Prediction Of Protein-protein Interactions Research Articles

Cross-domain contrastive graph neural network for lncRNA–protein interaction prediction

Identifying lncRNA–protein interactions (LPIs) is an important biomedical task, facilitating the comprehension of the biological functions and mechanisms of lncRNAs. Many computational methods have been developed for this task, especially graph neural network (GNN)-based methods have attracted increasing attention. Typically, the LPI network involves two types of interaction domains: the interactive domain capturing the direct interaction information between lncRNAs and proteins, and the collaborative domain reflecting the collaboration information among lncRNAs or proteins. However, existing GNN-based methods only leverage one of them to obtain topological information, which cannot fully characterize lncRNAs and proteins, resulting in suboptimal node representations. Moreover, each domain contains task-irrelevant redundant information, posing a challenge in effectively integrating information from different domains. To address these issues, we propose a novel Cross-domain Contrastive Graph Neural Network (CCGNN) for predicting potential LPIs. CCGNN employs a multi-domain encoder that consists of an interactive domain encoder and two collaborative domain encoders to capture valuable information from each interaction domain. Subsequently, domain-adaptive fusion is designed to integrate information from different domains to acquire comprehensive node representations. Furthermore, cross-domain contrastive learning is devised to enrich the node representations, drawing inspiration from the information bottleneck principle by retaining as much task-relevant information as possible within each domain and minimizing mutual information between representations across different domains. Extensive experiments on four real-world datasets demonstrate the superiority of CCGNN over state-of-the-art methods, and a further case study and generalization analysis illustrate the effectiveness of CCGNN in the biomedical link prediction tasks.

Improving protein-protein interaction prediction using protein language model and protein network features

Interactions between proteins are ubiquitous in a wide variety of biological processes. Accurately identifying the protein-protein interaction (PPI) is of significant importance for understanding the mechanisms of protein functions and facilitating drug discovery. Although the wet-lab technological methods are the best way to identify PPI, their major constraints are their time-consuming nature, high cost, and labor-intensiveness. Hence, lots of efforts have been made towards developing computational methods to improve the performance of PPI prediction. In this study, we propose a novel hybrid computational method (called KSGPPI) that aims at improving the prediction performance of PPI via extracting the discriminative information from protein sequences and interaction networks. The KSGPPI model comprises two feature extraction modules. In the first feature extraction module, a large protein language model, ESM-2, is employed to exploit the global complex patterns concealed within protein sequences. Subsequently, feature representations are further extracted through CKSAAP, and a two-dimensional convolutional neural network (CNN) is utilized to capture local information. In the second feature extraction module, the query protein acquires its similar protein from the STRING database via the sequence alignment tool NW-align and then captures the graph embedding feature for the query protein in the protein interaction network of the similar protein using the algorithm of Node2vec. Finally, the features of these two feature extraction modules are efficiently fused; the fused features are then fed into the multilayer perceptron to predict PPI. The results of five-fold cross-validation on the used benchmarked datasets demonstrate that KSGPPI achieves an average prediction accuracy of 88.96 %. Additionally, the average Matthews correlation coefficient value (0.781) of KSGPPI is significantly higher than that of those state-of-the-art PPI prediction methods. The standalone package of KSGPPI is freely downloaded at https://github.com/rickleezhe/KSGPPI.

In silico analysis of the wheat BBX gene family and identification of candidate genes for seed dormancy and germination

