Prediction Of Sites Research Articles

Autonomous UAV forced landing site prediction using machine learning

Autonomous UAV forced landing site prediction using machine learning

Modeling Chromatography Binding through Molecular Dynamics Simulations with Resin Fragments.

Accurate atomistic modeling of the interactions of a chromatography resin with a solute can inform the selection of purification conditions for a product, an important problem in the biotech and pharmaceutical industries. We present a molecular dynamics simulation-based approach for the qualitative prediction of interaction sites (specificity) and retention times (affinity) of a protein for a given chromatography resin. We mimicked the resin with an unrestrained ligand composed of the resin headgroup coupled with successively larger fragments of the agarose backbone. The interactions of the ligand with the protein are simulated in an explicit solvent using the Replica Exchange Molecular Dynamics enhanced sampling approach in conjunction with Hydrogen Mass Repartitioning (REMD-HMR). We computed the ligand interaction surface from the simulation trajectories and correlated the features of the interaction surface with experimentally determined retention times. The simulation and analysis protocol were first applied to a series of ubiquitin mutants for which retention times on Capto MMC resin are available. The ubiquitin simulations helped identify the optimal ligand that was used in subsequent simulations on six proteins for which Capto MMC elution times are available. For each of the six proteins, we computed the interaction surface and characterized it in terms of a range of simulation-averaged residue-level physicochemical descriptors. Modeling of the salt concentrations required for elution with respect to the descriptors resulted in a linear fit in terms of aromaphilicity and Kyte-Doolittle hydrophobicity that was robust to outliers, showed high correlation, and correctly ranked the protein elution order. The physics-based model building approach described here does not require a large experimental data set and can be readily applied to different resins and diverse biomolecules.

Placental Transcriptome Analysis in Connection with Low Litter Birth Weight Phenotype (LBWP) Sows.

It is possible to identify sub-populations of sows in every pig herd that consistently give birth to low birth weight (BW) piglets, irrespective of the litter size. A previous study from our group demonstrated that placental development is a main factor affecting the litter birth weight phenotype (LBWP) in sows, thereby impacting the BW of entire litters, but the biological and molecular pathways behind this phenomenon are largely unknown. The aim of this study was to investigate the differential gene expression in placental tissues at day 30 of gestation between low LBWP (LLBWP) vs. high LBWP (HLBWP) sows from a purebred Large White maternal line. Using mRNA sequencing, we found 45 differentially expressed genes (DEGs) in placental tissues of LLBWP and HLBWP sows. Furthermore, (GO) enrichment of upregulated DEGs predicted that there were two biological processes significantly related to cornification and regulation of cell population proliferation. To better understand the molecular interaction between cell proliferation and cornification, we conducted transcriptional factor binding site (TFBS) prediction analysis. The results indicated that a highly significant TFBS was located at the 5' upstream of all four upregulated genes (CDSN, DSG3, KLK14, KRT17), recognized by transcription factors EGR4 and FOSL1. Our findings provide novel insight into how transcriptional regulation of two different biological processes interact in placental tissues of LLBWP sows.

Computational Strategies in Drug Discovery: Leveraging Subtractive Genomic Analysis for Target Identification.

The utilization of In-silico subtractive genomic analysis has emerged as an important and essential method in modern drug discovery and development since it significantly improves the process of identifying and validating potential targets for discovering novel therapeutic compounds to treat severe infections caused by Antimicrobial-resistant (AMR) - pathogenic species. This review provides a complete overview of the methodology, advantages, disadvantages, and prospects, associated with subtractive genomic research in the context of drug discovery and development. The initial phase of analysis encompasses the retrieval of data, which serves as a foundation for the subsequent data mining process in Phase 1. After data mining, Phase 2 utilizes subtractive channels for the target's non-homology and essentiality analysis. Phase 3 of the study aims to provide a comprehensive understanding of prospective targets by their qualitative characterization. Further, Phase 4 of the study emphasizes on conducting structure-based analyses, which involves the determination, refinement, evaluation, and validation of three-dimensional structures of the target proteins, along with their active site prediction and selection of the novel therapeutic compounds against that active site on the obtained targets through virtual screening and docking studies by utilizing various databases and servers. The therapeutic compounds obtained can be then validated by in vitro and in vivo testing, thereby establishing a connection between the computational predictions and real applications.

