Improving cancer driver gene identification using multi-task learning on graph convolutional network

Integration of graph neural networks and transcriptomics analysis identify key pathways and gene signature for immunotherapy response and prognosis of skin melanoma

OBJECTIVE

The assessment of immunotherapy plays a pivotal role in the clinical management of skin melanoma. Graph neural networks (GNNs), alongside other deep learning algorithms and bioinformatics approaches, have demonstrated substantial promise in advancing cancer diagnosis and treatment strategies.

METHODS

GNNs models were developed to predict the response to immunotherapy and to pinpoint key pathways. Utilizing the genes from these key pathways, multi-omics bioinformatics methods were employed to refine the construction of a gene signature, termed responseScore, aimed at enhancing the precision of immunotherapy response predictions. Subsequently, responseScore was explored from the perspectives of prognosis, genetic variation, pathway enrichment, and the tumor microenvironment. Concurrently, the association among 13 genes contributing to responseScore and factors such as immunotherapy response, prognosis, and the tumor microenvironment was investigated. Among these genes, PSMB6 was subjected to an in-depth analysis of its biological effect through experimental approaches like transfection and co-culture.

RESULTS

In the finalized model utilizing GNNs, it has revealed an AUC of 0.854 within the training dataset and 0.824 within the testing set, pinpointing key pathways such as R-HSA-70,268. The indicator named as responseScore excelled in its predictive accuracy regarding immunotherapy response and patient prognosis. Investigations into genetic variation, pathway enrichment, tumor microenvironment disclosed a profound association between responseScore and the enhancement of immune cell infiltration and anti-tumor immunity. A negative correlation was observed between the expression of PSMB6 and immune genes, with elevated PSMB6 expression correlating with poor prognosis. ELISA detection after co-cultivation experiments revealed significant reductions in the levels of cytokines IL-6 and IL-1β in specimens from the PCDH-PSMB6 group.

CONCLUSION

The GNNs prediction model and the responseScore developed in this research effectively indicate the immunotherapy response and prognosis for patients with skin melanoma. Additionally, responseScore provides insights into the tumor microenvironment and the characteristics of tumor immunity of melanoma. Thirteen genes identified in this study show promise as potential tumor markers or therapeutic targets. Notably, PSMB6 emerges as a potential therapeutic target for skin melanoma, where its elevated expression exhibits an inhibitory effect on the tumor immunity.

Integrative network analysis reveals novel moderators of Aβ-Tau interaction in Alzheimer's disease

BACKGROUND

Although interactions between amyloid-beta and tau proteins have been implicated in Alzheimer's disease (AD), the precise mechanisms by which these interactions contribute to disease progression are not yet fully understood. Moreover, despite the growing application of deep learning in various biomedical fields, its application in integrating networks to analyze disease mechanisms in AD research remains limited. In this study, we employed BIONIC, a deep learning-based network integration method, to integrate proteomics and protein-protein interaction data, with an aim to uncover factors that moderate the effects of the Aβ-tau interaction on mild cognitive impairment (MCI) and early-stage AD.

METHODS

Proteomic data from the ROSMAP cohort were integrated with protein-protein interaction (PPI) data using a Deep Learning-based model. Linear regression analysis was applied to histopathological and gene expression data, and mutual information was used to detect moderating factors. Statistical significance was determined using the Benjamini-Hochberg correction (p < 0.05).

RESULTS

Our results suggested that astrocytes and GPNMB + microglia moderate the Aβ-tau interaction. Based on linear regression with histopathological and gene expression data, GFAP and IBA1 levels and GPNMB gene expression positively contributed to the interaction of tau with Aβ in non-dementia cases, replicating the results of the network analysis.

CONCLUSIONS

These findings suggest that GPNMB + microglia moderate the Aβ-tau interaction in early AD and therefore are a novel therapeutic target. To facilitate further research, we have made the integrated network available as a visualization tool for the scientific community (URL: https://igcore.cloud/GerOmics/AlzPPMap ).

Fusion of brain imaging genetic data for alzheimer's disease diagnosis and causal factors identification using multi-stream attention mechanisms and graph convolutional networks

Correctly diagnosing Alzheimer's disease (AD) and identifying pathogenic brain regions and genes play a vital role in understanding the AD and developing effective prevention and treatment strategies. Recent works combine imaging and genetic data, and leverage the strengths of both modalities to achieve better classification results. In this work, we propose MCA-GCN, a Multi-stream Cross-Attention and Graph Convolutional Network-based classification method for AD patients. It first constructs a brain region-gene association network based on brain region fMRI time series and gene SNP data. Then it integrates the absolute and relative positions of the brain region time series to obtain a new brain region time series containing temporal information. Then long-range and local association features between brain regions and genes are sequentially aggregated by multi-stream cross-attention and graph convolutional networks. Finally, the learned brain region and gene features are input to the fully connected network to predict AD types. Experimental results on the ADNI dataset show that our model outperforms other methods in AD classification tasks. Moreover, MCA-GCN designed a multi-stage feature scoring process to extract high-risk genes and brain regions related to disease classification.

An efficient graph attention framework enhances bladder cancer prediction

Bladder (BL) cancer is the 10th most common cancer worldwide, ranking 9th in males and 13th in females in the United States, respectively. BL cancer is a quick-growing tumor of all cancer forms. Given a malignant tumor's high malignancy, rapid metastasis prediction and accurate treatment are critical. The most significant drivers of the intricate genesis of cancer are complex genetics, including deoxyribonucleic acid (DNA) insertions and deletions, abnormal structure, copy number variations (CNVs), and single nucleotide variations (SNVs). The proposed method enhances the identification of driver genes at the individual patient level by employing attention mechanisms to extract features of both coding and non-coding genes and predict BL cancer based on the personalized driver gene (PDG) detection. The embedded vectors are propagated through the three dense blocks for the binary classification of PDGs. The novel constructure of graph neural network (GNN) with attention mechanism, called Multi Stacked-Layered GAT (MSL-GAT) leverages graph attention mechanisms (GAT) to identify and predict critical driver genes associated with BL cancer progression. In order to pick out and extract essential features from both coding and non-coding genes, including long non-coding RNAs (lncRNAs), which are known to be crucial to the advancement of BL cancer. The approach analyzes key genetic changes (such as SNVs, CNVs, and structural abnormalities) that lead to tumorigenesis and metastasis by concentrating on personalized driver genes (PDGs). The discovery of genes crucial for the survival and proliferation of cancer cells is made possible by the model's precise classification of PDGs. MSL-GAT draws attention to certain lncRNAs and other non-coding elements that control carcinogenic pathways by utilizing the attention mechanism. Tumor development, metastasis, and medication resistance are all facilitated by these lncRNAs, which are frequently overexpressed or dysregulated in BL cancer. In order to reduce the survival of cancer cells, the model's predictions can direct specific treatment approaches, such as RNA interference (RNAi), to mute or suppress the expression of these important genes. MSL-GAT is followed by three dense blocks that spread the embedded vectors to categorize PDGs, making it possible to determine which genes are more likely to cause BL cancer in a certain patient. The model facilitates the identification of new treatment targets by offering a thorough understanding of the molecular landscape of BL cancer through the integration of multi-omics data, encompassing as genomic, transcriptomic, and epigenomic metadata. We compared the novel approach with classical machine learning methods and other deep learning-based methods on benchmark TCGA-BLCA, and the leave-one-out experimental results showed that MSL-GAT achieved better performance than competitive methods. This approach achieves accuracy with 97.72% and improves specificity and sensitivity. It can potentially aid physicians during early prediction of BL cancer.

Pan-cancer analysis shapes the understanding of cancer biology and medicine

Advances in multi-omics datasets and analytical methods have revolutionized cancer research, offering a comprehensive, pan-cancer perspective. Pan-cancer studies identify shared mechanisms and unique traits across different cancer types, which are reshaping diagnostic and treatment strategies. However, continued innovation is required to refine these approaches and deepen our understanding of cancer biology and medicine. This review summarized key findings from pan-cancer research and  explored their potential to drive future advancements in oncology.