BackgroundB-box (BBX) proteins are a type of zinc finger proteins containing one or two B-box domains. They play important roles in development and diverse stress responses of plants, yet their roles in wheat remain unclear.ResultsIn this study, 96 BBX genes were identified in the wheat genome and classified into five subfamilies. Subcellular localization prediction results showed that 68 TaBBXs were localized in the nucleus. Protein interaction prediction analysis indicated that interaction was one way that these proteins exerted their functions. Promoter analysis indicated that TaBBXs may play important roles in light signal, hormone, and stress responses. qRT-PCR analysis revealed that 14 TaBBXs were highly expressed in seeds compared with other tissues. These were probably involved in seed dormancy and germination, and their expression patterns were investigated during dormancy acquisition and release in the seeds of wheat varieties Jing 411 and Hongmangchun 21, showing significant differences in seed dormancy and germination phenotypes. Subcellular localization analysis confirmed that the three candidates TaBBX2-2 A, TaBBX4-2 A, and TaBBX11-2D were nuclear proteins. Transcriptional self-activation experiments further demonstrated that TaBBX4-2A was transcriptionally active, but TaBBX2-2A and TaBBX11-2D were not. Protein interaction analysis revealed that TaBBX2-2A, TaBBX4-2A, and TaBBX11-2D had no interaction with each other, while TaBBX2-2A and TaBBX11-2D interacted with each other, indicating that TaBBX4-2A may regulate seed dormancy and germination by transcriptional regulation, and TaBBX2-2A and TaBBX11-2D may regulate seed dormancy and germination by forming a homologous complex.ConclusionsIn this study, the wheat BBX gene family was identified and characterized at the genomic level by bioinformatics analysis. These observations provide a theoretical basis for future studies on the functions of BBXs in wheat and other species.

Strictosamide promotes wound healing through activation of the PI3K/AKT pathway

Nauclea officinalis, as a Chinese medicine in Hainan province, had the effect of treating lower limb ulcers, burn infections. In this paper, we studied the effect of Strictosamide (STR), the main bioactive compound in Nauclea officinals, on wound healing and explored its internal mechanism. Firstly, the wound healing potential of STR was evaluated in a rat model, demonstrating its ability to expedite wound healing, mitigate inflammatory infiltration, and enhance collagen deposition. Additionally, immunofluorescence analysis revealed that STR up-regulated the expression of CD31 and PCNA. Subsequently, target prediction, protein-protein interaction (PPI), gene ontology (GO), and pathway enrichment analyses were used to obtain potential targets, specific biological processes, and molecular mechanisms of STR for the potential treatment of wound healing. Furthermore, molecular docking was conducted to predict the binding affinity between STR and its associated targets. Additionally, in vivo and in vitro experiments confirmed that STR could increase the expression of P-PI3K, P-AKT and P-mTOR by activating the PI3K/AKT signaling pathway. In summary, this study provided a new explanation for the mechanism by which STR promotes wound healing through network pharmacology, suggesting that STR may be a new candidate for treating wound.

The Prediction of LptA and LptC Protein-Protein Interactions and Virtual Screening for Potential Inhibitors.

Antibiotic resistance in Gram-negative bacteria remains one of the most pressing challenges to global public health. Blocking the transportation of lipopolysaccharides (LPS), a crucial component of the outer membrane of Gram-negative bacteria, is considered a promising strategy for drug discovery. In the transportation process of LPS, two components of the LPS transport (Lpt) complex, LptA and LptC, are responsible for shuttling LPS across the periplasm to the outer membrane, highlighting their potential as targets for antibacterial drug development. In the current study, a protein-protein interaction (PPI) model of LptA and LptC was constructed, and a molecular screening strategy was employed to search a protein-protein interaction compound library. The screening results indicated that compound 18593 exhibits favorable binding free energy with LptA and LptC. In comparison with the molecular dynamics (MD) simulations on currently known inhibitors, compound 18593 shows more stable target binding ability at the same level. The current study suggests that compound 18593 may exhibit an inhibitory effect on the LPS transport process, making it a promising hit compound for further research.

Comparative proteomic analysis of papaya bud flowers reveals metabolic signatures and pathways driving hermaphrodite development

