Fig 2 - uploaded by Nurbubu T. Moldogazieva
Content may be subject to copyright.
![Types of complex networks (according to [131]). a) Schematic representation (on the left) and configuration (on the right) of scale-free network. Gray circles (on the left) correspond to hubs. b) Schematic representation (on the left) and configuration (on the right) of a modular network. Here all nodes have an equal number of links with adjacent nodes. Such a network is free of hubs. c) Schematic representation (on the left) and configuration (on the right) of hierarchically and modularly organized scale-free network. The figure is the courtesy of A.-L. Barabasi [131].](profile/Nurbubu-Moldogazieva/publication/41824103/figure/fig2/AS:669174451937294@1536555030608/Types-of-complex-networks-according-to-131-a-Schematic-representation-on-the-left.png)
Types of complex networks (according to [131]). a) Schematic representation (on the left) and configuration (on the right) of scale-free network. Gray circles (on the left) correspond to hubs. b) Schematic representation (on the left) and configuration (on the right) of a modular network. Here all nodes have an equal number of links with adjacent nodes. Such a network is free of hubs. c) Schematic representation (on the left) and configuration (on the right) of hierarchically and modularly organized scale-free network. The figure is the courtesy of A.-L. Barabasi [131].
Source publication
![Fig. 2. Types of complex networks (according to [131]). a) Schematic...](profile/Nurbubu-Moldogazieva/publication/41824103/figure/fig2/AS:669174451937294@1536555030608/Types-of-complex-networks-according-to-131-a-Schematic-representation-on-the-left_Q320.jpg)
This review is devoted to describing, summarizing, and analyzing of dynamic proteomics data obtained over the last few years and concerning the role of protein-protein interactions in modeling of the living cell. Principles of modern high-throughput experimental methods for investigation of protein-protein interactions are described. Systems biolog...
Contexts in source publication
Context 1
... factor or direction of a reac- tion [119,120]. Networks of signaling molecules may be represented as graphs both with directed and non-direct- ed edges. Since both partners are equally involved in pro- tein-protein interactions, protein networks are shown in the form of graphs in which adjacent nodes are bound to each other by non-directed edges (Fig. ...
Context 2
... key property of the scale-free architecture is the presence of hubs, i.e. nodes with high density of linkages, whereas most nodes are characterized by a small number of links (Fig. 2). However, a small number of hubs pro- vides for stability of the whole cell by uniting all the nodes in the network. Experiments on hub removal from protein and metabolic networks in D. melanogaster are indicative of the role of hubs [129]. Networks with scale- free architecture appeared to be resistant to random removal of nodes. Even ...
Similar publications
Acute kidney injury (AKI) is a disease that seriously endangers human health. At present, AKI lacks effective treatment methods, so it is particularly important to find effective treatment measures and targets. Bioinformatics analysis has become an important method to identify significant processes of disease occurrence and development. In this stu...
Modern experimental technology enables the identification of the sensory proteins that interact with the cells' environment or various pathogens. Expression and knockdown studies can determine the downstream effects of these interactions. However, when attempting to reconstruct the signaling networks and pathways between these sources and targets,...
Protein-protein interaction (PPI) network analysis presents an essential role in understanding the functional relationship among proteins in a living biological system. Despite the success of current approaches for understanding the PPI network, the large fraction of missing and spurious PPIs and a low coverage of complete PPI network are the sourc...
Overlaying differential changes in gene expression on protein interaction networks has proven to be a useful approach to interpreting the cell's dynamic response to a changing environment. Despite successes in finding active subnetworks in the context of a single species, the idea of overlaying lists of differentially expressed genes on networks ha...
Structural studies are increasingly providing huge amounts of information on multi-protein assemblies. Although a complete understanding of cellular processes will be dependent on an explicit characterization of the intermolecular interactions that underlie these assemblies and mediate molecular recognition, these are not well described by standard...
Citations
... Therefore, understanding the location and characteristics of protein binding sites is crucial for understanding protein function and drug design (Wells and McClendon 2007, De Las Rivas and Fontanillo 2012, Kuzmanov and Emili 2013, Valkov et al. 2016, Guilliam et al. 2017, Batra et al. 2018. Traditional binding site detection methods, such as X-ray crystallography, two-hybrid screening, surface plasmon resonance techniques, and affinity purification-mass spectrometry, are expensive and timeconsuming (Orengo et al. 1997, Shoemaker and Panchenko 2007, Terentiev et al. 2009, Brettner and Masel 2012, Wodak et al. 2013). In addition, several technical challenges, including the small size of peptides (Vlieghe et al. 2010), weak binding affinity (Dyson and Wright 2005), conformational flexibility (Bertolazzi et al. 2014), high transience, and dynamics of protein-protein interactions, increase the difficulty in accurately identifying the binding residues. ...
