of mutations as key players in the evolutionary trajectory of cancer. Anchored in this understanding, our methodology hinges on the consideration of two categorical attributes: mutation type and nucleotide change. These attributes are pivotal, as they encapsulate the critical variations that can precipitate substantial changes in gene behavior and ultimately influence disease progression. Our study takes on the challenge of formulating similarity measures that are intrinsic to genes' categorical data. Taking into account the co-occurrence probability of attribute values within single point mutations, our innovative mathematical approach surpasses the boundaries of conventional methods. We thereby provide a robust and comprehensive means to assess gene similarity and take a significant step forward in refining the tools available for uncovering the subtle yet impactful associations within the complex realm of gene interactions in cancer.

Noncoding RNAs improve the predictive power of network medicine

Network medicine has improved the mechanistic understanding of disease, offering quantitative insights into disease mechanisms, comorbidities, and novel diagnostic tools and therapeutic treatments. Yet, most network-based approaches rely on a comprehensive map of protein-protein interactions (PPI), ignoring interactions mediated by noncoding RNAs (ncRNAs). Here, we systematically combine experimentally confirmed binding interactions mediated by ncRNA with PPI, constructing a comprehensive network of all physical interactions in the human cell. We find that the inclusion of ncRNA expands the number of genes in the interactome by 46% and the number of interactions by 107%, significantly enhancing our ability to identify disease modules. Indeed, we find that 132 diseases lacked a statistically significant disease module in the protein-based interactome but have a statistically significant disease module after inclusion of ncRNA-mediated interactions, making these diseases accessible to the tools of network medicine. We show that the inclusion of ncRNAs helps unveil disease-disease relationships that were not detectable before and expands our ability to predict comorbidity patterns between diseases. Taken together, we find that including noncoding interactions improves both the breath and the predictive accuracy of network medicine.

Dissection of action mechanisms of Zuogui Pill in the treatment of liver cancer based on machine learning and network pharmacology: A review

This study aimed to investigate the underlying mechanism of Zuogui Pill in its efficacy against liver cancer, employing a combination of data mining approaches and network pharmacology methods. A novel clustering analysis algorithm was proposed to identify the core gene modules of Zuogui Pill. This algorithm successfully identified 5 core modules, with the first large module comprised of twelve proteins forming a 12-clique, representing the strongest connections among them. By utilizing GEO platform, ten key target proteins were detected, including FOS, PTGS2, and MYC. According to the GO annotation and KEGG analysis, desired target proteins were significantly enriched in various biological processes (BP). The analysis showed that ten key targets were strongly associated with signaling pathways mainly centered on MAPK and PI3K-Akt pathway. Additionally, molecular docking revealed strong binding affinities between core active ingredients of Zuogui Pill and these key targets, and the best affinity modes were observed for PTGS2-Sesamin, PRKCA-Sesamin, FOS-delta-Carotene. In order to establish the relationships between clinical symptoms and drug targets, a heterogeneous targets-related network was constructed. A total of 60 key target-symptom association pairs were detected, exemplified by the strongly association between fever and PTGS2 through the intermediary of Shu Di Huang. In summary, symptom-target associations are valuable in uncovering the underlying molecular mechanisms of Zuogui Pill. Our work reinforced the notion that Zuogui pill exhibits therapeutic potential on liver cancer through network targets, as well as synergistic effects of multi-component and multi-pathway. This study provided specific references for future experiments at the cost of less time.

Neurolysin Knockout Mice in a Diet-Induced Obesity Model

Neurolysin oligopeptidase (E.C.3.4.24.16; Nln), a member of the zinc metallopeptidase M3 family, was first identified in rat brain synaptic membranes hydrolyzing neurotensin at the Pro-Tyr peptide bond. The previous development of C57BL6/N mice with suppression of Nln gene expression (Nln-/-), demonstrated the biological relevance of this oligopeptidase for insulin signaling and glucose uptake. Here, several metabolic parameters were investigated in Nln-/- and wild-type C57BL6/N animals (WT; n = 5-8), male and female, fed either a standard (SD) or a hypercaloric diet (HD), for seven weeks. Higher food intake and body mass gain was observed for Nln-/- animals fed HD, compared to both male and female WT control animals fed HD. Leptin gene expression was higher in Nln-/- male and female animals fed HD, compared to WT controls. Both WT and Nln-/- females fed HD showed similar gene expression increase of dipeptidyl peptidase 4 (DPP4), a peptidase related to glucagon-like peptide-1 (GLP-1) metabolism. The present data suggest that Nln participates in the physiological mechanisms related to diet-induced obesity. Further studies will be necessary to better understand the molecular mechanism responsible for the higher body mass gain observed in Nln-/- animals fed HD.

