MOTIVATION: Accurately predicting the drug-target binding affinity (DTA) is crucial to drug discovery and repurposing. Although deep learning has been widely used in this field, it still faces challenges with insufficient generalization performance, inadequate use of 3D information, and poor interpretability. RESULTS: To alleviate these problems, we developed the PocketDTA model. This model enhances the generalization performance by pre-trained models ESM-2 and GraphMVP. It ingeniously handles the first 3 (top-3) target binding pockets and drug 3D information through customized GVP-GNN Layers and GraphMVP-Decoder. In addition, it uses a bilinear attention network to enhance interpretability. Comparative analysis with state-of-the-art (SOTA) methods on the optimized Davis and KIBA datasets reveals that the PocketDTA model exhibits significant performance advantages. Further, ablation studies confirm the effectiveness of the model components, whereas cold-start experiments illustrate its robust generalization capabilities. In particular, the PocketDTA model has shown significant advantages in identifying key drug functional groups and amino acid residues via molecular docking and literature validation, highlighting its strong potential for interpretability. AVAILABILITY AND IMPLEMENTATION: Code and data are available at: https://github.com/zhaolongNCU/PocketDTA.

Protein arginine methylation is an important posttranslational modification (PTM) associated with protein functional diversity and pathological conditions including cancer. Identification of methylation binding sites facilitates a better understanding of the molecular function of proteins. Recent developments in the field of deep neural networks have led to a proliferation of deep learning-based methylation identification studies because of their fast and accurate prediction. In this paper, we propose DeepGpgs, an advanced deep learning model incorporating Gaussian prior and gated attention mechanism. We introduce a residual network channel to extract the evolutionary information of proteins. Then we combine the adaptive embedding with bidirectional long short-term memory networks to form a context-shared encoder layer. A gated multi-head attention mechanism is followed to obtain the global information about the sequence. A Gaussian prior is injected into the sequence to assist in predicting PTMs. We also propose a weighted joint loss function to alleviate the false negative problem. We empirically show that DeepGpgs improves Matthews correlation coefficient by 6.3% on the arginine methylation independent test set compared with the existing state-of-the-art methylation site prediction methods. Furthermore, DeepGpgs has good robustness in phosphorylation site prediction of SARS-CoV-2, which indicates that DeepGpgs has good transferability and the potential to be extended to other modification sites prediction. The open-source code and data of the DeepGpgs can be obtained from https://github.com/saizhou1/DeepGpgs.

With the development of biotechnology, a large number of phosphorylation sites have been experimentally confirmed and collected, but only a few of them have kinase annotations. Since experimental methods to detect kinases at specific phosphorylation sites are expensive and accidental, some computational methods have been proposed to predict the kinase of these sites, but most methods only consider single sequence information or single functional network information. In this study, a new method Predicting Kinase of Specific Phosphorylation Sites (PKSPS) is developed to predict kinases of specific phosphorylation sites in human proteins by combining PKSPS-Net with PKSPS-Seq, which considers protein-protein interaction (PPI) network information and sequence information. For PKSPS-Net, kinase-kinase and substrate-substrate similarity are quantified based on the topological similarity of proteins in the PPI network, and maximum weighted bipartite matching algorithm is proposed to predict kinase-substrate relationship. In PKSPS-Seq, phosphorylation sequence enrichment analysis is used to analyze the similarity of local sequences around phosphorylation sites and predict the kinase of specific phosphorylation sites (KSP). PKSPS has been proved to be more effective than the PKSPS-Net or PKSPS-Seq on different sets of kinases. Further comparison results show that the PKSPS method performs better than existing methods. Finally, the case study demonstrates the effectiveness of the PKSPS in predicting kinases of specific phosphorylation sites. The open source code and data of the PKSPS can be obtained from https://github.com/guoxinyunncu/PKSPS.

Protein phosphorylation is a reversible and ubiquitous post-translational modification that primarily occurs at serine, threonine and tyrosine residues and regulates a variety of biological processes. In this paper, we first briefly summarized the current progresses in computational prediction of eukaryotic protein phosphorylation sites, which mainly focused on animals and plants, especially on human, with a less extent on fungi. Since the number of identified fungi phosphorylation sites has greatly increased in a wide variety of organisms and their roles in pathological physiology still remain largely unknown, more attention has been paid on the identification of fungi-specific phosphorylation. Here, experimental fungi phosphorylation sites data were collected and most of the sites were classified into different types to be encoded with various features and trained via a two-step feature optimization method. A novel method for prediction of species-specific fungi phosphorylation-PreSSFP was developed, which can identify fungi phosphorylation in seven species for specific serine, threonine and tyrosine residues (http://computbiol.ncu.edu.cn/PreSSFP). Meanwhile, we critically evaluated the performance of PreSSFP and compared it with other existing tools. The satisfying results showed that PreSSFP is a robust predictor. Feature analyses exhibited that there have some significant differences among seven species. The species-specific prediction via two-step feature optimization method to mine important features for training could considerably improve the prediction performance. We anticipate that our study provides a new lead for future computational analysis of fungi phosphorylation.