Comparative Analysis of Multi-Omics Integration Using Graph Neural Networks for Cancer Classification

Recent studies on integrating multiple omics data highlighted the potential to advance our understanding of the cancer disease process. Computational models based on graph neural networks and attention-based architectures have demonstrated promising results for cancer classification due to their ability to model complex relationships among biological entities. However, challenges related to addressing the high dimensionality and complexity in integrating multi-omics data, as well as in constructing graph structures that effectively capture the interactions between nodes, remain active areas of research. This study evaluates graph neural network architectures for multi-omics (MO) data integration based on graph-convolutional networks (GCN), graph-attention networks (GAT), and graph-transformer networks (GTN). Differential gene expression and LASSO (Least Absolute Shrinkage and Selection Operator) regression are employed for reducing the omics data dimensionality and feature selection; hence, the developed models are referred to as LASSO-MOGCN, LASSO-MOGAT, and LASSO-MOGTN. Graph structures constructed using sample correlation matrices and protein-protein interaction networks are investigated. Experimental validation is performed with a dataset of 8,464 samples from 31 cancer types and normal tissue, comprising messenger-RNA, micro-RNA, and DNA methylation data. The results show that the models integrating multi-omics data outperformed the models trained on single omics data, where LASSO-MOGAT achieved the best overall performance, with an accuracy of 95.9%. The findings also suggest that correlation-based graph structures enhance the models' ability to identify shared cancer-specific signatures across patients in comparison to protein-protein interaction networks-based graph structures. The code and data used in this study are available in the link (https://github.com/FadiAlharbi2024/Graph_Based_Architecture.git).

MONet: cancer driver gene identification algorithm based on integrated analysis of multi-omics data and network models

Cancer progression is orchestrated by the accrual of mutations in driver genes, which endow malignant cells with a selective proliferative advantage. Identifying cancer driver genes is crucial for elucidating the molecular mechanisms of cancer, advancing targeted therapies, and uncovering novel biomarkers. Based on integrated analysis of Multi-Omics data and Network models, we present MONet, a novel cancer driver gene identification algorithm. Our method utilizes two graph neural network algorithms on protein-protein interaction (PPI) networks to extract feature vector representations for each gene. These feature vectors are subsequently concatenated and fed into a multi-layer perceptron model (MLP) to perform semi-supervised identification of cancer driver genes. For each mutated gene, MONet assigns the probability of being potential driver, with genes identified in at least two PPI networks selected as candidate driver genes. When applied to pan-cancer datasets, MONet demonstrated robustness across various PPI networks, outperforming baseline models in terms of both the area under the receiver operating characteristic curve and the area under the precision-recall curve. Notably, MONet identified 37 novel driver genes that were missed by other methods, including 29 genes such as APOBEC2, GDNF, and PRELP, which are corroborated by existing literature, underscoring their critical roles in cancer development and progression. Through the MONet framework, we successfully identified known and novel candidate cancer driver genes, providing biologically meaningful insights into cancer mechanisms.

Predicting Clinical Anticancer Drug Response of Patients by Using Domain Alignment and Prototypical Learning

Anticancer drug response prediction is crucial in developing personalized treatment plans for cancer patients. However, High-quality patient anticancer drug response data are scarce and cell line data and patient data have different distributions, models trained solely on cell line data perform poorly. Some existing methods predict anticancer drug response by transferring knowledge from the cell line domain to the patient domain using transfer learning. However, the robustness of these classifiers is affected by anomalies in the cell line data, and they do not utilize the knowledge in the unlabeled target domain data. To this end, we proposed a model called DAPL to predict patient responses to anticancer drugs. The model extracts domain-invariant features from cell lines and patients by constructing multiple VAEs and extracts drug features using GNNs. These features are then combined for prototypical learning to train a classifier, resulting in better predictions of patient anticancer drug response. We used the cell line datasets CCLE and GDSC as source domains and the patient datasets TCGA and PDTC as target domains and conducted experiments. The results indicate that DAPL shows excellent performance in predicting patient anticancer drug response compared to other state-of-the-art methods.

MDMNI-DGD: A novel graph neural network approach for druggable gene discovery based on the integration of multi-omics data and the multi-view network

Accurately predicting druggable genes is of paramount importance for enhancing the efficacy of targeted therapies, reducing drug-related toxicities and improving patients' survival rates. Nevertheless, accurately predicting candidate cancer-druggable genes remains a critical challenge in translational medicine due to the high heterogeneity and complexity of cancer data. In this study, we proposed a novel graph neural approach called Druggable Gene Discovery based on the Integration of Multi-omics Data and the Multi-view Network (MDMNI-DGD), aiming to predict and evaluate cancer-druggable genes. MDMNI-DGD integrated a comprehensive set of multi-omics data, including copy number variations, DNA methylation, somatic mutations, and gene expression profiles. Simultaneously, it constructed the multi-view gene association network based on protein-protein interactions (PPI), protein structural domains, gene co-expression, pathway co-occurrence, gene sequence and gene ontology. Compared to other state-of-the-art approaches, MDMNI-DGD exhibits excellent performance in key evaluation metrics such as AUROC and AUPR. Moreover, the case study has also demonstrated the efficacy of our approach in discovering potentially druggable genes. Among more than 20,000 protein-coding genes, MDMNI-DGD successfully identified 872 potentially druggable genes. The findings from this investigation may serve to bolster the assessment of pan-cancer druggable genes, potentially catalyzing the development of more personalized and efficacious therapeutic interventions.

Integration of Graph Neural Networks and multi-omics analysis identify the predictive factor and key gene for immunotherapy response and prognosis of bladder cancer

OBJECTIVE

The evaluation of the efficacy of immunotherapy is of great value for the clinical treatment of bladder cancer. Graph Neural Networks (GNNs), pathway analysis and multi-omics analysis have shown great potential in the field of cancer diagnosis and treatment.

METHODS

A GNNs model was constructed to predict the immunotherapy response and identify key pathways. Based on the genes of key pathways, bioinformatic methods were used to generate a simple linear scoring model, namely responseScore. The intrinsic mechanism of responseScore was explored from the perspectives of multi-omics analysis. The relationship between each gene involved in responseScore and prognosis was also explored. Transfection experiments with human bladder cancer cells were used to investigate the biological effects of PSMB9 gene.

RESULTS

The final GNNs model had an AUC of 0.785 on the training set and an AUC of 0.839 on the validation set. R-HSA-69620 and others were identified as key pathways. ResponseScore had a good performance in predicted the immunotherapy response and prognosis. Analysis results from genetic variation, pathways and tumor microenvironment, showed that responseScore was significantly associated with immune cell infiltration and anti-tumor immunity. The results of single-cell analysis showed that responseScore was closely related to the functional state of natural killer cells. Compared with the PCDH-NC group, cell migration and proliferation were significantly inhibited while cell apoptosis increased in the PCDH-PSMB9 group.

CONCLUSION

The GNNs predictive model and responseScore constructed in this study can reflect the immunotherapy response and prognosis of bladder cancer patients. ResponseScore can also reflect features such as tumor microenvironment, antitumor immunity, and natural killer cell function status in bladder cancer. PSMB9 was identified as a significant gene for prognosis. High expression of PSMB9 can inhibit bladder cancer cell migration and proliferation while increasing cell apoptosis.

Towards simplified graph neural networks for identifying cancer driver genes in heterophilic networks

The identification of cancer driver genes is crucial for understanding the complex processes involved in cancer development, progression, and therapeutic strategies. Multi-omics data and biological networks provided by numerous databases enable the application of graph deep learning techniques that incorporate network structures into the deep learning framework. However, most existing methods do not account for the heterophily in the biological networks, which hinders the improvement of model performance. Meanwhile, feature confusion often arises in models based on graph neural networks in such graphs. To address this, we propose a Simplified Graph neural network for identifying Cancer Driver genes in heterophilic networks (SGCD), which comprises primarily two components: a graph convolutional neural network with representation separation and a bimodal feature extractor. The results demonstrate that SGCD not only performs exceptionally well but also exhibits robust discriminative capabilities compared to state-of-the-art methods across all benchmark datasets. Moreover, subsequent interpretability experiments on both the model and biological aspects provide compelling evidence supporting the reliability of SGCD. Additionally, the model can dissect gene modules, revealing clearer connections between driver genes in cancers. We are confident that SGCD holds potential in the field of precision oncology and may be applied to prognosticate biomarkers for a wide range of complex diseases.

Integrative Network Analysis Reveals Novel Moderators of Aβ-Tau Interaction in Alzheimer's Disease

Background

Although interactions between amyloid-beta and tau proteins have been implicated in Alzheimer's disease (AD), the precise mechanisms by which these interactions contribute to disease progression are not yet fully understood. Moreover, despite the growing application of deep learning in various biomedical fields, its application in integrating networks to analyze disease mechanisms in AD research remains limited. In this study, we employed BIONIC, a deep learning-based network integration method, to integrate proteomics and protein-protein interaction data, with an aim to uncover factors that moderate the effects of the Aβ-tau interaction on mild cognitive impairment (MCI) and early-stage AD.