Circ_0000592 facilitates the progression of esophageal squamous cell carcinoma via miR-155-5p/FZD5 axis.

Esophageal squamous cell carcinoma (ESCC) is one of the gastrointestinal malignancies with high prevalence and poor prognosis. Previous reports suggested that circular ribose nucleic acidsmight exert regulatory functions in ESCC. This study aims to explore the role of circ_0000592 in ESCC progression, providing novel insights into the diagnosis and therapeutic avenues for ESCC. The GSE131969 data set was utilized to assess circ_0000592 expression in ESCC. The validation was performed in the tumorous tissues of ESCC patients (n = 80) and human-immortalized ESCC cell lines. The correlation between circ_0000592 expression and prognosis was analyzed. The impact of circ_0000592 on ESCC cell activity was evaluated through downregulating circ_0000592, as well as encompassing cell viability, migration, and invasion abilities. The downstream pathway of circ_0000592 was explored by binding site prediction from the TargetScan database, followed by in vitro and in vivo experiments. An in vivo xenograft tumor model was established to highlight the role of circ_0000592 in ESCC. Patients with ESCC exhibited higher circ_0000592 expression levels compared to noncancerous patients, which were associated with reduced survival time, higher TNM stage, and increased lymph node metastasis. The circ_0000592 downregulation suppressed cell viability, migration, and invasion abilities in vitro. Mechanistically, circ_0000592 countered the inhibitory effects on the target gene Frizzled 5 (FZD5) through interactions with miR-155-5p. The overexpression of miR-155-5p curtailed the luciferase activity of circ_0000592 in ESCC cells, inhibiting downstream molecule FZD5 protein expression and subsequently mitigating the detrimental consequences of escalated circ_0000592 expression in ESCC cells. Consistently, circ_0000592 downregulation curbed proliferation and metastasis of ESCC tumors in vivo. In summary, circ_0000592 promoted the progress of ESCC by counteracting the inhibitory impact on FZD5 through its interaction with miR-155-5p. Together, our findings highlighted circ_0000592 as a prospective therapeutic target for ESCC.

EGPDI: identifying protein-DNA binding sites based on multi-view graph embedding fusion.

Mechanisms of protein-DNA interactions are involved in a wide range of biological activities and processes. Accurately identifying binding sites between proteins and DNA is crucial for analyzing genetic material, exploring protein functions, and designing novel drugs. In recent years, several computational methods have been proposed as alternatives to time-consuming and expensive traditional experiments. However, accurately predicting protein-DNA binding sites still remains a challenge. Existing computational methods often rely on handcrafted features and a single-model architecture, leaving room for improvement. We propose a novel computational method, called EGPDI, based on multi-view graph embedding fusion. This approach involves the integration of Equivariant Graph Neural Networks (EGNN) and Graph Convolutional Networks II (GCNII), independently configured to profoundly mine the global and local node embedding representations. An advanced gated multi-head attention mechanism is subsequently employed to capture the attention weights of the dual embedding representations, thereby facilitating the integration of node features. Besides, extra node features from protein language models are introduced to provide more structural information. To our knowledge, this is the first time that multi-view graph embedding fusion has been applied to the task of protein-DNA binding site prediction. The results of five-fold cross-validation and independent testing demonstrate that EGPDI outperforms state-of-the-art methods. Further comparative experiments and case studies also verify the superiority and generalization ability of EGPDI.

GAPS: a geometric attention-based network for peptide binding site identification by the transfer learning approach.

