BMC Bioinformatics最新文献

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.

Accurate cell type classification is critical for downstream analysis in single-cell RNA sequencing (scRNA-seq). Most existing methods rely on a single type of feature representation-such as statistical, information theory, matrix factorization, or deep learning-based features. However, each captures different aspects of the data, and no single feature type can fully represent the complex differences between cell types. Moreover, naïvely concatenating multiple features may introduce redundancy or noise, reducing model performance. To address these challenges, we propose scMFF, which is a multiple feature fusion framework that integrates four features and explores six fusion strategies in combination with various classifiers for single-cell type classification. Comprehensive evaluations on 42 disease-related datasets and an external COVID-19 dataset demonstrate that scMFF outperforms single-feature approaches in terms of performance and stability, providing a reliable and effective solution for scRNA-seq data analysis.

Background: Quantitative kinetic models of biological regulatory processes play an important role in understanding disease mechanisms. However, their simulation and analysis require specialized domain expertise.

Results: In this study, we present Talk2Biomodels (T2B), an open-source, user-friendly, large language model-based agentic AI platform designed to facilitate access to computational models of biological systems and promote the FAIRification (Findability, Accessibility, Interoperability, and Reusability) principles in systems biology. T2B allows users to interact with and analyse mathematical models of biological systems through conversations in natural language, thereby lowering the barrier to entry for model interpretation and hypothesis-driven exploration. The platform natively supports models encoded in the Systems Biology Markup Language, a widely adopted standard in the computational biology community. T2B is integrated with the BioModels database ( https://www.ebi.ac.uk/biomodels/ ), enabling retrieval, simulation, and analysis of curated systems biology models. We illustrate the platform's capabilities through use cases in precision medicine, infectious disease epidemiology, and the study of emergent network-level properties in cellular systems - demonstrating how both computational experts and domain scientists without formal modelling training can derive actionable insights from complex biological models. Talk2Biomodels is available at https://github.com/VirtualPatientEngine/AIAgents4Pharma . Detailed documentation and use cases are available at https://virtualpatientengine.github.io/AIAgents4Pharma/talk2biomodels/intro/ .

Conclusions: In summary, T2B lowers the barrier for non-experts to engage with and extract insights from computational models of biological systems, while simultaneously providing experts with a streamlined interface for analysing models and overall contributes to the FAIRification of models.