Capsule network for protein post-translational modification site prediction

CapsNet-TIS: Predicting translation initiation site based on multi-feature fusion and improved capsule network

Genes are the basic units of protein synthesis in organisms, and accurately identifying the translation initiation site (TIS) of genes is crucial for understanding the regulation, transcription, and translation processes of genes. However, the existing models cannot adequately extract the feature information in TIS sequences, and they also inadequately capture the complex hierarchical relationships among features. Therefore, a novel predictor named CapsNet-TIS is proposed in this paper. CapsNet-TIS first fully extracts the TIS sequence information using four encoding methods, including One-hot encoding, physical structure property (PSP) encoding, nucleotide chemical property (NCP) encoding, and nucleotide density (ND) encoding. Next, multi-scale convolutional neural networks are used to perform feature fusion of the encoded features to enhance the comprehensiveness of the feature representation. Finally, the fused features are classified using capsule network as the main network of the classification model to capture the complex hierarchical relationships among the features. Moreover, we improve the capsule network by introducing residual block, channel attention, and BiLSTM to enhance the model's feature extraction and sequence data modeling capabilities. In this paper, the performance of CapsNet-TIS is evaluated using TIS datasets from four species: human, mouse, bovine, and fruit fly, and the effectiveness of each part is demonstrated by performing ablation experiments. By comparing the experimental results with models proposed by other researchers, the results demonstrate the superior performance of CapsNet-TIS.

CapsEnhancer: An Effective Computational Framework for Identifying Enhancers Based on Chaos Game Representation and Capsule Network

Enhancers are a class of noncoding DNA, serving as crucial regulatory elements in governing gene expression by binding to transcription factors. The identification of enhancers holds paramount importance in the field of biology. However, traditional experimental methods for enhancer identification demand substantial human and material resources. Consequently, there is a growing interest in employing computational methods for enhancer prediction. In this study, we propose a two-stage framework based on deep learning, termed CapsEnhancer, for the identification of enhancers and their strengths. CapsEnhancer utilizes chaos game representation to encode DNA sequences into unique images and employs a capsule network to extract local and global features from sequence "images". Experimental results demonstrate that CapsEnhancer achieves state-of-the-art performance in both stages. In the first and second stages, the accuracy surpasses the previous best methods by 8 and 3.5%, reaching accuracies of 94.5 and 95%, respectively. Notably, this study represents the pioneering application of computer vision methods to enhancer identification tasks. Our work not only contributes novel insights to enhancer identification but also provides a fresh perspective for other biological sequence analysis tasks.

N-GlycoPred: A hybrid deep learning model for accurate identification of N-glycosylation sites

Studies have shown that protein glycosylation in cells reflects the real-time dynamics of biological processes, and the occurrence and development of many diseases are closely related to protein glycosylation. Abnormal protein glycosylation can be used as a potential diagnostic and prognostic marker of a disease, as well as a therapeutic target and a new breakthrough point for exploring pathogenesis. To address the issue of significant differences in the prediction results of previous models for different species, we constructed a hybrid deep learning model N-GlycoPred on the basis of dual-layer convolution, a paired attention mechanism and BiLSTM for accurate identification of N-glycosylation sites. By adopting one-hot encoding or the AAindex, we specifically selected the optimum combination of features and deep learning frameworks for human and mouse to refine the models. Based on six independent test datasets, our N-GlycoPred model achieved an average AUC of 0.9553, which is 0.23% higher than MusiteDeep. The comparison results indicate that our model can serve as a powerful tool for N-glycosylation site prescreening for biological researchers.

Sitetack: A Deep Learning Model that Improves PTM Prediction by Using Known PTMs

Post-translational modifications (PTMs) increase the diversity of the proteome and are vital to organismal life and therapeutic strategies. Deep learning has been used to predict PTM locations. Still, limitations in datasets and their analyses compromise success. Here we evaluate the use of known PTM sites in prediction via sequence-based deep learning algorithms. Specifically, PTM locations were encoded as a separate amino acid before sequences were encoded via word embedding and passed into a convolutional neural network that predicts the probability of a modification at a given site. Without labeling known PTMs, our model is on par with others. With labeling, however, we improved significantly upon extant models. Moreover, knowing PTM locations can increase the predictability of a different PTM. Our findings highlight the importance of PTMs for the installation of additional PTMs. We anticipate that including known PTM locations will enhance the performance of other proteomic machine learning algorithms.

Prediction of protein N-terminal acetylation modification sites based on CNN-BiLSTM-attention model

N-terminal acetylation is one of the most common and important post-translational modifications (PTM) of eukaryotic proteins. PTM plays a crucial role in various cellular processes and disease pathogenesis. Thus, the accurate identification of N-terminal acetylation modifications is important to gain insight into cellular processes and other possible functional mechanisms. Although some algorithmic models have been proposed, most have been developed based on traditional machine learning algorithms and small training datasets. Their practical applications are limited. Nevertheless, deep learning algorithmic models are better at handling high-throughput and complex data. In this study, DeepCBA, a model based on the hybrid framework of convolutional neural network (CNN), bidirectional long short-term memory network (BiLSTM), and attention mechanism deep learning, was constructed to detect the N-terminal acetylation sites. The DeepCBA was built as follows: First, a benchmark dataset was generated by selecting low-redundant protein sequences from the Uniport database and further reducing the redundancy of the protein sequences using the CD-HIT tool. Subsequently, based on the skip-gram model in the word2vec algorithm, tripeptide word vector features were generated on the benchmark dataset. Finally, the CNN, BiLSTM, and attention mechanism were combined, and the tripeptide word vector features were fed into the stacked model for multiple rounds of training. The model performed excellently on independent dataset test, with accuracy and area under the curve of 80.51% and 87.36%, respectively. Altogether, DeepCBA achieved superior performance compared with the baseline model, and significantly outperformed most existing predictors. Additionally, our model can be used to identify disease loci and drug targets.

MVNN-HNHC:A multi-view neural network for identification of human non-histone crotonylation sites

Crotonylation on lysine sites in human non-histone proteins plays a crucial role in biology activities. However, because traditional experimental methods for crotonylation site identification are time-consuming and labor-intensive, computational prediction methods have become increasingly popular in recent years. Despite its significance, crotonylation site prediction has received less attention in non-histone proteins than in histones. In this study, we proposed a Multi-View Neural Network for identification of Human Non-Histone Crotonylation sites, named MVNN-HNHC. MVNN-HNHC integrated multi-view encoding features and adaptive encoding features through multi-channel neural network to deeply learn about attribute differences between crotonylation sites and non-crotonylation sites from various aspects. In MVNN-HNHC, convolutional neural networks can obtain local information from these features, and bidirectional long short term memory networks were utilized to extract sequence information. Then, we employ the attention mechanism to fuse the outputs of various feature extraction modules. Finally, the fully connection network acted as the classifier to predict whether a lysine site was crotonylation site or non-crotonylation site. Performance metrics on independent test set, including sensitivity, specificity, accuracy, Matthews correlation coefficient, and area under the curve (AUC) values reach 80.06 %, 75.77 %, 77.06 %, 0.5203, and 0.7792, respectively. To verify the effectiveness of this method, we carry out a series of experiments and the results show that MVNN-HNHC is an effective tool for predicting crotonylation sites in non-histone proteins. The data and code are available on https://github.com/xbbxhbc/junjun0612.git.