Methods

Proteomic data from the ROSMAP cohort were integrated with protein-protein interaction (PPI) data using a Deep Learning-based model. Linear regression analysis was applied to histopathological and gene expression data, and mutual information was used to detect moderating factors. Statistical significance was determined using the Benjamini-Hochberg correction (p < 0.05).

Results

Our results suggested that astrocytes and GPNMB+ microglia moderate the Aβ-tau interaction. Based on linear regression with histopathological and gene expression data, GFAP and IBA1 levels and GPNMB gene expression positively contributed to the interaction of tau with Aβ in non-dementia cases, replicating the results of the network analysis.

Conclusions

These findings indicate that GPNMB+ microglia moderate the Aβ-tau interaction in early AD and therefore are a novel therapeutic target. To facilitate further research, we have made the integrated network available as a visualization tool for the scientific community (URL: https://igcore.cloud/GerOmics/AlzPPMap).

A heterogeneous graph transformer framework for accurate cancer driver gene prediction and downstream analysis

Accurately predicting cancer driver genes remains a formidable challenge amidst the burgeoning volume and intricacy of cancer genomic data. In this investigation, we propose HGTDG, an innovative heterogeneous graph transformer framework tailored for precisely predicting cancer driver genes and exploring downstream tasks. A heterogeneous graph construction module is central to the framework, which assembles a gene-protein heterogeneous network leveraging the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways and protein-protein interactions sourced from the STRING (search tool for recurring instances of neighboring genes) database. Moreover, our framework introduces a pioneering heterogeneous graph transformer module, harnessing multi-head attention mechanisms for nuanced node embedding. This transformative module proficiently captures distinct representations for both nodes and edges, thereby enriching the model's predictive capacity. Subsequently, the generated node embeddings are seamlessly integrated into a classification module, facilitating the discrimination between driver and non-driver genes. Our experimental findings evince the superiority of HGTDG over existing methodologies, as evidenced by the enhanced performance metrics, including the area under the receiver operating characteristic curves (AUROC) and the area under the precision-recall curves (AUPRC). Furthermore, the downstream analysis utilizing the newly identified cancer driver genes underscores the efficacy and versatility of our proposed framework.

SSCI: Self-Supervised Deep Learning Improves Network Structure for Cancer Driver Gene Identification

The pathogenesis of cancer is complex, involving abnormalities in some genes in organisms. Accurately identifying cancer genes is crucial for the early detection of cancer and personalized treatment, among other applications. Recent studies have used graph deep learning methods to identify cancer driver genes based on biological networks. However, incompleteness and the noise of the networks will weaken the performance of models. To address this, we propose a cancer driver gene identification method based on self-supervision for graph convolutional networks, which can efficiently enhance the structure of the network and further improve predictive accuracy. The reliability of SSCI is verified by the area under the receiver operating characteristic curves (AUROC), the area under the precision-recall curves (AUPRC), and the F1 score, with respective values of 0.966, 0.964, and 0.913. The results show that our method can identify cancer driver genes with strong discriminative power and biological interpretability.

Identifying cooperating cancer driver genes in individual patients through hypergraph random walk

OBJECTIVE

Identifying cancer driver genes, especially rare or patient-specific cancer driver genes, is a primary goal in cancer therapy. Although researchers have proposed some methods to tackle this problem, these methods mostly identify cancer driver genes at single gene level, overlooking the cooperative relationship among cancer driver genes. Identifying cooperating cancer driver genes in individual patients is pivotal for understanding cancer etiology and advancing the development of personalized therapies.

METHODS

Here, we propose a novel Personalized Cooperating cancer Driver Genes (PCoDG) method by using hypergraph random walk to identify the cancer driver genes that cooperatively drive individual patient cancer progression. By leveraging the powerful ability of hypergraph in representing multi-way relationships, PCoDG first employs the personalized hypergraph to depict the complex interactions among mutated genes and differentially expressed genes of an individual patient. Then, a hypergraph random walk algorithm based on hyperedge similarity is utilized to calculate the importance scores of mutated genes, integrating these scores with signaling pathway data to identify the cooperating cancer driver genes in individual patients.

RESULTS

The experimental results on three TCGA cancer datasets (i.e., BRCA, LUAD, and COADREAD) demonstrate the effectiveness of PCoDG in identifying personalized cooperating cancer driver genes. These genes identified by PCoDG not only offer valuable insights into patient stratification correlating with clinical outcomes, but also provide an useful reference resource for tailoring personalized treatments.

CONCLUSION

We propose a novel method that can effectively identify cooperating cancer driver genes for individual patients, thereby deepening our understanding of the cooperative relationship among personalized cancer driver genes and advancing the development of precision oncology.

TriFusion enables accurate prediction of miRNA-disease association by a tri-channel fusion neural network

The identification of miRNA-disease associations is crucial for early disease prevention and treatment. However, it is still a computational challenge to accurately predict such associations due to improper information encoding. Previous methods characterize miRNA-disease associations only from single levels, causing the loss of multi-level association information. In this study, we propose TriFusion, a powerful and interpretable deep learning framework for miRNA-disease association prediction. It develops a tri-channel architecture to encode the association features of miRNAs and diseases from different levels and designs a feature fusion encoder to smoothly fuse these features. After training and testing, TriFusion outperforms other leading methods and offers strong interpretability through its learned representations. Furthermore, TriFusion is applied to three high-risk sexually associated cancers (ovarian, breast, and prostate cancers) and exhibits remarkable ability in the identification of miRNAs associated with the three diseases.

ECD-CDGI: An efficient energy-constrained diffusion model for cancer driver gene identification

The identification of cancer driver genes (CDGs) poses challenges due to the intricate interdependencies among genes and the influence of measurement errors and noise. We propose a novel energy-constrained diffusion (ECD)-based model for identifying CDGs, termed ECD-CDGI. This model is the first to design an ECD-Attention encoder by combining the ECD technique with an attention mechanism. ECD-Attention encoder excels at generating robust gene representations that reveal the complex interdependencies among genes while reducing the impact of data noise. We concatenate topological embedding extracted from gene-gene networks through graph transformers to these gene representations. We conduct extensive experiments across three testing scenarios. Extensive experiments show that the ECD-CDGI model possesses the ability to not only be proficient in identifying known CDGs but also efficiently uncover unknown potential CDGs. Furthermore, compared to the GNN-based approach, the ECD-CDGI model exhibits fewer constraints by existing gene-gene networks, thereby enhancing its capability to identify CDGs. Additionally, ECD-CDGI is open-source and freely available. We have also launched the model as a complimentary online tool specifically crafted to expedite research efforts focused on CDGs identification.

Multiview representation learning for identification of novel cancer genes and their causative biological mechanisms

Tumorigenesis arises from the dysfunction of cancer genes, leading to uncontrolled cell proliferation through various mechanisms. Establishing a complete cancer gene catalogue will make precision oncology possible. Although existing methods based on graph neural networks (GNN) are effective in identifying cancer genes, they fall short in effectively integrating data from multiple views and interpreting predictive outcomes. To address these shortcomings, an interpretable representation learning framework IMVRL-GCN is proposed to capture both shared and specific representations from multiview data, offering significant insights into the identification of cancer genes. Experimental results demonstrate that IMVRL-GCN outperforms state-of-the-art cancer gene identification methods and several baselines. Furthermore, IMVRL-GCN is employed to identify a total of 74 high-confidence novel cancer genes, and multiview data analysis highlights the pivotal roles of shared, mutation-specific, and structure-specific representations in discriminating distinctive cancer genes. Exploration of the mechanisms behind their discriminative capabilities suggests that shared representations are strongly associated with gene functions, while mutation-specific and structure-specific representations are linked to mutagenic propensity and functional synergy, respectively. Finally, our in-depth analyses of these candidates suggest potential insights for individualized treatments: afatinib could counteract many mutation-driven risks, and targeting interactions with cancer gene SRC is a reasonable strategy to mitigate interaction-induced risks for NR3C1, RXRA, HNF4A, and SP1.

Identifying new cancer genes based on the integration of annotated gene sets via hypergraph neural networks

MOTIVATION

Identifying cancer genes remains a significant challenge in cancer genomics research. Annotated gene sets encode functional associations among multiple genes, and cancer genes have been shown to cluster in hallmark signaling pathways and biological processes. The knowledge of annotated gene sets is critical for discovering cancer genes but remains to be fully exploited.