Protein-peptide interactions (PPepIs) are vital to understanding cellular functions, which can facilitate the design of novel drugs. As an essential component in forming a PPepI, protein-peptide binding sites are the basis for understanding the mechanisms involved in PPepIs. Therefore, accurately identifying protein-peptide binding sites becomes a critical task. The traditional experimental methods for researching these binding sites are labor-intensive and time-consuming, and some computational tools have been invented to supplement it. However, these computational tools have limitations in generality or accuracy due to the need for ligand information, complex feature construction, or their reliance on modeling based on amino acid residues. To deal with the drawbacks of these computational algorithms, we describe a geometric attention-based network for peptide binding site identification (GAPS) in this work. The proposed model utilizes geometric feature engineering to construct atom representations and incorporates multiple attention mechanisms to update relevant biological features. In addition, the transfer learning strategy is implemented for leveraging the protein-protein binding sites information to enhance the protein-peptide binding sites recognition capability, taking into account the common structure and biological bias between proteins and peptides. Consequently, GAPS demonstrates the state-of-the-art performance and excellent robustness in this task. Moreover, our model exhibits exceptional performance across several extended experiments including predicting the apo protein-peptide, protein-cyclic peptide and the AlphaFold-predicted protein-peptide binding sites. These results confirm that the GAPS model is a powerful, versatile, stable method suitable for diverse binding site predictions.

UbNiRF: A Hybrid Framework Based on Null Importances and Random Forest that Combines Multiple Features to Predict Ubiquitination Sites in Arabidopsis thaliana and Homo sapiens.

Ubiquitination is a crucial post-translational modification of proteins that regulates diverse cellular functions. Accurate identification of ubiquitination sites in proteins is vital for understanding fundamental biological mechanisms, such as cell cycle and DNA repair. Conventional experimental approaches are resource-intensive, whereas machine learning offers a cost-effective means of accurately identifying ubiquitination sites. The prediction of ubiquitination sites is species-specific, with many existing models being tailored for Arabidopsis thaliana (A. thaliana) and Homo sapiens (H. sapiens). However, these models have shortcomings in sequence window selection and feature extraction, leading to suboptimal performance. This study initially employed the chi-square test to determine the optimal sequence window. Subsequently, a combination of six features was assessed: Binary Encoding (BE), Composition of K-Spaced Amino Acid Pair (CKSAAP), Enhanced Amino Acid Composition (EAAC), Position Weight Matrix (PWM), 531 Properties of Amino Acids (AA531), and Position-Specific Scoring Matrix (PSSM). Comparative evaluation involved three feature selection methods: Minimum Redundancy-Maximum Relevance (mRMR), Elastic net, and Null importances. Alongside these were four classifiers: Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The Null importances combined with the RF model exhibited superior predictive performance, and was denoted as UbNiRF (A. thaliana: ArUbNiRF; H. sapiens: HoUbNiRF). A comprehensive assessment indicated that UbNiRF is superior to existing prediction tools across five performance metrics. It notably excelled in the Matthews Correlation Coefficient (MCC), with values of 0.827 for the A. thaliana dataset and 0.781 for the H. sapiens dataset. Feature analysis underscores the significance of integrating six features and demonstrates their critical role in enhancing model performance. UbNiRF is a valuable predictive tool for identifying ubiquitination sites in both A. thaliana and H. sapiens. Its robust performance and species-specific discovery capabilities make it extremely useful for elucidating biological processes and disease mechanisms associated with ubiquitination.

BiLSTM- and CNN-Based m6A Modification Prediction Model for circRNAs.

m6A methylation, a ubiquitous modification on circRNAs, exerts a profound influence on RNA function, intracellular behavior, and diverse biological processes, including disease development. While prediction algorithms exist for mRNA m6A modifications, a critical gap remains in the prediction of circRNA m6A modifications. Therefore, accurate identification and prediction of m6A sites are imperative for understanding RNA function and regulation. This study presents a novel hybrid model combining a convolutional neural network (CNN) and a bidirectional long short-term memory network (BiLSTM) for precise m6A methylation site prediction in circular RNAs (circRNAs) based on data from HEK293 cells. This model exploits the synergy between CNN's ability to extract intricate sequence features and BiLSTM's strength in capturing long-range dependencies. Furthermore, the integrated attention mechanism empowers the model to pinpoint critical biological information for studying circRNA m6A methylation. Our model, exhibiting over 78% prediction accuracy on independent datasets, offers not only a valuable tool for scientific research but also a strong foundation for future biomedical applications. This work not only furthers our understanding of gene expression regulation but also opens new avenues for the exploration of circRNA methylation in biological research.