Papaya (Carica papaya) is a trioecious species with female, male, and hermaphrodite plants. Given the sex segregation, selecting hermaphroditic plants is vital for orchard establishment due to their greater commercial value. However, selecting hermaphrodite plants through sexing is laborious and costly. Moreover, environmental stressors can exacerbate the issue by potentially inducing abnormal flower development, thus affecting fruit quality. Despite these challenges, the molecular mechanisms governing sex development in papaya remain poorly understood. Thus, this study aimed to identify proteins associated with sex development in female and hermaphrodite flowers of papaya through comparative proteomic analysis. Proteins from flower buds at the early and late developmental stages of three papaya genotypes (UENF-CALIMAN 01, JS12, and Sunrise Solo 72/12) were studied via proteomic analysis via the combination of the shotgun method and nanoESI-HDMSE technology. In buds at an early stage of development, 496 (35.9%) proteins exhibited significantly different abundances between sexes for the SS72/12 genotype, 139 (10%) for the JS12 genotype, and 165 (11.9%) for the UC-01 genotype. At the final stage of development, there were 181 (13.5%) for SS72/12, 113 (8.4%) for JS12, and 125 (9.1%) for UC-01. The large group of differentially accumulated proteins (DAPs) between the sexes was related to metabolism, as shown by the observation of only the proteins that exhibited the same pattern of accumulation in the three genotypes. Specifically, carbohydrate metabolism proteins were up-regulated in hermaphrodite flower buds early in development, while those linked to monosaccharide and amino acid metabolism increased during late development. Enrichment of sporopollenin and phenylpropanoid biosynthesis pathways characterizes hermaphrodite samples across developmental stages, with predicted protein interactions highlighting the crucial role of phenylpropanoids in sporopollenin biosynthesis for pollen wall formation. Most of the DAPs played key roles in pectin, cellulose, and lignin synthesis and were essential for cell wall formation and male flower structure development, notably in the pollen coat. These findings suggest that hermaphrodite flowers require more energy for development, likely due to complex pollen wall formation. Overall, these insights illuminate the molecular mechanisms of papaya floral development, revealing complex regulatory networks and energetic demands in the formation of male reproductive structures.

PagEXPA1 combines with PagCDKB2;1 to regulate plant growth and the elongation of fibers in Populus alba × Populus glandulosa

Expansins are important plant cell wall proteins. They can loosen and soften the cell walls and lead to wall extension and cell expansion. To investigate their role in wood formation and fiber elongation, the PagEXPA1 that highly expressed in cell differentiation and expansion tissues was cloned from 84K poplar (Populus alba × P. glandulosa). The subcellular localization showed that PagEXPA1 located in the cell wall and it was highly expressed in primary stems and young leaves. Compared with non-transgenic 84K poplar, overexpression of PagEXPA1 can promote plant-growth, lignification, and fiber cell elongation, while PagEXPA1 Cas9-editing mutant lines exhibited the opposite phenotype. Transcriptome analysis revealed that DEGs were mainly enriched in some important processes, which are associated with cell wall formation and cellulose synthesis. The protein interaction prediction and expression analysis showed that PagCDKB2:1 and PagEXPA1 might have an interaction relationship. The luciferase complementary assay and bimolecular fluorescence complementary assay validated that PagEXPA1 can combined with PagCDKB2;1. So they promoted the expansion of xylem vascular tissues and the development of poplar though participating in the regulation of cell division and differentiation by programming the cell-cycle. It provides good foundation for molecular breeding of fast-growing and high-quality poplar varieties.

Genome-wide identification and expression analysis of ARF gene family in embryonic development of Korean pine (Pinus koraiensis)

BackgroundThe Auxin Responsive Factor (ARF) family plays a crucial role in mediating auxin signal transduction and is vital for plant growth and development. However, the function of ARF genes in Korean pine (Pinus koraiensis), a conifer species of significant economic value, remains unclear.ResultsThis study utilized the whole genome of Korean pine to conduct bioinformatics analysis, resulting in the identification of 13 ARF genes. A phylogenetic analysis revealed that these 13 PkorARF genes can be classified into 4 subfamilies, indicating the presence of conserved structural characteristics within each subfamily. Protein interaction prediction indicated that Pkor01G00962.1 and Pkor07G00704.1 may have a significant role in regulating plant growth and development as core components of the PkorARFs family. Additionally, the analysis of RNA-seq and RT-qPCR expression patterns suggested that PkorARF genes play a crucial role in the development process of Korean pine.ConclusionPkor01G00962.1 and Pkor07G00704.1, which are core genes of the PkorARFs family, play a potentially crucial role in regulating the fertilization and developmental process of Korean pine. This study provides a valuable reference for investigating the molecular mechanism of embryonic development in Korean pine and establishes a foundation for cultivating high-quality Korean pine.

Expressional vagaries of OsCAMTA genes under differential abiotic stresses supported with protein–protein interaction study and prediction of miRNA target sites

Expressional vagaries of OsCAMTA genes under differential abiotic stresses supported with protein–protein interaction study and prediction of miRNA target sites

Decoding the Arsenal: Protist Effectors and Their Impact on Photosynthetic Hosts.