RESULTS

Here, we present the DIsease-Specific Hypergraph neural network (DISHyper), a hypergraph-based computational method that integrates the knowledge from multiple types of annotated gene sets to predict cancer genes. First, our benchmark results demonstrate that DISHyper outperforms the existing state-of-the-art methods and highlight the advantages of employing hypergraphs for representing annotated gene sets. Second, we validate the accuracy of DISHyper-predicted cancer genes using functional validation results and multiple independent functional genomics data. Third, our model predicts 44 novel cancer genes, and subsequent analysis shows their significant associations with multiple types of cancers. Overall, our study provides a new perspective for discovering cancer genes and reveals previously undiscovered cancer genes.

AVAILABILITY AND IMPLEMENTATION

DISHyper is freely available for download at https://github.com/genemine/DISHyper.

MCDHGN: heterogeneous network-based cancer driver gene prediction and interpretability analysis

MOTIVATION

Accurately predicting the driver genes of cancer is of great significance for carcinogenesis progress research and cancer treatment. In recent years, more and more deep-learning-based methods have been used for predicting cancer driver genes. However, deep-learning algorithms often have black box properties and cannot interpret the output results. Here, we propose a novel cancer driver gene mining method based on heterogeneous network meta-paths (MCDHGN), which uses meta-path aggregation to enhance the interpretability of predictions.

RESULTS

MCDHGN constructs a heterogeneous network by using several types of multi-omics data that are biologically linked to genes. And the differential probabilities of SNV, DNA methylation, and gene expression data between cancerous tissues and normal tissues are extracted as initial features of genes. Nine meta-paths are manually selected, and the representation vectors obtained by aggregating information within and across meta-path nodes are used as new features for subsequent classification and prediction tasks. By comparing with eight homogeneous and heterogeneous network models on two pan-cancer datasets, MCDHGN has better performance on AUC and AUPR values. Additionally, MCDHGN provides interpretability of predicted cancer driver genes through the varying weights of biologically meaningful meta-paths.

AVAILABILITY AND IMPLEMENTATION

https://github.com/1160300611/MCDHGN.

Predicting associations between drugs and G protein-coupled receptors using a multi-graph convolutional network

Developing new drugs is an expensive, time-consuming process that frequently involves safety concerns. By discovering novel uses for previously verified drugs, drug repurposing helps to bypass the time-consuming and costly process of drug development. As the largest family of proteins targeted by verified drugs, G protein-coupled receptors (GPCR) are vital to efficiently repurpose drugs by inferring their associations with drugs. Drug repurposing may be sped up by computational models that predict the strength of novel drug-GPCR pairs interaction. To this end, a number of models have been put forth. In existing methods, however, drug structure, drug-drug interactions, GPCR sequence, and subfamily information couldn't simultaneously be taken into account to detect novel drugs-GPCR relationships. In this study, based on a multi-graph convolutional network, an end-to-end deep model was developed to efficiently and precisely discover latent drug-GPCR relationships by combining data from multi-sources. We demonstrated that our model, based on multi-graph convolutional networks, outperformed rival deep learning techniques as well as non-deep learning models in terms of inferring drug-GPCR relationships. Our results indicated that integrating data from multi-sources can lead to further advancement.

Advancing cancer driver gene detection via Schur complement graph augmentation and independent subspace feature extraction

Accurately identifying cancer driver genes (CDGs) is crucial for guiding cancer treatment and has recently received great attention from researchers. However, the high complexity and heterogeneity of cancer gene regulatory networks limit the precition accuracy of existing deep learning models. To address this, we introduce a model called SCIS-CDG that utilizes Schur complement graph augmentation and independent subspace feature extraction techniques to effectively predict potential CDGs. Firstly, a random Schur complement strategy is adopted to generate two augmented views of gene network within a graph contrastive learning framework. Rapid randomization of the random Schur complement strategy enhances the model's generalization and its ability to handle complex networks effectively. Upholding the Schur complement principle in expectations promotes the preservation of the original gene network's vital structure in the augmented views. Subsequently, we employ feature extraction technology using multiple independent subspaces, each trained with independent weights to reduce inter-subspace dependence and improve the model's expressiveness. Concurrently, we introduced a feature expansion component based on the structure of the gene network to address issues arising from the limited dimensionality of node features. Moreover, it can alleviate the challenges posed by the heterogeneity of cancer gene networks to some extent. Finally, we integrate a learnable attention weight mechanism into the graph neural network (GNN) encoder, utilizing feature expansion technology to optimize the significance of various feature levels in the prediction task. Following extensive experimental validation, the SCIS-CDG model has exhibited high efficiency in identifying known CDGs and uncovering potential unknown CDGs in external datasets. Particularly when compared to previous conventional GNN models, its performance has seen significant improved. The code and data are publicly available at: https://github.com/mxqmxqmxq/SCIS-CDG.

GLIMS: A two-stage gradual-learning method for cancer genes prediction using multi-omics data and co-splicing network

Identifying cancer genes is vital for cancer diagnosis and treatment. However, because of the complexity of cancer occurrence and limited cancer genes knowledge, it is hard to identify cancer genes accurately using only a few omics data, and the overall performance of existing methods is being called for further improvement. Here, we introduce a two-stage gradual-learning strategy GLIMS to predict cancer genes using integrative features from multi-omics data. Firstly, it uses a semi-supervised hierarchical graph neural network to predict the initial candidate cancer genes by integrating multi-omics data and protein-protein interaction (PPI) network. Then, it uses an unsupervised approach to further optimize the initial prediction by integrating the co-splicing network in post-transcriptional regulation, which plays an important role in cancer development. Systematic experiments on multi-omics cancer data demonstrated that GLIMS outperforms the state-of-the-art methods for the identification of cancer genes and it could be a useful tool to help advance cancer analysis.

Personalized Driver Gene Prediction Using Graph Convolutional Networks with Conditional Random Fields

Cancer is a complex and evolutionary disease mainly driven by the accumulation of genetic variations in genes. Identifying cancer driver genes is important. However, most related studies have focused on the population level. Cancer is a disease with high heterogeneity. Thus, the discovery of driver genes at the individual level is becoming more valuable but is a great challenge. Although there have been some computational methods proposed to tackle this challenge, few can cover all patient samples well, and there is still room for performance improvement. In this study, to identify individual-level driver genes more efficiently, we propose the PDGCN method. PDGCN integrates multiple types of data features, including mutation, expression, methylation, copy number data, and system-level gene features, along with network structural features extracted using Node2vec in order to construct a sample-gene interaction network. Prediction is performed using a graphical convolutional neural network model with a conditional random field layer, which is able to better combine the network structural features with biological attribute features. Experiments on the ACC (Adrenocortical Cancer) and KICH (Kidney Chromophobe) datasets from TCGA (The Cancer Genome Atlas) demonstrated that the method performs better compared to other similar methods. It can identify not only frequently mutated driver genes, but also rare candidate driver genes and novel biomarker genes. The results of the survival and enrichment analyses of these detected genes demonstrate that the method can identify important driver genes at the individual level.

The multifaceted roles of COL4A4 in lung adenocarcinoma: An integrated bioinformatics and experimental study

BACKGROUND

Abnormal expression of collagen IV subunits has been reported in cancers, but the significance is not clear. No study has reported the significance of COL4A4 in lung adenocarcinoma (LUAD).

METHODS

COL4A4 expression data, single-cell sequencing data and clinical data were downloaded from public databases. A range of bioinformatics and experimental methods were adopted to analyze the association of COL4A4 expression with clinical parameters, tumor microenvironment (TME), drug resistance and immunotherapy response, and to investigate the roles and underlying mechanism of COL4A4 in LUAD.

RESULTS

COL4A4 is differentially expressed in most of cancers analyzed, being associated with prognosis, tumor stemness, immune checkpoint gene expression and TME parameters. In LUAD, COL4A4 expression is down-regulated and associated with various TME parameters, response to immunotherapy and drug resistance. LUAD patients with lower COL4A4 have worse prognosis. Knockdown of COL4A4 significantly inhibited the expression of cell-cycle associated genes, and the expression and activation of signaling pathways including JAK/STAT3, p38, and ERK pathways, and induced quiescence in LUAD cells. Besides, it significantly induced the expression of a range of bioactive molecule genes that have been shown to have critical roles in TME remodeling and immune regulation.

CONCLUSIONS

COL4A4 is implicated in the pathogenesis of cancers including LUAD. Its function may be multifaceted. It can modulate the activity of LUAD cells, TME remodeling and tumor stemness, thus affecting the pathological process of LUAD. COL4A4 may be a prognostic molecular marker and a potential therapeutic target.

