Network-based classification of breast cancer metastasis

Current and future directions in network biology

Summary

Network biology is an interdisciplinary field bridging computational and biological sciences that has proved pivotal in advancing the understanding of cellular functions and diseases across biological systems and scales. Although the field has been around for two decades, it remains nascent. It has witnessed rapid evolution, accompanied by emerging challenges. These stem from various factors, notably the growing complexity and volume of data together with the increased diversity of data types describing different tiers of biological organization. We discuss prevailing research directions in network biology, focusing on molecular/cellular networks but also on other biological network types such as biomedical knowledge graphs, patient similarity networks, brain networks, and social/contact networks relevant to disease spread. In more detail, we highlight areas of inference and comparison of biological networks, multimodal data integration and heterogeneous networks, higher-order network analysis, machine learning on networks, and network-based personalized medicine. Following the overview of recent breakthroughs across these five areas, we offer a perspective on future directions of network biology. Additionally, we discuss scientific communities, educational initiatives, and the importance of fostering diversity within the field. This article establishes a roadmap for an immediate and long-term vision for network biology.

Availability and implementation

Not applicable.

A framework for performance enhancement of classifiers in detection of prostate cancer from microarray gene

Prostate cancer is a major world health problem for men. This shows how important early detection and accurate diagnosis are for better treatment and patient outcomes. This study compares different ways to find Prostate Cancer (PCa) and label tumors as normal or abnormal, with the goal of speeding up current work in microarray gene data analysis. The study looks at how well several feature extraction methods work with three feature selection strategies: Harmonic Search (HS), Firefly Algorithm (FA), and Elephant Herding Optimization (EHO). The techniques tested are Expectation Maximization (EM), Nonlinear Regression (NLR), K-means, Principal Component Analysis (PCA), and Discrete Cosine Transform (DCT). Eight classifiers are used for the task of classification. These are Random Forest, Decision Tree, Adaboost, XGBoost, and Support Vector Machine (SVM) with linear, polynomial, and radial basis function kernels. This study looks at how well these classifiers work with and without feature selection methods. It finds that the SVM with radial basis function kernel, using DCT for feature extraction and EHO for feature selection, does the best of all of them, with an accuracy of 94.8 % and an error rate of 5.15 %.

Community cohesion looseness in gene networks reveals individualized drug targets and resistance

Community cohesion plays a critical role in the determination of an individual's health in social science. Intriguingly, a community structure of gene networks indicates that the concept of community cohesion could be applied between the genes as well to overcome the limitations of single gene-based biomarkers for precision oncology. Here, we develop community cohesion scores which precisely quantify the community ability to retain the interactions between the genes and their cellular functions in each individualized gene network. Using breast cancer as a proof-of-concept study, we measure the community cohesion score profiles of 950 case samples and predict the individualized therapeutic targets in 2-fold. First, we prioritize them by finding druggable genes present in the community with the most and relatively decreased scores in each individual. Then, we pinpoint more individualized therapeutic targets by discovering the genes which greatly contribute to the community cohesion looseness in each individualized gene network. Compared with the previous approaches, the community cohesion scores show at least four times higher performance in predicting effective individualized chemotherapy targets based on drug sensitivity data. Furthermore, the community cohesion scores successfully discover the known breast cancer subtypes and we suggest new targeted therapy targets for triple negative breast cancer (e.g. KIT and GABRP). Lastly, we demonstrate that the community cohesion scores can predict tamoxifen responses in ER+ breast cancer and suggest potential combination therapies (e.g. NAMPT and RXRA inhibitors) to reduce endocrine therapy resistance based on individualized characteristics. Our method opens new perspectives for the biomarker development in precision oncology.

Predicting immunotherapy response in melanoma using a novel tumor immunological phenotype-related gene index

Introduction

Melanoma is a highly aggressive and recurrent form of skin cancer, posing challenges in prognosis and therapy prediction.

