BERT6mA: prediction of DNA N6-methyladenine site using deep learning-based approaches

Multi-scale DNA language model improves 6 mA binding sites prediction

DNA methylation at the N6 position of adenine (N6-methyladenine, 6 mA), which refers to the attachment of a methyl group to the N6 site of the adenine (A) of DNA, is an important epigenetic modification in prokaryotic and eukaryotic genomes. Accurately predicting the 6 mA binding sites can provide crucial insights into gene regulation, DNA repair, disease development and so on. Wet experiments are commonly used for analyzing 6 mA binding sites. However, they suffer from high cost and expensive time. Therefore, various deep learning methods have been widely used to predict 6 mA binding sites recently. In this study, we develop a framework based on multi-scale DNA language model named "iDNA6mA-MDL". "iDNA6mA-MDL" integrates multiple kmers and the nucleotide property and frequency method for feature embedding, which can capture a full range of DNA sequence context information. At the prediction stage, it also leverages DNABERT to compensate for the incomplete capture of global DNA information. Experiments show that our framework obtains average AUC of 0.981 on a classic 6 mA rice gene dataset, going beyond all existing advanced models under fivefold cross-validations. Moreover, "iDNA6mA-MDL" outperforms most of the popular state-of-the-art methods on another 11 6 mA datasets, demonstrating its effectiveness in 6 mA binding sites prediction.

TransC-ac4C: Identification of N4-Acetylcytidine (ac4C) Sites in mRNA Using Deep Learning

N4-acetylcytidine (ac4C) is a post-transcriptional modification in mRNA that is critical in mRNA translation in terms of stability and regulation. In the past few years, numerous approaches employing convolutional neural networks (CNN) and Transformer have been proposed for the identification of ac4C sites, with each variety of approaches processing distinct characteristics. CNN-based methods excel at extracting local features and positional information, whereas Transformer-based ones stands out in establishing long-range dependencies and generating global representations. Given the importance of both local and global features in mRNA ac4C sites identification, we propose a novel method termed TransC-ac4C which combines CNN and Transformer together for enhancing the feature extraction capability and improving the identification accuracy. Five different feature encoding strategies (One-hot, NCP, ND, EIIP, and K-mer) are employed to generate the mRNA sequence representations, in which way the sequence attributes and physical and chemical properties of the sequences can be embedded. To strengthen the relevance of features, we construct a novel feature fusion method. Firstly, the CNN is employed to process five single features, stitch them together and feed them to the Transformer layer. Then, our approach employs CNN to extract local features and Transformer subsequently to establish global long-range dependencies among extracted features. We use 5-fold cross-validation to evaluate the model, and the evaluation indicators are significantly improved. The prediction accuracy of the two datasets is as high as 81.42% and 80.69%, respectively. It demonstrates the stronger competitiveness and generalization performance of our model.

STM-ac4C: a hybrid model for identification of N4-acetylcytidine (ac4C) in human mRNA based on selective kernel convolution, temporal convolutional network, and multi-head self-attention

N4-acetylcysteine (ac4C) is a chemical modification in mRNAs that alters the structure and function of mRNA by adding an acetyl group to the N4 position of cytosine. Researchers have shown that ac4C is closely associated with the occurrence and development of various cancers. Therefore, accurate prediction of ac4C modification sites on human mRNA is crucial for revealing its role in diseases and developing new diagnostic and therapeutic strategies. However, existing deep learning models still have limitations in prediction accuracy and generalization ability, which restrict their effectiveness in handling complex biological sequence data. This paper introduces a deep learning-based model, STM-ac4C, for predicting ac4C modification sites on human mRNA. The model combines the advantages of selective kernel convolution, temporal convolutional networks, and multi-head self-attention mechanisms to effectively extract and integrate multi-level features of RNA sequences, thereby achieving high-precision prediction of ac4C sites. On the independent test dataset, STM-ac4C showed improvements of 1.81%, 3.5%, and 0.37% in accuracy, Matthews correlation coefficient, and area under the curve, respectively, compared to the existing state-of-the-art technologies. Moreover, its performance on additional balanced and imbalanced datasets also confirmed the model's robustness and generalization ability. Various experimental results indicate that STM-ac4C outperforms existing methods in predictive performance. In summary, STM-ac4C excels in predicting ac4C modification sites on human mRNA, providing a powerful new tool for a deeper understanding of the biological significance of mRNA modifications and cancer treatment. Additionally, the model reveals key sequence features that influence the prediction of ac4C sites through sequence region impact analysis, offering new perspectives for future research. The source code and experimental data are available at https://github.com/ymy12341/STM-ac4C.