DF-Phos: Prediction of Protein Phosphorylation Sites by Deep Forest

Phosphorylation is the most important and studied post-translational modification (PTM), which plays a crucial role in protein function studies and experimental design. Many significant studies have been performed to predict phosphorylation sites using various machine-learning methods. Recently, several studies have claimed that deep learning-based methods are the best way to predict the phosphorylation sites because deep learning as an advanced machine learning method can automatically detect complex representations of phosphorylation patterns from raw sequences and thus offers a powerful tool to improve phosphorylation site prediction. In this study, we report DF-Phos, a new phosphosite predictor based on the Deep Forest to predict phosphorylation sites. In DF-Phos, the feature vector taken from the CkSAApair method is as input for a Deep Forest framework for predicting phosphorylation sites. The results of 10-fold cross-validation show that the Deep Forest method has the highest performance among other available methods. We implemented a Python program of DF-Phos, which is freely available for non-commercial use at https://github.com/zahiriz/DF-Phos Moreover, users can use it for various PTM predictions.

In Silico Analysis of Glutamate Receptors in Capsicum chinense: Structure, Evolution, and Molecular Interactions

Plant glutamate receptors (GLRs) are integral membrane proteins that function as non-selective cation channels, involved in the regulation of developmental events crucial in plants. Knowledge of these proteins is restricted to a few species and their true agonists are still unknown in plants. Using tomato SlGLRs, a search was performed in the pepper database to identify GLR sequences in habanero pepper (Capsicum chinense Jacq.). Structural, phylogenetic, and orthology analysis of the CcGLRs, as well as molecular docking and protein interaction networks, were conducted. Seventeen CcGLRs were identified, which contained the characteristic domains of GLR. The variation of conserved residues in the M2 transmembrane domain between members suggests a difference in ion selectivity and/or conduction. Also, new conserved motifs in the ligand-binding regions are reported. Duplication events seem to drive the expansion of the species, and these were located in the evolution by using orthologs. Molecular docking analysis allowed us to identify differences in the agonist binding pocket between CcGLRs, which suggest the existence of different affinities for amino acids. The possible interaction of some CcGLRs with proteins leads to suggesting specific functions for them within the plant. These results offer important functional clues for CcGLR, probably extrapolated to other Solanaceae.

Mannose-binding lectin gene polymorphism in psoriasis and vitiligo: an observational study and computational analysis

Introduction

Psoriasis and vitiligo are inflammatory autoimmune skin disorders with remarkable genetic involvement. Mannose-binding lectin (MBL) represents a significant immune molecule with one of its gene variants strongly linked to autoimmune diseases. Therefore, in this study, we investigated the role of the MBL variant, rs1800450, in psoriasis and vitiligo disease susceptibility.

Methods

The study comprised performing in silico analysis, performing an observational study regarding psoriasis patients, and performing an observational study regarding vitiligo patients. Various in silico tools were used to investigate the impact of the selected mutation on the function, stability, post-translational modifications (PTMs), and secondary structures of the protein. In addition, a total of 489 subjects were enrolled in this study, including their demographic and clinicopathological data. Genotyping analysis was performed using real-time PCR for the single nucleotide polymorphism (SNP) rs1800450 on codon 54 of the MBL gene, utilizing TaqMan genotyping technology. In addition, implications of the studied variant on disease susceptibility and various clinicopathological data were analyzed.

Results

Computational analysis demonstrated the anticipated effects of the mutation on MBL protein. Furthermore, regarding the observational studies, rs1800450 SNP on codon 54 displayed comparable results in our population relative to global frequencies reported via the 1,000 Genomes Project. This SNP showed no significant association with either psoriasis or vitiligo disease risk in all genetic association models. Furthermore, rs1800450 SNP did not significantly correlate with any of the demographic or clinicopathological features of both psoriasis and vitiligo.

Discussion

Our findings highlighted that the rs1800450 SNP on the MBL2 gene has no role in the disease susceptibility to autoimmune skin diseases, such as psoriasis and vitiligo, among Egyptian patients. In addition, our analysis advocated the notion of the redundancy of MBL and revealed the lack of significant impact on both psoriasis and vitiligo disorders.

SNO-DCA: A model for predicting S-nitrosylation sites based on densely connected convolutional networks and attention mechanism

Protein S-nitrosylation is a reversible oxidative reduction post-translational modification that is widely present in the biological community. S-nitrosylation can regulate protein function and is closely associated with a variety of diseases, thus identifying S-nitrosylation sites are crucial for revealing the function of proteins and related drug discovery. Traditional experimental methods are time-consuming and expensive; therefore, it is necessary to explore more efficient computational methods. Deep learning algorithms perform well in the field of bioinformatics sites prediction, and many studies show that they outperform existing machine learning algorithms. In this work, we proposed a deep learning algorithm-based predictor SNO-DCA for distinguishing between S-nitrosylated and non-S-nitrosylated sequences. First, one-hot encoding of protein sequences was performed. Second, the dense convolutional blocks were used to capture feature information, and an attention module was added to weigh different features to improve the prediction ability of the model. The 10-fold cross-validation and independent testing experimental results show that our SNO-DCA model outperforms existing S-nitrosylation sites prediction models under imbalanced data. In this paper, a web server prediction website: https://sno.cangmang.xyz/SNO-DCA/was established to provide an online prediction service for users. SNO-DCA can be available at https://github.com/peanono/SNO-DCA.

O-GlcNAcPRED-DL: Prediction of Protein O-GlcNAcylation Sites Based on an Ensemble Model of Deep Learning

O-linked β-N-acetylglucosamine (O-GlcNAc) is a post-translational modification (i.e., O-GlcNAcylation) on serine/threonine residues of proteins, regulating a plethora of physiological and pathological events. As a dynamic process, O-GlcNAc functions in a site-specific manner. However, the experimental identification of the O-GlcNAc sites remains challenging in many scenarios. Herein, by leveraging the recent progress in cataloguing experimentally identified O-GlcNAc sites and advanced deep learning approaches, we establish an ensemble model, O-GlcNAcPRED-DL, a deep learning-based tool, for the prediction of O-GlcNAc sites. In brief, to make a benchmark O-GlcNAc data set, we extracted the information on O-GlcNAc from the recently constructed database O-GlcNAcAtlas, which contains thousands of experimentally identified and curated O-GlcNAc sites on proteins from multiple species. To overcome the imbalance between positive and negative data sets, we selected five groups of negative data sets in humans and mice to construct an ensemble predictor based on connection of a convolutional neural network and bidirectional long short-term memory. By taking into account three types of sequence information, we constructed four network frameworks, with the systematically optimized parameters used for the models. The thorough comparison analysis on two independent data sets of humans and mice and six independent data sets from other species demonstrated remarkably increased sensitivity and accuracy of the O-GlcNAcPRED-DL models, outperforming other existing tools. Moreover, a user-friendly Web server for O-GlcNAcPRED-DL has been constructed, which is freely available at http://oglcnac.org/pred_dl.

Proteome encoded determinants of protein sorting into extracellular vesicles

Extracellular vesicles (EVs) are membranous structures released by cells into the extracellular space and are thought to be involved in cell-to-cell communication. While EVs and their cargo are promising biomarker candidates, sorting mechanisms of proteins to EVs remain unclear. In this study, we ask if it is possible to determine EV association based on the protein sequence. Additionally, we ask what the most important determinants are for EV association. We answer these questions with explainable AI models, using human proteome data from EV databases to train and validate the model. It is essential to correct the datasets for contaminants introduced by coarse EV isolation workflows and for experimental bias caused by mass spectrometry. In this study, we show that it is indeed possible to predict EV association from the protein sequence: a simple sequence-based model for predicting EV proteins achieved an area under the curve of 0.77 ± 0.01, which increased further to 0.84 ± 0.00 when incorporating curated post-translational modification (PTM) annotations. Feature analysis shows that EV-associated proteins are stable, polar, and structured with low isoelectric point compared to non-EV proteins. PTM annotations emerged as the most important features for correct classification; specifically, palmitoylation is one of the most prevalent EV sorting mechanisms for unique proteins. Palmitoylation and nitrosylation sites are especially prevalent in EV proteins that are determined by very strict isolation protocols, indicating they could potentially serve as quality control criteria for future studies. This computational study offers an effective sequence-based predictor of EV associated proteins with extensive characterisation of the human EV proteome that can explain for individual proteins which factors contribute to their EV association.