Methods

In this study, we developed a novel TIPRGPI consisting of 20 genes using Univariate Cox regression and the LASSO algorithm. The high and low-risk groups based on TIPRGPI exhibited distinct mutation profiles, hallmark pathways, and immune cell infiltration in the tumor microenvironment.

Results

Notably, significant differences in tumor immunogenicity and TIDE were observed between the risk groups, suggesting a better response to immune checkpoint blockade therapy in the low-TIPRGPI group. Additionally, molecular docking predicted 10 potential drugs that bind to the core target, PTPRC, of the TIPRGPI signature.

Discussion

Our findings highlight the reliability of TIPRGPI as a prognostic signature and its potential application in risk classification, immunotherapy response prediction, and drug candidate identification for melanoma treatment. The "TIP genes" guided strategy presented in this study may have implications beyond melanoma and could be applied to other cancer types.

USP30 promotes the progression of breast cancer by stabilising Snail

Breast cancer (BC) is the most prevalent tumour in women worldwide. USP30 is a deubiquitinase that has been previously reported to promote tumour progression and lipid synthesis in hepatocellular carcinoma. However, the role of USP30 in breast cancer remains unclear. Therefore, we investigated its biological action and corresponding mechanisms in vitro and in vivo. In our study, we found that USP30 was highly expressed in breast cancer samples and correlated with a poor patient prognosis. Knockdown of USP30 significantly suppressed the proliferation, invasion and migration abilities of BC cells in vitro and tumour growth in vivo, whereas overexpression of USP30 exhibited the opposite effect. Mechanistically, we verified that USP30 interacts with and stabilises Snail to promote its protein expression through deubiquitination by K48-linked polyubiquitin chains and then accelerates the EMT program. More importantly, USP30 reduced the chemosensitivity of BC cells to paclitaxel (PTX). Collectively, these data demonstrate that USP30 promotes the BC cell EMT program by stabilising Snail and attenuating chemosensitivity to PTX and may be a potential therapeutic target in BC.

Identification of potential regulatory mechanisms and therapeutic targets for lung cancer

Lung cancer poses a significant health threat globally, especially in regions like India, with 5-year survival rates remain alarmingly low. Our study aimed to uncover key markers for effective treatment and early detection. We identified specific genes related to lung cancer using the BioXpress database and delved into their roles through DAVID enrichment analysis. By employing network theory, we explored the intricate interactions within lung cancer networks, identifying ASPM and MKI67 as crucial regulator genes. Predictions of microRNA and transcription factor interactions provided additional insights. Examining gene expression patterns using GEPIA and KM Plotter revealed the clinical relevance of these key genes. In our pursuit of targeted therapies, Drug Bank pointed to methotrexate as a potential drug for the identified key regulator genes. Confirming this, molecular docking studies through Swiss Dock showed promising binding interactions. To ensure stability, we conducted molecular dynamics simulations using the AMBER 16 suite. In summary, our study pinpoints ASPM and MKI67 as vital regulators in lung cancer networks. The identification of hub genes and functional pathways enhances our understanding of molecular processes, offering potential therapeutic targets. Importantly, methotrexate emerged as a promising drug candidate, supported by robust docking and simulation studies. These findings lay a solid foundation for further experimental validations and hold promise for advancing personalized therapeutic strategies in lung cancer.Communicated by Ramaswamy H. Sarma.

Structural deep clustering network for stratification of breast cancer patients through integration of somatic mutation profiles

BACKGROUND AND OBJECTIVE

Breast cancer is among of the most malignant tumor that occurs in women and is one of the leading causes of death from gynecologic malignancy worldwide. The high degree of heterogeneity that characterizes breast cancer makes it challenging to devise effective therapeutic strategies. Accumulating evidence highlights the crucial role of stratifying breast cancer patients into clinically significant subtypes to achieve better prognoses and treatments. The structural deep clustering network is a graph convolutional network-based clustering algorithm that integrates structural information and has achieved state-of-the-art performance in various applications.

METHODS

In this study, we employed structural deep clustering network to integrate somatic mutation profiles for stratifying 2526 breast cancer patients from the Memorial Sloan Kettering Cancer Center into two clinically differentiable subtypes.