Construction of a Model for Predicting the Risk of pT3 Based on Perioperative Characteristics in cT1 Renal Cell Carcinoma: A Retrospective Study at a Single Institution

IntroductionThis study explored the predictors of upstaging and multiple sites of extension, and constructed a predictive model based on perioperative characteristics to calculate the risk of upstaging of cT1 renal cell carcinoma to pT3. MethodsWe retrospectively reviewed 1012 patients diagnosed with cT1 renal cell carcinoma who underwent surgical treatment at the Affiliated Hospital of Qingdao University between June 2016 and August 2021. The continuous and categorical variables were analyzed using the Mann–Whitney U test and Chi-square test, respectively. After randomly dividing patients into a training set and an internal validation set with a ratio of 7:3, univariate and multivariate logistic regression analyses were used to explore the predictors of upstaging and multiple sites of extension. A nomogram model was established based on the predictors of upstaging and was validated. ResultsNinety-one cases (8.99%) of renal cell carcinoma were upstaged to pT3. In the training set, multivariate logistic regression identified the following predictors of upstaging: maximum tumor diameter, hilus involvement, tumor necrosis, tumor edge irregularity, symptoms, smoking, and platelet–lymphocyte ratio. A nomogram model was established based on the predictors. The area under the receiver operating characteristic curve was 0.810 in the training set, and 0.804 in the validation set. A 10-fold internal cross-validation conducted 200 times showed that the mean area under the curve was 0.797. The calibration curve and decision curve analysis suggested that the nomogram had robust clinical predictive power. Analyses showed higher neutrophil–lymphocyte ratio and tumor necrosis were associated with multiple sites of extrarenal extension in patients with pT3a renal cell carcinoma. ConclusionsWe identified 7 predictors of upstaging to pT3 and 2 predictors of multiple sites of extension. A nomogram model was constructed with satisfactory accuracy for predicting upstaging to pT3.

Experimental validation of a PNS-optimized whole-body gradient coil.

Peripheral nerve stimulation (PNS) limits the usability of state-of-the-art whole-body and head-only MRI gradient coils. We used detailed electromagnetic and neurodynamic modeling to set an explicit PNS constraint during the design of a whole-body gradient coil and constructed it to compare the predicted and experimentally measured PNS thresholds to those of a matched design without PNS constraints. We designed, constructed, and tested two actively shielded whole-body Y-axis gradient coil winding patterns: YG1 is a conventional symmetric design without PNS-optimization, whereas YG2's design used an additional constraint on the allowable PNS threshold in the head-imaging landmark, yielding an asymmetric winding pattern. We measured PNS thresholds in 18 healthy subjects at five landmark positions (head, cardiac, abdominal, pelvic, and knee). The PNS-optimized design YG2 achieved 46% higher average experimental thresholds for a head-imaging landmark than YG1 while incurring a 15% inductance penalty. For cardiac, pelvic, and knee imaging landmarks, the PNS thresholds increased between +22% and +35%. For abdominal imaging, PNS thresholds did not change significantly between YG1 and YG2 (-3.6%). The agreement between predicted and experimental PNS thresholds was within 11.4% normalized root mean square error for both coils and all landmarks. The PNS model also produced plausible predictions of the stimulation sites when compared to the sites of perception reported by the subjects. The PNS-optimization improved the PNS thresholds for the target scan landmark as well as most other studied landmarks, potentially yielding a significant improvement in image encoding performance that can be safely used in humans.

Computational prediction of phosphorylation sites of SARS-CoV-2 infection using feature fusion and optimization strategies

SARS-CoV-2′s global spread has instigated a critical health and economic emergency, impacting countless individuals. Understanding the virus's phosphorylation sites is vital to unravel the molecular intricacies of the infection and subsequent changes in host cellular processes. Several computational methods have been proposed to identify phosphorylation sites, typically focusing on specific residue (S/T) or Y phosphorylation sites. Unfortunately, current predictive tools perform best on these specific residues and may not extend their efficacy to other residues, emphasizing the urgent need for enhanced methodologies. In this study, we developed a novel predictor that integrated all the residues (STY) phosphorylation sites information. We extracted ten different feature descriptors, primarily derived from composition, evolutionary, and position-specific information, and assessed their discriminative power through five classifiers. Our results indicated that Light Gradient Boosting (LGB) showed superior performance, and five descriptors displayed excellent discriminative capabilities. Subsequently, we identified the top two integrated features have high discriminative capability and trained with LGB to develop the final prediction model, LGB-IPs. The proposed approach shows an excellent performance on 10-fold cross-validation with an ACC, MCC, and AUC values of 0.831, 0.662, 0.907, respectively. Notably, these performances are replicated in the independent evaluation. Consequently, our approach may provide valuable insights into the phosphorylation mechanisms in SARS-CoV-2 infection for biomedical researchers.

