Prediction Of Protein-protein Interactions Research Articles

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/Ta2O5/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.

Boosting Prediction of Protein-Protein Interactions using Word Embedding Techniques

Understanding protein-protein interactions (PPIs) helps to identify protein functions and develop other important applications such as drug preparation, protein-disease relationship identification. Machine learning methods have been developed for the PPI prediction task in order to reduce the cost and time of previous experimental methods. In this paper, we study a method for determining PPIs using deep learning and protein sequence representation learning. In our method, an word embedding technique is utilized for protein sequence representation learning. This technique captures the semantic relationship between amino acids in protein sequences. The semantic relationship is then used as the input information, which is fed into a neural network to help recognize the interaction signature of the input protein pair. Different from previous studies, we integrate the protein sequence embedding mechanism into a neural network model. Thereby, the protein sequence embedding is better controlled for PPI prediction by our neural network model. We evaluate our method on benchmark datasets including Yeast, Human, and eight different independent sets. In addition, we also conduct an extensive comparison with the other existing methods. Our results show that the proposed method is superior to other existing methods and achieves high efficiency in predicting cross-species PPIs. The dataset and our source code are available at https://github.com/thnhub/BoostPPIP.git.

Transcriptome analysis of tomato plants following salicylic acid-induced immunity against Clavibacter michiganensis ssp. michiganensis.

Salicylic acid (SA) is known to be involved in the immunity against Clavibacter michiganensis ssp. michiganensis (Cmm) that causes bacterial canker in tomato. To identify the candidate genes associated with SA-inducible Cmm resistance, transcriptome analysis was conducted via RNA sequencing in tomato plants treated with SA. SA treatment upregulated various defense-associated genes, such as PR and GST genes, in tomato cotyledons. A comparison of SA- and Cmm-responsive genes revealed that both SA treatment and Cmm infection commonly upregulated a large number of genes. Gene Ontology (GO) analysis indicated that the GO terms associated with plant immunity were over-represented in both SA- and Cmm-induced genes. The genes commonly downregulated by both SA treatment and Cmm infection were associated with the cell cycle and may be involved in growth and immunity trade-off through cell division. After SA treatment, several proteins that were predicted to play a role in immune signaling, such as resistance gene analogs, Ca2+ sensors, and WRKY transcription factors, were transcriptionally upregulated. The W-box element, which was targeted by WRKYs, was over-represented in the promoter regions of genes upregulated by both SA treatment and Cmm infection, supporting the speculation that WRKYs are important for the SA-mediated immunity against Cmm. Prediction of protein-protein interactions suggested that genes encoding receptor-like kinases and EF-hand proteins play an important role in immune signaling. Thus, various candidate genes involved in SA-inducible Cmm resistance were identified.

DL-PPI: a method on prediction of sequenced protein–protein interaction based on deep learning

PurposeSequenced Protein–Protein Interaction (PPI) prediction represents a pivotal area of study in biology, playing a crucial role in elucidating the mechanistic underpinnings of diseases and facilitating the design of novel therapeutic interventions. Conventional methods for extracting features through experimental processes have proven to be both costly and exceedingly complex. In light of these challenges, the scientific community has turned to computational approaches, particularly those grounded in deep learning methodologies. Despite the progress achieved by current deep learning technologies, their effectiveness diminishes when applied to larger, unfamiliar datasets.ResultsIn this study, the paper introduces a novel deep learning framework, termed DL-PPI, for predicting PPIs based on sequence data. The proposed framework comprises two key components aimed at improving the accuracy of feature extraction from individual protein sequences and capturing relationships between proteins in unfamiliar datasets. 1. Protein Node Feature Extraction Module: To enhance the accuracy of feature extraction from individual protein sequences and facilitate the understanding of relationships between proteins in unknown datasets, the paper devised a novel protein node feature extraction module utilizing the Inception method. This module efficiently captures relevant patterns and representations within protein sequences, enabling more informative feature extraction. 2. Feature-Relational Reasoning Network (FRN): In the Global Feature Extraction module of our model, the paper developed a novel FRN that leveraged Graph Neural Networks to determine interactions between pairs of input proteins. The FRN effectively captures the underlying relational information between proteins, contributing to improved PPI predictions. DL-PPI framework demonstrates state-of-the-art performance in the realm of sequence-based PPI prediction.