iDNA-OpenPrompt: OpenPrompt learning model for identifying DNA methylation

Introduction: DNA methylation is a critical epigenetic modification involving the addition of a methyl group to the DNA molecule, playing a key role in regulating gene expression without changing the DNA sequence. The main difficulty in identifying DNA methylation sites lies in the subtle and complex nature of methylation patterns, which may vary across different tissues, developmental stages, and environmental conditions. Traditional methods for methylation site identification, such as bisulfite sequencing, are typically labor-intensive, costly, and require large amounts of DNA, hindering high-throughput analysis. Moreover, these methods may not always provide the resolution needed to detect methylation at specific sites, especially in genomic regions that are rich in repetitive sequences or have low levels of methylation. Furthermore, current deep learning approaches generally lack sufficient accuracy. Methods: This study introduces the iDNA-OpenPrompt model, leveraging the novel OpenPrompt learning framework. The model combines a prompt template, prompt verbalizer, and Pre-trained Language Model (PLM) to construct the prompt-learning framework for DNA methylation sequences. Moreover, a DNA vocabulary library, BERT tokenizer, and specific label words are also introduced into the model to enable accurate identification of DNA methylation sites. Results and Discussion: An extensive analysis is conducted to evaluate the predictive, reliability, and consistency capabilities of the iDNA-OpenPrompt model. The experimental outcomes, covering 17 benchmark datasets that include various species and three DNA methylation modifications (4mC, 5hmC, 6mA), consistently indicate that our model surpasses outstanding performance and robustness approaches.

PSAC-6mA: 6mA site identifier using self-attention capsule network based on sequence-positioning

DNA N6-methyladenine (6mA) modifications play a pivotal role in the regulation of growth, development, and diseases in organisms. As a significant epigenetic marker, 6mA modifications extensively participate in the intricate regulatory networks of the genome. Hence, gaining a profound understanding of how 6mA is intricately involved in these biological processes is imperative for deciphering the gene regulatory networks within organisms. In this study, we propose PSAC-6mA (Position-self-attention Capsule-6mA), a sequence-location-based self-attention capsule network. The positional layer in the model enables positional relationship extraction and independent parameter setting for each base position, avoiding parameter sharing inherent in convolutional approaches. Simultaneously, the self-attention capsule network enhances dimensionality, capturing correlation information between capsules and achieving exceptional results in feature extraction across multiple spatial dimensions within the model. Experimental results demonstrate the superior performance of PSAC-6mA in recognizing 6mA motifs across various species.

Multiple sequence alignment-based RNA language model and its application to structural inference

Compared with proteins, DNA and RNA are more difficult languages to interpret because four-letter coded DNA/RNA sequences have less information content than 20-letter coded protein sequences. While BERT (Bidirectional Encoder Representations from Transformers)-like language models have been developed for RNA, they are ineffective at capturing the evolutionary information from homologous sequences because unlike proteins, RNA sequences are less conserved. Here, we have developed an unsupervised multiple sequence alignment-based RNA language model (RNA-MSM) by utilizing homologous sequences from an automatic pipeline, RNAcmap, as it can provide significantly more homologous sequences than manually annotated Rfam. We demonstrate that the resulting unsupervised, two-dimensional attention maps and one-dimensional embeddings from RNA-MSM contain structural information. In fact, they can be directly mapped with high accuracy to 2D base pairing probabilities and 1D solvent accessibilities, respectively. Further fine-tuning led to significantly improved performance on these two downstream tasks compared with existing state-of-the-art techniques including SPOT-RNA2 and RNAsnap2. By comparison, RNA-FM, a BERT-based RNA language model, performs worse than one-hot encoding with its embedding in base pair and solvent-accessible surface area prediction. We anticipate that the pre-trained RNA-MSM model can be fine-tuned on many other tasks related to RNA structure and function.

