Protein-protein interactions (PPIs) play an essential role in life activities. Many artificial intelligence algorithms based on protein sequence information have been developed to predict PPIs. However, these models have difficulty dealing with various sequence lengths and suffer from low generalization and prediction accuracy. In this study, we proposed a novel end-to-end deep learning framework, RSPPI, combining residual neural network (ResNet) and spatial pyramid pooling (SPP), to predict PPIs based on the protein sequence physicochemistry properties and spatial structural information. In the RSPPI model, ResNet was employed to extract the structural and physicochemical information from the protein three-dimensional structure and primary sequence; the SPP layer was used to transform feature maps to a single vector and avoid the fixed-length requirement. The RSPPI model possessed excellent cross-species performance and outperformed several state-of-the-art methods based either on protein sequence or gene ontology in most evaluation metrics. The RSPPI model provides a novel strategy to develop an AI PPI prediction algorithm.

The mechanism research of skin wrinkles, conducted on volunteers underwent high-intensity desk work and mice subjected to partial sleep deprivation, revealed a significant reduction in dermal thickness associated with the presence of wrinkles. This can be attributed to the activation of facial nerves in a state of hysteria due to an abnormally elevated interaction between SNAP25 and RAB3A proteins involved in the synaptic vesicle cycle (SVC). Facilitated by AI-assisted structural design, a refined peptide called RSIpep is developed to modulate this interaction and normalize SVC. Drawing inspiration from prions, which possess the ability to protect themselves against proteolysis and invade neighboring nerve cells through macropinocytosis, RSIpep is engineered to demonstrate a GSH-responsive reversible self-assembly into a prion-like supermolecule (RSIprion). RSIprion showcases protease resistance, micropinocytosis-dependent cellular internalization, and low adhesion with constituent molecules in the cuticle, thereby endowing it with the transdermic absorption and subsequent biofunction in redressing the frenzied SVC. As a facial mud mask, it effectively reduces periorbital and perinasal wrinkles in the human face. Collectively, RSIprion not only presents a clinical potential as an anti-wrinkle prion-like supermolecule, but also exemplifies a reproducible instance of bionic strategy-guided drug development that bestows transdermal ability upon the pharmaceutical molecule.

The process of experimentally confirming complex interaction networks among proteins is time-consuming and laborious. This study aims to address Protein-Protein Interactions (PPIs) prediction based on graph neural networks (GNN). A novel multilevel prediction model for PPIs named DSSGNN-PPI (Double Structure and Sequence GNN for PPIs) is designed. Initially, a distance graph between amino acid residues is constructed. Subsequently, the distance graph is fed into an underlying graph attention network module. This enables us to efficiently learn vector representations that encode the three-dimensional structure of proteins and simultaneously aggregate key local patterns and overall topological information to obtain graph embedding that adequately represent local and global structural features. In addition, the embedding representations that reflect sequence properties are obtained. Two features are fused to construct high-level protein complex networks, which are fed into the designed gated graph attention network to extract complex topological patterns. By combining heterogeneous multi-source information from downstream structure graph and upstream sequence models, the understanding of PPIs is comprehensively enhanced. A series of evaluation results validate the remarkable effectiveness of DSSGNN-PPI framework in enhancing the prediction of multi-type interactions among proteins. The multilevel representation learning and information fusion strategies provide a new effective solution paradigm for structural biology problems. The source code for DSSGNN-PPI has been hosted on GitHub and is available at https://github.com/cstudy1/DSSGNN-PPI.

Diabetic cardiomyopathy (DCM) is a prevalent complication of type 2 diabetes (T2D). 6-phosphofructo-2-kinase/fructose-2,6-biphosphatase 3 (PFKFB3) is a glycolysis regulator. However, the potential effects of PFKFB3 in the DCM remain unclear. In comparison to db/m mice, PFKFB3 levels decreased in the hearts of db/db mice. Cardiac-specific PFKFB3 overexpression inhibited myocardial oxidative stress and cardiomyocyte apoptosis, suppressed mitochondrial fragmentation, and partly restored mitochondrial function in db/db mice. Moreover, PFKFB3 overexpression stimulated glycolysis. Interestingly, based on the inhibition of glycolysis, PFKFB3 overexpression still suppressed oxidative stress and apoptosis of cardiomyocytes in vitro, which indicated that PFKFB3 overexpression could alleviate DCM independent of glycolysis. Using mass spectrometry combined with co-immunoprecipitation, we identified optic atrophy 1 (OPA1) interacting with PFKFB3. In db/db mice, the knockdown of OPA1 receded the effects of PFKFB3 overexpression in alleviating cardiac remodeling and dysfunction. Mechanistically, PFKFB3 stabilized OPA1 expression by promoting E3 ligase NEDD4L-mediated atypical K6-linked polyubiquitination and thus prevented the degradation of OPA1 by the proteasomal pathway. Our study indicates that PFKFB3/OPA1 could be potential therapeutic targets for DCM.