Accumulative studies have indicated that amino acid variations through changing the type of residues of the target sites or key flanking residues could directly or indirectly influence protein posttranslational modifications (PTMs) and bring about a detrimental effect on protein function. Computational mutation analysis can greatly narrow down the efforts on experimental work. To increase the utilization of current computational resources, we first provide an overview of computational prediction of amino acid variations that influence protein PTMs and their functional analysis. We also discuss the challenges that are faced while developing novel in silico approaches in the future. The development of better methods for mutation analysis-related protein PTMs will help to facilitate the development of personalized precision medicine.

MOTIVATION: Protein glycation is a familiar post-translational modification (PTM) which is a two-step non-enzymatic reaction. Glycation not only impairs the function but also changes the characteristics of the proteins so that it is related to many human diseases. It is still much more difficult to systematically detect glycation sites due to the glycated residues without crucial patterns. Computational approaches, which can filter supposed sites prior to experimental verification, can extremely increase the efficiency of experiment work. However, the previous lysine glycation prediction method uses a small number of training datasets. Hence, the model is not generalized or pervasive. RESULTS: By searching from a new database, we collected a large dataset in Homo sapiens. PredGly, a novel software, can predict lysine glycation sites for H.sapiens, which was developed by combining multiple features. In addition, XGboost was adopted to optimize feature vectors and to improve the model performance. Through comparing various classifiers, support vector machine achieved an optimal performance. On the basis of a new independent test set, PredGly outperformed other glycation tools. It suggests that PredGly can provide more instructive guidance for further experimental research of lysine glycation. AVAILABILITY AND IMPLEMENTATION: https://github.com/yujialinncu/PredGly. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Motivation: Lysine acetylation exists extensively in prokaryotes, and plays a vital role in function adjustment. Recent progresses in the identification of prokaryote acetylation substrates and sites provide a great opportunity to explore the difference of substrate site specificity between prokaryotic and eukaryotic acetylation. Motif analysis suggests that prokaryotic and eukaryotic acetylation sites have distinct location-specific difference, and it is necessary to develop a prokaryote-specific acetylation sites prediction tool. Results: Therefore, we collected nine species of prokaryote lysine acetylation data from various databases and literature, and developed a novel online tool named ProAcePred for predicting prokaryote lysine acetylation sites. Optimization of feature vectors via elastic net could considerably improve the prediction performance. Feature analyses demonstrated that evolutionary information played significant roles in prediction model for prokaryote acetylation. Comparison between our method and other tools suggested that our species-specific prediction outperformed other existing works. We expect that the ProAcePred could provide more instructive help for further experimental investigation of prokaryotes acetylation. Availability and implementation: http://computbiol.ncu.edu.cn/ProAcePred. Supplementary information: Supplementary data are available at Bioinformatics online.

MOTIVATION: Protein malonylation is a novel post-translational modification (PTM) which orchestrates a variety of biological processes. Annotation of malonylation in proteomics is the first-crucial step to decipher its physiological roles which are implicated in the pathological processes. Comparing with the expensive and laborious experimental research, computational prediction can provide an accurate and effective approach to the identification of many types of PTMs sites. However, there is still no online predictor for lysine malonylation. RESULTS: By searching from literature and database, a well-prepared up-to-data benchmark datasets were collected in multiple organisms. Data analyses demonstrated that different organisms were preferentially involved in different biological processes and pathways. Meanwhile, unique sequence preferences were observed for each organism. Thus, a novel malonylation site online prediction tool, called MaloPred, which can predict malonylation for three species, was developed by integrating various informative features and via an enhanced feature strategy. On the independent test datasets, AUC (area under the receiver operating characteristic curves) scores are obtained as 0.755, 0.827 and 0.871 for Escherichia coli ( E.coli ), Mus musculus ( M.musculus ) and Homo sapiens ( H.sapiens ), respectively. The satisfying results suggest that MaloPred can provide more instructive guidance for further experimental investigation of protein malonylation. AVAILABILITY AND IMPLEMENTATION: http://bioinfo.ncu.edu.cn/MaloPred.aspx . CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