Motivation
Identifying the functional sites of a protein, such as the binding sites of proteins, peptides, or other biological components, is crucial for understanding related biological processes and drug design. However, existing sequence-based methods have limited predictive accuracy, as they only consider sequence-adjacent contextual features and lack structural information.
Results
In this study, DeepProSite is presented as a new framework for identifying protein binding site that utilizes protein structure and sequence information. DeepProSite first generates protein structures from ESMFold and sequence representations from pretrained language models. It then uses Graph Transformer and formulates binding site predictions as graph node classifications. In predicting protein–protein/peptide binding sites, DeepProSite outperforms state-of-the-art sequence- and structure-based methods on most metrics. Moreover, DeepProSite maintains its performance when predicting unbound structures, in contrast to competing structure-based prediction methods. DeepProSite is also extended to the prediction of binding sites for nucleic acids and other ligands, verifying its generalization capability. Finally, an online server for predicting multiple types of residue is established as the implementation of the proposed DeepProSite.
Availability and implementation
The datasets and source codes can be accessed at https://github.com/WeiLab-Biology/DeepProSite. The proposed DeepProSite can be accessed at https://inner.wei-group.net/DeepProSite/.
... 6 Diseases are the result of disturbed molecular interactions, meaning it is essential to investigate numerous interacting partners and analyse the networks for accurate diagnoses and understanding of its mechanisms. 7,8 Factors that can disrupt or perturb the network may be intrinsic, such as mutations in certain genes, or extrinsic, like environmental cues, to the human system. 9,10 The native network will respond differently to each disruption depending on unique robust characteristics, thereby producing distinct phenotypic responses that constitute a corresponding pathological state. ...
... arXiv:2303.06945v1 [q-bio.QM] 13 Mar 2023 methods, such as two-hybrid screening, relationship purification, and intragenic complementation, being commonly applied to identify PPIs (Westermarck et al., 2013;Terentiev et al., 2009;Brettner and Masel, 2012;Smallwood et al., 2002). However, these experimental methods suffer from being costly and timeconsuming so that more accurate and efficient computational predictors for PPIs are of great value for biologists. ...
Protein-protein interactions are essential in biochemical processes. Accurate prediction of the protein-protein interaction sites (PPIs) deepens our understanding of biological mechanism and is crucial for new drug design. However, conventional experimental methods for PPIs prediction are costly and time-consuming so that many computational approaches, especially ML-based methods, have been developed recently. Although these approaches have achieved gratifying results, there are still two limitations: (1) Most models have excavated some useful input features, but failed to take coevolutionary features into account, which could provide clues for inter-residue relationships; (2) The attention-based models only allocate attention weights for neighboring residues, instead of doing it globally, neglecting that some residues being far away from the target residues might also matter. We propose a coevolution-enhanced global attention neural network, a sequence-based deep learning model for PPIs prediction, called CoGANPPIS. It utilizes three layers in parallel for feature extraction: (1) Local-level representation aggregation layer, which aggregates the neighboring residues' features; (2) Global-level representation learning layer, which employs a novel coevolution-enhanced global attention mechanism to allocate attention weights to all the residues on the same protein sequences; (3) Coevolutionary information learning layer, which applies CNN & pooling to coevolutionary information to obtain the coevolutionary profile representation. Then, the three outputs are concatenated and passed into several fully connected layers for the final prediction. Application on two benchmark datasets demonstrated a state-of-the-art performance of our model. The source code is publicly available at https://github.com/Slam1423/CoGANPPIS_source_code.
... Conventional biological experimental methods, such as affinity systems, two-hybrid assay, and affinity purification coupled to mass spectrometry, are labor-intensive and timeconsuming [5][6][7][8]. Consequently, many artificial intelligence (AI)-based studies have emerged predicting the binding residues of proteins from sequences with the help of machine learning [3,4,[9][10][11]. However, due to the limited number of accurately measured protein crystal structures [12,13], most sequence-based predictors can only be trained using evolutionary conservatism profiles and predicted secondary structure. ...