Protein-protein interactions (PPI) play a crucial role in numerous key biological processes, and the structure of protein complexes provides valuable clues for in-depth exploration of molecular-level biological processes. Protein-protein docking technology is widely used to simulate the spatial structure of proteins. However, there are still challenges in selecting candidate decoys that closely resemble the native structure from protein-protein docking simulations. In this study, we introduce a docking evaluation method based on three-dimensional point cloud neural networks named SurfPro-NN, which represents protein structures as point clouds and learns interaction information from protein interfaces by applying a point cloud neural network. With the continuous advancement of deep learning in the field of biology, a series of knowledge-rich pre-trained models have emerged. We incorporate protein surface representation models and language models into our approach, greatly enhancing feature representation capabilities and achieving superior performance in protein docking model scoring tasks. Through comprehensive testing on public datasets, we find that our method outperforms state-of-the-art deep learning approaches in protein-protein docking model scoring. Not only does it significantly improve performance, but it also greatly accelerates training speed. This study demonstrates the potential of our approach in addressing protein interaction assessment problems, providing strong support for future research and applications in the field of biology.

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

UNASSIGNED: HMGB1 is a non-histone chromatin protein released or secreted in response to tissue damage or infection. Extracellular HMGB1, as a crucial immunomodulatory factor, binds with several different receptors to innate inflammatory responses that aggravate acute and chronic liver diseases. The increased levels of HMGB1 have been reported in various liver diseases, highlighting that it represents a potential biomarker and druggable target for therapeutic development.
UNASSIGNED: This review summarizes the current knowledge on the structure, function, and interacting receptors of HMGB1 and its significance in multiple liver diseases. The latest patented and preclinical studies of HMGB1 inhibitors (antibodies, peptides, and small molecules) for liver diseases are summarized by using the keywords \'HMGB1,\' \'HMGB1 antagonist, HMGB1-inhibitor,\' \'liver disease\' in Web of Science, Google Scholar, Google Patents, and PubMed databases in the year from 2017 to 2023.
UNASSIGNED: In recent years, extensive research on HMGB1-dependent inflammatory signaling has discovered potent inhibitors of HMGB1 to reduce the severity of liver injury. Despite significant progress in the development of HMGB1 antagonists, few of them are approved for clinical treatment of liver-related diseases. Developing safe and effective specific inhibitors for different HMGB1 isoforms and their interaction with receptors is the focus of future research.

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 .

Apoptosis signaling controls the cell cycle through the protein-protein interactions (PPIs) of its major B-cell lymphoma 2-associated x protein (BAX) and B-cell lymphoma 2 protein (Bcl-2). Due to the antagonistic function of both proteins, apoptosis depends on a properly tuned balance of the kinetics of BAX and Bcl-2 activities. The utilization of natural polyphenols to regulate the binding process of PPIs is feasible. However, the mechanism of this modulation has not been studied in detail. Here, we utilized atomic force microscopy (AFM) to evaluate the effects of polyphenols (kaempferol, quercetin, dihydromyricetin, baicalin, curcumin, rutin, epigallocatechin gallate, and gossypol) on the BAX/Bcl-2 binding mechanism. We demonstrated at the molecular scale that polyphenols quantitatively affect the interaction forces, kinetics, thermodynamics, and structural properties of BAX/Bcl-2 complex formation. We observed that rutin, epigallocatechin gallate, and baicalin reduced the binding affinity of BAX/Bcl-2 by an order of magnitude. Combined with surface free energy and molecular docking, the results revealed that polyphenols are driven by multiple forces that affect the orientation freedom of PPIs, with hydrogen bonding, hydrophobic interactions, and van der Waals forces being the major contributors. Overall, our work provides valuable insights into how molecules tune PPIs to modulate their function.

Protein-protein interactions play an important role in various biological processes. Interaction among proteins has a wide range of applications. Therefore, the correct identification of protein-protein interactions sites is crucial. In this paper, we propose a novel predictor for protein-protein interactions sites, AGF-PPIS, where we utilize a multi-head self-attention mechanism (introducing a graph structure), graph convolutional network, and feed-forward neural network. We use the Euclidean distance between each protein residue to generate the corresponding protein graph as the input of AGF-PPIS. On the independent test dataset Test_60, AGF-PPIS achieves superior performance over comparative methods in terms of seven different evaluation metrics (ACC, precision, recall, F1-score, MCC, AUROC, AUPRC), which fully demonstrates the validity and superiority of the proposed AGF-PPIS model. The source codes and the steps for usage of AGF-PPIS are available at https://github.com/fxh1001/AGF-PPIS.