DeepCellEss: cell line-specific essential protein prediction with attention-based interpretable deep learning

GP-HTNLoc: A graph prototype head-tail network-based model for multi-label subcellular localization prediction of ncRNAs

Numerous research results demonstrated that understanding the subcellular localization of non-coding RNAs (ncRNAs) is pivotal in elucidating their roles and regulatory mechanisms in cells. Despite the existence of over ten computational models dedicated to predicting the subcellular localization of ncRNAs, a majority of these models are designed solely for single-label prediction. In reality, ncRNAs often exhibit localization across multiple subcellular compartments. Furthermore, the existing multi-label localization prediction models are insufficient in addressing the challenges posed by the scarcity of training samples and class imbalance in ncRNA dataset. To address these limitations, this study proposes a novel multi-label localization prediction model for ncRNAs, named GP-HTNLoc. To mitigate class imbalance, GP-HTNLoc adopts separate training approaches for head and tail location labels. Additionally, GP-HTNLoc introduces a pioneering graph prototype module to enhance its performance in small-sample, multi-label scenarios. The experimental results based on 10-fold cross-validation on benchmark datasets demonstrate that GP-HTNLoc achieves competitive predictive performance. The average results from 10 rounds of testing on an independent dataset show that GP-HTNLoc outperforms the best existing models on the human lncRNA, human snoRNA, and human miRNA subsets, with average precision improvements of 31.5%, 14.2%, and 5.6%, respectively, reaching 0.685, 0.632, and 0.704. A user-friendly online GP-HTNLoc server is accessible at https://56s8y85390.goho.co.

In-silico identification of therapeutic targets in pancreatic ductal adenocarcinoma using WGCNA and Trader

Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive malignancy, accounting for over 90% of pancreatic cancers, and is characterized by limited treatment options and poor survival rates. Systems biology provides in-depth insights into the molecular mechanisms of PDAC. In this context, novel algorithms and comprehensive strategies are essential for advancing the identification of critical network nodes and therapeutic targets within disease-related protein-protein interaction networks. This study employed a comprehensive computational strategy using the metaheuristic algorithm Trader to enhance the identification of potential therapeutic targets. Analysis of the expression data from the PDAC dataset (GSE132956) involved co-expression analysis and clustering of differentially expressed genes to identify key disease-associated modules. The STRING database was used to construct a network of differentially expressed genes, and the Trader algorithm pinpointed the top 30 DEGs whose removal caused the most significant network disconnections. Enriched gene ontology terms included "Signaling by Rho GTPases," "Signaling by receptor tyrosine kinases," and "immune system." Additionally, nine hub genes-FYN, MAPK3, CDK2, SNRPG, GNAQ, PAK1, LPCAT4, MAP1LC3B, and FBN1-were identified as central to PDAC pathogenesis. This integrated approach, combining co-expression analysis with protein-protein interaction network analysis using a metaheuristic algorithm, provides valuable insights into PDAC mechanisms and highlights several hub genes as potential therapeutic targets.

ACDMBI: A deep learning model based on community division and multi-source biological information fusion predicts essential proteins

Accurately identifying essential proteins is vital for drug research and disease diagnosis. Traditional centrality methods and machine learning approaches often face challenges in accurately discerning essential proteins, primarily relying on information derived from protein-protein interaction (PPI) networks. Despite attempts by some researchers to integrate biological data and PPI networks for predicting essential proteins, designing effective integration methods remains a challenge. In response to these challenges, this paper presents the ACDMBI model, specifically designed to overcome the aforementioned issues. ACDMBI is comprised of two key modules: feature extraction and classification. In terms of capturing relevant information, we draw insights from three distinct data sources. Initially, structural features of proteins are extracted from the PPI network through community division. Subsequently, these features are further optimized using Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT). Moving forward, protein features are extracted from gene expression data utilizing Bidirectional Long Short-Term Memory networks (BiLSTM) and a multi-head self-attention mechanism. Finally, protein features are derived by mapping subcellular localization data to a one-dimensional vector and processing it through fully connected layers. In the classification phase, we integrate features extracted from three different data sources, crafting a multi-layer deep neural network (DNN) for protein classification prediction. Experimental results on brewing yeast data showcase the ACDMBI model's superior performance, with AUC reaching 0.9533 and AUPR reaching 0.9153. Ablation experiments further reveal that the effective integration of features from diverse biological information significantly boosts the model's performance.