RESULTS

Breast cancer patients in cluster 1 exhibited better prognosis than breast cancer patients in cluster 2, and the difference between them was statistically significant. The immunogenomic landscape further demonstrated that cluster 1 was associated with remarkable infiltration of the tumor infiltrating lymphocytes. The clustering subtype could be used to evaluate the therapeutic benefit of immunotherapy and chemotherapy in breast cancer patients. Furthermore, our approach effectively classified patients from eight different cancer types, demonstrating its generalizability.

CONCLUSIONS

Our study represents a step towards a generic methodology for classifying cancer patients using only somatic mutation data and structural deep clustering network approaches. Employing structural deep clustering network to identify breast cancer subtypes is promising and can inform the development of more accurate and personalized therapies.

Identifying Lymph Node Metastasis-Related Factors in Breast Cancer Using Differential Modular and Mutational Structural Analysis

Complex diseases are generally caused by disorders of biological networks and/or mutations in multiple genes. Comparisons of network topologies between different disease states can highlight key factors in their dynamic processes. Here, we propose a differential modular analysis approach that integrates protein-protein interactions with gene expression profiles for modular analysis, and introduces inter-modular edges and date hubs to identify the "core network module" that quantifies the significant phenotypic variation. Then, based on this core network module, key factors, including functional protein-protein interactions, pathways, and driver mutations, are predicted by the topological-functional connection score and structural modeling. We applied this approach to analyze the lymph node metastasis (LNM) process in breast cancer. The functional enrichment analysis showed that both inter-modular edges and date hubs play important roles in cancer metastasis and invasion, and in metastasis hallmarks. The structural mutation analysis suggested that the LNM of breast cancer may be the outcome of the dysfunction of rearranged during transfection (RET) proto-oncogene-related interactions and the non-canonical calcium signaling pathway via an allosteric mutation of RET. We believe that the proposed method can provide new insights into disease progression such as cancer metastasis.

A framework for considering prior information in network-based approaches to omics data analysis

For decades, molecular biologists have been uncovering the mechanics of biological systems. Efforts to bring their findings together have led to the development of multiple databases and information systems that capture and present pathway information in a computable network format. Concurrently, the advent of modern omics technologies has empowered researchers to systematically profile cellular processes across different modalities. Numerous algorithms, methodologies, and tools have been developed to use prior knowledge networks (PKNs) in the analysis of omics datasets. Interestingly, it has been repeatedly demonstrated that the source of prior knowledge can greatly impact the results of a given analysis. For these methods to be successful it is paramount that their selection of PKNs is amenable to the data type and the computational task they aim to accomplish. Here we present a five-level framework that broadly describes network models in terms of their scope, level of detail, and ability to inform causal predictions. To contextualize this framework, we review a handful of network-based omics analysis methods at each level, while also describing the computational tasks they aim to accomplish.