DeepMPSF: A Deep Learning Network for Predicting General Protein Phosphorylation Sites Based on Multiple Protein Sequence Features

Phosphorylation, as one of the most important post-translational modifications, plays a key role in various cellular physiological processes and disease occurrences. In recent years, computer technology has been gradually applied to the prediction of protein phosphorylation sites. However, most existing methods rely on simple protein sequence features that provide limited contextual information. To overcome this limitation, we propose DeepMPSF, a phosphorylation site prediction model based on multiple protein sequence features. There are two types of features: sequence semantic features, which comprise protein residue type information and relative position information within protein sequence, and protein background biophysical features, which include global semantic information containing more comprehensive protein background information obtained from pretrained models. To extract these features, DeepMPSF employs two separate subnetworks: the S71SFE module and the BBFE module, which automatically extract high-level semantic features. Our model incorporates a learning strategy for handling imbalanced datasets through ensemble learning during training and prediction. DeepMPSF is trained and evaluated on a well-established dataset of human proteins. Comparing the analysis with other benchmark methods reveals that DeepMPSF outperforms in predicting both S/T residues and Y residues. In particular, DeepMPSF showed excellent generalization performance in cross-species blind test performance, with an average improvement of 5.63%/5.72%, 22.28%/25.94%, 20.11%/17.49%, and 26.40%/28.33% for Mus musculus/Rattus norvegicus test sets in area under curves (AUCs) of ROC curve, AUC of the PR curve, F1-score, and MCC metrics, respectively. Furthermore, it also shows excellent performance in the latest updated case of natural proteins with functional phosphorylation sites. Through an ablation study and visual analysis, we uncover that the design of different feature modules significantly contributes to the accurate classification of DeepMPSF, which provides valuable insights for predicting phosphorylation sites and offers effective support for future downstream research.

Nucleotide-level prediction of CircRNA-protein binding based on fully convolutional neural network

Introduction: CircRNA-protein binding plays a critical role in complex biological activity and disease. Various deep learning-based algorithms have been proposed to identify CircRNA-protein binding sites. These methods predict whether the CircRNA sequence includes protein binding sites from the sequence level, and primarily concentrate on analysing the sequence specificity of CircRNA-protein binding. For model performance, these methods are unsatisfactory in accurately predicting motif sites that have special functions in gene expression. Methods: In this study, based on the deep learning models that implement pixel-level binary classification prediction in computer vision, we viewed the CircRNA-protein binding sites prediction as a nucleotide-level binary classification task, and use a fully convolutional neural networks to identify CircRNA-protein binding motif sites (CPBFCN). Results: CPBFCN provides a new path to predict CircRNA motifs. Based on the MEME tool, the existing CircRNA-related and protein-related database, we analysed the motif functions discovered by CPBFCN. We also investigated the correlation between CircRNA sponge and motif distribution. Furthermore, by comparing the motif distribution with different input sequence lengths, we found that some motifs in the flanking sequences of CircRNA-protein binding region may contribute to CircRNA-protein binding. Conclusion: This study contributes to identify circRNA-protein binding and provides help in understanding the role of circRNA-protein binding in gene expression regulation.

Deciphering the functional landscape of phosphosites with deep neural network

Current biochemical approaches have only identified the most well-characterized kinases for a tiny fraction of the phosphoproteome, and the functional assignments of phosphosites are almost negligible. Herein, we analyze the substrate preference catalyzed by a specific kinase and present a novel integrated deep neural network model named FuncPhos-SEQ for functional assignment of human proteome-level phosphosites. FuncPhos-SEQ incorporates phosphosite motif information from a protein sequence using multiple convolutional neural network (CNN) channels and network features from protein-protein interactions (PPIs) using network embedding and deep neural network (DNN) channels. These concatenated features are jointly fed into a heterogeneous feature network to prioritize functional phosphosites. Combined with a series of in vitro and cellular biochemical assays, we confirm that NADK-S48/50 phosphorylation could activate its enzymatic activity. In addition, ERK1/2 are discovered as the primary kinases responsible for NADK-S48/50 phosphorylation. Moreover, FuncPhos-SEQ is developed as an online server.

Empirical comparison and analysis of machine learning-based approaches for druggable protein identification

Efficiently and precisely identifying drug targets is crucial for developing and discovering potential medications. While conventional experimental approaches can accurately pinpoint these targets, they suffer from time constraints and are not easily adaptable to high-throughput processes. On the other hand, computational approaches, particularly those utilizing machine learning (ML), offer an efficient means to accelerate the prediction of druggable proteins based solely on their primary sequences. Recently, several state-of-the-art computational methods have been developed for predicting and analyzing druggable proteins. These computational methods showed high diversity in terms of benchmark datasets, feature extraction schemes, ML algorithms, evaluation strategies and webserver/software usability. Thus, our objective is to reexamine these computational approaches and conduct a comprehensive assessment of their strengths and weaknesses across multiple aspects. In this study, we deliver the first comprehensive survey regarding the state-of-the-art computational approaches for in silico prediction of druggable proteins. First, we provided information regarding the existing benchmark datasets and the types of ML methods employed. Second, we investigated the effectiveness of these computational methods in druggable protein identification for each benchmark dataset. Third, we summarized the important features used in this field and the existing webserver/software. Finally, we addressed the present constraints of the existing methods and offer valuable guidance to the scientific community in designing and developing novel prediction models. We anticipate that this comprehensive review will provide crucial information for the development of more accurate and efficient druggable protein predictors.

CapsNetYY1: identifying YY1-mediated chromatin loops based on a capsule network architecture

BACKGROUND

Previous studies have identified that chromosome structure plays a very important role in gene control. The transcription factor Yin Yang 1 (YY1), a multifunctional DNA binding protein, could form a dimer to mediate chromatin loops and active enhancer-promoter interactions. The deletion of YY1 or point mutations at the YY1 binding sites significantly inhibit the enhancer-promoter interactions and affect gene expression. To date, only a few computational methods are available for identifying YY1-mediated chromatin loops.

RESULTS

We proposed a novel model named CapsNetYY1, which was based on capsule network architecture to identify whether a pair of YY1 motifs can form a chromatin loop. Firstly, we encode the DNA sequence using one-hot encoding method. Secondly, multi-scale convolution layer is used to extract local features of the sequence, and bidirectional gated recurrent unit is used to learn the features across time steps. Finally, capsule networks (convolution capsule layer and digital capsule layer) used to extract higher level features and recognize YY1-mediated chromatin loops. Compared with DeepYY1, the only prediction for YY1-mediated chromatin loops, our model CapsNetYY1 achieved the better performance on the independent datasets (AUC [Formula: see text]).

CONCLUSION

The results indicate that CapsNetYY1 is an excellent method for identifying YY1-mediated chromatin loops. We believe that the CapsNetYY1 method will be used for predictive classification of other DNA sequences.

LMPhosSite: A Deep Learning-Based Approach for General Protein Phosphorylation Site Prediction Using Embeddings from the Local Window Sequence and Pretrained Protein Language Model

Phosphorylation is one of the most important post-translational modifications and plays a pivotal role in various cellular processes. Although there exist several computational tools to predict phosphorylation sites, existing tools have not yet harnessed the knowledge distilled by pretrained protein language models. Herein, we present a novel deep learning-based approach called LMPhosSite for the general phosphorylation site prediction that integrates embeddings from the local window sequence and the contextualized embedding obtained using global (overall) protein sequence from a pretrained protein language model to improve the prediction performance. Thus, the LMPhosSite consists of two base-models: one for capturing effective local representation and the other for capturing global per-residue contextualized embedding from a pretrained protein language model. The output of these base-models is integrated using a score-level fusion approach. LMPhosSite achieves a precision, recall, Matthew's correlation coefficient, and F1-score of 38.78%, 67.12%, 0.390, and 49.15%, for the combined serine and threonine independent test data set and 34.90%, 62.03%, 0.298, and 44.67%, respectively, for the tyrosine independent test data set, which is better than the compared approaches. These results demonstrate that LMPhosSite is a robust computational tool for the prediction of the general phosphorylation sites in proteins.