Large language models in bioinformatics: applications and perspectives

Large language models (LLMs) are a class of artificial intelligence models based on deep learning, which have great performance in various tasks, especially in natural language processing (NLP). Large language models typically consist of artificial neural networks with numerous parameters, trained on large amounts of unlabeled input using self-supervised or semi-supervised learning. However, their potential for solving bioinformatics problems may even exceed their proficiency in modeling human language. In this review, we will present a summary of the prominent large language models used in natural language processing, such as BERT and GPT, and focus on exploring the applications of large language models at different omics levels in bioinformatics, mainly including applications of large language models in genomics, transcriptomics, proteomics, drug discovery and single cell analysis. Finally, this review summarizes the potential and prospects of large language models in solving bioinformatic problems.

Time series-based hybrid ensemble learning model with multivariate multidimensional feature coding for DNA methylation prediction

BACKGROUND

DNA methylation is a form of epigenetic modification that impacts gene expression without modifying the DNA sequence, thereby exerting control over gene function and cellular development. The prediction of DNA methylation is vital for understanding and exploring gene regulatory mechanisms. Currently, machine learning algorithms are primarily used for model construction. However, several challenges remain to be addressed, including limited prediction accuracy, constrained generalization capability, and insufficient learning capacity.

RESULTS

In response to the aforementioned challenges, this paper leverages the similarities between DNA sequences and time series to introduce a time series-based hybrid ensemble learning model, called Multi2-Con-CAPSO-LSTM. The model utilizes multivariate and multidimensional encoding approach, combining three types of time series encodings with three kinds of genetic feature encodings, resulting in a total of nine types of feature encoding matrices. Convolutional Neural Networks are utilized to extract features from DNA sequences, including temporal, positional, physicochemical, and genetic information, thereby creating a comprehensive feature matrix. The Long Short-Term Memory model is then optimized using the Chaotic Accelerated Particle Swarm Optimization algorithm for predicting DNA methylation.

CONCLUSIONS

Through cross-validation experiments conducted on 17 species involving three types of DNA methylation (6 mA, 5hmC, and 4mC), the results demonstrate the robust predictive capabilities of the Multi2-Con-CAPSO-LSTM model in DNA methylation prediction across various types and species. Compared with other benchmark models, the Multi2-Con-CAPSO-LSTM model demonstrates significant advantages in sensitivity, specificity, accuracy, and correlation. The model proposed in this paper provides valuable insights and inspiration across various disciplines, including sequence alignment, genetic evolution, time series analysis, and structure-activity relationships.

StableDNAm: towards a stable and efficient model for predicting DNA methylation based on adaptive feature correction learning

BACKGROUND

DNA methylation, instrumental in numerous life processes, underscores the paramount importance of its accurate prediction. Recent studies suggest that deep learning, due to its capacity to extract profound insights, provides a more precise DNA methylation prediction. However, issues related to the stability and generalization performance of these models persist.

RESULTS

In this study, we introduce an efficient and stable DNA methylation prediction model. This model incorporates a feature fusion approach, adaptive feature correction technology, and a contrastive learning strategy. The proposed model presents several advantages. First, DNA sequences are encoded at four levels to comprehensively capture intricate information across multi-scale and low-span features. Second, we design a sequence-specific feature correction module that adaptively adjusts the weights of sequence features. This improvement enhances the model's stability and scalability, or its generality. Third, our contrastive learning strategy mitigates the instability issues resulting from sparse data. To validate our model, we conducted multiple sets of experiments on commonly used datasets, demonstrating the model's robustness and stability. Simultaneously, we amalgamate various datasets into a single, unified dataset. The experimental outcomes from this combined dataset substantiate the model's robust adaptability.

