Abstract Understanding the biological functions and processes of genes, particularly those not yet characterized, is crucial for advancing molecular biology and identifying therapeutic targets. The ...hypothesis guiding this study is that the 3D proximity of genes correlates with their functional interactions and relevance in prokaryotes. We introduced 3D-GeneNet, an innovative software tool that utilizes high-throughput sequencing data from chromosome conformation capture techniques and integrates topological metrics to construct gene association networks. Through a series of comparative analyses focused on spatial versus linear distances, we explored various dimensions such as topological structure, functional enrichment levels, distribution patterns of linear distances among gene pairs, and the area under the receiver operating characteristic curve by utilizing model organism Escherichia coli K-12. Furthermore, 3D-GeneNet was shown to maintain good accuracy compared to multiple algorithms (neighbourhood, co-occurrence, coexpression, and fusion) across multiple bacteria, including E. coli, Brucella abortus, and Vibrio cholerae. In addition, the accuracy of 3D-GeneNet’s prediction of long-distance gene interactions was identified by bacterial two-hybrid assays on E. coli K-12 MG1655, where 3D-GeneNet not only increased the accuracy of linear genomic distance tripled but also achieved 60% accuracy by running alone. Finally, it can be concluded that the applicability of 3D-GeneNet will extend to various bacterial forms, including Gram-negative, Gram-positive, single-, and multi-chromosomal bacteria through Hi-C sequencing and analysis. Such findings highlight the broad applicability and significant promise of this method in the realm of gene association network. 3D-GeneNet is freely accessible at https://github.com/gaoyuanccc/3D-GeneNet.
Abstract Bioactive peptide therapeutics has been a long-standing research topic. Notably, the antimicrobial peptides (AMPs) have been extensively studied for its therapeutic potential. Meanwhile, the ...demand for annotating other therapeutic peptides, such as antiviral peptides (AVPs) and anticancer peptides (ACPs), also witnessed an increase in recent years. However, we conceive that the structure of peptide chains and the intrinsic information between the amino acids is not fully investigated among the existing protocols. Therefore, we develop a new graph deep learning model, namely TP-LMMSG, which offers lightweight and easy-to-deploy advantages while improving the annotation performance in a generalizable manner. The results indicate that our model can accurately predict the properties of different peptides. The model surpasses the other state-of-the-art models on AMP, AVP and ACP prediction across multiple experimental validated datasets. Moreover, TP-LMMSG also addresses the challenges of time-consuming pre-processing in graph neural network frameworks. With its flexibility in integrating heterogeneous peptide features, our model can provide substantial impacts on the screening and discovery of therapeutic peptides. The source code is available at https://github.com/NanjunChen37/TP_LMMSG.
Abstract Drug–target interactions (DTIs) are a key part of drug development process and their accurate and efficient prediction can significantly boost development efficiency and reduce development ...time. Recent years have witnessed the rapid advancement of deep learning, resulting in an abundance of deep learning-based models for DTI prediction. However, most of these models used a single representation of drugs and proteins, making it difficult to comprehensively represent their characteristics. Multimodal data fusion can effectively compensate for the limitations of single-modal data. However, existing multimodal models for DTI prediction do not take into account both intra- and inter-modal interactions simultaneously, resulting in limited presentation capabilities of fused features and a reduction in DTI prediction accuracy. A hierarchical multimodal self-attention-based graph neural network for DTI prediction, called HMSA-DTI, is proposed to address multimodal feature fusion. Our proposed HMSA-DTI takes drug SMILES, drug molecular graphs, protein sequences and protein 2-mer sequences as inputs, and utilizes a hierarchical multimodal self-attention mechanism to achieve deep fusion of multimodal features of drugs and proteins, enabling the capture of intra- and inter-modal interactions between drugs and proteins. It is demonstrated that our proposed HMSA-DTI has significant advantages over other baseline methods on multiple evaluation metrics across five benchmark datasets.