Align-gram: Rethinking the Skip-gram Model for Protein Sequence Analysis

The inception of next generations sequencing technologies have exponentially increased the volume of biological sequence data. Protein sequences, being quoted as the 'language of life', has been analyzed for a multitude of applications and inferences. Owing to the rapid development of deep learning, in recent years there have been a number of breakthroughs in the domain of Natural Language Processing. Since these methods are capable of performing different tasks when trained with a sufficient amount of data, off-the-shelf models are used to perform various biological applications. In this study, we investigated the applicability of the popular Skip-gram model for protein sequence analysis and made an attempt to incorporate some biological insights into it. We propose a novel k-mer embedding scheme, Align-gram, which is capable of mapping the similar k-mers close to each other in a vector space. Furthermore, we experiment with other sequence-based protein representations and observe that the embeddings derived from Align-gram aids modeling and training deep learning models better. Our experiments with a simple baseline LSTM model and a much complex CNN model of DeepGoPlus shows the potential of Align-gram in performing different types of deep learning applications for protein sequence analysis.

Liver CT Image Recognition Method Based on Capsule Network

The automatic recognition of CT (Computed Tomography) images of liver cancer is important for the diagnosis and treatment of early liver cancer. However, there are problems such as single model structure and loss of pooling layer information when using a traditional convolutional neural network to recognize CT images of liver cancer. Therefore, this paper proposes an efficient method for liver CT image recognition based on the capsule network (CapsNet). Firstly, the liver CT images are preprocessed, and in the process of image denoising, the traditional non-local mean (NLM) denoising algorithm is optimized with a superpixel segmentation algorithm to better protect the information of image edges. After that, CapsNet was used for image recognition for liver CT images. The experimental results show that the average recognition rate of liver CT images reaches 92.9% when CapsNet is used, which is 5.3% higher than the traditional CNN model, indicating that CapsNet has better recognition accuracy for liver CT images.

In Silico Examination of Single Nucleotide Missense Mutations in NHLH2, a Gene Linked to Infertility and Obesity

Continual advances in our understanding of the human genome have led to exponential increases in known single nucleotide variants. The characterization of each of the variants lags behind. For researchers needing to study a single gene, or multiple genes in a pathway, there must be ways to narrow down pathogenic variants from those that are silent or pose less pathogenicity. In this study, we use the NHLH2 gene which encodes the nescient helix-loop-helix 2 (Nhlh2) transcription factor in a systematic analysis of all missense mutations to date in the gene. The NHLH2 gene was first described in 1992. Knockout mice created in 1997 indicated a role for this protein in body weight control, puberty, and fertility, as well as the motivation for sex and exercise. Only recently have human carriers of NHLH2 missense variants been characterized. Over 300 missense variants for the NHLH2 gene are listed in the NCBI single nucleotide polymorphism database (dbSNP). Using in silico tools, predicted pathogenicity of the variants narrowed the missense variants to 37 which were predicted to affect NHLH2 function. These 37 variants cluster around the basic-helix-loop-helix and DNA binding domains of the transcription factor, and further analysis using in silico tools provided 21 SNV resulting in 22 amino acid changes for future wet lab analysis. The tools used, findings, and predictions for the variants are discussed considering the known function of the NHLH2 transcription factor. Overall use of these in silico tools and analysis of these data contribute to our knowledge of a protein which is both involved in the human genetic syndrome, Prader-Willi syndrome, and in controlling genes involved in body weight control, fertility, puberty, and behavior in the general population, and may provide a systematic methodology for others to characterize variants for their gene of interest.

Phosformer: an explainable transformer model for protein kinase-specific phosphorylation predictions

MOTIVATION

The human genome encodes over 500 distinct protein kinases which regulate nearly all cellular processes by the specific phosphorylation of protein substrates. While advances in mass spectrometry and proteomics studies have identified thousands of phosphorylation sites across species, information on the specific kinases that phosphorylate these sites is currently lacking for the vast majority of phosphosites. Recently, there has been a major focus on the development of computational models for predicting kinase-substrate associations. However, most current models only allow predictions on a subset of well-studied kinases. Furthermore, the utilization of hand-curated features and imbalances in training and testing datasets pose unique challenges in the development of accurate predictive models for kinase-specific phosphorylation prediction. Motivated by the recent development of universal protein language models which automatically generate context-aware features from primary sequence information, we sought to develop a unified framework for kinase-specific phosphosite prediction, allowing for greater investigative utility and enabling substrate predictions at the whole kinome level.

RESULTS

We present a deep learning model for kinase-specific phosphosite prediction, termed Phosformer, which predicts the probability of phosphorylation given an arbitrary pair of unaligned kinase and substrate peptide sequences. We demonstrate that Phosformer implicitly learns evolutionary and functional features during training, removing the need for feature curation and engineering. Further analyses reveal that Phosformer also learns substrate specificity motifs and is able to distinguish between functionally distinct kinase families. Benchmarks indicate that Phosformer exhibits significant improvements compared to the state-of-the-art models, while also presenting a more generalized, unified, and interpretable predictive framework.

AVAILABILITY AND IMPLEMENTATION

Code and data are available at https://github.com/esbgkannan/phosformer.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Sumoylation regulates functional properties of the oocyte transcription factors SOHLH1 and NOBOX

SOHLH1 and NOBOX are oocyte-expressed transcription factors with critical roles in ovary development and fertility. In mice, Sohlh1 and Nobox are essential for fertility through their regulation of the oocyte transcriptional network and cross-talk to somatic cells. Sumoylation is a posttranslational modification that regulates transcription factor function, and we previously showed that mouse oocytes deficient for sumoylation had an altered transcriptional landscape that included significant changes in NOBOX target genes. Here, we show that mouse SOHLH1 is modified by SUMO2/3 at lysine 345 and mutation of this residue alters SOHLH1 nuclear to cytoplasmic localization. In NOBOX, we identify a non-consensus SUMO site, K97, that eliminates NOBOX mono-SUMO2/3 conjugation, while a point mutation at K125 had no effect on NOBOX sumoylation. However, NOBOXK97R/K125R double mutants showed loss of mono-SUMO2/3 and altered higher molecular weight modifications, suggesting cooperation between these lysine's. NOBOXK97R and NOBOXK97R/K125R differentially regulated NOBOX promoter targets, with increased activity on the Gdf9 promoter, but no effect on the Pou5f1 promoter. These data implicate sumoylation as a novel regulatory mechanism for SOHLH1 and NOBOX, which may prove useful in refining their roles during oogenesis as well as their function during reprogramming to generate de novo germ cells.

Applications of deep learning in understanding gene regulation

Gene regulation is a central topic in cell biology. Advances in omics technologies and the accumulation of omics data have provided better opportunities for gene regulation studies than ever before. For this reason deep learning, as a data-driven predictive modeling approach, has been successfully applied to this field during the past decade. In this article, we aim to give a brief yet comprehensive overview of representative deep-learning methods for gene regulation. Specifically, we discuss and compare the design principles and datasets used by each method, creating a reference for researchers who wish to replicate or improve existing methods. We also discuss the common problems of existing approaches and prospectively introduce the emerging deep-learning paradigms that will potentially alleviate them. We hope that this article will provide a rich and up-to-date resource and shed light on future research directions in this area.