Multi-scale topology and position feature learning and relationship-aware graph reasoning for prediction of drug-related microbes

MOTIVATION

The human microbiome may impact the effectiveness of drugs by modulating their activities and toxicities. Predicting candidate microbes for drugs can facilitate the exploration of the therapeutic effects of drugs. Most recent methods concentrate on constructing of the prediction models based on graph reasoning. They fail to sufficiently exploit the topology and position information, the heterogeneity of multiple types of nodes and connections, and the long-distance correlations among nodes in microbe-drug heterogeneous graph.

RESULTS

We propose a new microbe-drug association prediction model, NGMDA, to encode the position and topological features of microbe (drug) nodes, and fuse the different types of features from neighbors and the whole heterogeneous graph. First, we formulate the position and topology features of microbe (drug) nodes by t-step random walks, and the features reveal the topological neighborhoods at multiple scales and the position of each node. Second, as the features of nodes are high-dimensional and sparse, we designed an embedding enhancement strategy based on supervised fully connected autoencoders to form the embeddings with representative features and the more discriminative node distributions. Third, we propose an adaptive neighbor feature fusion module, which fuses features of neighbors by the constructed position- and topology-sensitive heterogeneous graph neural networks. A novel self-attention mechanism is developed to estimate the importance of the position and topology of each neighbor to a target node. Finally, a heterogeneous graph feature fusion module is constructed to learn the long-distance correlations among the nodes in the whole heterogeneous graph by a relationship-aware graph transformer. Relationship-aware graph transformer contains the strategy for encoding the connection relationship types among the nodes, which is helpful for integrating the diverse semantics of these connections. The extensive comparison experimental results demonstrate NGMDA's superior performance over five state-of-the-art prediction methods. The ablation experiment shows the contributions of the multi-scale topology and position feature learning, the embedding enhancement strategy, the neighbor feature fusion, and the heterogeneous graph feature fusion. Case studies over three drugs further indicate that NGMDA has ability in discovering the potential drug-related microbes.

AVAILABILITY AND IMPLEMENTATION

Source codes and Supplementary Material are available at https://github.com/pingxuan-hlju/NGMDA.

Improving anti-cancer drug response prediction using multi-task learning on graph convolutional networks

Predicting the therapeutic effect of anti-cancer drugs on tumors based on the characteristics of tumors and patients is one of the important contents of precision oncology. Existing computational methods regard the drug response prediction problem as a classification or regression task. However, few of them consider leveraging the relationship between the two tasks. In this work, we propose a Multi-task Interaction Graph Convolutional Network (MTIGCN) for anti-cancer drug response prediction. MTIGCN first utilizes an graph convolutional network-based model to produce embeddings for both cell lines and drugs. After that, the model employs multi-task learning to predict anti-cancer drug response, which involves training the model on three different tasks simultaneously: the main task of the drug sensitive or resistant classification task and the two auxiliary tasks of regression prediction and similarity network reconstruction. By sharing parameters and optimizing the losses of different tasks simultaneously, MTIGCN enhances the feature representation and reduces overfitting. The results of the experiments on two in vitro datasets demonstrated that MTIGCN outperformed seven state-of-the-art baseline methods. Moreover, the well-trained model on the in vitro dataset GDSC exhibited good performance when applied to predict drug responses in in vivo datasets PDX and TCGA. The case study confirmed the model's ability to discover unknown drug responses in cell lines.

HGSMDA: miRNA-Disease Association Prediction Based on HyperGCN and Sørensen-Dice Loss

Biological research has demonstrated the significance of identifying miRNA-disease associations in the context of disease prevention, diagnosis, and treatment. However, the utilization of experimental approaches involving biological subjects to infer these associations is both costly and inefficient. Consequently, there is a pressing need to devise novel approaches that offer enhanced accuracy and effectiveness. Presently, the predominant methods employed for predicting disease associations rely on Graph Convolutional Network (GCN) techniques. However, the Graph Convolutional Network algorithm, which is locally aggregated, solely incorporates information from the immediate neighboring nodes of a given node at each layer. Consequently, GCN cannot simultaneously aggregate information from multiple nodes. This constraint significantly impacts the predictive efficacy of the model. To tackle this problem, we propose a novel approach, based on HyperGCN and Sørensen-Dice loss (HGSMDA), for predicting associations between miRNAs and diseases. In the initial phase, we developed multiple networks to represent the similarity between miRNAs and diseases and employed GCNs to extract information from diverse perspectives. Subsequently, we draw into HyperGCN to construct a miRNA-disease heteromorphic hypergraph using hypernodes and train GCN on the graph to aggregate information. Finally, we utilized the Sørensen-Dice loss function to evaluate the degree of similarity between the predicted outcomes and the ground truth values, thereby enabling the prediction of associations between miRNAs and diseases. In order to assess the soundness of our methodology, an extensive series of experiments was conducted employing the Human MicroRNA Disease Database (HMDD v3.2) as the dataset. The experimental outcomes unequivocally indicate that HGSMDA exhibits remarkable efficacy when compared to alternative methodologies. Furthermore, the predictive capacity of HGSMDA was corroborated through a case study focused on colon cancer. These findings strongly imply that HGSMDA represents a dependable and valid framework, thereby offering a novel avenue for investigating the intricate association between miRNAs and diseases.

Prediction of cancer driver genes and mutations: the potential of integrative computational frameworks

The vast amount of available sequencing data allows the scientific community to explore different genetic alterations that may drive cancer or favor cancer progression. Software developers have proposed a myriad of predictive tools, allowing researchers and clinicians to compare and prioritize driver genes and mutations and their relative pathogenicity. However, there is little consensus on the computational approach or a golden standard for comparison. Hence, benchmarking the different tools depends highly on the input data, indicating that overfitting is still a massive problem. One of the solutions is to limit the scope and usage of specific tools. However, such limitations force researchers to walk on a tightrope between creating and using high-quality tools for a specific purpose and describing the complex alterations driving cancer. While the knowledge of cancer development increases daily, many bioinformatic pipelines rely on single nucleotide variants or alterations in a vacuum without accounting for cellular compartments, mutational burden or disease progression. Even within bioinformatics and computational cancer biology, the research fields work in silos, risking overlooking potential synergies or breakthroughs. Here, we provide an overview of databases and datasets for building or testing predictive cancer driver tools. Furthermore, we introduce predictive tools for driver genes, driver mutations, and the impact of these based on structural analysis. Additionally, we suggest and recommend directions in the field to avoid silo-research, moving towards integrative frameworks.

A sequence-based machine learning model for predicting antigenic distance for H3N2 influenza virus

Introduction

Seasonal influenza A H3N2 viruses are constantly changing, reducing the effectiveness of existing vaccines. As a result, the World Health Organization (WHO) needs to frequently update the vaccine strains to match the antigenicity of emerged H3N2 variants. Traditional assessments of antigenicity rely on serological methods, which are both labor-intensive and time-consuming. Although numerous computational models aim to simplify antigenicity determination, they either lack a robust quantitative linkage between antigenicity and viral sequences or focus restrictively on selected features.

Methods

Here, we propose a novel computational method to predict antigenic distances using multiple features, including not only viral sequence attributes but also integrating four distinct categories of features that significantly affect viral antigenicity in sequences.

Results

This method exhibits low error in virus antigenicity prediction and achieves superior accuracy in discerning antigenic drift. Utilizing this method, we investigated the evolution process of the H3N2 influenza viruses and identified a total of 21 major antigenic clusters from 1968 to 2022.

Discussion

Interestingly, our predicted antigenic map aligns closely with the antigenic map generated with serological data. Thus, our method is a promising tool for detecting antigenic variants and guiding the selection of vaccine candidates.

Drug-disease association prediction using semantic graph and function similarity representation learning over heterogeneous information networks

Discovering new indications for existing drugs is a promising development strategy at various stages of drug research and development. However, most of them complete their tasks by constructing a variety of heterogeneous networks without considering available higher-order connectivity patterns in heterogeneous biological information networks, which are believed to be useful for improving the accuracy of new drug discovering. To this end, we propose a computational-based model, called SFRLDDA, for drug-disease association prediction by using semantic graph and function similarity representation learning. Specifically, SFRLDDA first integrates a heterogeneous information network (HIN) by drug-disease, drug-protein, protein-disease associations, and their biological knowledge. Second, different representation learning strategies are applied to obtain the feature representations of drugs and diseases from different perspectives over semantic graph and function similarity graphs constructed, respectively. At last, a Random Forest classifier is incorporated by SFRLDDA to discover potential drug-disease associations (DDAs). Experimental results demonstrate that SFRLDDA yields a best performance when compared with other state-of-the-art models on three benchmark datasets. Moreover, case studies also indicate that the simultaneous consideration of semantic graph and function similarity of drugs and diseases in the HIN allows SFRLDDA to precisely predict DDAs in a more comprehensive manner.