The 3'UTR Polymorphisms in the NLRP3 Gene Associated with the Risk of COPD and Their Putative Effects on the microRNA Mechanism.

Aims: Evaluating the association between a single nucleotide polymorphism in the 3' untranslated region (3'UTR) of the miRNA binding site of the NLRP3 gene and the occurrence and development of chronic obstructive pulmonary disease (COPD) and providing information to aid in the early detection and treatment of COPD. Materials and Methods: The regulatory single nuclear polymorphisms (SNPs) located in NLRP3 3'UTR were searched by using the dbSNP database and miRNA binding site prediction database. Meanwhile, samples from COPD patients and healthy controls in the same period were used for verification. The clinical baseline information of all subjects was collected, and the transcription level and protein expression level of NLRP3 and the expression level of inflammatory factors downstream of NLRP3 were detected. The effects of SNPs' single nucleotide changes on the transcription and expression of inflammatory factors were analyzed. Results: The study included 418 participants (249 in the COPD group and 169 in the control group). NLRP3 SNPs with miRNA binding sites include rs10754558 (G > C), rs1664774076 (ATAT > del), and rs1664775106 (C > G). Furthermore, two genotypes, GCG and GCA, were discovered to have a linkage mutation at 3'UTR 459-461. COPD susceptibility is tightly associated with the expression of the rs1664774076 del/del genotype, and the risk of COPD increased by 2.770 times (p = 0.003). Type 459-461 GCA was substantially related to the likelihood of developing COPD at various stages (p < 0.05). Except for rs10754558, all homozygous mutants increased NLRP3 mRNA and protein levels. NLRP3 had the greatest area under the receiver operating characteristic (ROC) curve for predicting the development and diagnosis of COPD when compared with its downstream inflammatory variables (AUC = 0.9291). Conclusions: The NLRP3 rs1664774076 del/del genotype is a COPD susceptibility gene, and the GCA genotype at 459-461 can be used as an early predictor of COPD exacerbation. The NLRP3 3'UTR polymorphism may alter the loss of miRNA binding sites, leading to an increase in NLRP3 expression. In the development of COPD, NLRP3 has a better diagnostic value than traditional inflammatory factors. The Clinical Trials Registration number Z: protocol KY01-2020-11-06.

Prediction of Transcription Factor Binding Sites on Cell-Free DNA Based on Deep Learning.

Transcription factors (TFs) are important regulatory elements for vital cellular activities, and the identification of transcription factor binding sites (TFBS) can help to explore gene regulatory mechanisms. Research studies have proved that cfDNA (cell-free DNA) shows relatively higher coverage at TFBS due to the protection by TF from degradation by nucleases and short fragments of cfDNA are enriched in TFBS. However, there are still great difficulties in the noninvasive identification of TFBSs from experimental techniques. In this study, we propose a deep learning-based approach that can noninvasively predict TFBSs of cfDNA by learning sequence information from known TFBSs through convolutional neural networks. Under the addition of long short-term memory, our model achieved an area under the curve of 84%. Based on this model to predict cfDNA, we found consistent motifs in cfDNA fragments and lower coverage occurred upstream and downstream of these cfDNA fragments, which is consistent with a previous study. We also found that the binding sites of the same TF differ in different cell lines. TF-specific target genes were detected from cfDNA and were enriched in cancer-related pathways. In summary, our method of locating TFBSs from plasma has the potential to reflect the intrinsic regulatory mechanism from a noninvasive perspective and provide technical guidance for dynamic monitoring of disease in clinical practice.