Abstract The identification of protein complexes from protein interaction networks is crucial in the understanding of protein function, cellular processes and disease mechanisms. Existing methods ...commonly rely on the assumption that protein interaction networks are highly reliable, yet in reality, there is considerable noise in the data. In addition, these methods fail to account for the regulatory roles of biomolecules during the formation of protein complexes, which is crucial for understanding the generation of protein interactions. To this end, we propose a SpatioTemporal constrained RNA–protein heterogeneous network for Protein Complex Identification (STRPCI). STRPCI first constructs a multiplex heterogeneous protein information network to capture deep semantic information by extracting spatiotemporal interaction patterns. Then, it utilizes a dual-view aggregator to aggregate heterogeneous neighbor information from different layers. Finally, through contrastive learning, STRPCI collaboratively optimizes the protein embedding representations under different spatiotemporal interaction patterns. Based on the protein embedding similarity, STRPCI reweights the protein interaction network and identifies protein complexes with core-attachment strategy. By considering the spatiotemporal constraints and biomolecular regulatory factors of protein interactions, STRPCI measures the tightness of interactions, thus mitigating the impact of noisy data on complex identification. Evaluation results on four real PPI networks demonstrate the effectiveness and strong biological significance of STRPCI. The source code implementation of STRPCI is available from https://github.com/LI-jasm/STRPCI.
Abstract Large sample datasets have been regarded as the primary basis for innovative discoveries and the solution to missing heritability in genome-wide association studies. However, their ...computational complexity cannot consider all comprehensive effects and all polygenic backgrounds, which reduces the effectiveness of large datasets. To address these challenges, we included all effects and polygenic backgrounds in a mixed logistic model for binary traits and compressed four variance components into two. The compressed model combined three computational algorithms to develop an innovative method, called FastBiCmrMLM, for large data analysis. These algorithms were tailored to sample size, computational speed, and reduced memory requirements. To mine additional genes, linkage disequilibrium markers were replaced by bin-based haplotypes, which are analyzed by FastBiCmrMLM, named FastBiCmrMLM-Hap. Simulation studies highlighted the superiority of FastBiCmrMLM over GMMAT, SAIGE and fastGWA-GLMM in identifying dominant, small α (allele substitution effect), and rare variants. In the UK Biobank-scale dataset, we demonstrated that FastBiCmrMLM could detect variants as small as 0.03% and with α ≈ 0. In re-analyses of seven diseases in the WTCCC datasets, 29 candidate genes, with both functional and TWAS evidence, around 36 variants identified only by the new methods, strongly validated the new methods. These methods offer a new way to decipher the genetic architecture of binary traits and address the challenges outlined above.
Abstract Gene–environment (GE) interactions are essential in understanding human complex traits. Identifying these interactions is necessary for deciphering the biological basis of such traits. In ...this study, we review state-of-art methods for estimating the proportion of phenotypic variance explained by genome-wide GE interactions and introduce a novel statistical method Linkage-Disequilibrium Eigenvalue Regression for Gene–Environment interactions (LDER-GE). LDER-GE improves the accuracy of estimating the phenotypic variance component explained by genome-wide GE interactions using large-scale biobank association summary statistics. LDER-GE leverages the complete Linkage Disequilibrium (LD) matrix, as opposed to only the diagonal squared LD matrix utilized by LDSC (Linkage Disequilibrium Score)-based methods. Our extensive simulation studies demonstrate that LDER-GE performs better than LDSC-based approaches by enhancing statistical efficiency by ~23%. This improvement is equivalent to a sample size increase of around 51%. Additionally, LDER-GE effectively controls type-I error rate and produces unbiased results. We conducted an analysis using UK Biobank data, comprising 307 259 unrelated European-Ancestry subjects and 966 766 variants, across 217 environmental covariate-phenotype (E-Y) pairs. LDER-GE identified 34 significant E-Y pairs while LDSC-based method only identified 23 significant E-Y pairs with 22 overlapped with LDER-GE. Furthermore, we employed LDER-GE to estimate the aggregated variance component attributed to multiple GE interactions, leading to an increase in the explained phenotypic variance with GE interactions compared to considering main genetic effects only. Our results suggest the importance of impacts of GE interactions on human complex traits.