A Graph Convolution Network-Based Model for Prioritizing Personalized Cancer Driver Genes of Individual Patients

Cancer driver genes are mutated genes that play a key role in the growth of cancer cells. Accurately identifying the cancer driver genes helps us understand cancer's pathogenesis and develop effective treatment strategies. However, cancers are highly heterogeneous diseases; patients with the same cancer type may have different genomic characteristics and clinical symptoms. Hence, it is urgent to devise effective methods to identify personalized cancer driver genes of individual patients to help determine whether a patient can be treated with a certain targeted drug. This work presents a method for predicting personalized cancer Driver genes of individual patients based on Graph Convolution Networks and Neighbor Interactions called NIGCNDriver. NIGCNDriver first constructs a gene-sample association matrix using the associations between a sample and its known driver genes. Then, it employs graph convolution models on the gene-sample network to aggregate neighbor node features, and themself features, and then combines with the element-wise level interactions between neighbors to learn new feature representations for the samples and gene nodes. Finally, a linear correlation coefficient decoder is used to reconstruct the association between the sample and the mutant gene, enabling the prediction of a personalized driver gene for the individual sample. We applied the NIGCNDriver method to predict cancer driver genes for individual samples in the TCGA and cancer cell line datasets. The results show that our method outperforms the baseline methods in cancer driver gene prediction for individual samples.

SMG: self-supervised masked graph learning for cancer gene identification

Cancer genomics is dedicated to elucidating the genes and pathways that contribute to cancer progression and development. Identifying cancer genes (CGs) associated with the initiation and progression of cancer is critical for characterization of molecular-level mechanism in cancer research. In recent years, the growing availability of high-throughput molecular data and advancements in deep learning technologies has enabled the modelling of complex interactions and topological information within genomic data. Nevertheless, because of the limited labelled data, pinpointing CGs from a multitude of potential mutations remains an exceptionally challenging task. To address this, we propose a novel deep learning framework, termed self-supervised masked graph learning (SMG), which comprises SMG reconstruction (pretext task) and task-specific fine-tuning (downstream task). In the pretext task, the nodes of multi-omic featured protein-protein interaction (PPI) networks are randomly substituted with a defined mask token. The PPI networks are then reconstructed using the graph neural network (GNN)-based autoencoder, which explores the node correlations in a self-prediction manner. In the downstream tasks, the pre-trained GNN encoder embeds the input networks into feature graphs, whereas a task-specific layer proceeds with the final prediction. To assess the performance of the proposed SMG method, benchmarking experiments are performed on three node-level tasks (identification of CGs, essential genes and healthy driver genes) and one graph-level task (identification of disease subnetwork) across eight PPI networks. Benchmarking experiments and performance comparison with existing state-of-the-art methods demonstrate the superiority of SMG on multi-omic feature engineering.

InDEP: an interpretable machine learning approach to predict cancer driver genes from multi-omics data

Cancer driver genes are critical in driving tumor cell growth, and precisely identifying these genes is crucial in advancing our understanding of cancer pathogenesis and developing targeted cancer drugs. Despite the current methods for discovering cancer driver genes that mainly rely on integrating multi-omics data, many existing models are overly complex, and it is difficult to interpret the results accurately. This study aims to address this issue by introducing InDEP, an interpretable machine learning framework based on cascade forests. InDEP is designed with easy-to-interpret features, cascade forests based on decision trees and a KernelSHAP module that enables fine-grained post-hoc interpretation. Integrating multi-omics data, InDEP can identify essential features of classified driver genes at both the gene and cancer-type levels. The framework accurately identifies driver genes, discovers new patterns that make genes as driver genes and refines the cancer driver gene catalog. In comparison with state-of-the-art methods, InDEP proved to be more accurate on the test set and identified reliable candidate driver genes. Mutational features were the primary drivers for InDEP's identifying driver genes, with other omics features also contributing. At the gene level, the framework concluded that substitution-type mutations were the main reason most genes were identified as driver genes. InDEP's ability to identify reliable candidate driver genes opens up new avenues for precision oncology and discovering new biomedical knowledge. This framework can help advance cancer research by providing an interpretable method for identifying cancer driver genes and their contribution to cancer pathogenesis, facilitating the development of targeted cancer drugs.

Recent Advances in Deep Learning for Protein-Protein Interaction Analysis: A Comprehensive Review

Deep learning, a potent branch of artificial intelligence, is steadily leaving its transformative imprint across multiple disciplines. Within computational biology, it is expediting progress in the understanding of Protein-Protein Interactions (PPIs), key components governing a wide array of biological functionalities. Hence, an in-depth exploration of PPIs is crucial for decoding the intricate biological system dynamics and unveiling potential avenues for therapeutic interventions. As the deployment of deep learning techniques in PPI analysis proliferates at an accelerated pace, there exists an immediate demand for an exhaustive review that encapsulates and critically assesses these novel developments. Addressing this requirement, this review offers a detailed analysis of the literature from 2021 to 2023, highlighting the cutting-edge deep learning methodologies harnessed for PPI analysis. Thus, this review stands as a crucial reference for researchers in the discipline, presenting an overview of the recent studies in the field. This consolidation helps elucidate the dynamic paradigm of PPI analysis, the evolution of deep learning techniques, and their interdependent dynamics. This scrutiny is expected to serve as a vital aid for researchers, both well-established and newcomers, assisting them in maneuvering the rapidly shifting terrain of deep learning applications in PPI analysis.

Unraveling the Drivers of Tumorigenesis in the Context of Evolution: Theoretical Models and Bioinformatics Tools

Cancer originates from somatic cells that have accumulated mutations. These mutations alter the phenotype of the cells, allowing them to escape homeostatic regulation that maintains normal cell numbers. The emergence of malignancies is an evolutionary process in which the random accumulation of somatic mutations and sequential selection of dominant clones cause cancer cells to proliferate. The development of technologies such as high-throughput sequencing has provided a powerful means to measure subclonal evolutionary dynamics across space and time. Here, we review the patterns that may be observed in cancer evolution and the methods available for quantifying the evolutionary dynamics of cancer. An improved understanding of the evolutionary trajectories of cancer will enable us to explore the molecular mechanism of tumorigenesis and to design tailored treatment strategies.

Identifying driver pathways based on a parameter-free model and a partheno-genetic algorithm

BACKGROUND

Tremendous amounts of omics data accumulated have made it possible to identify cancer driver pathways through computational methods, which is believed to be able to offer critical information in such downstream research as ascertaining cancer pathogenesis, developing anti-cancer drugs, and so on. It is a challenging problem to identify cancer driver pathways by integrating multiple omics data.

RESULTS

In this study, a parameter-free identification model SMCMN, incorporating both pathway features and gene associations in Protein-Protein Interaction (PPI) network, is proposed. A novel measurement of mutual exclusivity is devised to exclude some gene sets with "inclusion" relationship. By introducing gene clustering based operators, a partheno-genetic algorithm CPGA is put forward for solving the SMCMN model. Experiments were implemented on three real cancer datasets to compare the identification performance of models and methods. The comparisons of models demonstrate that the SMCMN model does eliminate the "inclusion" relationship, and produces gene sets with better enrichment performance compared with the classical model MWSM in most cases.

CONCLUSIONS

The gene sets recognized by the proposed CPGA-SMCMN method possess more genes engaging in known cancer related pathways, as well as stronger connectivity in PPI network. All of which have been demonstrated through extensive contrast experiments among the CPGA-SMCMN method and six state-of-the-art ones.

Computational Methods Summarizing Mutational Patterns in Cancer: Promise and Limitations for Clinical Applications

Since the rise of next-generation sequencing technologies, the catalogue of mutations in cancer has been continuously expanding. To address the complexity of the cancer-genomic landscape and extract meaningful insights, numerous computational approaches have been developed over the last two decades. In this review, we survey the current leading computational methods to derive intricate mutational patterns in the context of clinical relevance. We begin with mutation signatures, explaining first how mutation signatures were developed and then examining the utility of studies using mutation signatures to correlate environmental effects on the cancer genome. Next, we examine current clinical research that employs mutation signatures and discuss the potential use cases and challenges of mutation signatures in clinical decision-making. We then examine computational studies developing tools to investigate complex patterns of mutations beyond the context of mutational signatures. We survey methods to identify cancer-driver genes, from single-driver studies to pathway and network analyses. In addition, we review methods inferring complex combinations of mutations for clinical tasks and using mutations integrated with multi-omics data to better predict cancer phenotypes. We examine the use of these tools for either discovery or prediction, including prediction of tumor origin, treatment outcomes, prognosis, and cancer typing. We further discuss the main limitations preventing widespread clinical integration of computational tools for the diagnosis and treatment of cancer. We end by proposing solutions to address these challenges using recent advances in machine learning.