CONCLUSIONS

Our research findings affirm that the StableDNAm model is a general, stable, and effective instrument for DNA methylation prediction. It holds substantial promise for providing invaluable assistance in future methylation-related research and analyses.

DLC-ac4C: A Prediction Model for N4-acetylcytidine Sites in Human mRNA Based on DenseNet and Bidirectional LSTM Methods

Introduction

N4 acetylcytidine (ac4C) is a highly conserved nucleoside modification that is essential for the regulation of immune functions in organisms. Currently, the identification of ac4C is primarily achieved using biological methods, which can be time-consuming and labor-intensive. In contrast, accurate identification of ac4C by computational methods has become a more effective method for classification and prediction.

Aim

To the best of our knowledge, although there are several computational methods for ac4C locus prediction, the performance of the models they constructed is poor, and the network structure they used is relatively simple and suffers from the disadvantage of network degradation. This study aims to improve these limitations by proposing a predictive model based on integrated deep learning to better help identify ac4C sites.

Methods

In this study, we propose a new integrated deep learning prediction framework, DLC-ac4C. First, we encode RNA sequences based on three feature encoding schemes, namely C2 encoding, nucleotide chemical property (NCP) encoding, and nucleotide density (ND) encoding. Second, one-dimensional convolutional layers and densely connected convolutional networks (DenseNet) are used to learn local features, and bi-directional long short-term memory networks (Bi-LSTM) are used to learn global features. Third, a channel attention mechanism is introduced to determine the importance of sequence characteristics. Finally, a homomorphic integration strategy is used to limit the generalization error of the model, which further improves the performance of the model.

Results

The DLC-ac4C model performed well in terms of sensitivity (Sn), specificity (Sp), accuracy (Acc), Mathews correlation coefficient (MCC), and area under the curve (AUC) for the independent test data with 86.23%, 79.71%, 82.97%, 66.08%, and 90.42%, respectively, which was significantly better than the prediction accuracy of the existing methods.

Conclusion

Our model not only combines DenseNet and Bi-LSTM, but also uses the channel attention mechanism to better capture hidden information features from a sequence perspective, and can identify ac4C sites more effectively.

MSTL-Kace: Prediction of Prokaryotic Lysine Acetylation Sites Based on Multistage Transfer Learning Strategy

As one of the most important post-translational modifications (PTM), lysine acetylation (Kace) plays an important role in various biological activities. Traditional experimental methods for identifying Kace sites are inefficient and expensive. Instead, several machine learning methods have been developed for Kace site prediction, and hand-crafted features have been used to encode the protein sequences. However, there are still two challenges: the complex biological information may be under-represented by these manmade features and the small sample issue of some species needs to be addressed. We propose a novel model, MSTL-Kace, which was developed based on transfer learning strategy with pretrained bidirectional encoder representations from transformers (BERT) model. In this model, the high-level embeddings were extracted from species-specific BERT models, and a two-stage fine-tuning strategy was used to deal with small sample issue. Specifically, a domain-specific BERT model was pretrained using all of the sequences in our data sets, which was then fine-tuned, or two-stage fine-tuned based on the training data set of each species to obtain the species-specific BERT models. Afterward, the embeddings of residues were extracted from the fine-tuned model and fed to the different downstream learning algorithms. After comparison, the best model for the six prokaryotic species was built by using a random forest. The results for the independent test sets show that our model outperforms the state-of-the-art methods on all six species. The source codes and data for MSTL-Kace are available at https://github.com/leo97king/MSTL-Kace.