A Novel Capsule Network with Attention Routing to Identify Prokaryote Phosphorylation Sites

By denaturing proteins and promoting the formation of multiprotein complexes, protein phosphorylation has important effects on the activity of protein functional molecules and cell signaling. The regulation of protein phosphorylation allows microbes to respond rapidly and reversibly to specific environmental stimuli or niches, which is closely related to the molecular mechanisms of bacterial drug resistance. Accurate prediction of phosphorylation sites (p-site) of prokaryotes can contribute to addressing bacterial resistance and providing new perspectives for developing novel antibacterial drugs. Most existing studies focus on human phosphorylation sites, while tools targeting phosphorylation site identification of prokaryotic proteins are still relatively scarce. This study designs a capsule network-based prediction technique for p-site in prokaryotes. To address the poor scalability and unreliability of dynamic routing processes in the output space of capsule networks, a more reliable way is introduced to learn the consistency between capsules. We incorporate a self-attention mechanism into the routing algorithm to capture the global information of the capsule, reducing the computational effort while enriching the representation capability of the capsule. Aiming at the weak robustness of the model, EcapsP improves the prediction accuracy and stability by introducing shortcuts and unconditional reconfiguration. In addition, the study compares and analyzes the prediction performance based on word vectors, physicochemical properties, and mixing characteristics in predicting serine (Ser/S), threonine (Thr/T), and tyrosine (Tyr/Y) p-site. The comprehensive experimental results show that the accuracy of the developed technique is close to 70% for the identification of the three phosphorylation sites in prokaryotes. Importantly, in side-by-side comparisons with other state-of-the-art predictors, our method improves the Matthews correlation coefficient (MCC) by approximately 7%. The results demonstrate the superiority of EcapsP in terms of high performance and reliability.

Multi-dimensional feature recognition model based on capsule network for ubiquitination site prediction

Ubiquitination is an important post-translational modification of proteins that regulates many cellular activities. Traditional experimental methods for identification are costly and time-consuming, so many researchers have proposed computational methods for ubiquitination site prediction in recent years. However, traditional machine learning methods focus on feature engineering and are not suitable for large-scale proteomic data. In addition, deep learning methods are mostly based on convolutional neural networks and fuse multiple coding approaches to achieve classification prediction. This cannot effectively identify potential fine-grained features of the input data and has limitations in the representation of dependencies between low-level features and high-level features. A multi-dimensional feature recognition model based on a capsule network (MDCapsUbi) was proposed to predict protein ubiquitination sites. The proposed module consisting of convolution operations and channel attention was used to recognize coarse-grained features in the sequence dimension and the feature map dimension. The capsule network module consisting of capsule vectors was used to identify fine-grained features and classify ubiquitinated sites. With ten-fold cross-validation, the MDCapsUbi achieved 91.82% accuracy, 91.39% sensitivity, 92.24% specificity, 0.837 MCC, 0.918 F-Score and 0.97 AUC. Experimental results indicated that the proposed method outperformed other ubiquitination site prediction technologies.

CapsNh-Kcr: Capsule network-based prediction of lysine crotonylation sites in human non-histone proteins

Lysine crotonylation (Kcr) is one of the most important post-translational modifications (PTMs) that is widely detected in both histone and non-histone proteins. In fact, Kcr is reported to be involved in various biological processes, such as metabolism and cell differentiation. However, the available experimental methods for Kcr site identification are laborious and costly. To effectively replace existing experimental approaches, some computational methods have been developed in the last few years. The available computational methods still lack some important aspects, as they can only identify Kcr sites on either histone-only or combined histone and nonhistone proteins. Although a tool was developed to identify Kcr sites on non-histone proteins only, its performance is inadequate and the exploration of hidden Kcr patterns (motifs) has been completely ignored, which might be significant for detailed Kcr studies. Therefore, algorithms that can more effectively predict Kcr sites on non-histone proteins with their biological meaning need to be designed. Accordingly, we developed a novel deep learning (capsule network)-based model, named CapsNh-Kcr, for Kcr site prediction, particularly focusing on non-histone proteins. Based on the independent results, the proposed model achieves an AUC of 0.9120, which is approximately 6% higher than that of previous nhKcr model in the prediction of Kcr sites on non-histone proteins. Further, we revealed, for the first time, that the proposed model can represent obvious motif distribution across Kcr sites in non-histone proteins. The source code (in Python) is publicly available at https://github.com/Jhabindra-bioinfo/CapsNh-Kcr.

pSuc-EDBAM: Predicting lysine succinylation sites in proteins based on ensemble dense blocks and an attention module

Background

Lysine succinylation is a newly discovered protein post-translational modifications. Predicting succinylation sites helps investigate the metabolic disease treatments. However, the biological experimental approaches are costly and inefficient, it is necessary to develop efficient computational approaches.

Results

In this paper, we proposed a novel predictor based on ensemble dense blocks and an attention module, called as pSuc-EDBAM, which adopted one hot encoding to derive the feature maps of protein sequences, and generated the low-level feature maps through 1-D CNN. Afterward, the ensemble dense blocks were used to capture feature information at different levels in the process of feature learning. We also introduced an attention module to evaluate the importance degrees of different features. The experimental results show that Acc reaches 74.25%, and MCC reaches 0.2927 on the testing dataset, which suggest that the pSuc-EDBAM outperforms the existing predictors.

Conclusions

The experimental results of ten-fold cross-validation on the training dataset and independent test on the testing dataset showed that pSuc-EDBAM outperforms the existing succinylation site predictors and can predict potential succinylation sites effectively. The pSuc-EDBAM is feasible and obtains the credible predictive results, which may also provide valuable references for other related research. To make the convenience of the experimental scientists, a user-friendly web server has been established (http://bioinfo.wugenqiang.top/pSuc-EDBAM/), by which the desired results can be easily obtained.

CNNArginineMe: A CNN structure for training models for predicting arginine methylation sites based on the One-Hot encoding of peptide sequence

Protein arginine methylation (PRme), as one post-translational modification, plays a critical role in numerous cellular processes and regulates critical cellular functions. Though several in silico models for predicting PRme sites have been reported, new models may be required to develop due to the significant increase of identified PRme sites. In this study, we constructed multiple machine-learning and deep-learning models. The deep-learning model CNN combined with the One-Hot coding showed the best performance, dubbed CNNArginineMe. CNNArginineMe performed best in AUC scoring metrics in comparisons with several reported predictors. Additionally, we employed CNNArginineMe to predict arginine methylation proteome and performed functional analysis. The arginine methylated proteome is significantly enriched in the amyotrophic lateral sclerosis (ALS) pathway. CNNArginineMe is freely available at https://github.com/guoyangzou/CNNArginineMe.

Computational Analysis of Deleterious SNPs in NRAS to Assess Their Potential Correlation With Carcinogenesis

The NRAS gene is a well-known oncogene that acts as a major player in carcinogenesis. Mutations in the NRAS gene have been linked to multiple types of human tumors. Therefore, the identification of the most deleterious single nucleotide polymorphisms (SNPs) in the NRAS gene is necessary to understand the key factors of tumor pathogenesis and therapy. We aimed to retrieve NRAS missense SNPs and analyze them comprehensively using sequence and structure approaches to determine the most deleterious SNPs that could increase the risk of carcinogenesis. We also adopted structural biology methods and docking tools to investigate the behavior of the filtered SNPs. After retrieving missense SNPs and analyzing them using six in silico tools, 17 mutations were found to be the most deleterious mutations in NRAS. All SNPs except S145L were found to decrease NRAS stability, and all SNPs were found on highly conserved residues and important functional domains, except R164C. In addition, all mutations except G60E and S145L showed a higher binding affinity to GTP, implicating an increase in malignancy tendency. As a consequence, all other 14 mutations were expected to increase the risk of carcinogenesis, with 5 mutations (G13R, G13C, G13V, P34R, and V152F) expected to have the highest risk. Thermodynamic stability was ensured for these SNP models through molecular dynamics simulation based on trajectory analysis. Free binding affinity toward the natural substrate, GTP, was higher for these models as compared to the native NRAS protein. The Gly13 SNP proteins depict a differential conformational state that could favor nucleotide exchange and catalytic potentiality. A further application of experimental methods with all these 14 mutations could reveal new insights into the pathogenesis and management of different types of tumors.