Omics-Based Investigations of Breast Cancer

Breast cancer (BC) is characterized by an extensive genotypic and phenotypic heterogeneity. In-depth investigations into the molecular bases of BC phenotypes, carcinogenesis, progression, and metastasis are necessary for accurate diagnoses, prognoses, and therapy assessments in predictive, precision, and personalized oncology. This review discusses both classic as well as several novel omics fields that are involved or should be used in modern BC investigations, which may be integrated as a holistic term, onco-breastomics. Rapid and recent advances in molecular profiling strategies and analytical techniques based on high-throughput sequencing and mass spectrometry (MS) development have generated large-scale multi-omics datasets, mainly emerging from the three "big omics", based on the central dogma of molecular biology: genomics, transcriptomics, and proteomics. Metabolomics-based approaches also reflect the dynamic response of BC cells to genetic modifications. Interactomics promotes a holistic view in BC research by constructing and characterizing protein-protein interaction (PPI) networks that provide a novel hypothesis for the pathophysiological processes involved in BC progression and subtyping. The emergence of new omics- and epiomics-based multidimensional approaches provide opportunities to gain insights into BC heterogeneity and its underlying mechanisms. The three main epiomics fields (epigenomics, epitranscriptomics, and epiproteomics) are focused on the epigenetic DNA changes, RNAs modifications, and posttranslational modifications (PTMs) affecting protein functions for an in-depth understanding of cancer cell proliferation, migration, and invasion. Novel omics fields, such as epichaperomics or epimetabolomics, could investigate the modifications in the interactome induced by stressors and provide PPI changes, as well as in metabolites, as drivers of BC-causing phenotypes. Over the last years, several proteomics-derived omics, such as matrisomics, exosomics, secretomics, kinomics, phosphoproteomics, or immunomics, provided valuable data for a deep understanding of dysregulated pathways in BC cells and their tumor microenvironment (TME) or tumor immune microenvironment (TIMW). Most of these omics datasets are still assessed individually using distinct approches and do not generate the desired and expected global-integrative knowledge with applications in clinical diagnostics. However, several hyphenated omics approaches, such as proteo-genomics, proteo-transcriptomics, and phosphoproteomics-exosomics are useful for the identification of putative BC biomarkers and therapeutic targets. To develop non-invasive diagnostic tests and to discover new biomarkers for BC, classic and novel omics-based strategies allow for significant advances in blood/plasma-based omics. Salivaomics, urinomics, and milkomics appear as integrative omics that may develop a high potential for early and non-invasive diagnoses in BC. Thus, the analysis of the tumor circulome is considered a novel frontier in liquid biopsy. Omics-based investigations have applications in BC modeling, as well as accurate BC classification and subtype characterization. The future in omics-based investigations of BC may be also focused on multi-omics single-cell analyses.

Network Biology-Inspired Machine Learning Features Predict Cancer Gene Targets and Reveal Target Coordinating Mechanisms

Anticipating and understanding cancers' need for specific gene activities is key for novel therapeutic development. Here we utilized DepMap, a cancer gene dependency screen, to demonstrate that machine learning combined with network biology can produce robust algorithms that both predict what genes a cancer is dependent on and what network features coordinate such gene dependencies. Using network topology and biological annotations, we constructed four groups of novel engineered machine learning features that produced high accuracies when predicting binary gene dependencies. We found that in all examined cancer types, F1 scores were greater than 0.90, and model accuracy remained robust under multiple hyperparameter tests. We then deconstructed these models to identify tumor type-specific coordinators of gene dependency and identified that in certain cancers, such as thyroid and kidney, tumors' dependencies are highly predicted by gene connectivity. In contrast, other histologies relied on pathway-based features such as lung, where gene dependencies were highly predictive by associations with cell death pathway genes. In sum, we show that biologically informed network features can be a valuable and robust addition to predictive pharmacology models while simultaneously providing mechanistic insights.

Identification of biomarkers predictive of metastasis development in early-stage colorectal cancer using network-based regularization

Colorectal cancer (CRC) is the third most common cancer and the second most deathly worldwide. It is a very heterogeneous disease that can develop via distinct pathways where metastasis is the primary cause of death. Therefore, it is crucial to understand the molecular mechanisms underlying metastasis. RNA-sequencing is an essential tool used for studying the transcriptional landscape. However, the high-dimensionality of gene expression data makes selecting novel metastatic biomarkers problematic. To distinguish early-stage CRC patients at risk of developing metastasis from those that are not, three types of binary classification approaches were used: (1) classification methods (decision trees, linear and radial kernel support vector machines, logistic regression, and random forest) using differentially expressed genes (DEGs) as input features; (2) regularized logistic regression based on the Elastic Net penalty and the proposed iTwiner-a network-based regularizer accounting for gene correlation information; and (3) classification methods based on the genes pre-selected using regularized logistic regression. Classifiers using the DEGs as features showed similar results, with random forest showing the highest accuracy. Using regularized logistic regression on the full dataset yielded no improvement in the methods' accuracy. Further classification using the pre-selected genes found by different penalty factors, instead of the DEGs, significantly improved the accuracy of the binary classifiers. Moreover, the use of network-based correlation information (iTwiner) for gene selection produced the best classification results and the identification of more stable and robust gene sets. Some are known to be tumor suppressor genes (OPCML-IT2), to be related to resistance to cancer therapies (RAC1P3), or to be involved in several cancer processes such as genome stability (XRCC6P2), tumor growth and metastasis (MIR602) and regulation of gene transcription (NME2P2). We show that the classification of CRC patients based on pre-selected features by regularized logistic regression is a valuable alternative to using DEGs, significantly increasing the models' predictive performance. Moreover, the use of correlation-based penalization for biomarker selection stands as a promising strategy for predicting patients' groups based on RNA-seq data.

