BMC Bioinformatics最新文献

Background: Most multiple sequence alignment and string-graph alignment algorithms focus on global alignment, but many applications exist for semi-global and local string-graph alignment. Long reads require enormous amounts of memory and runtime to fill out large dynamic programming tables. Effective algorithms for finding the backbone and thus defining a band of an alignment such as the longest common subsequence with kmer matches (LCSk++) exist but do not work with graphs. This study introduces an adaptation of the Longest Common Subsequence with kmer matches (LCSk++) algorithm tailored for graph structures, particularly focusing on Partial Order Alignment (POA) graphs. POA graphs, which are directed acyclic graphs, represent multiple sequence alignments and effectively capture the relationships between sequences. State-of-the-art methods like ABPOA and SPOA improve upon POA, while ABPOA incorporates banding, SPOA does not; however, neither utilizes parallel processing despite leveraging SIMD for faster matrix calculations. Our approach addresses these limitations by extending the LCSk++ algorithm to handle the complexities of graph-based alignment while incorporating SIMD, banding, and parallel processing for enhanced efficiency.

Results: Our extended LCSk++ algorithm integrates dynamic programming and graph traversal techniques to detect conserved regions within POA graphs, termed the LCSk++ backbone. This backbone enables precise banding of the POA matrix for all alignment modes (global, semi-global, and local). Unlike ABPOA, which only allows banded global alignment, our approach enables broader flexibility and significantly improves consensus sequence construction. While supporting more alignment modes than ABPOA, it also outperforms SPOA's global alignment, with substantial memory savings (up to 98%) and significant run-time reductions (up to 25x), particularly for long sequences (> 30,000 bp). Our method maintains high alignment accuracy and proves effective across various string lengths and datasets, including synthetic and PacBio HiFi reads. Parallel processing further enhances runtime efficiency, achieving up to 150x speed improvements on conventional PCs.

Conclusion: The extended LCSk++ algorithm for graph structures offers a substantial advancement in sequence alignment technology. It effectively reduces memory consumption and optimizes run times without compromising alignment quality, thus providing a robust solution for all alignment modes (global, local, and semi-global) in POA. This method enhances the utility of POA in critical applications such as multiple sequence alignment for phylogeny construction and graph-based reference alignment.

Background: Reconstructing ECG signals from PPG measurements is a critical task for non-invasive cardiac monitoring. While several public ECG-PPG datasets exist, they lack the diversity found in image datasets, and the data collection process often introduces noise, making ECG reconstruction from PPG signals challenging even for advanced machine learning models.

Results: We propose a novel ODE-based method for generating synthetic ECG-PPG pairs to enhance training diversity. Building on this, we introduce CLEP-GAN, a subject-independent PPG-to-ECG reconstruction framework that integrates contrastive learning, adversarial learning, and attention gating. CLEP-GAN achieves performance that matches or surpasses current state-of-the-art methods, particularly in reconstructing ECG signals from unseen subjects. Evaluation on real-world datasets (BIDMC and CapnoBase) confirms its effectiveness. Additionally, our analysis shows that demographic factors such as sex and age significantly impact reconstruction accuracy, emphasizing the importance of incorporating demographic diversity during model training and data augmentation.

Conclusions: Our method produces synthetic ECG-PPG pairs with RR interval distributions closely aligned with their real counterparts and shows strong potential to simulate diverse rhythms such as regular sinus rhythm (RSR), sinus arrhythmia (SA), and atrial fibrillation (AFib). Furthermore, CLEP-GAN demonstrates robust performance on both synthetic and real datasets, achieving near-perfect reconstruction in synthetic settings and competitive results on real data. These findings highlight CLEP-GAN's promise for reliable, non-invasive ECG monitoring in clinical applications.