Comprehensive analysis of m6A modifications in oral squamous cell carcinoma by MeRIP sequencing

N6-methyladenosine (m6A) modifications are the most abundant internal modifications of mRNA and have a significant role in various cancers; however, the m6A methylome profile of oral squamous cell carcinoma (OSCC) in the mRNA-wide remains unknown. In this study, we examined the relationship between m6A and OSCC. Four pairs of OSCC and adjacent normal tissues were compared by Methylated RNA immunoprecipitation sequencing (MeRIP-seq). Gene Ontology, Kyoto Encyclopedia of Genes and Genomes (KEGG), and Ingenuity Pathway Analysis (IPA) analyses were used to further analyze the MeRIP-seq data. A total of 2,348 different m6A peaks were identified in the OSCC group, including 85 m6A upregulated peaks and 2,263 m6A downregulated peaks. Differentially methylated m6A binding sites were enriched in the coding sequence in proximity to the stop codon of both groups. KEGG analysis revealed genes with upregulated m6A-modified sites in the OSCC group, which were prominently associated with the forkhead box O (FOXO) signaling pathway. Genes containing downregulated m6A-modified sites were significantly correlated with the PI3K/Akt signaling pathway, spliceosome, protein processing in the endoplasmic reticulum, and endocytosis. IPA analysis indicated that several genes with differential methylation peaks form networks with m6A regulators. Overall, this study established the mRNA-wide m6A map for human OSCC and indicated the potential links between OSCC and N6-methyladenosine modification.

Prediction of DNA Methylation based on Multi-dimensional feature encoding and double convolutional fully connected convolutional neural network

DNA methylation takes on critical significance to the regulation of gene expression by affecting the stability of DNA and changing the structure of chromosomes. DNA methylation modification sites should be identified, which lays a solid basis for gaining more insights into their biological functions. Existing machine learning-based methods of predicting DNA methylation have not fully exploited the hidden multidimensional information in DNA gene sequences, such that the prediction accuracy of models is significantly limited. Besides, most models have been built in terms of a single methylation type. To address the above-mentioned issues, a deep learning-based method was proposed in this study for DNA methylation site prediction, termed the MEDCNN model. The MEDCNN model is capable of extracting feature information from gene sequences in three dimensions (i.e., positional information, biological information, and chemical information). Moreover, the proposed method employs a convolutional neural network model with double convolutional layers and double fully connected layers while iteratively updating the gradient descent algorithm using the cross-entropy loss function to increase the prediction accuracy of the model. Besides, the MEDCNN model can predict different types of DNA methylation sites. As indicated by the experimental results,the deep learning method based on coding from multiple dimensions outperformed single coding methods, and the MEDCNN model was highly applicable and outperformed existing models in predicting DNA methylation between different species. As revealed by the above-described findings, the MEDCNN model can be effective in predicting DNA methylation sites.

Transformer Architecture and Attention Mechanisms in Genome Data Analysis: A Comprehensive Review

The emergence and rapid development of deep learning, specifically transformer-based architectures and attention mechanisms, have had transformative implications across several domains, including bioinformatics and genome data analysis. The analogous nature of genome sequences to language texts has enabled the application of techniques that have exhibited success in fields ranging from natural language processing to genomic data. This review provides a comprehensive analysis of the most recent advancements in the application of transformer architectures and attention mechanisms to genome and transcriptome data. The focus of this review is on the critical evaluation of these techniques, discussing their advantages and limitations in the context of genome data analysis. With the swift pace of development in deep learning methodologies, it becomes vital to continually assess and reflect on the current standing and future direction of the research. Therefore, this review aims to serve as a timely resource for both seasoned researchers and newcomers, offering a panoramic view of the recent advancements and elucidating the state-of-the-art applications in the field. Furthermore, this review paper serves to highlight potential areas of future investigation by critically evaluating studies from 2019 to 2023, thereby acting as a stepping-stone for further research endeavors.