Differential expression of the genes encoding immune system components in response to Pseudomonas syringae and Pseudomonas aeruginosa in Arabidopsis thaliana.

In innate immunity, the first layer of defense against any microbial infection is triggered by the perception of pathogen-associated molecular patterns by highly specific pattern recognition receptors. The Pseudomonas syringae pv. tomato and Pseudomonas aeruginosa are plant-pathogenic bacterial species that include pathogenic strains in a wide range of different plant species. In the current study, extensive analysis including gene expression of 12 hub genes, gene ontology, protein-protein interaction, and cis-element prediction to dissect the Arabidopsis response to above-mentioned bacteria were performed. Further, we evaluated weighted co-expression network analysis (WGCNA) in the wild-type plants and coi-1 mutant line and determined changes in responsive genes at two time-points (4 and 8h) of post-treatment with P. syringae and P. aeruginosa. Compared to the wild-type plants, coi-1 mutant showed significant expression in most of the genes involved, indicating that their protein products have important role in innate immunity and RNA silencing pathways. Our findings showed that 12 hub genes were co-expressed in response to P. syringae and P. aeruginosa infections. Based on the network analysis, transcription factors, receptors, protein kinase, and pathogenesis-related protein (PR1) were involved in the immunity system. Gene ontology related to each module was involved in defense response, protein serine kinase activity, and primary miRNA processing. Based on the cis-elements prediction, MYB, MYC, WRE3, W-box, STRE, and ARE contained the most number of cis-elements in co-expressed network genes. Also, in coi-1 mutant, most responsive genes against theses pathogens were up-regulated. The knowledge gained in the gene expression analysis in response to P. syringae and P. aeruginosa in the model plant, i.e., Arabidopsis, is essential to allow us to gain more insight about the innate immunity in other crops.

DeepCompoundNet: enhancing compound–protein interaction prediction with multimodal convolutional neural networks

Virtual screening has emerged as a valuable computational tool for predicting compound–protein interactions, offering a cost-effective and rapid approach to identifying potential candidate drug molecules. Current machine learning-based methods rely on molecular structures and their relationship in the network. The former utilizes information such as amino acid sequences and chemical structures, while the latter leverages interaction network data, such as protein–protein interactions, drug–disease interactions, and protein–disease interactions. However, there has been limited exploration of integrating molecular information with interaction networks. This study presents DeepCompoundNet, a deep learning-based model that integrates protein features, drug properties, and diverse interaction data to predict chemical–protein interactions. DeepCompoundNet outperforms state-of-the-art methods for compound–protein interaction prediction, as demonstrated through performance evaluations. Our findings highlight the complementary nature of multiple interaction data, extending beyond amino acid sequence homology and chemical structure similarity. Moreover, our model’s analysis confirms that DeepCompoundNet gets higher performance in predicting interactions between proteins and chemicals not observed in the training samples. Communicated by Ramaswamy H. Sarma

PLO3S: Protein LOcal Surficial Similarity Screening

The study of protein molecular surfaces enables to better understand and predict protein interactions. Different methods have been developed in computer vision to compare surfaces that can be applied to protein molecular surfaces. The present work proposes a method using the Wave Kernel Signature: Protein LOcal Surficial Similarity Screening (PLO3S). The descriptor of the PLO3S method is a local surface shape descriptor projected on a unit sphere mapped onto a 2D plane and called Surface Wave Interpolated Maps (SWIM). PLO3S allows to rapidly compare protein surface shapes through local comparisons to filter large protein surfaces datasets in protein structures virtual screening protocols.

AraPathogen2.0: An Improved Prediction of Plant-Pathogen Protein-Protein Interactions Empowered by the Natural Language Processing Technique.

Plant-pathogen protein-protein interactions (PPIs) play crucial roles in the arm race between plants and pathogens. Therefore, the identification of these interspecies PPIs is very important for the mechanistic understanding of pathogen infection and plant immunity. Computational prediction methods can complement experimental efforts, but their predictive performance still needs to be improved. Motivated by the rapid development of natural language processing and its successful applications in the field of protein bioinformatics, here we present an improved XGBoost-based plant-pathogen PPI predictor (i.e., AraPathogen2.0), in which sequence encodings from the pretrained protein language model ESM2 and Arabidopsis PPI network-related node representations from the graph embedding technique struc2vec are used as input. Stringent benchmark experiments showed that AraPathogen2.0 could achieve a better performance than its precedent version, especially for processing the test data set with novel proteins unseen in the training data.