Abstract High-throughput DNA sequencing technologies decode tremendous amounts of microbial protein-coding gene sequences. However, accurately assigning protein functions to novel gene sequences ...remain a challenge. To this end, we developed FunGeneTyper, an extensible framework with two new deep learning models (i.e., FunTrans and FunRep), structured databases, and supporting resources for achieving highly accurate (Accuracy > 0.99, F1-score > 0.97) and fine-grained classification of antibiotic resistance genes (ARGs) and virulence factor genes. Using an experimentally confirmed dataset of ARGs comprising remote homologous sequences as the test set, our framework achieves by-far-the-best performance in the discovery of new ARGs from human gut (F1-score: 0.6948), wastewater (0.6072), and soil (0.5445) microbiomes, beating the state-of-the-art bioinformatics tools and sequence alignment-based (F1-score: 0.0556–0.5065) and domain-based (F1-score: 0.2630–0.5224) annotation approaches. Furthermore, our framework is implemented as a lightweight, privacy-preserving, and plug-and-play neural network module, facilitating its versatility and accessibility to developers and users worldwide. We anticipate widespread utilization of FunGeneTyper (https://github.com/emblab-westlake/FunGeneTyper) for precise classification of protein-coding gene functions and the discovery of numerous valuable enzymes. This advancement will have a significant impact on various fields, including microbiome research, biotechnology, metagenomics, and bioinformatics.
Abstract Unsupervised feature selection is a critical step for efficient and accurate analysis of single-cell RNA-seq data. Previous benchmarks used two different criteria to compare feature ...selection methods: (i) proportion of ground-truth marker genes included in the selected features and (ii) accuracy of cell clustering using ground-truth cell types. Here, we systematically compare the performance of 11 feature selection methods for both criteria. We first demonstrate the discordance between these criteria and suggest using the latter. We then compare the distribution of selected genes in their means between feature selection methods. We show that lowly expressed genes exhibit seriously high coefficients of variation and are mostly excluded by high-performance methods. In particular, high-deviation- and high-expression-based methods outperform the widely used in Seurat package in clustering cells and data visualization. We further show they also enable a clear separation of the same cell type from different tissues as well as accurate estimation of cell trajectories.
Abstract Peptide- and protein-based therapeutics are becoming a promising treatment regimen for myriad diseases. Toxicity of proteins is the primary hurdle for protein-based therapies. Thus, there is ...an urgent need for accurate in silico methods for determining toxic proteins to filter the pool of potential candidates. At the same time, it is imperative to precisely identify non-toxic proteins to expand the possibilities for protein-based biologics. To address this challenge, we proposed an ensemble framework, called VISH-Pred, comprising models built by fine-tuning ESM2 transformer models on a large, experimentally validated, curated dataset of protein and peptide toxicities. The primary steps in the VISH-Pred framework are to efficiently estimate protein toxicities taking just the protein sequence as input, employing an under sampling technique to handle the humongous class-imbalance in the data and learning representations from fine-tuned ESM2 protein language models which are then fed to machine learning techniques such as Lightgbm and XGBoost. The VISH-Pred framework is able to correctly identify both peptides/proteins with potential toxicity and non-toxic proteins, achieving a Matthews correlation coefficient of 0.737, 0.716 and 0.322 and F1-score of 0.759, 0.696 and 0.713 on three non-redundant blind tests, respectively, outperforming other methods by over $10\%$ on these quality metrics. Moreover, VISH-Pred achieved the best accuracy and area under receiver operating curve scores on these independent test sets, highlighting the robustness and generalization capability of the framework. By making VISH-Pred available as an easy-to-use web server, we expect it to serve as a valuable asset for future endeavors aimed at discerning the toxicity of peptides and enabling efficient protein-based therapeutics.
Abstract The progression of complex diseases often involves abrupt and non-linear changes characterized by sudden shifts that trigger critical transformations. Identifying these critical states or ...tipping points is crucial for understanding disease progression and developing effective interventions. To address this challenge, we have developed a model-free method named Network Information Entropy of Edges (NIEE). Leveraging dynamic network biomarkers, sample-specific networks, and information entropy theories, NIEE can detect critical states or tipping points in diverse data types, including bulk, single-sample expression data. By applying NIEE to real disease datasets, we successfully identified critical predisease stages and tipping points before disease onset. Our findings underscore NIEE’s potential to enhance comprehension of complex disease development.