EMDL-ac4C: identifying N4-acetylcytidine based on ensemble two-branch residual connection DenseNet and attention

Introduction: N4-acetylcytidine (ac4C) is a critical acetylation modification that has an essential function in protein translation and is associated with a number of human diseases. Methods: The process of identifying ac4C sites by biological experiments is too cumbersome and costly. And the performance of several existing computational models needs to be improved. Therefore, we propose a new deep learning tool EMDL-ac4C to predict ac4C sites, which uses a simple one-hot encoding for a unbalanced dataset using a downsampled ensemble deep learning network to extract important features to identify ac4C sites. The base learner of this ensemble model consists of a modified DenseNet and Squeeze-and-Excitation Networks. In addition, we innovatively add a convolutional residual structure in parallel with the dense block to achieve the effect of two-layer feature extraction. Results: The average accuracy (Acc), mathews correlation coefficient (MCC), and area under the curve Area under curve of EMDL-ac4C on ten independent testing sets are 80.84%, 61.77%, and 87.94%, respectively. Discussion: Multiple experimental comparisons indicate that EMDL-ac4C outperforms existing predictors and it greatly improved the predictive performance of the ac4C sites. At the same time, EMDL-ac4C could provide a valuable reference for the next part of the study. The source code and experimental data are available at: https://github.com/13133989982/EMDLac4C.

NeuroPpred-SVM: A New Model for Predicting Neuropeptides Based on Embeddings of BERT

Neuropeptides play pivotal roles in different physiological processes and are related to different kinds of diseases. Identification of neuropeptides is of great benefit for studying the mechanism of these physiological processes and the treatment of neurological disorders. Several state-of-the-art neuropeptide predictors have been developed by using a two-layer stacking ensemble algorithm. Although the two-layer stacking ensemble algorithm can improve the feature representability, these models are complex, which are not as efficient as the models based on one classifier. In this study, we proposed a new model, NeuroPpred-SVM, to predict neuropeptides based on the embeddings of Bidirectional Encoder Representations from Transformers and other sequential features by using a support vector machine (SVM). The experimental results indicate that our model achieved a cross-validation area under the receiver operating characteristic (AUROC) curve of 0.969 on the training data set and an AUROC of 0.966 on the independent test set. By comparing our model with the other four state-of-the-art models including NeuroPIpred, PredNeuroP, NeuroPpred-Fuse, and NeuroPpred-FRL on the independent test set, our model achieved the highest AUROC, Matthews correlation coefficient, accuracy, and specificity, which indicate that our model outperforms the existing models. We believed that NeuroPpred-SVM could be a useful tool for identifying neuropeptides with high accuracy and low cost. The data sets and Python code are available at https://github.com/liuyf-a/NeuroPpred-SVM.

DNA-MP: a generalized DNA modifications predictor for multiple species based on powerful sequence encoding method

Accurate prediction of deoxyribonucleic acid (DNA) modifications is essential to explore and discern the process of cell differentiation, gene expression and epigenetic regulation. Several computational approaches have been proposed for particular type-specific DNA modification prediction. Two recent generalized computational predictors are capable of detecting three different types of DNA modifications; however, type-specific and generalized modifications predictors produce limited performance across multiple species mainly due to the use of ineffective sequence encoding methods. The paper in hand presents a generalized computational approach "DNA-MP" that is competent to more precisely predict three different DNA modifications across multiple species. Proposed DNA-MP approach makes use of a powerful encoding method "position specific nucleotides occurrence based 117 on modification and non-modification class densities normalized difference" (POCD-ND) to generate the statistical representations of DNA sequences and a deep forest classifier for modifications prediction. POCD-ND encoder generates statistical representations by extracting position specific distributional information of nucleotides in the DNA sequences. We perform a comprehensive intrinsic and extrinsic evaluation of the proposed encoder and compare its performance with 32 most widely used encoding methods on $17$ benchmark DNA modifications prediction datasets of $12$ different species using $10$ different machine learning classifiers. Overall, with all classifiers, the proposed POCD-ND encoder outperforms existing $32$ different encoders. Furthermore, combinedly over 5-fold cross validation benchmark datasets and independent test sets, proposed DNA-MP predictor outperforms state-of-the-art type-specific and generalized modifications predictors by an average accuracy of 7% across 4mc datasets, 1.35% across 5hmc datasets and 10% for 6ma datasets. To facilitate the scientific community, the DNA-MP web application is available at https://sds_genetic_analysis.opendfki.de/DNA_Modifications/.