Current progress on the computational methods for prediction of host-pathogen protein-protein interaction in the Ganoderma boninense-oil palm pathosystem

Ganoderma boninense is a major pathogen for basal stem rot disease that can depolymerize lignocellulosic materials of the oil palm plant by secreting the cell wall-degrading enzymes. The management of this disease is complicated by the asymptomatic phase mediated by the protein-protein interaction (PPI) between the pathogen's effector and plant proteins. There is a lack of network-wide studies on the PPI to elucidate the action of effectors on plant pathways from a systemic perspective as the computational prediction of host-pathogen PPI (HP PPI) is focused on human interaction. Hence, this minireview explores the current computational methods for predicting HP PPI and proposes an approach to predict PPI between G. boninense and oil palm.

Structure Prediction and Genome Mining-Aided Discovery of the Bacterial C-Terminal Tryptophan Prenyltransferase PalQ.

Post-translational prenylations, found in eukaryotic primary metabolites and bacterial secondary metabolites, play crucial roles in biomolecular interactions. Employing genome mining methods combined with AlphaFold2-based predictions of protein interactions, PalQ , a prenyltransferase responsible for the tryptophan prenylation of RiPPs produced by Paenibacillus alvei, is identified. PalQ differs from cyanobactin prenyltransferases because of its evolutionary relationship to isoprene synthases, which enables PalQ to transfer extended prenyl chains to the indole C3position. This prenylation introduces structural diversity to the tryptophan side chain and also leads to conformational dynamics in the peptide backbone, attributed to the cis/trans isomerization that arises from the formation of a pyrrolidine ring. Additionally, PalQ exhibited pronounced positional selectivity for the C-terminal tryptophan. Such enzymatic characteristics offer a toolkit for peptide therapeutic lipidation.

Genome-wide identification and expression analysis of the NHX gene family under salt stress in wheat (Triticum aestivum L).

Salt stress affects plant growth and development, resulting in the loss of crop yield across the world, and sodium-proton antiporters (NHXs) are one of the genes known to promote salt tolerance in transgenic plants. In this study, we conducted a comprehensive genome-wide analysis and expression profile of NHX genes in wheat under salinity stress. We identified 30 TaNHX genes in wheat based on the Na+/H+ exchanger domain, with all genes containing an amiloride motif except one, a known for inhibiting Na+ ions in plants. Phylogenetic analysis classified these genes into three classes with subfamilies: 12 were localized in vacuoles, while 18 were in the endoplasmic reticulum and plasma membrane. Promoter analysis revealed stress-related cis-acting elements, indicating their potential role in abiotic stress tolerance. The non-synonymous (Ka)/synonymous (Ks) ratios highlighted that the majority of TaNHX genes experienced robust purifying selection throughout their evolutionary history. Transcriptomis data analysis and qRT-PCR demonstrated distinct expression patterns for TaNHX genes across various tissues when subjected to salt stress. Additionally, we predicted 20 different miRNA candidates targeting the identified TaNHX genes. Protein-protein interaction prediction revealed NHX6's involvement in the SOS1 pathway, while NHX1 gene exhibit proton antiporter activity. Molecular dynamics (MD) simulations were also conducted to examine the interactions of TaNHX1, TaNHX2, and TaNHX3. These results represent a significant advancement in our understanding of the molecular mechanisms governing Na+ transporters. This may also offer promising avenues for future studies aimed at unraveling the intricate details of their biological roles and applications.