Comparative toxicity assessment of fisetin-aided artificial intelligence-assisted drug design targeting epibulbar dermoid through phytochemicals

Abstract Epibulbar dermoid, benign tumors resulting from the improper function of the pathogenic protein Patched 1 (PTCH1), surgical interventions are employed to mitigate the lethal effects. However, these procedures often lead to complications such as scleral weakening and corneal astigmatism. Due to the absence of effective medical treatments, there is a critical need for novel approaches to prevent the spread of this disease. This study not only fills a key gap in medical therapy for epibulbar dermoid, but it also demonstrates AI’s transformational potential in drug development. Employing an AI drug design service, three efficient de novo therapeutic compounds targeting the PTCH1 protein were crafted with Fisetin. The method included obtaining the PTCH1 protein sequence from NCBI, computing physiochemical parameters with Expasy Protparam, and estimating the 3D structure with SWISS-MODEL. Quality assessment, binding site prediction, drug design with WADDAICA, Lipinski’s Rule of 5, toxicity screening, ADMET evaluation, docking analysis with CB-dock and Patch dock, and MD simulations with IMOD all work together to provide an adequate basis for the development and validation of AI-designed phytochemical medicines for epibulbar dermoid. Comprehensive pharmacokinetic and toxicity assessments demonstrated the outstanding absorbency of AI-designed Fisetin in the blood–brain barrier, emphasizing its non-toxic nature. The AI-designed Fisetin exhibits a notable affinity of approximately −9.2 kcal/mol during docking with the PTCH1 protein, suggesting its potential as a drug. While the in silico results indicate efficiency and safety, the necessity for in vivo testing is acknowledged to validate these promising findings. This research significantly advances the frontier of knowledge by proposing a non-invasive solution to epibulbar dermoid, addressing current limitations, and offering potential alternatives to conventional surgical interventions.

MLm5C: A high-precision human RNA 5-methylcytosine sites predictor based on a combination of hybrid machine learning models

RNA modification serves as a pivotal component in numerous biological processes. Among the prevalent modifications, 5-methylcytosine (m5C) significantly influences mRNA export, translation efficiency and cell differentiation and are also associated with human diseases, including Alzheimer’s disease, autoimmune disease, cancer, and cardiovascular diseases. Identification of m5C is critically responsible for understanding the RNA modification mechanisms and the epigenetic regulation of associated diseases. However, the large-scale experimental identification of m5C present significant challenges due to labor intensity and time requirements. Several computational tools, using machine learning, have been developed to supplement experimental methods, but identifying these sites lack accuracy and efficiency. In this study, we introduce a new predictor, MLm5C, for precise prediction of m5C sites using sequence data. Briefly, we evaluated eleven RNA sequence-derived features with four basic machine learning algorithms to generate baseline models. From these 44 models, we ranked them based on their performance and subsequently stacked the Top 20 baseline models as the best model, named MLm5C. The MLm5C outperformed the-state-of-the-art predictors. Notably, the optimization of the sequence length surrounding the modification sites significantly improved the prediction performance. MLm5C is an invaluable tool in accelerating the detection of m5C sites within the human genome, thereby facilitating in the characterization of their roles in post-transcriptional regulation.

D-CyPre: a machine learning-based tool for accurate prediction of human CYP450 enzyme metabolic sites

The advancement of graph neural networks (GNNs) has made it possible to accurately predict metabolic sites. Despite the combination of GNNs with XGBOOST showing impressive performance, this technology has not yet been applied in the realm of metabolic site prediction. Previous metabolic site prediction tools focused on bonds and atoms, regardless of the overall molecular skeleton. This study introduces a novel tool, named D-CyPre, that amalgamates atom, bond, and molecular skeleton information via two directed message-passing neural networks (D-MPNN) to predict the metabolic sites of the nine cytochrome P450 enzymes using XGBOOST. In D-CyPre Precision Mode, the model produces fewer, but more accurate results (Jaccard score: 0.497, F1: 0.660, and precision: 0.737 in the test set). In D-CyPre Recall Mode, the model produces less accurate, but more comprehensive results (Jaccard score: 0.506, F1: 0.669, and recall: 0.720 in the test set). In the test set of 68 reactants, D-CyPre outperformed BioTransformer on all isoenzymes and CyProduct on most isoenzymes (5/9). For the subtypes where D-CyPre outperformed CyProducts, the Jaccard score and F1 scores increased by 24% and 16% in Precision Mode (4/9) and 19% and 12% in Recall Mode (5/9), respectively, relative to the second-best CyProduct. Overall, D-CyPre provides more accurate prediction results for human CYP450 enzyme metabolic sites.