As one of the most important reversible types of post-translational modification, protein methylation catalyzed by methyltransferases carries many pivotal biological functions as well as many essential biological processes. Identification of methylation sites is prerequisite for decoding methylation regulatory networks in living cells and understanding their physiological roles. Experimental methods are limitations of labor-intensive and time-consuming. While in silicon approaches are cost-effective and high-throughput manner to predict potential methylation sites, but those previous predictors only have a mixed model and their prediction performances are not fully satisfactory now. Recently, with increasing availability of quantitative methylation datasets in diverse species (especially in eukaryotes), there is a growing need to develop a species-specific predictor. Here, we designed a tool named PSSMe based on information gain (IG) feature optimization method for species-specific methylation site prediction. The IG method was adopted to analyze the importance and contribution of each feature, then select the valuable dimension feature vectors to reconstitute a new orderly feature, which was applied to build the finally prediction model. Finally, our method improves prediction performance of accuracy about 15% comparing with single features. Furthermore, our species-specific model significantly improves the predictive performance compare with other general methylation prediction tools. Hence, our prediction results serve as useful resources to elucidate the mechanism of arginine or lysine methylation and facilitate hypothesis-driven experimental design and validation. AVAILABILITY AND IMPLEMENTATION: The tool online service is implemented by C# language and freely available at http://bioinfo.ncu.edu.cn/PSSMe.aspx CONTACT: [email protected] information: Supplementary data are available at Bioinformatics online.

MOTIVATION: Protein phosphorylation is the most common post-translational modification (PTM) regulating major cellular processes through highly dynamic and complex signaling pathways. Large-scale comparative phosphoproteomic studies have frequently been done on whole cells or organs by conventional bottom-up mass spectrometry approaches, i.e at the phosphopeptide level. Using this approach, there is no way to know from where the phosphopeptide signal originated. Also, as a consequence of the scale of these studies, important information on the localization of phosphorylation sites in subcellular compartments (SCs) is not surveyed. RESULTS: Here, we present a first account of the emerging field of subcellular phosphoproteomics where a support vector machine (SVM) approach was combined with a novel algorithm of discrete wavelet transform (DWT) to facilitate the identification of compartment-specific phosphorylation sites and to unravel the intricate regulation of protein phosphorylation. Our data reveal that the subcellular phosphorylation distribution is compartment type dependent and that the phosphorylation displays site-specific sequence motifs that diverge between SCs. AVAILABILITY AND IMPLEMENTATION: The method and database both are available as a web server at: http://bioinfo.ncu.edu.cn/SubPhos.aspx. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

UNLABELLED: Lysine succinylation orchestrates a variety of biological processes. Annotation of succinylation in proteomes is the first-crucial step to decipher physiological roles of succinylation implicated in the pathological processes. In this work, we developed a novel succinylation site online prediction tool, called SuccFind, which is constructed to predict the lysine succinylation sites based on two major categories of characteristics: sequence-derived features and evolutionary-derived information of sequence and via an enhanced feature strategy for further optimizations. The assessment results obtained from cross-validation suggest that SuccFind can provide more instructive guidance for further experimental investigation of protein succinylation. AVAILABILITY AND IMPLEMENTATION: A user-friendly server is freely available on the web at: http://bioinfo.ncu.edu.cn/SuccFind.aspx. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Systematic dissection of the ubiquitylation proteome is emerging as an appealing but challenging research topic because of the significant roles ubiquitylation play not only in protein degradation but also in many other cellular functions. High-throughput experimental studies using mass spectrometry have identified many ubiquitylation sites, primarily from eukaryotes. However, the vast majority of ubiquitylation sites remain undiscovered, even in well-studied systems. Because mass spectrometry-based experimental approaches for identifying ubiquitylation events are costly, time-consuming and biased toward abundant proteins and proteotypic peptides, in silico prediction of ubiquitylation sites is a potentially useful alternative strategy for whole proteome annotation. Because of various limitations, current ubiquitylation site prediction tools were not well designed to comprehensively assess proteomes. RESULTS: We present a novel tool known as UbiProber, specifically designed for large-scale predictions of both general and species-specific ubiquitylation sites. We collected proteomics data for ubiquitylation from multiple species from several reliable sources and used them to train prediction models by a comprehensive machine-learning approach that integrates the information from key positions and key amino acid residues. Cross-validation tests reveal that UbiProber achieves some improvement over existing tools in predicting species-specific ubiquitylation sites. Moreover, independent tests show that UbiProber improves the areas under receiver operating characteristic curves by ~15% by using the Combined model. AVAILABILITY: The UbiProber server is freely available on the web at http://bioinfo.ncu.edu.cn/UbiProber.aspx. The software system of UbiProber can be downloaded at the same site. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.