MaTPIP: A deep-learning architecture with eXplainable AI for sequence-driven, feature mixed protein-protein interaction prediction

Background and ObjectiveProtein-protein interaction (PPI) is a vital process in all living cells, controlling essential cell functions such as cell cycle regulation, signal transduction, and metabolic processes with broad applications that include antibody therapeutics, vaccines, and drug discovery. The problem of sequence-based PPI prediction has been a long-standing issue in computational biology. MethodsWe introduce MaTPIP, a cutting-edge deep-learning framework for predicting PPI. MaTPIP stands out due to its innovative design, fusing pre-trained Protein Language Model (PLM)-based features with manually curated protein sequence attributes, emphasizing the part-whole relationship by incorporating two-dimensional granular part (amino-acid) level features and one-dimensional whole-level (protein) features. What sets MaTPIP apart is its ability to integrate these features across three different input terminals seamlessly. MatPIP also includes a distinctive configuration of Convolutional Neural Network (CNN) with Transformer components for concurrent utilization of CNN and sequential characteristics in each iteration and a one-dimensional to two-dimensional converter followed by a unified embedding. The statistical significance of this classifier is validated using McNemar's test. ResultsMaTPIP outperformed the existing methods on both the Human PPI benchmark and cross-species PPI testing datasets, demonstrating its immense generalization capability for PPI prediction. We used seven diverse datasets with varying PPI target class distributions. Notably, within the novel PPI scenario, the most challenging category for Human PPI Benchmark, MaTPIP improves the existing state-of-the-art score from 74.1% to 78.6% (measured in Area under ROC Curve), from 23.2% to 32.8% (in average precision) and from 4.9% to 9.5% (in precision at 3% recall) for 50%, 10% and 0.3% target class distributions, respectively. In cross-species PPI evaluation, hybrid MaTPIP establishes a new benchmark score (measured in Area Under precision-recall curve) of 81.1% from the previous 60.9% for Mouse, 80.9% from 56.2% for Fly, 78.1% from 55.9% for Worm, 59.9% from 41.7% for Yeast, and 66.2% from 58.8% for E.coli. Our eXplainable AI-based assessment reveals an average contribution of different feature families per prediction on these datasets. ConclusionsMaTPIP mixes manually curated features with the feature extracted from the pre-trained PLM to predict sequence-based protein-protein association. Furthermore, MaTPIP demonstrates strong generalization capabilities for cross-species PPI predictions.

ProteinMAE: masked autoencoder for protein surface self-supervised learning.

The biological functions of proteins are determined by the chemical and geometric properties of their surfaces. Recently, with the booming progress of deep learning, a series of learning-based surface descriptors have been proposed and achieved inspirational performance in many tasks such as protein design, protein-protein interaction prediction, etc. However, they are still limited by the problem of label scarcity, since the labels are typically obtained through wet experiments. Inspired by the great success of self-supervised learning in natural language processing and computer vision, we introduce ProteinMAE, a self-supervised framework specifically designed for protein surface representation to mitigate label scarcity. Specifically, we propose an efficient network and utilize a large number of accessible unlabeled protein data to pretrain it by self-supervised learning. Then we use the pretrained weights as initialization and fine-tune the network on downstream tasks. To demonstrate the effectiveness of our method, we conduct experiments on three different downstream tasks including binding site identification in protein surface, ligand-binding protein pocket classification, and protein-protein interaction prediction. The extensive experiments show that our method not only successfully improves the network's performance on all downstream tasks, but also achieves competitive performance with state-of-the-art methods. Moreover, our proposed network also exhibits significant advantages in terms of computational cost, which only requires less than a tenth of memory cost of previous methods. https://github.com/phdymz/ProteinMAE.

Molecular Cloning, Expression Analysis, and Functional Analysis of Nine IbSWEETs in Ipomoea batatas (L.) Lam

Sugar Will Eventually be Exported Transporter (SWEET) genes play an important regulatory role in plants’ growth and development, stress response, and sugar metabolism, but there are few reports on the role of SWEET proteins in sweet potato. In this study, nine IbSWEET genes were obtained via PCR amplification from the cDNA of sweet potato. Phylogenetic analysis showed that nine IbSWEETs separately belong to four clades (Clade I~IV) and contain two MtN3/saliva domains or PQ-loop superfamily and six~seven transmembrane domains. Protein interaction prediction showed that seven SWEETs interact with other proteins, and SWEETs interact with each other (SWEET1 and SWEET12; SWEET2 and SWEET17) to form heterodimers. qRT-PCR analysis showed that IbSWEETs were tissue-specific, and IbSWEET1b was highly expressed during root growth and development. In addition to high expression in leaves, IbSWEET15 was also highly expressed during root expansion, and IbSWEET7, 10a, 10b, and 12 showed higher expression in the leaves. The expression of SWEETs showed a significant positive/negative correlation with the content of soluble sugar and starch in storage roots. Under abiotic stress treatment, IbSWEET7 showed a strong response to PEG treatment, while IbSWEET10a, 10b, and 12 responded significantly to 4 °C treatment and, also, at 1 h after ABA, to NaCl treatment. A yeast mutant complementation assay showed that IbSWEET7 had fructose, mannose, and glucose transport activity; IbSWEET15 had glucose transport activity and weaker sucrose transport activity; and all nine IbSWEETs could transport 2-deoxyglucose. These results provide a basis for further elucidating the functions of SWEET genes and promoting molecular breeding in sweet potato.