GPS-SUMO 2.0: an updated online service for the prediction of SUMOylation sites and SUMO-interacting motifs.

Small ubiquitin-like modifiers (SUMOs) are tiny but important protein regulators involved in orchestrating a broad spectrum of biological processes, either by covalently modifying protein substrates or by noncovalently interacting with other proteins. Here, we report an updated server, GPS-SUMO 2.0, for the prediction of SUMOylation sites and SUMO-interacting motifs (SIMs). For predictor training, we adopted three machine learning algorithms, penalized logistic regression (PLR), a deep neural network (DNN), and a transformer, and used 52404 nonredundant SUMOylation sites in 8262 proteins and 163 SIMs in 102 proteins. To further increase the accuracy of predicting SUMOylation sites, a pretraining model was first constructed using 145545 protein lysine modification sites, followed by transfer learning to fine-tune the model. GPS-SUMO 2.0 exhibited greater accuracy in predicting SUMOylation sites than did other existing tools. For users, one or multiple protein sequences or identifiers can be input, and the prediction results are shown in a tabular list. In addition to the basic statistics, we integrated knowledge from 35 public resources to annotate SUMOylation sites or SIMs. The GPS-SUMO 2.0 server is freely available at https://sumo.biocuckoo.cn/. We believe that GPS-SUMO 2.0 can serve as a useful tool for further analysis of SUMOylation and SUMO interactions.

MR2CPPIS: Accurate prediction of protein–protein interaction sites based on multi-scale Res2Net with coordinate attention mechanism

Proteins play a vital role in various biological processes and achieve their functions through protein–protein interactions (PPIs). Thus, accurate identification of PPI sites is essential. Traditional biological methods for identifying PPIs are costly, labor-intensive, and time-consuming. The development of computational prediction methods for PPI sites offers promising alternatives. Most known deep learning (DL) methods employ layer-wise multi-scale CNNs to extract features from protein sequences. But, these methods usually neglect the spatial positions and hierarchical information embedded within protein sequences, which are actually crucial for PPI site prediction. In this paper, we propose MR2CPPIS, a novel sequence-based DL model that utilizes the multi-scale Res2Net with coordinate attention mechanism to exploit multi-scale features and enhance PPI site prediction capability. We leverage the multi-scale Res2Net to expand the receptive field for each network layer, thus capturing multi-scale information of protein sequences at a granular level. To further explore the local contextual features of each target residue, we employ a coordinate attention block to characterize the precise spatial position information, enabling the network to effectively extract long-range dependencies. We evaluate our MR2CPPIS on three public benchmark datasets (Dset 72, Dset 186, and PDBset 164), achieving state-of-the-art performance. The source codes are available at https://github.com/YyinGong/MR2CPPIS.

Accurate Prediction of Lysine Methylation Sites Using Evolutionary and Structural-Based Information

Methylation is considered one of the proteins’ most important post-translational modifications (PTM). Plasticity and cellular dynamics are among the many traits that are regulated by methylation. Currently, methylation sites are identified using experimental approaches. However, these methods are time-consuming and expensive. With the use of computer modelling, methylation sites can be identified quickly and accurately, providing valuable information for further trial and investigation. In this study, we propose a new machine-learning model called MeSEP to predict methylation sites that incorporates both evolutionary and structural-based information. To build this model, we first extract evolutionary and structural features from the PSSM and SPD2 profiles, respectively. We then employ Extreme Gradient Boosting (XGBoost) as the classification model to predict methylation sites. To address the issue of imbalanced data and bias towards negative samples, we use the SMOTETomek-based hybrid sampling method. The MeSEP was validated on an independent test set (ITS) and 10-fold cross-validation (TCV) using lysine methylation sites. The method achieved: an accuracy of 82.9% in ITS and 84.6% in TCV; precision of 0.92 in ITS and 0.94 in TCV; area under the curve values of 0.90 in ITS and 0.92 in TCV; F1 score of 0.81 in ITS and 0.83 in TCV; and MCC of 0.67 in ITS and 0.70 in TCV. MeSEP significantly outperformed previous studies found in the literature. MeSEP as a standalone toolkit and all its source codes are publicly available at https://github.com/arafatro/MeSEP.