Hybrid framework for membrane protein type prediction based on the PSSM

Membrane proteins are considered the major source of drug targets and are indispensable for drug design and disease prevention. However, traditional biomechanical experiments are costly and time-consuming; thus, many computational methods for predicting membrane protein types are gaining popularity. The position-specific scoring matrix (PSSM) method is an excellent method for describing the evolutionary information of protein sequences. In this study, we propose an improved capsule neural network (ICNN) model based on a capsule neural network to acquire sufficient relevant information from the PSSM. Furthermore, accounting for the complementarity between traditional machine learning and deep learning, we propose a hybrid framework that combines both approaches to predict protein types. This framework trains 41 baseline models based on the PSSM. The optimal subset features, selected after traversal, are fused using a two-level decision-level feature fusion approach. Subsequently, comparisons are made using three combined strategies within an ensemble learning framework. The experimental results demonstrate that solely relying on PSSM input, the proposed method not only surpasses the optimal methods by 1.52 % , 2.26 % and 2.67 % on Dataset1, Dataset2, and Datasets3, respectively, but also exhibits superior generalizability. Furthermore, the code and dataset can be free download at https://github.com/ruanxiaoli/membrane-protein-types .

LncLocFormer: a Transformer-based deep learning model for multi-label lncRNA subcellular localization prediction by using localization-specific attention mechanism

MOTIVATION

There is mounting evidence that the subcellular localization of lncRNAs can provide valuable insights into their biological functions. In the real world of transcriptomes, lncRNAs are usually localized in multiple subcellular localizations. Furthermore, lncRNAs have specific localization patterns for different subcellular localizations. Although several computational methods have been developed to predict the subcellular localization of lncRNAs, few of them are designed for lncRNAs that have multiple subcellular localizations, and none of them take motif specificity into consideration.

RESULTS

In this study, we proposed a novel deep learning model, called LncLocFormer, which uses only lncRNA sequences to predict multi-label lncRNA subcellular localization. LncLocFormer utilizes eight Transformer blocks to model long-range dependencies within the lncRNA sequence and shares information across the lncRNA sequence. To exploit the relationship between different subcellular localizations and find distinct localization patterns for different subcellular localizations, LncLocFormer employs a localization-specific attention mechanism. The results demonstrate that LncLocFormer outperforms existing state-of-the-art predictors on the hold-out test set. Furthermore, we conducted a motif analysis and found LncLocFormer can capture known motifs. Ablation studies confirmed the contribution of the localization-specific attention mechanism in improving the prediction performance.

AVAILABILITY AND IMPLEMENTATION

The LncLocFormer web server is available at http://csuligroup.com:9000/LncLocFormer. The source code can be obtained from https://github.com/CSUBioGroup/LncLocFormer.

'Bingo'-a large language model- and graph neural network-based workflow for the prediction of essential genes from protein data

The identification and characterization of essential genes are central to our understanding of the core biological functions in eukaryotic organisms, and has important implications for the treatment of diseases caused by, for example, cancers and pathogens. Given the major constraints in testing the functions of genes of many organisms in the laboratory, due to the absence of in vitro cultures and/or gene perturbation assays for most metazoan species, there has been a need to develop in silico tools for the accurate prediction or inference of essential genes to underpin systems biological investigations. Major advances in machine learning approaches provide unprecedented opportunities to overcome these limitations and accelerate the discovery of essential genes on a genome-wide scale. Here, we developed and evaluated a large language model- and graph neural network (LLM-GNN)-based approach, called 'Bingo', to predict essential protein-coding genes in the metazoan model organisms Caenorhabditis elegans and Drosophila melanogaster as well as in Mus musculus and Homo sapiens (a HepG2 cell line) by integrating LLM and GNNs with adversarial training. Bingo predicts essential genes under two 'zero-shot' scenarios with transfer learning, showing promise to compensate for a lack of high-quality genomic and proteomic data for non-model organisms. In addition, the attention mechanisms and GNNExplainer were employed to manifest the functional sites and structural domain with most contribution to essentiality. In conclusion, Bingo provides the prospect of being able to accurately infer the essential genes of little- or under-studied organisms of interest, and provides a biological explanation for gene essentiality.