Identification of disease modules using higher-order network structure

Motivation

Higher-order interaction patterns among proteins have the potential to reveal mechanisms behind molecular processes and diseases. While clustering methods are used to identify functional groups within molecular interaction networks, these methods largely focus on edge density and do not explicitly take into consideration higher-order interactions. Disease genes in these networks have been shown to exhibit rich higher-order structure in their vicinity, and considering these higher-order interaction patterns in network clustering have the potential to reveal new disease-associated modules.

Results

We propose a higher-order community detection method which identifies community structure in networks with respect to specific higher-order connectivity patterns beyond edges. Higher-order community detection on four different protein-protein interaction networks identifies biologically significant modules and disease modules that conventional edge-based clustering methods fail to discover. Higher-order clusters also identify disease modules from genome-wide association study data, including new modules that were not discovered by top-performing approaches in a Disease Module DREAM Challenge. Our approach provides a more comprehensive view of community structure that enables us to predict new disease-gene associations.

Availability and implementation

https://github.com/Reed-CompBio/graphlet-clustering.

Mapping the protein-protein interactome in the tumor immune microenvironment

The cell-to-cell communication primarily occurs through cell-surface and secreted proteins, which form a sophisticated network that coordinates systemic immune function. Uncovering these protein-protein interactions (PPIs) is indispensable for understanding the molecular mechanism and elucidating immune system aberrances under diseases. Traditional biological studies typically focus on a limited number of PPI pairs due to the relative low throughput of commonly used techniques. Encouragingly, classical methods have advanced, and many new systems tailored for large-scale protein-protein screening have been developed and successfully utilized. These high-throughput PPI investigation techniques have already made considerable achievements in mapping the immune cell interactome, enriching PPI databases and analysis tools, and discovering therapeutic targets for cancer and other diseases, which will definitely bring unprecedented insight into this field.

HPC-Atlas: Computationally Constructing A Comprehensive Atlas of Human Protein Complexes

A fundamental principle of biology is that proteins tend to form complexes to play important roles in the core functions of cells. For a complete understanding of human cellular functions, it is crucial to have a comprehensive atlas of human protein complexes. Unfortunately, we still lack such a comprehensive atlas of experimentally validated protein complexes, which prevents us from gaining a complete understanding of the compositions and functions of human protein complexes, as well as the underlying biological mechanisms. To fill this gap, we built Human Protein Complexes Atlas (HPC-Atlas), as far as we know, the most accurate and comprehensive atlas of human protein complexes available to date. We integrated two latest protein interaction networks, and developed a novel computational method to identify nearly 9000 protein complexes, including many previously uncharacterized complexes. Compared with the existing methods, our method achieved outstanding performance on both testing and independent datasets. Furthermore, with HPC-Atlas we identified 751 severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-affected human protein complexes, and 456 multifunctional proteins that contain many potential moonlighting proteins. These results suggest that HPC-Atlas can serve as not only a computing framework to effectively identify biologically meaningful protein complexes by integrating multiple protein data sources, but also a valuable resource for exploring new biological findings. The HPC-Atlas webserver is freely available at http://www.yulpan.top/HPC-Atlas.

Intracellular peptides in SARS-CoV-2-infected patients

Intracellular peptides (InPeps) generated by the orchestrated action of the proteasome and intracellular peptidases have biological and pharmacological significance. Here, human plasma relative concentration of specific InPeps was compared between 175 patients infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), and 45 SARS-CoV-2 non-infected patients; 2,466 unique peptides were identified, of which 67% were InPeps. The results revealed differences of a specific group of peptides in human plasma comparing non-infected individuals to patients infected by SARS-CoV-2, following the results of the semi-quantitative analyses by isotope-labeled electrospray mass spectrometry. The protein-protein interactions networks enriched pathways, drawn by genes encoding the proteins from which the peptides originated, revealed the presence of the coronavirus disease/COVID-19 network solely in the group of patients fatally infected by SARS-CoV-2. Thus, modulation of the relative plasma levels of specific InPeps could be employed as a predictive tool for disease outcome.