Proteomic investigation reveals the role of bacterial laccase from Bacillus pumilus in oxidative stress defense

The wide distribution of laccases in nature makes them involved in different biological processes. However, little information is known about how laccase participates in the defense machinery of bacteria against oxidative stress. The present study aimed to elucidate the oxidative stress response mechanism of Bacillus pumilus ZB1 and the functional role of bacterial laccase in stress defense. The oxidative stress caused by methyl methanesulfonate (MMS) significantly induced laccase activity and its transcript level. The morphological analysis revealed that the defense of B. pumilus ZB1 against oxidative stress was activated. Based on the proteomic study, 114 differentially expressed proteins (DEPs) were up-regulated and 79 DEPs were down-regulated. In COG analysis, 66.40% DEPs were classified into the category “Metabolism”. We confirmed that laccase was up-regulated in response to MMS stress and its functional annotation was related to “Secondary metabolites biosynthesis, transport and catabolism”. Based on protein-protein interaction prediction, two up-regulated DEPs (YcnJ and GabP) showed interaction with laccase and contributed to the formation of laccase stability and adaptability. The overexpressed laccase might improve the antioxidative property of B. pumilus ZB1. These findings provide an insight and the guidelines for better exploitation of bioremediation using bacterial laccase. SignificanceBacillus pumilus is a gram-positive bacterium that has the potential for many applications, such as bioremediation. The expression of bacterial laccase is significantly influenced by oxidative stress, while the underlying mechanism of laccase overexpression in bacteria has not been fully studied. Elucidation of the biological process may benefit the bioremediation using bacteria in the future. In this study, the differentially expressed proteins were analyzed using a TMT-labeling proteomic approach when B. pumilus was treated with methyl methanesulfonate (MMS). Reactive oxygen species induced by MMS activated the secondary metabolites biosynthesis, transport, and catabolism in B. pumilus, including laccase overexpression. Moreover, the simultaneously up-regulated YcnJ and GabP may benefit the synthesis and the stability of laccase, then improve the antioxidative property of B. pumilus against environmental stress. Our findings advance the understanding of the adaptive mechanism of B. pumilus to environmental conditions.

Targeted Metabolome and Transcriptome Analyses Reveal the Molecular Mechanism of Color Variation between Sepals and Petals in Fuchsia hybrida

The sepal color of Fuchsia hybrida is colorful instead of green and usually varies from the petal colors, which greatly increases its ornamental value and attract customers’ preference. However, the potential molecular mechanism underlying the color variation between sepals and petals remains unclear. The present study collected F. hybrida with red sepals and purple petals to explore the key pigments and genes involved in color development using a targeted metabolome and transcriptome. A total of 43 metabolites with diverse hydroxylation, glycosylation, methylation and acylation patterns were isolated and identified by UPLC-MS/MS. The quantification analysis showed that peonidin-3,5-O-diglucoside and malvidin-3,5-O-diglucoside were the most abundant anthocyanins accumulating in the sepals and petals, respectively. Then, six libraries from the sepals and petals were constructed for the transcriptome and 70,135 unigenes were generated. The transcript level of FhF3′H was significantly higher in the sepals, while Fh3′5′H showed more abundant expression in the petals, which can account for the abundant peonidin and malvidin accumulation in the sepals and petals, respectively. The subsequent multiomics analysis showed that both the differentially accumulated anthocyanins and expressed unigenes were enriched in the anthocyanin biosynthesis pathway. Additionally, FhMYBs potentially regulating anthocyanin biosynthesis were screened out by correlation analysis and protein interaction prediction. These findings help to elucidate the molecular mechanisms underlying the color variation between the sepals and petals in F. hybrida.