As data complexity and volume increase rapidly, efficient statistical methods for identifying significant variables become crucial. Variable selection plays a vital role in establishing relationships between predictors and response variables. The challenge lies in achieving this goal while controlling the False Discovery Rate (FDR) and maintaining statistical power. The knockoff filter, a recent approach, generates inexpensive knockoff variables that mimic the correlation structure of the original variables, serving as negative controls for inference. In this study, we extend the use of knockoffs to Light Gradient Boosting Machine (LightGBM), a fast and accurate machine learning technique. Shapely Additive Explanations (SHAP) values are employed to interpret the black-box nature of machine learning. Through extensive experimentation, our proposed method outperforms traditional approaches, accurately identifying important variables for each class. It offers improved speed and efficiency across multiple datasets. To validate our approach, an extensive simulation study is conducted. The integration of knockoffs into LightGBM enhances performance and interpretability, contributing to the advancement of variable selection methods. Our research addresses the challenges of variable selection in the era of big data, providing a valuable tool for identifying relevant variables in statistical modeling and machine learning applications.

Background: Accurately identifying RNA 2'-O-methylation (2OM) sites is a crucial step in gaining an in-depth understanding of RNA regulatory mechanisms. Although there are currently multiple prediction tools available, they still suffer from limited prediction accuracy and an inability to fully capture the associations between sequences and sites.

Results: This study constructs a novel low-redundancy dataset and innovatively proposes the KN-PairMatrix encoding scheme, effectively addressing the research gap in sequence-site association analysis. Based on this foundation, we developed the deep learning framework OMetaNet, which integrates residual and downsampling-optimized CNN modules, Mamba network, and a proprietary cross-modal interactive fusion module. The framework incorporates a contrastive learning-driven adaptive hybrid loss function. Employing a progressive feature disentanglement strategy, it enhances the learning capability for 2OM site-specific patterns. Independent evaluation results demonstrate that OMetaNet significantly outperforms existing methods in predicting 2OM sites across all four nucleotide types.

Conclusions: We proposed a novel computational model, OMetaNet. Its unique design structure may potentially reshape the paradigm of transcriptome analysis, open up new directions for extracting modification site information, and show significant potential in biomarker research and cross-species generalization studies.

Background: Protein-protein interactions regulate the dynamic operation of intracellular molecular networks, serving as the molecular basis for revealing protein functions and disease mechanisms. Recently, several computational methods for predicting protein-protein interaction sites (PPIs) have been presented as alternatives to costly and labor-intensive traditional experiments. However, existing methods generally ignore the inherent hierarchical structure of protein chains. Furthermore, the equivariance of graph structure during spatial transformations is often neglected when applying graph neural networks to modeling. Therefore, accurately identifying PPIs remains a challenging task.

Results: In this work, we propose an end-to-end GNN-based computational method, EGCPPIS, for efficiently identifying protein-protein interaction sites. First, we construct a hierarchical graph representation of the protein chain, including residue-level graph and atom-level graph. Next, EGCPPIS designs an E(n) Equivariant Graph Neural Network (EGNN) module to learn residue-level embeddings with equivariant features. After further extracting atom-level embeddings using the GraphSAGE module, we introduce the contrastive learning strategy to integrate hierarchical graph features. This strategy enables us to learn consistent embeddings between residue-level and atom-level representations. Finally, the fused embeddings are weighted using an improved gated multi-head attention mechanism.

Conclusion: Comprehensive evaluation results on multiple datasets demonstrate that EGCPPIS significantly outperforms state-of-the-art methods. Extensive comparative experiments and case studies further confirm that EGCPPIS can reveal the decision-making patterns in PPIs prediction, facilitating the discovery of potential PPIs. The original datasets and code of EGCPPIS are available at https://github.com/GuicongSun/EGCPPIS .

Background: RNA methylation (RM) regulates gene expression regulation, RNA stability, and protein translation. Accurate prediction of RM modification sites is essential for understanding their biological functions. However, existing wet-lab detection techniques face challenges including operational complexity and high costs. Deep learning (DL) methods have been applied to this task. However, existing methods show performance degradation with smaller training datasets. For instance, the Bidirectional Gated Recurrent Unit (BGRU) demonstrates substantial performance degradation. Contrastive Learning Network (CNN) can extract local pattern features but learns overly specific patterns with sample-limited data, resulting in poor feature generalization. Bidirectional Long Short-Term Memory (BiLSTM) excels at modeling long-range dependencies but cannot sufficiently learn gating mechanism parameters to capture effective sequence representations with limited samples. Transformer processes sequences in parallel and captures global dependencies through self-attention, but its quadratic computational complexity and large parameter count make it prone to overfitting on small datasets. Current DL methods show reduced performance when training data is limited.