Link prediction in complex network using information flow

Link prediction in complex networks has recently attracted a great deal of attraction in diverse scientific domains, including social and biological sciences. Given a snapshot of a network, the goal is to predict links that are missing in the network or that are likely to occur in the near future. This problem has both theoretical and practical significance; it not only helps us to identify missing links in a network more efficiently by avoiding the expensive and time consuming experimental processes, but also allows us to study the evolution of a network with time. To address the problem of link prediction, numerous attempts have been made over the recent years that exploit the local and the global topological properties of the network to predict missing links in the network. In this paper, we use parametrised matrix forest index (PMFI) to predict missing links in a network. We show that, for small parameter values, this index is linked to a heat diffusion process on a graph and therefore encodes geometric properties of the network. We then develop a framework that combines the PMFI with a local similarity index to predict missing links in the network. The framework is applied to numerous networks obtained from diverse domains such as social network, biological network, and transport network. The results show that the proposed method can predict missing links with higher accuracy when compared to other state-of-the-art link prediction methods.

Predicting Protein-Protein Interactions Using Sequence and Network Information via Variational Graph Autoencoder

Protein-protein interactions (PPIs) play a critical role in the proteomics study, and a variety of computational algorithms have been developed to predict PPIs. Though effective, their performance is constrained by high false-positive and false-negative rates observed in PPI data. To overcome this problem, a novel PPI prediction algorithm, namely PASNVGA, is proposed in this work by combining the sequence and network information of proteins via variational graph autoencoder. To do so, PASNVGA first applies different strategies to extract the features of proteins from their sequence and network information, and obtains a more compact form of these features using principal component analysis. In addition, PASNVGA designs a scoring function to measure the higher-order connectivity between proteins and so as to obtain a higher-order adjacency matrix. With all these features and adjacency matrices, PASNVGA trains a variational graph autoencoder model to further learn the integrated embeddings of proteins. The prediction task is then completed by using a simple feedforward neural network. Extensive experiments have been conducted on five PPI datasets collected from different species. Compared with several state-of-the-art algorithms, PASNVGA has been demonstrated as a promising PPI prediction algorithm.

Combination of antidepressants and antipsychotics as a novel treatment option for psychosis in Alzheimer's disease

Psychotic symptoms are reported as one of the most common complications of Alzheimer's disease (AD), in whom they are associated with more rapid deterioration and increased mortality. Empiric treatments, namely first and second-generation antipsychotics, confer modest efficacy in patients with AD and with psychosis (AD+P) and themselves increase mortality. Recent studies suggested the use and beneficial effects of antidepressants among patients with AD+P. This motivates our rationale for exploring their potential as a novel combination therapy option among these patients. We included electronic medical records of 10,260 patients with AD in our study. Survival analysis was performed to assess the effects of the combination of antipsychotics and antidepressants on the mortality of these patients. A protein-protein interaction network representing AD+P was built, and network analysis methods were used to quantify the efficacy of these drugs on AD+P. A combined score was developed to measure the potential synergetic effect against AD+P. Our survival analyses showed that the co-administration of antidepressants with antipsychotics have a significant beneficial effect in reducing mortality. Our network analysis showed that the targets of antipsychotics and antidepressants are well-separated, and antipsychotics and antidepressants have similar Signed Jaccard Index (SJI) scores to AD+P. Eight drug pairs, including some popular recommendations like aripiprazole/sertraline, showed higher than average scores which suggest their potential in treating AD+P via strong synergetic effects. Our proposed combinations of antipsychotic and antidepressant therapy showed a strong superiority over current antipsychotics treatment for AD+P. The observed beneficial effects can be further strengthened by optimizing drug-pair selection based on our systems pharmacology analysis.

Topological properties and organizing principles of semantic networks

Interpreting natural language is an increasingly important task in computer algorithms due to the growing availability of unstructured textual data. Natural Language Processing (NLP) applications rely on semantic networks for structured knowledge representation. The fundamental properties of semantic networks must be taken into account when designing NLP algorithms, yet they remain to be structurally investigated. We study the properties of semantic networks from ConceptNet, defined by 7 semantic relations from 11 different languages. We find that semantic networks have universal basic properties: they are sparse, highly clustered, and many exhibit power-law degree distributions. Our findings show that the majority of the considered networks are scale-free. Some networks exhibit language-specific properties determined by grammatical rules, for example networks from highly inflected languages, such as e.g. Latin, German, French and Spanish, show peaks in the degree distribution that deviate from a power law. We find that depending on the semantic relation type and the language, the link formation in semantic networks is guided by different principles. In some networks the connections are similarity-based, while in others the connections are more complementarity-based. Finally, we demonstrate how knowledge of similarity and complementarity in semantic networks can improve NLP algorithms in missing link inference.