CNN6mA: Interpretable neural network model based on position-specific CNN and cross-interactive network for 6mA site prediction

N6-methyladenine (6mA) plays a critical role in various epigenetic processing including DNA replication, DNA repair, silencing, transcription, and diseases such as cancer. To understand such epigenetic mechanisms, 6 mA has been detected by high-throughput technologies on a genome-wide scale at single-base resolution, together with conventional methods such as immunoprecipitation, mass spectrometry and capillary electrophoresis, but these experimental approaches are time-consuming and laborious. To complement these problems, we have developed a CNN-based 6 mA site predictor, named CNN6mA, which proposed two new architectures: a position-specific 1-D convolutional layer and a cross-interactive network. In the position-specific 1-D convolutional layer, position-specific filters with different window sizes were applied to an inquiry sequence instead of sharing the same filters over all positions in order to extract the position-specific features at different levels. The cross-interactive network explored the relationships between all the nucleotide patterns within the inquiry sequence. Consequently, CNN6mA outperformed the existing state-of-the-art models in many species and created the contribution score vector that intelligibly interpret the prediction mechanism. The source codes and web application in CNN6mA are freely accessible at https://github.com/kuratahiroyuki/CNN6mA.git and http://kurata35.bio.kyutech.ac.jp/CNN6mA/, respectively.

MuLan-Methyl-multiple transformer-based language models for accurate DNA methylation prediction

Transformer-based language models are successfully used to address massive text-related tasks. DNA methylation is an important epigenetic mechanism, and its analysis provides valuable insights into gene regulation and biomarker identification. Several deep learning-based methods have been proposed to identify DNA methylation, and each seeks to strike a balance between computational effort and accuracy. Here, we introduce MuLan-Methyl, a deep learning framework for predicting DNA methylation sites, which is based on 5 popular transformer-based language models. The framework identifies methylation sites for 3 different types of DNA methylation: N6-adenine, N4-cytosine, and 5-hydroxymethylcytosine. Each of the employed language models is adapted to the task using the "pretrain and fine-tune" paradigm. Pretraining is performed on a custom corpus of DNA fragments and taxonomy lineages using self-supervised learning. Fine-tuning aims at predicting the DNA methylation status of each type. The 5 models are used to collectively predict the DNA methylation status. We report excellent performance of MuLan-Methyl on a benchmark dataset. Moreover, we argue that the model captures characteristic differences between different species that are relevant for methylation. This work demonstrates that language models can be successfully adapted to applications in biological sequence analysis and that joint utilization of different language models improves model performance. Mulan-Methyl is open source, and we provide a web server that implements the approach.

Feedback-AVPGAN: Feedback-guided generative adversarial network for generating antiviral peptides

In this study, we propose Feedback-AVPGAN, a system that aims to computationally generate novel antiviral peptides (AVPs). This system relies on the key premise of the Generative Adversarial Network (GAN) model and the Feedback method. GAN, a generative modeling approach that uses deep learning methods, comprises a generator and a discriminator. The generator is used to generate peptides; the generated proteins are fed to the discriminator to distinguish between the AVPs and non-AVPs. The original GAN design uses actual data to train the discriminator. However, not many AVPs have been experimentally obtained. To solve this problem, we used the Feedback method to allow the discriminator to learn from the existing as well as generated synthetic data. We implemented this method using a classifier module that classifies each peptide sequence generated by the GAN generator as AVP or non-AVP. The classifier uses the transformer network and achieves high classification accuracy. This mechanism enables the efficient generation of peptides with a high probability of exhibiting antiviral activity. Using the Feedback method, we evaluated various algorithms and their performance. Moreover, we modeled the structure of the generated peptides using AlphaFold2 and determined the peptides having similar physicochemical properties and structures to those of known AVPs, although with different sequences.