Though AlphaFold2 has attained considerably high precision on protein structure prediction, it is reported that directly inputting coordinates into deep learning networks cannot achieve desirable results on downstream tasks. Thus, how to process and encode the predicted results into effective forms that deep learning models can understand to improve the performance of downstream tasks is worth exploring. In this study, we tested the effects of five processing strategies of coordinates on two single-sequence protein binding site prediction tasks. These five strategies are spatial filtering, the singular value decomposition of a distance map, calculating the secondary structure feature, and the relative accessible surface area feature of proteins. The computational experiment results showed that all strategies were suitable and effective methods to encode structural information for deep learning models. In addition, by performing a case study of a mutated protein, we showed that the spatial filtering strategy could introduce structural changes into HHblits profiles and deep learning networks when protein mutation happens. In sum, this work provides new insight into the downstream tasks of protein-molecule interaction prediction, such as predicting the binding residues of proteins and estimating the effects of mutations.
... It is suggested in [189] that locations of protein-protein binding sites are engraved in the proteins' structures. Although experimentally determined 3-D protein structures may facilitate the detection of interaction sites and the understanding of protein functions, experimental biological methods are laborious and time-consuming, and consequently, the geometries of only a small fraction of known proteins have been determined [189][190][191][192][193][194]. To address this shortcoming, various studies use deep learning to predict, from protein structure and other protein features, potential PPI [185,186,[195][196][197]. ...
Most proteins perform their biological function by interacting with themselves or other molecules. Thus, one may obtain biological insights into protein functions, disease prevalence, and therapy development by identifying protein–protein interactions (PPI). However, finding the interacting and non-interacting protein pairs through experimental approaches is labour-intensive and time-consuming, owing to the variety of proteins. Hence, protein–protein interaction and protein–ligand binding problems have drawn attention in the fields of bioinformatics and computer-aided drug discovery. Deep learning methods paved the way for scientists to predict the 3-D structure of proteins from genomes, predict the functions and attributes of a protein, and modify and design new proteins to provide desired functions. This review focuses on recent deep learning methods applied to problems including predicting protein functions, protein–protein interaction and their sites, protein–ligand binding, and protein design.
... This new insight could potentially aid in the formulation of novel antibacterial drugs [6]. Conventionally, PPIs have been identified using experimental methods such as affinity purification coupled with mass spectrometry and two-hybrid screening [7][8][9]. However, these experimental methods are limited by their high cost and time consumption. ...
Protein–protein interactions (PPIs) are responsible for various essential biological processes. This information can help develop a new drug against diseases. Various experimental methods have been employed for this purpose; however, their application is limited by their cost and time consumption. Alternatively, computational methods are considered viable means to achieve this crucial task. Various techniques have been explored in the literature using the sequential information of amino acids in a protein sequence, including machine learning and deep learning techniques. The current efficiency of interaction-site prediction still has growth potential. Hence, a deep neural network-based model, ProB-site, is proposed. ProB-site utilizes sequential information of a protein to predict its binding sites. The proposed model uses evolutionary information and predicted structural information extracted from sequential information of proteins, generating three unique feature sets for every amino acid in a protein sequence. Then, these feature sets are fed to their respective sub-CNN architecture to acquire complex features. Finally, the acquired features are concatenated and classified using fully connected layers. This methodology performed better than state-of-the-art techniques because of the selection of the best features and contemplation of local information of each amino acid.
... However, practical experimental methods for judging whether a residue of protein sequence belongs to the binding sites remains costly and time-consuming (Terentiev et al., 2009;Brettner and Masel, 2012;Wodak et al., 2013). Therefore, a lot of computational predictors for proteinprotein interaction site (PPIs) prediction have been developed to bridge the gap. ...
Motivation: Protein-protein interactions are of great importance in the life cycles of living cells. Accurate prediction of the protein-protein interaction site (PPIs) from protein sequence improves our understanding of protein-protein interaction, contributes to the protein-protein docking and is crucial for drug design. However, practical experimental methods are costly and time-consuming so that many sequence-based computational methods have been developed. Most of those methods employ a sliding window approach, which utilize local neighbor information within a window size. However, they don't distinguish and use the effect of each individual neighboring residue at different position.
Results: We propose a novel sequence-based deep learning method consisting of convolutional neural networks (CNNs) and attention mechanism to improve the performance of PPIs prediction. Our attention-based CNNs captures the different effect of each neighboring residue within a sliding window, and therefore making a better understanding of the local environment of target residue. We employ experiments on several public benchmark datasets. The experimental results demonstrate that our proposed method significantly outperforms the state-of-the-art techniques. We also analyze the difference using various sliding window lengths and amino acid residue features combination.
Availability and implementation: The source code can be obtained from https://github.com/biolushuai/attention-based-CNNs-for-PPIs-prediction
Contact: iexfnan@zzu.edu.cn or zhangst@zzu.edu.cn
Supplementary information: Supplementary data are available at Bioinformatics online.