Abstract 14233: Checkpoint Kinase 1 Combines PKM2 C-domain to Stimulate Endogenous Cardiomyocyte Renewal and Cardiac Repair by Activating Cardiac Metabolic Reprogramming in a Porcine Model of Myocardial Ischemia/Reperfusion Injury

Background: The regenerative capacity of adult mammalian hearts is limited. We previously reported CHK1 in adult mice could promote cardiac regeneration after MI. However, the specific mechanism of CHK1 needs more comprehensive and in-depth interpretation. Methods: I/R injury was induced in pigs, recombinant human checkpoint kinase 1 (rhCHK1) protein encapsulated in hydrogel was injected into the infarct border zone. The therapeutic efficacy of rhCHK1 was evaluated by echocardiography, cMRI, hematological indices and immunofluorescence. Multi-omics analysis were performed to explore the potential mechanisms of rhCHK1. Further, protein interaction prediction and CO-IP experiments were conducted to verify the specific interaction pattern and domains between CHK1 and PKM2. Hipsc-CMs and porcine were used for confirming whether rhCHK1 promotes cardiac regeneration through combining with the PKM2 C-domain. Results: RhCHK1 protein stimulated CMs proliferation and reduced cardiac inflammation at 3 dpi, improved cardiac function and attenuated ventricular remodeling, and reduced the infarct area at 28 dpi. Mechanistically, multiomics analysis showed that glycolysis and mTOR pathways were significantly enriched in this process. Further CO-IP experiments and protein docking prediction showed that CHK1 directly bound to and activated the S37 and Y105 sites of PKM2 to promote metabolic reprogramming. We further constructed plasmids that knock out different CHK1 and PKM2 domains, and transfected them into H293T cells for CO-IP experiments. It was found that the 391-476 domain of CHK1 directly binds to the 157-400 amino acids of PKM2. Further hipsc-CMs and pig experiments both demonstrated that CHK1 stimulates CMs renewal and cardiac repair by activating PKM2 C-domain-mediated cardiac metabolic reprogramming and mTORC1 pathway. Conclusion: This study demonstrates that rhCHK1 could combine with PKM2 391-476 amino acid domain to mediate metabolic reprogramming and mTORC1 pathways to promote CM proliferation and myocardial repair. This study is the first to clarify the specific functional mechanism of CHK1 in pigs. Our results underscore the potential of the local applied rhCHK1 as a safe and simple feasible treatment option for repairing heart.

DeepSurf2.0: A Deep Learning Approach for Predicting Interactions of B Cell Receptors with Antigens