Improving drug response prediction based on two-space graph convolution

Patients with the same cancer types may present different genomic features and therefore have different drug sensitivities. Accordingly, correctly predicting patients' responses to the drugs can guide treatment decisions and improve the outcome of cancer patients. Existing computational methods leverage the graph convolution network model to aggregate features of different types of nodes in the heterogeneous network. They most fail to consider the similarity between homogeneous nodes. To this end, we propose an algorithm based on two-space graph convolutional neural networks, TSGCNN, to predict the response of anticancer drugs. TSGCNN first constructs the cell line feature space and the drug feature space and separately performs the graph convolution operation on the feature spaces to diffuse similarity information among homogeneous nodes. After that, we generate a heterogeneous network based on the known cell line and drug relationship and perform graph convolution operations on the heterogeneous network to collect the features of different types of nodes. Subsequently, the algorithm produces the final feature representations for cell lines and drugs by adding their self features, the feature space representations, and the heterogeneous space representations. Finally, we leverage the linear correlation coefficient decoder to reconstruct the cell line-drug correlation matrix for drug response prediction based on the final representations. We tested our model on the Cancer Drug Sensitivity Data (GDSC) and Cancer Cell Line Encyclopedia (CCLE) databases. The results indicate that TSGCNN shows excellent performance drug response prediction compared with other eight state-of-the-art methods.

Identifying cancer driver genes based on multi-view heterogeneous graph convolutional network and self-attention mechanism

BACKGROUND

Correctly identifying the driver genes that promote cell growth can significantly assist drug design, cancer diagnosis and treatment. The recent large-scale cancer genomics projects have revealed multi-omics data from thousands of cancer patients, which requires to design effective models to unlock the hidden knowledge within the valuable data and discover cancer drivers contributing to tumorigenesis.

RESULTS

In this work, we propose a graph convolution network-based method called MRNGCN that integrates multiple gene relationship networks to identify cancer driver genes. First, we constructed three gene relationship networks, including the gene-gene, gene-outlying gene and gene-miRNA networks. Then, genes learnt feature presentations from the three networks through three sharing-parameter heterogeneous graph convolution network (HGCN) models with the self-attention mechanism. After that, these gene features pass a convolution layer to generate fused features. Finally, we utilized the fused features and the original feature to optimize the model by minimizing the node and link prediction losses. Meanwhile, we combined the fused features, the original features and the three features learned from every network through a logistic regression model to predict cancer driver genes.

CONCLUSIONS

We applied the MRNGCN to predict pan-cancer and cancer type-specific driver genes. Experimental results show that our model performs well in terms of the area under the ROC curve (AUC) and the area under the precision-recall curve (AUPRC) compared to state-of-the-art methods. Ablation experimental results show that our model successfully improved the cancer driver identification by integrating multiple gene relationship networks.

Improving therapeutic synergy score predictions with adverse effects using multi-task heterogeneous network learning

Drug combinations could trigger pharmacological therapeutic effects (TEs) and adverse effects (AEs). Many computational methods have been developed to predict TEs, e.g. the therapeutic synergy scores of anti-cancer drug combinations, or AEs from drug-drug interactions. However, most of the methods treated the AEs and TEs predictions as two separate tasks, ignoring the potential mechanistic commonalities shared between them. Based on previous clinical observations, we hypothesized that by learning the shared mechanistic commonalities between AEs and TEs, we could learn the underlying MoAs (mechanisms of actions) and ultimately improve the accuracy of TE predictions. To test our hypothesis, we formulated the TE prediction problem as a multi-task heterogeneous network learning problem that performed TE and AE learning tasks simultaneously. To solve this problem, we proposed Muthene (multi-task heterogeneous network embedding) and evaluated it on our collected drug-drug interaction dataset with both TEs and AEs indications. Our experimental results showed that, by including the AE prediction as an auxiliary task, Muthene generated more accurate TE predictions than standard single-task learning methods, which supports our hypothesis. Using a drug pair Vincristine-Dasatinib as a case study, we demonstrated that our method not only provides a novel way of TE predictions but also helps us gain a deeper understanding of the MoAs of drug combinations.

Metastasis-related gene identification by compound constrained NMF and a semisupervised cluster approach using pancancer multiomics features

In recent years, with the gradual increase in pancancer-related research, more attention has been given to the field of pancancer metastasis. However, the molecular mechanism of pancancer metastasis is very unclear, and identification methods for pancancer metastasis-related genes are still lacking. In view of this research status, we developed a novel pipeline to identify pancancer metastasis-related genes based on compound constrained nonnegative matrix factorization (CCNMF). To solve the above problems, the following modules were designed. A correntropy operator and feature similarity fusion (FSF) were first adopted to process the multiomics features of genes; thus, the influences caused by irrelevant biomolecular patterns, manifested as non-Gaussian noise, were minimized. CCNMF was then adopted to handle the above features with compound constraints consisting of a gene relation network and a "metastasis-related" gene set, which maximizes the biological interpretability of the metafeatures generated by NMF. Since a negative set of pancancer "metastasis-related" genes could hardly be obtained, semisupervised analyses were performed on gene features acquired by each step in our pipeline to examine our method's effect. 83% of the 236 candidates identified by the above method were associated with the metastasis of one or more cancers, 71.9% candidates were identified immune-related in pancancer in addition to the hallmark genes. Our study provides an effective and interpretable method for identifying metastasis-related as well as immune-related genes, and the method is successfully applied to TCGA pancancer data.

Protein function annotation based on heterogeneous biological networks

Background

Accurate annotation of protein function is the key to understanding life at the molecular level and has great implications for biomedicine and pharmaceuticals. The rapid developments of high-throughput technologies have generated huge amounts of protein–protein interaction (PPI) data, which prompts the emergence of computational methods to determine protein function. Plagued by errors and noises hidden in PPI data, these computational methods have undertaken to focus on the prediction of functions by integrating the topology of protein interaction networks and multi-source biological data. Despite effective improvement of these computational methods, it is still challenging to build a suitable network model for integrating multiplex biological data.

Results

In this paper, we constructed a heterogeneous biological network by initially integrating original protein interaction networks, protein-domain association data and protein complexes. To prove the effectiveness of the heterogeneous biological network, we applied the propagation algorithm on this network, and proposed a novel iterative model, named Propagate on Heterogeneous Biological Networks (PHN) to score and rank functions in descending order from all functional partners, Finally, we picked out top L of these predicted functions as candidates to annotate the target protein. Our comprehensive experimental results demonstrated that PHN outperformed seven other competing approaches using cross-validation. Experimental results indicated that PHN performs significantly better than competing methods and improves the Area Under the Receiver-Operating Curve (AUROC) in Biological Process (BP), Molecular Function (MF) and Cellular Components (CC) by no less than 33%, 15% and 28%, respectively.

Conclusions

We demonstrated that integrating multi-source data into a heterogeneous biological network can preserve the complex relationship among multiplex biological data and improve the prediction accuracy of protein function by getting rid of the constraints of errors in PPI networks effectively. PHN, our proposed method, is effective for protein function prediction.

MODIG: Integrating Multi-Omics and Multi-Dimensional Gene Network for Cancer Driver Gene Identification based on Graph Attention Network Model

MOTIVATION

Identifying genes that play a causal role in cancer evolution remains one of the biggest challenges in cancer biology. With the accumulation of high-throughput multi-omics data over decades, it becomes a great challenge to effectively integrate these data into the identification of cancer driver genes.

RESULTS

Here, we propose MODIG, a graph attention network (GAT)-based framework to identify cancer driver genes by combining multi-omics pan-cancer data (mutations, copy number variants, gene expression, and methylation levels) with multi-dimensional gene networks. First, we established diverse types of gene relationship maps based on protein-protein interactions (PPI), gene sequence similarity, KEGG pathway co-occurrence, gene co-expression patterns, and Gene Ontology (GO). Then, we constructed a multi-dimensional gene network consisting of approximately 20,000 genes as nodes and five types of gene associations as multiplex edges. We applied a GAT to model within-dimension interactions to generate a gene representation for each dimension based on this graph. Moreover, we introduced a joint learning module to fuse multiple dimension-specific representations to generate general gene representations. Finally, we used the obtained gene representation to perform a semi-supervised driver gene identification task. The experiment results show that MODIG outperforms the baseline models in terms of area under precision-recall curves (AUPR) and area under the receiver operating characteristic curves (AUROC).