Mini-review: Recent advances in post-translational modification site prediction based on deep learning

Post-translational modifications (PTMs) are closely linked to numerous diseases, playing a significant role in regulating protein structures, activities, and functions. Therefore, the identification of PTMs is crucial for understanding the mechanisms of cell biology and diseases therapy. Compared to traditional machine learning methods, the deep learning approaches for PTM prediction provide accurate and rapid screening, guiding the downstream wet experiments to leverage the screened information for focused studies. In this paper, we reviewed the recent works in deep learning to identify phosphorylation, acetylation, ubiquitination, and other PTM types. In addition, we summarized PTM databases and discussed future directions with critical insights.

DeepDA-Ace: A Novel Domain Adaptation Method for Species-Specific Acetylation Site Prediction

Protein lysine acetylation is an important type of post-translational modification (PTM), and it plays a crucial role in various cellular processes. Recently, although many researchers have focused on developing tools for acetylation site prediction based on computational methods, most of these tools are based on traditional machine learning algorithms for acetylation site prediction without species specificity, still maintained as a single prediction model. Recent studies have shown that the acetylation sites of distinct species have evident location-specific differences; however, there is currently no integrated prediction model that can effectively predict acetylation sites cross all species. Therefore, to enhance the scope of species-specific level, it is necessary to establish a framework for species-specific acetylation site prediction. In this work, we propose a domain adaptation framework DeepDA-Ace for species-specific acetylation site prediction, including Rattus norvegicus, Schistosoma japonicum, Arabidopsis thaliana, and other types of species. In DeepDA-Ace, an attention based densely connected convolutional neural network is designed to capture sequence features, and the semantic adversarial learning strategy is proposed to align features of different species so as to achieve knowledge transfer. The DeepDA-Ace outperformed both the general prediction model and fine-tuning based species-specific model across most types of species. The experiment results have demonstrated that DeepDA-Ace is superior to the general and fine-tuning methods, and its precision exceeds 0.75 on most species. In addition, our method achieves at least 5% improvement over the existing acetylation prediction tools.

A switchable Cas12a enabling CRISPR-based direct histone deacetylase activity detection

The efficient and robust signal reporting ability of CRISPR-Cas system exhibits huge value in biosensing, but its applicability for non-nucleic acid analyte detection relies on the coupling of additional recognition modules. To address this limitation, we described a switchable Cas12a and exploited it for CRISPR-based direct analysis of histone deacetylase (HDAC) activity. Starting from the acetylation-mediated inactivation of Cas12a by anti-CRISPR protein AcrVA5, we demonstrated that the acetyl-inactivated Cas12a could be reversibly activated by HDAC-mediated deacetylation based on computational simulations (e.g., deep learning and protein-protein docking analysis) and experimental verifications. By leveraging this switchable Cas12a for both target sensing and signal amplification, we established a sensitive one-pot assay capable of detecting deacetylase sirtuin-1 with sub-nanomolar sensitivity, which is 50 times lower than the standard two-step peptide-based assay. The versability of this assay was validated by the sensitive assessment of cellular HDAC activities in different cell lines with good accuracy, making it a valuable tool for biochemical studies and clinical diagnostics.

A Comprehensive Review of Computation-Based Metal-Binding Prediction Approaches at the Residue Level

Clear evidence has shown that metal ions strongly connect and delicately tune the dynamic homeostasis in living bodies. They have been proved to be associated with protein structure, stability, regulation, and function. Even small changes in the concentration of metal ions can shift their effects from natural beneficial functions to harmful. This leads to degenerative diseases, malignant tumors, and cancers. Accurate characterizations and predictions of metalloproteins at the residue level promise informative clues to the investigation of intrinsic mechanisms of protein-metal ion interactions. Compared to biophysical or biochemical wet-lab technologies, computational methods provide open web interfaces of high-resolution databases and high-throughput predictors for efficient investigation of metal-binding residues. This review surveys and details 18 public databases of metal-protein binding. We collect a comprehensive set of 44 computation-based methods and classify them into four categories, namely, learning-, docking-, template-, and meta-based methods. We analyze the benchmark datasets, assessment criteria, feature construction, and algorithms. We also compare several methods on two benchmark testing datasets and include a discussion about currently publicly available predictive tools. Finally, we summarize the challenges and underlying limitations of the current studies and propose several prospective directions concerning the future development of the related databases and methods.

A parallel model of DenseCNN and ordered-neuron LSTM for generic and species-specific succinylation site prediction

Lysine succinylation (Ksucc) regulates various metabolic processes, participates in vital life processes, ans is involved in the occurrence and development of numerous diseases. Accurate recognition of succinylation sites can reveal underlying functional mechanisms and pathogenesis. However, most remain undetected. Moreover, a deep learning architecture focusing on generic and species-specific predictions is still lacking. Thus, we proposed a deep learning-based framework named Deep-Ksucc, combining a dense convolutional network (DenseCNN) and ordered-neuron long short-term memory (OnLSTM) in parallel, which took the cascading characteristics of sequence information and physicochemical properties as the input. The results of the generic and species-specific predictions indicated that Deep-Ksucc can identify sequence patterns of different organisms and recognize plenty of succinylation sites. The case study showed that Deep-Ksucc can serve as a reliable tool for biology verification and computer-aided recognition of succinylation sites. This article is protected by copyright. All rights reserved.

iKcr_CNN: A novel computational tool for imbalance classification of human nonhistone crotonylation sites based on convolutional neural networks with focal loss

Lysine crotonylation (Kcr) is a newly discovered protein post-translational modification and has been proved to be widely involved in various biological processes and human diseases. Thus, the accurate and fast identification of this modification became the preliminary task in investigating the related biological functions. Due to the long duration, high cost and intensity of traditional high-throughput experimental techniques, constructing bioinformatics predictors based on machine learning algorithms is treated as a most popular solution. Although dozens of predictors have been reported to identify Kcr sites, only two, nhKcr and DeepKcrot, focused on human nonhistone protein sequences. Moreover, due to the imbalance nature of data distribution, associated detection performance is severely biased towards the major negative samples and remains much room for improvement. In this research, we developed a convolutional neural network framework, dubbed iKcr_CNN, to identify the human nonhistone Kcr modification. To overcome the imbalance issue (Kcr: 15,274; non-Kcr: 74,018 with imbalance ratio: 1:4), we applied the focal loss function instead of the standard cross-entropy as the indicator to optimize the model, which not only assigns different weights to samples belonging to different categories but also distinguishes easy- and hard-classified samples. Ultimately, the obtained model presents more balanced prediction scores between real-world positive and negative samples than existing tools. The user-friendly web server is accessible at ikcrcnn.webmalab.cn/, and the involved Python scripts can be conveniently downloaded at github.com/lijundou/iKcr_CNN/. The proposed model may serve as an efficient tool to assist academicians with their experimental researches.

Maximizing Depth of PTM Coverage: Generating Robust MS Datasets for Computational Prediction Modeling

Post-translational modifications (PTMs) regulate complex biological processes through the modulation of protein activity, stability, and localization. Insights into the specific modification type and localization within a protein sequence can help ascertain functional significance. Computational models are increasingly demonstrated to offer a low-cost, high-throughput method for comprehensive PTM predictions. Algorithms are optimized using existing experimental PTM data, thus accurate prediction performance relies on the creation of robust datasets. Herein, advancements in mass spectrometry-based proteomics technologies to maximize PTM coverage are reviewed. Further, requisite experimental validation approaches for PTM predictions are explored to ensure that follow-up mechanistic studies are focused on accurate modification sites.