Interactions between various microbial pathogens including viruses, bacteria, fungi, oomycetes, and their plant hosts have traditionally been the focus of phytopathology. In recent years, a significant and growing interest in the study of eukaryotic microorganisms not classified among fungi or oomycetes has emerged. Many of these protists establish complex interactions with photosynthetic hosts, and understanding these interactions is crucial in understanding the dynamics of these parasites within traditional and emerging types of farming, including marine aquaculture. Many phytopathogenic protists are biotrophs with complex polyphasic life cycles, which makes them difficult or impossible to culture, a fact reflected in a wide gap in the availability of comprehensive genomic data when compared to fungal and oomycete plant pathogens. Furthermore, our ability to use available genomic resources for these protists is limited by the broad taxonomic distance that these organisms span, which makes comparisons with other genomic datasets difficult. The current rapid progress in genomics and computational tools for the prediction of protein functions and interactions is revolutionizing the landscape in plant pathology. This is also opening novel possibilities, specifically for a deeper understanding of protist effectors. Tools like AlphaFold2 enable structure-based function prediction of effector candidates with divergent protein sequences. In turn, this allows us to ask better biological questions and, coupled with innovative experimental strategies, will lead into a new era of effector research, especially for protists, to expand our knowledge on these elusive pathogens and their interactions with photosynthetic hosts. [Formula: see text] Copyright © 2024 The Author(s). This is an open access article distributed under the CC BY-NC-ND 4.0 International license.

Xuefu Zhuyu decoction promotes synaptic plasticity by targeting miR-191a-5p/BDNF-TrkB axis in severe traumatic brain injury

BackgroundXuefu Zhuyu decoction (XFZYD) is a traditional Chinese herbal formula known for its ability to eliminate blood stasis and improve blood circulation, providing neuroprotection against severe traumatic brain injury (sTBI). However, the underlying mechanism is still unclear. PurposeWe aim to investigate the neuroprotective effects of XFZYD in sTBI from a novel mechanistic perspective of miRNA-mRNA. Additionally, we sought to elucidate a potential specific mechanism by integrating transcriptomics, bioinformatics, and conducting both in vitro and in vivo experiments. MethodsThe sTBI rat model was established, and the rats were treated with XFZYD for 14 days. The neuroprotective effects of XFZYD were evaluated using a modified neurological severity score, hematoxylin and eosin staining, as well as Nissl staining. The anti-inflammatory effects of XFZYD were explored using quantitative real-time PCR (qRT-PCR), Western blot analysis, and immunofluorescence. Next, miRNA sequencing of the hippocampus was performed to determine which miRNAs were differentially expressed. Subsequently, qRT-PCR was used to validate the differentially expressed miRNAs. Target core mRNAs were determined using various methods, including miRNA prediction targets, mRNA sequencing, miRNA-mRNA network, and protein-protein interaction (PPI) analysis. The miRNA/mRNA regulatory axis were verified through qRT-PCR or Western blot analysis. Finally, morphological changes in the neural synapses were observed using transmission electron microscopy and immunofluorescence. ResultsXFZYD exhibited significant neuroprotective and anti-inflammatory effects on subacute sTBI rats' hippocampus. The analyses of miRNA/mRNA sequences combined with the PPI network revealed that the therapeutic effects of XFZYD on sTBI were associated with the regulation of the rno-miR-191a-5p/BDNF axis. Subsequently, qRT-PCR and Western blot analysis confirmed XFZYD reversed the decrease of BDNF and TrkB in the hippocampus caused by sTBI. Additionally, XFZYD treatment potentially increased the number of synaptic connections, and the expression of the synapse-related protein PSD95, axon-related protein GAP43 and neuron-specific protein TUBB3. ConclusionsXFZYD exerts neuroprotective effects by promoting hippocampal synaptic remodeling and improving cognition during the subacute phase of sTBI through downregulating of rno-miR-191a-5p/BDNF axis, further activating BDNF-TrkB signaling.