AVAILABILITY

The MODIG program is available at https://github.com/zjupgx/modig. The code and data underlying this article are also available on Zenodo, at https://doi.org/10.5281/zenodo.7057241.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Discovering driver nodes in chronic kidney disease-related networks using Trader as a newly developed algorithm

Thanks to the advances in the field of computational-based biology, a huge volume of disease-related data has been generated so far. From the existing data, the disease-related protein-protein interaction (PPI) networks seem to yield effective treatment plans due to the informative/systematic representation of diseases. Yet, a large number of previous studies have failed due to the complex nature of such disease-related networks. For addressing this limitation, in the present study, we combined Trader and the DFS algorithms to identify a minimal subset of nodes (driver nodes) whose removal produces a maximum number of disjoint sub-networks. We then screened the nodes in the disease-associated PPI networks and to evaluate the efficiency of the suggested method, it was applied to six PPI networks of differentially expressed genes in chronic kidney diseases. The performance of Trader was superior to other well-known algorithms in terms of identifying driver nodes. Besides, the proportion of proteins that were targeted by at least one FDA-approved drug was significantly higher among the identified driver nodes when compared with the rest of the proteins in the networks. The proposed algorithm could be applied for predicting future therapeutic targets in complex disorder networks. In conclusion, unlike the common methods, computationally efficient algorithms can generate more practical outcomes which are compatible with real-world biological facts.

Contrastive learning-based computational histopathology predict differential expression of cancer driver genes

MOTIVATION

Digital pathological analysis is run as the main examination used for cancer diagnosis. Recently, deep learning-driven feature extraction from pathology images is able to detect genetic variations and tumor environment, but few studies focus on differential gene expression in tumor cells.

RESULTS

In this paper, we propose a self-supervised contrastive learning framework, HistCode, to infer differential gene expression from whole slide images (WSIs). We leveraged contrastive learning on large-scale unannotated WSIs to derive slide-level histopathological features in latent space, and then transfer it to tumor diagnosis and prediction of differentially expressed cancer driver genes. Our experiments showed that our method outperformed other state-of-the-art models in tumor diagnosis tasks, and also effectively predicted differential gene expression. Interestingly, we found the genes with higher fold change can be more precisely predicted. To intuitively illustrate the ability to extract informative features from pathological images, we spatially visualized the WSIs colored by the attention scores of image tiles. We found that the tumor and necrosis areas were highly consistent with the annotations of experienced pathologists. Moreover, the spatial heatmap generated by lymphocyte-specific gene expression patterns was also consistent with the manually labeled WSIs.

A Deep Spatiotemporal Attention Network for Mild Cognitive Impairment Identification

Mild cognitive impairment (MCI) is a nervous system disease, and its clinical status can be used as an early warning of Alzheimer's disease (AD). Subtle and slow changes in brain structure between patients with MCI and normal controls (NCs) deprive them of effective diagnostic methods. Therefore, the identification of MCI is a challenging task. The current functional brain network (FBN) analysis to predict human brain tissue structure is a new method emerging in recent years, which provides sensitive and effective medical biomarkers for the diagnosis of neurological diseases. Therefore, to address this challenge, we propose a novel Deep Spatiotemporal Attention Network (DSTAN) framework for MCI recognition based on brain functional networks. Specifically, we first extract spatiotemporal features between brain functional signals and FBNs by designing a spatiotemporal convolution strategy (ST-CONV). Then, on this basis, we introduce a learned attention mechanism to further capture brain nodes strongly correlated with MCI. Finally, we fuse spatiotemporal features for MCI recognition. The entire network is trained in an end-to-end fashion. Extensive experiments show that our proposed method significantly outperforms current baselines and state-of-the-art methods, with a classification accuracy of 84.21%.

A tensor-based bi-random walks model for protein function prediction

Background

The accurate characterization of protein functions is critical to understanding life at the molecular level and has a huge impact on biomedicine and pharmaceuticals. Computationally predicting protein function has been studied in the past decades. Plagued by noise and errors in protein–protein interaction (PPI) networks, researchers have undertaken to focus on the fusion of multi-omics data in recent years. A data model that appropriately integrates network topologies with biological data and preserves their intrinsic characteristics is still a bottleneck and an aspirational goal for protein function prediction.

Results

In this paper, we propose the RWRT (Random Walks with Restart on Tensor) method to accomplish protein function prediction by applying bi-random walks on the tensor. RWRT firstly constructs a functional similarity tensor by combining protein interaction networks with multi-omics data derived from domain annotation and protein complex information. After this, RWRT extends the bi-random walks algorithm from a two-dimensional matrix to the tensor for scoring functional similarity between proteins. Finally, RWRT filters out possible pretenders based on the concept of cohesiveness coefficient and annotates target proteins with functions of the remaining functional partners. Experimental results indicate that RWRT performs significantly better than the state-of-the-art methods and improves the area under the receiver-operating curve (AUROC) by no less than 18%.

Conclusions

The functional similarity tensor offers us an alternative, in that it is a collection of networks sharing the same nodes; however, the edges belong to different categories or represent interactions of different nature. We demonstrate that the tensor-based random walk model can not only discover more partners with similar functions but also free from the constraints of errors in protein interaction networks effectively. We believe that the performance of function prediction depends greatly on whether we can extract and exploit proper functional similarity information on protein correlations.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04747-2.

Predicting miRNA-disease associations via learning multimodal networks and fusing mixed neighborhood information

MOTIVATION

In recent years, a large number of biological experiments have strongly shown that miRNAs play an important role in understanding disease pathogenesis. The discovery of miRNA-disease associations is beneficial for disease diagnosis and treatment. Since inferring these associations through biological experiments is time-consuming and expensive, researchers have sought to identify the associations utilizing computational approaches. Graph Convolutional Networks (GCNs), which exhibit excellent performance in link prediction problems, have been successfully used in miRNA-disease association prediction. However, GCNs only consider 1st-order neighborhood information at one layer but fail to capture information from high-order neighbors to learn miRNA and disease representations through information propagation. Therefore, how to aggregate information from high-order neighborhood effectively in an explicit way is still challenging.

RESULTS

To address such a challenge, we propose a novel method called mixed neighborhood information for miRNA-disease association (MINIMDA), which could fuse mixed high-order neighborhood information of miRNAs and diseases in multimodal networks. First, MINIMDA constructs the integrated miRNA similarity network and integrated disease similarity network respectively with their multisource information. Then, the embedding representations of miRNAs and diseases are obtained by fusing mixed high-order neighborhood information from multimodal network which are the integrated miRNA similarity network, integrated disease similarity network and the miRNA-disease association networks. Finally, we concentrate the multimodal embedding representations of miRNAs and diseases and feed them into the multilayer perceptron (MLP) to predict their underlying associations. Extensive experimental results show that MINIMDA is superior to other state-of-the-art methods overall. Moreover, the outstanding performance on case studies for esophageal cancer, colon tumor and lung cancer further demonstrates the effectiveness of MINIMDA.

AVAILABILITY AND IMPLEMENTATION

https://github.com/chengxu123/MINIMDA and http://120.79.173.96/.

Machine learning methods for prediction of cancer driver genes: a survey paper

Identifying the genes and mutations that drive the emergence of tumors is a critical step to improving our understanding of cancer and identifying new directions for disease diagnosis and treatment. Despite the large volume of genomics data, the precise detection of driver mutations and their carrying genes, known as cancer driver genes, from the millions of possible somatic mutations remains a challenge. Computational methods play an increasingly important role in discovering genomic patterns associated with cancer drivers and developing predictive models to identify these elements. Machine learning (ML), including deep learning, has been the engine behind many of these efforts and provides excellent opportunities for tackling remaining gaps in the field. Thus, this survey aims to perform a comprehensive analysis of ML-based computational approaches to identify cancer driver mutations and genes, providing an integrated, panoramic view of the broad data and algorithmic landscape within this scientific problem. We discuss how the interactions among data types and ML algorithms have been explored in previous solutions and outline current analytical limitations that deserve further attention from the scientific community. We hope that by helping readers become more familiar with significant developments in the field brought by ML, we may inspire new researchers to address open problems and advance our knowledge towards cancer driver discovery.