iDNA-ABF: multi-scale deep biological language learning model for the interpretable prediction of DNA methylations

In this study, we propose iDNA-ABF, a multi-scale deep biological language learning model that enables the interpretable prediction of DNA methylations based on genomic sequences only. Benchmarking comparisons show that our iDNA-ABF outperforms state-of-the-art methods for different methylation predictions. Importantly, we show the power of deep language learning in capturing both sequential and functional semantics information from background genomes. Moreover, by integrating the interpretable analysis mechanism, we well explain what the model learns, helping us build the mapping from the discovery of important sequential determinants to the in-depth analysis of their biological functions.

Cross-attention PHV: Prediction of human and virus protein-protein interactions using cross-attention-based neural networks

•

Cross-attention PHV implements two key technologies: cross-attention mechanism and 1D-CNN.

•

It accurately predicts PPIs between human and unknown influenza viruses/SARS-CoV-2.

•

It extracts critical taxonomic and evolutionary differences responsible for PPI prediction.

Viral infections represent a major health concern worldwide. The alarming rate at which SARS-CoV-2 spreads, for example, led to a worldwide pandemic. Viruses incorporate genetic material into the host genome to hijack host cell functions such as the cell cycle and apoptosis. In these viral processes, protein–protein interactions (PPIs) play critical roles. Therefore, the identification of PPIs between humans and viruses is crucial for understanding the infection mechanism and host immune responses to viral infections and for discovering effective drugs. Experimental methods including mass spectrometry-based proteomics and yeast two-hybrid assays are widely used to identify human-virus PPIs, but these experimental methods are time-consuming, expensive, and laborious. To overcome this problem, we developed a novel computational predictor, named cross-attention PHV, by implementing two key technologies of the cross-attention mechanism and a one-dimensional convolutional neural network (1D-CNN). The cross-attention mechanisms were very effective in enhancing prediction and generalization abilities. Application of 1D-CNN to the word2vec-generated feature matrices reduced computational costs, thus extending the allowable length of protein sequences to 9000 amino acid residues. Cross-attention PHV outperformed existing state-of-the-art models using a benchmark dataset and accurately predicted PPIs for unknown viruses. Cross-attention PHV also predicted human–SARS-CoV-2 PPIs with area under the curve values >0.95. The Cross-attention PHV web server and source codes are freely available at https://kurata35.bio.kyutech.ac.jp/Cross-attention_PHV/ and https://github.com/kuratahiroyuki/Cross-Attention_PHV, respectively.

DNA N6-Methyladenine Modification in Eukaryotic Genome

DNA methylation is treated as an important epigenetic mark in various biological activities. In the past, a large number of articles focused on 5 mC while lacking attention to N6-methyladenine (6 mA). The presence of 6 mA modification was previously discovered only in prokaryotes. Recently, with the development of detection technologies, 6 mA has been found in several eukaryotes, including protozoans, metazoans, plants, and fungi. The importance of 6 mA in prokaryotes and single-celled eukaryotes has been widely accepted. However, due to the incredibly low density of 6 mA and restrictions on detection technologies, the prevalence of 6 mA and its role in biological processes in eukaryotic organisms are highly debated. In this review, we first summarize the advantages and disadvantages of 6 mA detection methods. Then, we conclude existing reports on the prevalence of 6 mA in eukaryotic organisms. Next, we highlight possible methyltransferases, demethylases, and the recognition proteins of 6 mA. In addition, we summarize the functions of 6 mA in eukaryotes. Last but not least, we summarize our point of view and put forward the problems that need further research.