Abstract 550: Identification of isoform switching events linked with esophageal adenocarcinoma patient survival informs novel prognostic and therapeutic targets

Abstract Esophageal adenocarcinoma (EAC) represents a growing health problem characterized by rising incidence and poor prognosis. Although it is a cancer with a high mutational burden, it lacks highly prevalent oncogenic drivers that can be therapeutically targeted. Recently, our group characterized isoform switching events, defined by the changing of dominant gene isoforms between conditions, associated with EAC progression and identified 75 switching events comparing Barrett’s low-grade dysplasia (BE.LGD) and Barrett’s high-grade dysplasia (BE.HGD) patient samples. Herein, we further investigated whether isoform-switching events may offer prognostic or therapeutic value in EAC. Isoform switching analysis was performed using RNA-seq data derived from patient samples between BE.LGD and BE.HGD combined with EAC (BE.HGD + EAC) alone or in combination with TP53 mutations. Patients were further stratified into tertiles based on isoform expression level followed by survival analysis. Thirty isoforms were significantly (P≤0.05) linked with all-cause mortality, comparing BE.LGD with BE.HGD + EAC, whereas 20 isoforms were identified when TP53 mutation status was included. In terms of cancer-specific mortality, 10 isoforms were significantly linked with survival comparing BE.LGD with BE.HGD+EAC. With the inclusion of TP53 mutation, 16 isoforms were also significantly linked with cancer-specific mortality. Isoform-specific genetic knockdown experiments were designed targeting the top isoforms identified in the analysis, including TTLL12 and HM13 isoforms. Knockdown of TTLL12 and HM13 isoforms led to significant inhibition of cell viability and migration in two EAC cell lines (OE19 and OE33). Chemotherapeutic agents (Paclitaxel + Carboplatin) further decreased cell viability with synergistic effects observed in both siRNA-treated cell lines suggesting a role for specific isoform switches in therapeutic sensitization. Protein-interaction prediction using STRING and immunoblot analysis suggest different mechanisms leading to the inhibition of cell viability and migration. TTLL12 is linked with the activation of chaperon-medicated autophagy (LAMP2A and HSC70) and protein translation, whereas HM13 is linked with unfolded protein response (IRE1α, PERK, and ATF6) and may be linked with immunotherapy outcome. An antigen-dependent cell-mediated cytotoxicity assay is currently underway to investigate whether the knockdown of HM13 isoforms can sensitize EAC cells to PD-1/PD-L1 immunotherapy agents. Future direction includes using FDA-approved agents to target the two major pathways identified above. In conclusion, isoform switching may provide fresh insight for the identification of prognostic markers and inform new potential therapeutic targets for EAC treatment or prevention. Citation Format: Yun Zhang, Rachel Israel, Bryce Vandenburg, Shari Barnett, Jean-Jack Riethoven, Jennifer L. Clarke, Michelle P. Lee, Kiran Lagisetty, Jules Lin, Rishindra Reddy, Andrew Chang, Laura A. Kresty. Identification of isoform switching events linked with esophageal adenocarcinoma patient survival informs novel prognostic and therapeutic targets [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 550.

Chalkiness and premature controlled by energy homeostasis in OsNAC02 Ko-mutant during vegetative endosperm development.

Chalkiness is a common phenotype induced by various reasons, such as abiotic stress or the imbalance of starch synthesis and metabolism during the development period. However, the reason mainly for one gene losing its function such as NAC (TFs has a large family in rice) which may cause premature is rarely known to us. The Ko-Osnac02 mutant demonstrated an obviously early maturation stage compared to the wild type (WT) with 15days earlier. The result showed that the mature endosperm of Ko-Osnac02 mutant exhibited chalkiness, characterized by white-core and white-belly in mature endosperm. As grain filling rate is a crucial factor in determining the yield and quality of rice (Oryza sativa, ssp. japonica), it's significant that mutant has a lower amylose content (AC) and higher soluble sugar content in the mature endosperm. Interestingly among the top DEGs in the RNA sequencing of N2 (3DAP) and WT seeds revealed that the OsBAM2 (LOC_Os10g32810) expressed significantly high in N2 mutant, which involved in Maltose up-regulated by the starch degradation. As Prediction of Protein interaction showed in the chalky endosperm formation in N2 seeds (3 DAP), seven genes were expressed at a lower-level which should be verified by a heatmap diagrams based on DEGs of N2 versus WT. The Tubulin genes controlling cell cycle are downregulated together with the MCM family genes MCM4 ( ↓), MCM7 ( ↑), which may cause white-core in the early endosperm development. In conclusion, the developing period drastically decreased in the Ko-Osnac02 mutants, which might cause the chalkiness in seeds during the early endosperm development. The gene OsNAC02 which controls a great genetic co-network for cell cycle regulation in early development, and KO-Osnac02 mutant shows prematurity and white-core in endosperm.