A novel strategy to uncover specific GO terms/phosphorylation pathways in phosphoproteomic data in Arabidopsis thaliana

BACKGROUND

Proteins are the workforce of the cell and their phosphorylation status tailors specific responses efficiently. One of the main challenges of phosphoproteomic approaches is to deconvolute biological processes that specifically respond to an experimental query from a list of phosphoproteins. Comparison of the frequency distribution of GO (Gene Ontology) terms in a given phosphoproteome set with that observed in the genome reference set (GenRS) is the most widely used tool to infer biological significance. Yet, this comparison assumes that GO term distribution between the phosphoproteome and the genome are identical. However, this hypothesis has not been tested due to the lack of a comprehensive phosphoproteome database.

RESULTS

In this study, we test this hypothesis by constructing three phosphoproteome databases in Arabidopsis thaliana: one based in experimental data (ExpRS), another based in in silico phosphorylation protein prediction (PredRS) and a third that is the union of both (UnRS). Our results show that the three phosphoproteome reference sets show default enrichment of several GO terms compared to GenRS, indicating that GO term distribution in the phosphoproteomes does not match that of the genome. Moreover, these differences overshadow the identification of GO terms that are specifically enriched in a particular condition. To overcome this limitation, we present an additional comparison of the sample of interest with UnRS to uncover GO terms specifically enriched in a particular phosphoproteome experiment. Using this strategy, we found that mRNA splicing and cytoplasmic microtubule compounds are important processes specifically enriched in the phosphoproteome of dark-grown Arabidopsis seedlings.

CONCLUSIONS

This study provides a novel strategy to uncover GO specific terms in phosphoproteome data of Arabidopsis that could be applied to any other organism. We also highlight the importance of specific phosphorylation pathways that take place during dark-grown Arabidopsis development.

DeepCap-Kcr: accurate identification and investigation of protein lysine crotonylation sites based on capsule network

Lysine crotonylation (Kcr) is a posttranslational modification widely detected in histone and nonhistone proteins. It plays a vital role in human disease progression and various cellular processes, including cell cycle, cell organization, chromatin remodeling and a key mechanism to increase proteomic diversity. Thus, accurate information on such sites is beneficial for both drug development and basic research. Existing computational methods can be improved to more effectively identify Kcr sites in proteins. In this study, we proposed a deep learning model, DeepCap-Kcr, a capsule network (CapsNet) based on a convolutional neural network (CNN) and long short-term memory (LSTM) for robust prediction of Kcr sites on histone and nonhistone proteins (mammals). The proposed model outperformed the existing CNN architecture Deep-Kcr and other well-established tools in most cases and provided promising outcomes for practical use; in particular, the proposed model characterized the internal hierarchical representation as well as the important features from multiple levels of abstraction automatically learned from a small number of samples. The trained model was well generalized in other species (papaya). Moreover, we showed the features and properties generated by the internal capsule layer that can explore the internal data distribution related to biological significance (as a motif detector). The source code and data are freely available at https://github.com/Jhabindra-bioinfo/DeepCap-Kcr.

DeepReac+: deep active learning for quantitative modeling of organic chemical reactions

Various computational methods have been developed for quantitative modeling of organic chemical reactions; however, the lack of universality as well as the requirement of large amounts of experimental data limit their broad applications. Here, we present DeepReac+, an efficient and universal computational framework for prediction of chemical reaction outcomes and identification of optimal reaction conditions based on deep active learning. Under this framework, DeepReac is designed as a graph-neural-network-based model, which directly takes 2D molecular structures as inputs and automatically adapts to different prediction tasks. In addition, carefully-designed active learning strategies are incorporated to substantially reduce the number of necessary experiments for model training. We demonstrate the universality and high efficiency of DeepReac+ by achieving the state-of-the-art results with a minimum of labeled data on three diverse chemical reaction datasets in several scenarios. Collectively, DeepReac+ has great potential and utility in the development of AI-aided chemical synthesis. DeepReac+ is freely accessible at https://github.com/bm2-lab/DeepReac.

An Ensemble Deep Learning based Predictor for Simultaneously Identifying Protein Ubiquitylation and SUMOylation Sites

BACKGROUND

Several computational tools for predicting protein Ubiquitylation and SUMOylation sites have been proposed to study their regulatory roles in gene location, gene expression, and genome replication. However, existing methods generally rely on feature engineering, and ignore the natural similarity between the two types of protein translational modification. This study is the first all-in-one deep network to predict protein Ubiquitylation and SUMOylation sites from protein sequences as well as their crosstalk sites simultaneously. Our deep learning architecture integrates several meta classifiers that apply deep neural networks to protein sequence information and physico-chemical properties, which were trained on multi-label classification mode for simultaneously identifying protein Ubiquitylation and SUMOylation as well as their crosstalk sites.

RESULTS

The promising AUCs of our method on Ubiquitylation, SUMOylation and crosstalk sites achieved 0.838, 0.888, and 0.862 respectively on tenfold cross-validation. The corresponding APs reached 0.683, 0.804 and 0.552, which also validated our effectiveness.

CONCLUSIONS

The proposed architecture managed to classify ubiquitylated and SUMOylated lysine residues along with their crosstalk sites, and outperformed other well-known Ubiquitylation and SUMOylation site prediction tools.

CL-ACP: a parallel combination of CNN and LSTM anticancer peptide recognition model

BACKGROUND

Anticancer peptides are defence substances with innate immune functions that can selectively act on cancer cells without harming normal cells and many studies have been conducted to identify anticancer peptides. In this paper, we introduce the anticancer peptide secondary structures as additional features and propose an effective computational model, CL-ACP, that uses a combined network and attention mechanism to predict anticancer peptides.

RESULTS

The CL-ACP model uses secondary structures and original sequences of anticancer peptides to construct the feature space. The long short-term memory and convolutional neural network are used to extract the contextual dependence and local correlations of the feature space. Furthermore, a multi-head self-attention mechanism is used to strengthen the anticancer peptide sequences. Finally, three categories of feature information are classified by cascading. CL-ACP was validated using two types of datasets, anticancer peptide datasets and antimicrobial peptide datasets, on which it achieved good results compared to previous methods. CL-ACP achieved the highest AUC values of 0.935 and 0.972 on the anticancer peptide and antimicrobial peptide datasets, respectively.

CONCLUSIONS

CL-ACP can effectively recognize antimicrobial peptides, especially anticancer peptides, and the parallel combined neural network structure of CL-ACP does not require complex feature design and high time cost. It is suitable for application as a useful tool in antimicrobial peptide design.

Multitask CapsNet: An Imbalanced Data Deep Learning Method for Predicting Toxicants

Drug development has a high failure rate, with safety properties constituting a considerable challenge. To reduce risk, in silico tools, including various machine learning methods, have been applied for toxicity prediction. However, these approaches often confront a serious problem: the training data sets are usually biased (imbalanced positive and negative samples), which would result in model training difficulty and unsatisfactory prediction accuracy. Multitask networks obtained significantly better predictive accuracies than single-task methods, and capsule neural networks showed excellent performance in sparse data sets in previous studies. In this study, we developed a new multitask framework based on a capsule neural network (multitask CapsNet) to measure 12 different toxic effects simultaneously. We found that multitask CapsNet excelled in toxicity prediction and outperformed many other computational approaches using the multitask strategy. Only after training on biased data sets did multitask CapsNet achieve significantly improved prediction accuracy on the Tox21 Data Challenge, which gave the largest ratio of highest accuracy (8/12) among compared models. Our model gave a prediction accuracy of 96.6% for the target NR.PPAR.gamma, whose ratio of negative to positive samples was up to 36:1. These results suggested that multitask CapsNet could overcome the bias problems and would provide a novel, accurate, and efficient approach for predicting the toxicities of compounds.