The B cell receptor immunoglobulin (BcR IG) is a unique molecular identity for each B cell clone, underpinning interactions with foreign and (auto)antigens that eventually affect clonal behavior. BcR signaling is crucial for the homeostasis of B cells, affecting all aspects of their physiology including cell activation, proliferation, differentiation and apoptosis. Moreover, it is highly relevant for pathological conditions implicating B cells, e.g. B cell lymphomas and autoimmune disorders. Structural analysis of the BcR IG and its cognate antigenic epitopes is vital in elucidating the mechanisms of BcR-antigen interactions. While analyzing actual protein crystals would be ideal, the crystallographic procedures are notoriously labor-intensive and challenging. Hence, we pivot to an in-silico approach, utilizing 3D analysis of BcR-antigen interactions. Confronted with the inherent variability of BcRs and the arduous nature of experimental analyses, we present a cutting-edge solution: DeepSurf2.0. This innovative computational tool leverages deep learning algorithms to predict Protein-Protein Interactions (PPI) and more specifically BcR-antigen interactions, creating a foundation for fast and accurate protein-protein docking. DeepSurf2.0, specifically tailored for the 3D structures of BcR IG and associated antigens, harnesses the power of deep learning to predict PPI: therefore, a carefully curated dataset is of paramount importance. To achieve the latter, we took advantage of SAbDab, a database containing all the antibody structures available in the Protein Data Bank (PDB), annotated and presented in a consistent fashion. We refined the SAbDab dataset by applying the following filtering steps: (i) we retained only complete BcR IG, i.e. those with available heavy and light chains, (ii) we preserved only one biological assembly from multimeric protein complexes, (iii) we excluded BcRs without associated antigens, and (iv) we constructed each BcR-antigen pair to consist of three chains (one each heavy and light for the BcR and one for the antigen). Through these exacting measures, we created a comprehensive collection of 10,543 BcR-antigen pairs. DeepSurf2.0 was evaluated using two metrics: DCA (Distance between Predicted binding site center and nearest antigen Atom) and OVR (Intersection of real and predicted binding sites divided by their union). A binding site prediction was considered as a hit if DCA < 4 Å. For training purposes, we utilized 9,440 BcR-antigen pairs to optimize DeepSurf2.0. The model was then evaluated on a separate test set of 1,103 BcR-antigen pairs. In this evaluation, DeepSurf2.0 achieved a DCA rate of 33%, which means that a hit was detected in 364 out of 1,103 cases. To measure the quality of these predictions, we assessed the OVR metric that resulted in a rate of 22%. To the best of our knowledge, there are no relevant methods that have been tested in a similar dataset. Existing state-of-the-art PPI prediction approaches achieve similar scores in DCA and OVR; however, the utilized datasets consisted of single chains in receptor and ligand. In contrast, our model incorporates a more complex two-chain receptor paradigm, which is a more challenging task but closer to the reality of BcR-antigen interactions. The aforementioned results not only facilitate understanding molecular interactions but also provide valuable insights into potential BcR docking areas for antigens. This ability to predict and locate the most probable interaction sites has immediate practical implications, significantly expediting the docking process by negating the need for time-consuming blind docking. Since our results are not directly comparable with those of the current state-of-the-art methods, our dataset will be provided publicly as a benchmark to evaluate similar methods in two-chain receptor cases. In conclusion, DeepSurf2.0 serves as a foundation for enabling subsequent docking algorithms to target the predicted interaction binding surface rather than the entire protein structure. This advancement underscores the transformative potential of deep learning within the realm of (immuno)hematology, holding the potential to provide novel insights into the pathogenesis and progression of B cell-related disorders.

LncRNA–protein interaction prediction with reweighted feature selection

LncRNA–protein interactions are ubiquitous in organisms and play a crucial role in a variety of biological processes and complex diseases. Many computational methods have been reported for lncRNA–protein interaction prediction. However, the experimental techniques to detect lncRNA–protein interactions are laborious and time-consuming. Therefore, to address this challenge, this paper proposes a reweighting boosting feature selection (RBFS) method model to select key features. Specially, a reweighted apporach can adjust the contribution of each observational samples to learning model fitting; let higher weights are given more influence samples than those with lower weights. Feature selection with boosting can efficiently rank to iterate over important features to obtain the optimal feature subset. Besides, in the experiments, the RBFS method is applied to the prediction of lncRNA–protein interactions. The experimental results demonstrate that our method achieves higher accuracy and less redundancy with fewer features.

Genome-wide identification and expression analysis of heat shock protein gene family in cassava.

Heat shock proteins are important molecular chaperones that are involved in plant growth and stress responses. However, members of the Hsp family have been poorly studied in cassava. In this study, 225 MeHsp genes were identified in the cassava genome, and their genetic structures exhibited relatively conserved features within each subfamily. The 225 MeHsp genes showed random chromosomal distribution, and at least 74 pairs of segmentally duplicated MeHsp genes. Eleven tandemly duplicated MeHsp genes were identified. Cis-element analysis revealed the importance of MeHsps in plant adaptations to the environment. The prediction of protein interactions suggested that MeHsp70-20 may play a critical regulatory role in the interactive network. Furthermore, the expression profiles of MeHsps in different tissues and cell subsets were analyzed using bulk transcriptomics and single-cell transcriptomic data. Several subfamily genes exhibited unique expression patterns in the transcriptome and were selected for detailed analysis of the single-cell transcriptome. Quantitative real-time polymerase chain reaction (qRT-PCR) revealed the expression patterns of these genes under temperature stress, further supporting the prediction of cis-acting elements. This study provides valuable information for understanding the functional characteristics of MeHsp genes and the evolutionary relationships between MeHsps.