SpatialPPI: Three-dimensional space protein-protein interaction prediction with AlphaFold Multimer

Rapid advancements in protein sequencing technology have resulted in gaps between proteins with identified sequences and those with mapped structures. Although sequence-based predictions offer insights, they can be incomplete due to the absence of structural details. Conversely, structure-based methods face challenges with respect to newly sequenced proteins. The AlphaFold Multimer has remarkable accuracy in predicting the structure of protein complexes. However, it cannot distinguish whether the input protein sequences can interact. Nonetheless, by analyzing the information in the models predicted by the AlphaFold Multimer, we propose a highly accurate method for predicting protein interactions. This study focuses on the use of deep neural networks, specifically to analyze protein complex structures predicted by the AlphaFold Multimer. By transforming atomic coordinates and utilizing sophisticated image-processing techniques, vital 3D structural details were extracted from protein complexes. Recognizing the significance of evaluating residue distances in protein interactions, this study leveraged image recognition approaches by integrating Densely Connected Convolutional Networks (DenseNet) and Deep Residual Network (ResNet) within 3D convolutional networks for protein 3D structure analysis. When benchmarked against leading protein-protein interaction prediction methods, such as SpeedPPI, D-script, DeepTrio, and PEPPI, our proposed method, named SpatialPPI, exhibited notable efficacy, emphasizing the promising role of 3D spatial processing in advancing the realm of structural biology. The SpatialPPI code is available at: https://github.com/ohuelab/SpatialPPI.

Computational prediction of protein interactions in single cells by proximity sequencing.

Proximity sequencing (Prox-seq) simultaneously measures gene expression, protein expression and protein complexes on single cells. Using information from dual-antibody binding events, Prox-seq infers surface protein dimers at the single-cell level. Prox-seq provides multi-dimensional phenotyping of single cells in high throughput, and was recently used to track the formation of receptor complexes during cell signaling and discovered a novel interaction between CD9 and CD8 in naïve T cells. The distribution of protein abundance can affect identification of protein complexes in a complicated manner in dual-binding assays like Prox-seq. These effects are difficult to explore with experiments, yet important for accurate quantification of protein complexes. Here, we introduce a physical model of Prox-seq and computationally evaluate several different methods for reducing background noise when quantifying protein complexes. Furthermore, we developed an improved method for analysis of Prox-seq data, which resulted in more accurate and robust quantification of protein complexes. Finally, our Prox-seq model offers a simple way to investigate the behavior of Prox-seq data under various biological conditions and guide users toward selecting the best analysis method for their data.

A multi-source molecular network representation model for protein–protein interactions prediction

The prediction of potential protein–protein interactions (PPIs) is a critical step in decoding diseases and understanding cellular mechanisms. Traditional biological experiments have identified plenty of potential PPIs in recent years, but this problem is still far from being solved. Hence, there is urgent to develop computational models with good performance and high efficiency to predict potential PPIs. In this study, we propose a multi-source molecular network representation learning model (called MultiPPIs) to predict potential protein–protein interactions. Specifically, we first extract the protein sequence features according to the physicochemical properties of amino acids by utilizing the auto covariance method. Second, a multi-source association network is constructed by integrating the known associations among miRNAs, proteins, lncRNAs, drugs, and diseases. The graph representation learning method, DeepWalk, is adopted to extract the multisource association information of proteins with other biomolecules. In this way, the known protein–protein interaction pairs can be represented as a concatenation of the protein sequence and the multi-source association features of proteins. Finally, the Random Forest classifier and corresponding optimal parameters are used for training and prediction. In the results, MultiPPIs obtains an average 86.03% prediction accuracy with 82.69% sensitivity at the AUC of 93.03% under five-fold cross-validation. The experimental results indicate that MultiPPIs has a good prediction performance and provides valuable insights into the field of potential protein–protein interactions prediction. MultiPPIs is free available at https://github.com/jiboyalab/multiPPIs.