iCDI-W2vCom: Identifying the Ion Channel-Drug Interaction in Cellular Networking Based on word2vec and node2vec

Ion channels are the second largest drug target family. Ion channel dysfunction may lead to a number of diseases such as Alzheimer’s disease, epilepsy, cephalagra, and type II diabetes. In the research work for predicting ion channel–drug, computational approaches are effective and efficient compared with the costly, labor-intensive, and time-consuming experimental methods. Most of the existing methods can only be used to deal with the ion channels of knowing 3D structures; however, the 3D structures of most ion channels are still unknown. Many predictors based on protein sequence were developed to address the challenge, while most of their results need to be improved, or predicting web servers are missing. In this paper, a sequence-based classifier, called “iCDI-W2vCom,” was developed to identify the interactions between ion channels and drugs. In the predictor, the drug compound was formulated by SMILES-word2vec, FP2-word2vec, SMILES-node2vec, and ECFPs via a 1184D vector, ion channel was represented by the word2vec via a 64D vector, and the prediction engine was operated by the LightGBM classifier. The accuracy and AUC achieved by iCDI-W2vCom via the fivefold cross validation were 91.95% and 0.9703, which outperformed other existing predictors in this area. A user-friendly web server for iCDI-W2vCom was established at http://www.jci-bioinfo.cn/icdiw2v. The proposed method may also be a potential method for predicting target–drug interaction.

EMCBOW-GPCR: A method for identifying G-protein coupled receptors based on word embedding and wordbooks

•

An computational method was developed to identify G-protein coupled receptors.

•

Three word-embedding models and a bag-of-words model are used to extract original features.

•

A high accuracy was achieved by using fusion information.

•

A powerful tool was established.

G Protein-Coupled Receptors (GPCRs) are one of the largest membrane protein receptor family in human, which are also important targets for many drugs. Thence, it’s of great significance to judge whether a protein is a GPCR or not. However, identifying GPCRs by experimental methods is very expensive and time-consuming. As more and more GPCR primary sequences are accumulated, it’s feasible to develop a computational model to predict GPCRs precisely and quickly. In this paper, a novel method called EMCBOW-GPCR has been proposed to improve the accuracy of identifying GPCRs based on natural language processing (NLP). For representing GPCRs, three word-embedding models and a bag-of-words model are used to extract original features. Then, the original features are thrown into a Deep-learning algorithm to extract features further and reduce the dimension. Finally, the obtained features are fed into Extreme Gradient Boosting. As shown with the results comparison, the overall prediction metrics of EMCBOW-GPCR are higher than the state of the arts. In order to be convenient for more researchers to use EMCBOW-GPCR, the method and source code have been opened in github, which are available at https://github.com/454170054/EMCBOW-GPCR, and a user-friendly web-server for EMCBOW-GPCR has been established at http://www.jci-bioinfo.cn/emcbowgpcr.

RFCM-PALM: In-Silico Prediction of S-Palmitoylation Sites in the Synaptic Proteins for Male/Female Mouse Data

S-palmitoylation is a reversible covalent post-translational modification of cysteine thiol side chain by palmitic acid. S-palmitoylation plays a critical role in a variety of biological processes and is engaged in several human diseases. Therefore, identifying specific sites of this modification is crucial for understanding their functional consequences in physiology and pathology. We present a random forest (RF) classifier-based consensus strategy (RFCM-PALM) for predicting the palmitoylated cysteine sites on synaptic proteins from male/female mouse data. To design the prediction model, we have introduced a heuristic strategy for selection of the optimum set of physicochemical features from the AAIndex dataset using (a) K-Best (KB) features, (b) genetic algorithm (GA), and (c) a union (UN) of KB and GA based features. Furthermore, decisions from best-trained models of the KB, GA, and UN-based classifiers are combined by designing a three-star quality consensus strategy to further refine and enhance the scores of the individual models. The experiment is carried out on three categorized synaptic protein datasets of a male mouse, female mouse, and combined (male + female), whereas in each group, weighted data is used as training, and knock-out is used as the hold-out set for performance evaluation and comparison. RFCM-PALM shows ~80% area under curve (AUC) score in all three categories of datasets and achieve 10% average accuracy (male—15%, female—15%, and combined—7%) improvements on the hold-out set compared to the state-of-the-art approaches. To summarize, our method with efficient feature selection and novel consensus strategy shows significant performance gains in the prediction of S-palmitoylation sites in mouse datasets.

Machine Learning Methods in Prediction of Protein Palmitoylation Sites: A Brief Review

Protein palmitoylation is a fundamental and reversible post-translational lipid modification that involves a series of biological processes. Although a large number of experimental studies have explored the molecular mechanism behind the palmitoylation process, the computational methods has attracted much attention for its good performance in predicting palmitoylation sites compared with expensive and time-consuming biochemical experiments. The prediction of protein palmitoylation sites is helpful to reveal its biological mechanism. Therefore, the research on the application of machine learning methods to predict palmitoylation sites has become a hot topic in bioinformatics and promoted the development in the related fields. In this review, we briefly introduced the recent development in predicting protein palmitoylation sites by using machine learningbased methods and discussed their benefits and drawbacks. The perspective of machine learning-based methods in predicting palmitoylation sites was also provided. We hope the review could provide a guide in related fields.

How can artificial intelligence be used for peptidomics?

INTRODUCTION

Peptidomics is an emerging field of omics sciences using advanced isolation, analysis, and computational techniques that enable qualitative and quantitative analyses of various peptides in biological samples. Peptides can act as useful biomarkers and as therapeutic molecules for diseases.

AREAS COVERED

The use of therapeutic peptides can be predicted quickly and efficiently using data-driven computational methods, particularly artificial intelligence (AI) approach. Various AI approaches are useful for peptide-based drug discovery, such as support vector machine, random forest, extremely randomized trees, and other more recently developed deep learning methods. AI methods are relatively new to the development of peptide-based therapies, but these techniques already become essential tools in protein science by dissecting novel therapeutic peptides and their functions (Figure 1).[Figure: see text].

EXPERT OPINION

Researchers have shown that AI models can facilitate the development of peptidomics and selective peptide therapies in the field of peptide science. Biopeptide prediction is important for the discovery and development of successful peptide-based drugs. Due to their ability to predict therapeutic roles based on sequence details, many AI-dependent prediction tools have been developed (Figure 1).

PhosIDN: an integrated deep neural network for improving protein phosphorylation site prediction by combining sequence and protein-protein interaction information

Motivation

Phosphorylation is one of the most studied post-translational modifications, which plays a pivotal role in various cellular processes. Recently, deep learning methods have achieved great success in prediction of phosphorylation sites, but most of them are based on convolutional neural network that may not capture enough information about long-range dependencies between residues in a protein sequence. In addition, existing deep learning methods only make use of sequence information for predicting phosphorylation sites, and it is highly desirable to develop a deep learning architecture that can combine heterogeneous sequence and protein–protein interaction (PPI) information for more accurate phosphorylation site prediction.

Results

We present a novel integrated deep neural network named PhosIDN, for phosphorylation site prediction by extracting and combining sequence and PPI information. In PhosIDN, a sequence feature encoding sub-network is proposed to capture not only local patterns but also long-range dependencies from protein sequences. Meanwhile, useful PPI features are also extracted in PhosIDN by a PPI feature encoding sub-network adopting a multi-layer deep neural network. Moreover, to effectively combine sequence and PPI information, a heterogeneous feature combination sub-network is introduced to fully exploit the complex associations between sequence and PPI features, and their combined features are used for final prediction. Comprehensive experiment results demonstrate that the proposed PhosIDN significantly improves the prediction performance of phosphorylation sites and compares favorably with existing general and kinase-specific phosphorylation site prediction methods.

Availability and implementation

PhosIDN is freely available at https://github.com/ustchangyuanyang/PhosIDN.

Supplementary information

Supplementary data are available at Bioinformatics online.