... Protein modules are groups of highly connected proteins that tend to be co-localized and coexpressed. Proteins in protein-modules form a single multimolecular machine by interacting with each other at the same time and place [34,35]. The MCODE plugin of the Cytoscape tool was used for identifying protein modules in CTN with degree cut-off value equals to 2, node score cut-off value equals to 0.2 and k-core value equals to 2. MCODE algorithm operates on three stages, i.e., vertex weighing, complex prediction, and optionally post-processing step, for identifying the locally highly connected region in the interaction network [36]. ...
Although COVID-19 largely causes respiratory complications, it can also lead to various extrapulmonary manifestations resulting in higher mortality and these comorbidities are posing a challenge to the health care system. Reports indicate that 30–60% of patients with COVID-19 suffer from neurological symptoms. To understand the molecular basis of the neurologic comorbidity in COVID-19 patients, we have investigated the genetic association between COVID-19 and various brain disorders through a systems biology-based network approach and observed a remarkable resemblance. Our results showed 123 brain-related disorders associated with COVID-19 and form a high-density disease-disease network. The brain-disease-gene network revealed five highly clustered modules demonstrating a greater complexity of COVID-19 infection. Moreover, we have identified 35 hub proteins of the network which were largely involved in the protein catabolic process, cell cycle, RNA metabolic process, and nuclear transport. Perturbing these hub proteins by drug repurposing will improve the clinical conditions in comorbidity. In the near future, we assumed that in COVID-19 patients, many other neurological manifestations will likely surface. Thus, understanding the infection mechanisms of SARS-CoV-2 and associated comorbidity is a high priority to contain its short- and long-term effects on human health. Our network-based analysis strengthens the understanding of the molecular basis of the neurological manifestations observed in COVID-19 and also suggests drug for repurposing.
... Protein-protein interaction (PPI) sites are the interfacial residues of a protein that interact with other protein molecules. Several wet-lab methods, including two-hybrid screening and affinity purification coupled to mass spectrometry are usually used to identify PPI sites (Wodak et al., 2013;Brettner and Masel, 2012;Terentiev et al., 2009). However, the experimental determination of PPI sites is costly and time-and labour-intensive (Hamp and Rost, 2015;Ezkurdia et al., 2009;Giot et al., 2003). ...
Motivation: Protein-protein interactions are central to most biological processes. However, reliable identification of protein-protein interaction (PPI) sites using conventional experimental methods is slow and expensive. Therefore, great efforts are being put into computational methods to identify PPI sites.
Results: We present EGRET, a highly accurate deep learning based method for PPI site prediction, where we have introduced a novel edge aggregated graph attention network to effectively leverage the structural information. We, for the first time, have used transfer learning in PPI site prediction. Our proposed edge aggregated network, together with transfer learning, has achieved remarkable improvement over the best alternate methods. Furthermore, EGRET offers a more interpretable framework than the typical black-box deep neural networks.
Availability: EGRET is freely available as an open source project at https://github.com/ Sazan-Mahbub/EGRET.
... In addition, it can help design new antibacterial drugs (Russell and Aloy, 2008). Conventional biological experimental methods, such as two-hybrid screening and affinity purification coupled to mass spectrometry, are used to identify PPIs (Brettner and Masel, 2012;Terentiev et al., 2009;Wodak et al., 2013). However, these biological experimental methods are costly and time-consuming. ...
Motivation:
Protein-protein interactions (PPIs) play important roles in many biological processes. Conventional biological experiments for identifying PPI sites are costly and time-consuming. Thus, many computational approaches have been proposed to predict PPI sites. Existing computational methods usually use local contextual features to predict PPI sites. Actually, global features of protein sequences are critical for PPI site prediction.
Results:
A new end-to-end deep learning framework, named DeepPPISP, through combining local contextual and global sequence features, is proposed for PPI site prediction. For local contextual features, we use a sliding window to capture features of neighbors of a target amino acid as in previous studies. For global sequence features, a text convolutional neural network is applied to extract features from the whole protein sequence. Then the local contextual and global sequence features are combined to predict PPI sites. By integrating local contextual and global sequence features, DeepPPISP achieves the state-of-the-art performance, which is better than the other competing methods. In order to investigate if global sequence features are helpful in our deep learning model, we remove or change some components in DeepPPISP. Detailed analyses show that global sequence features play important roles in DeepPPISP.
Availability and implementation:
The DeepPPISP web server is available at http://bioinformatics.csu.edu.cn/PPISP/. The source code can be obtained from https://github.com/CSUBioGroup/DeepPPISP.
Supplementary information:
Supplementary data are available at Bioinformatics online.