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.

Enhancing coevolutionary signals in protein–protein interaction prediction through clade-wise alignment integration

Protein–protein interactions (PPIs) play essential roles in most biological processes. The binding interfaces between interacting proteins impose evolutionary constraints that have successfully been employed to predict PPIs from multiple sequence alignments (MSAs). To construct MSAs, critical choices have to be made: how to ensure the reliable identification of orthologs, and how to optimally balance the need for large alignments versus sufficient alignment quality. Here, we propose a divide-and-conquer strategy for MSA generation: instead of building a single, large alignment for each protein, multiple distinct alignments are constructed under distinct clades in the tree of life. Coevolutionary signals are searched separately within these clades, and are only subsequently integrated using machine learning techniques. We find that this strategy markedly improves overall prediction performance, concomitant with better alignment quality. Using the popular DCA algorithm to systematically search pairs of such alignments, a genome-wide all-against-all interaction scan in a bacterial genome is demonstrated. Given the recent successes of AlphaFold in predicting direct PPIs at atomic detail, a discover-and-refine approach is proposed: our method could provide a fast and accurate strategy for pre-screening the entire genome, submitting to AlphaFold only promising interaction candidates—thus reducing false positives as well as computation time.

XCAPT5: protein–protein interaction prediction using deep and wide multi-kernel pooling convolutional neural networks with protein language model

BackgroundPredicting protein–protein interactions (PPIs) from sequence data is a key challenge in computational biology. While various computational methods have been proposed, the utilization of sequence embeddings from protein language models, which contain diverse information, including structural, evolutionary, and functional aspects, has not been fully exploited. Additionally, there is a significant need for a comprehensive neural network capable of efficiently extracting these multifaceted representations.ResultsAddressing this gap, we propose xCAPT5, a novel hybrid classifier that uniquely leverages the T5-XL-UniRef50 protein large language model for generating rich amino acid embeddings from protein sequences. The core of xCAPT5 is a multi-kernel deep convolutional siamese neural network, which effectively captures intricate interaction features at both micro and macro levels, integrated with the XGBoost algorithm, enhancing PPIs classification performance. By concatenating max and average pooling features in a depth-wise manner, xCAPT5 effectively learns crucial features with low computational cost.ConclusionThis study represents one of the initial efforts to extract informative amino acid embeddings from a large protein language model using a deep and wide convolutional network. Experimental results show that xCAPT5 outperforms recent state-of-the-art methods in binary PPI prediction, excelling in cross-validation on several benchmark datasets and demonstrating robust generalization across intra-species, cross-species, inter-species, and stringent similarity contexts.

Genome-Wide Identification and Expression Analysis of the PUB Gene Family in Zoysia japonica under Salt Stress.

The U-box protein family of ubiquitin ligases is important in the biological processes of plant growth, development, and biotic and abiotic stress responses. Plants in the genus Zoysia are recognized as excellent warm-season turfgrass species with drought, wear and salt tolerance. In this study, we conducted the genome-wide identification of plant U-box (PUB) genes in Zoysia japonica based on U-box domain searching. In total, 71 ZjPUB genes were identified, and a protein tree was constructed of AtPUBs, OsPUBs, and ZjPUBs, clustered into five groups. The gene structures, characteristics, cis-elements and protein interaction prediction network were analyzed. There were mainly ABRE, ERE, MYB and MYC cis-elements distributed in the promoter regions of ZjPUBs. ZjPUBs were predicted to interact with PDR1 and EXO70B1, related to the abscisic acid signaling pathway. To better understand the roles of ZjPUBs under salt stress, the expression levels of 18 ZjPUBs under salt stress were detected using transcriptome data and qRT-PCR analysis, revealing that 16 ZjPUBs were upregulated in the roots under salt treatment. This indicates that ZjPUBs might participate in the Z. japonica salt stress response. This research provides insight into the Z. japonica PUB gene family and may support the genetic improvement in the molecular breeding of salt-tolerant zoysiagrass varieties.