Results: This study proposes a Multi-view Contrastive Learning with CNN-BiLSTM-Attention (MCLCBA) framework for RM modification site prediction. The multi-view approach comprises a primary view and auxiliary view, where the primary view utilizes DNA Bidirectional Encoder Representations from Transformers (DNABERT) to extract sequence contextual features, and the auxiliary view employs Chaos Game Representation (CGR) to extract structural features. Feature extraction includes four components: data augmentation, multi-view encoders, projection heads, and contrastive loss functions. By implementing dual differential data augmentation strategies and constructing multi-view network architectures for feature processing and fusion, the model learns discriminative feature representations invariant to data augmentation through maximizing positive sample similarity while minimizing negative sample similarity. This effectively addresses sample-limited feature learning scenarios. Experimental results on the sample-limited m⁷G dataset demonstrate that MCLCBA achieves AUROC and AUPRC of 85.64% and 86.94%, respectively, improving upon existing methods by 5-6% in both metrics.

Conclusions: Through multi-view contrastive learning, MCLCBA provides an approach for RM sites under sample-limited scenarios.

Background: Single-cell RNA sequencing (scRNA-seq) provides extensive opportunities to explore cellular heterogeneity but is often limited by substantial technical noise and variability. The prevalence of zero counts, arising from both biological variation and technical dropout events, poses significant challenges for downstream analyses. Existing imputation methods face inherent trade-offs: statistical approaches maintain interpretability but exhibit limited capacity for capturing complex, non-linear gene expression relationships, whereas deep learning methods demonstrate superior flexibility but are prone to overfitting and lack mechanistic interpretability, particularly in settings with limited sample sizes.

Methods: We present ZILLNB (Zero-Inflated Latent factors Learning-based Negative Binomial), a novel computational framework that integrates zero-inflated negative binomial (ZINB) regression with deep generative modeling. ZILLNB employs an ensemble architecture combining Information Variational Autoencoder (InfoVAE) and Generative Adversarial Network (GAN) to learn latent representations at cellular and gene levels. These latent factors serve as dynamic covariates within a ZINB regression framework, with parameters iteratively optimized through an Expectation-Maximization algorithm. This approach enables systematic decomposition of technical variability from intrinsic biological heterogeneity.

Results: Comparative evaluations across multiple scRNA-seq datasets demonstrate ZILLNB's superior performance. In cell type classification tasks using mouse cortex and human PBMC datasets, ZILLNB achieved the highest Adjusted Rand index (ARI) and Adjusted Mutual Information (AMI) among tested methods, with improvements ranging from 0.05 to 0.2 over VIPER, scImpute, DCA, DeepImpute, SAVER, scMultiGAN and ALRA. For differential expression analysis validated against matched bulk RNA-seq data, ZILLNB demonstrated improvements ranging from 0.05 to 0.3 for area under the Receiver Operating Characteristic curve (AUC-ROC) and the Precision-Recall curve (AUC-PR) compared to standard and other imputation methods, with consistently lower false discovery rates. Application to idiopathic pulmonary fibrosis (IPF) datasets revealed distinct fibroblast subpopulations undergoing fibroblast-to-myofibroblast transition, validated through marker gene expression and pathway enrichment analyses.

Conclusion: ZILLNB provides a principled framework for addressing technical artifacts in scRNA-seq data while preserving biological variation. The integration of statistical modeling with deep learning enables robust performance across diverse analytical tasks, including cell type identification, differential expression analysis, and rare cell population discovery, demonstrating utility across common single-cell analysis tasks.