Construction and analysis of protein-protein interaction networks based on nuclear proteomics data of the desiccation-tolerant Xerophyta schlechteri leaves subjected to dehydration stress

In order to understand the mechanism of desiccation tolerance in Xerophyta schlechteri, we carried out an in silico study to identify hub proteins and functional modules in the nuclear proteome of the leaves. Protein-protein interaction networks were constructed and analyzed from proteome data obtained from Abdalla and Rafudeen. We constructed networks in Cytoscape using the GeneMania software and analyzed them using a Network Analyzer. Functional enrichment analysis of key proteins in the respective networks was done using GeneMania network enrichment analysis, and GO (Gene Ontology) terms were summarized using REViGO. Also, community analysis of differentially expressed proteins was conducted using the Cytoscape Apps, GeneMania and ClusterMaker. Functional modules associated with the communities were identified using an online tool, ShinyGO. We identified HSP 70-2 as the super-hub protein among the up-regulated proteins. On the other hand, 40S ribosomal protein S2-3 (a protein added by GeneMANIA) was identified as a super-hub protein associated with the down-regulated proteins. For up-regulated proteins, the enriched biological process terms were those associated with chromatin organization and negative regulation of transcription. In the down-regulated protein-set, terms associated with protein synthesis were significantly enriched. Community analysis identified three functional modules that can be categorized as chromatin organization, anti-oxidant activity and metabolic processes.

Identification of Drug-Disease Associations Using a Random Walk with Restart Method and Supervised Learning

Drug-disease correlations play an important role in revealing the mechanism of disease, finding new indications of available drugs, or drug repositioning. A variety of computational approaches were proposed to find drug-disease correlations and achieve good performances. However, these methods used a variety of network information, but integrated networks were rarely used. In addition, the role of known drug-disease association data has not been fully played. In this work, we designed a combination algorithm of random walk and supervised learning to find the drug-disease correlations. We used an integrated network to update the model and selected a gene set as the start of random walk based on the known drug-disease correlations data. The experimental results show that the proposed method can effectively find the correlation between drugs and diseases, and the prediction accuracy is 82.7%. We found that there are 8 pairs of drug-disease relationships that have not yet been reported, and 5 of them have pharmacodynamic effects on Parkinson's disease. We also found that a key linkage between Parkinson's disease and phenylhexol, a drug for the treatment of Parkinson's disease α-synuclein and tau protein, provides a useful exploration for the effectiveness of the treatment of Parkinson's disease.

Risk stratification and pathway analysis based on graph neural network and interpretable algorithm

Background

Pathway-based analysis of transcriptomic data has shown greater stability and better performance than traditional gene-based analysis. Until now, some pathway-based deep learning models have been developed for bioinformatic analysis, but these models have not fully considered the topological features of pathways, which limits the performance of the final prediction result.

Results

To address this issue, we propose a novel model, called PathGNN, which constructs a Graph Neural Networks (GNNs) model that can capture topological features of pathways. As a case, PathGNN was applied to predict long-term survival of four types of cancer and achieved promising predictive performance when compared to other common methods. Furthermore, the adoption of an interpretation algorithm enabled the identification of plausible pathways associated with survival.

Conclusion

PathGNN demonstrates that GNN can be effectively applied to build a pathway-based model, resulting in promising predictive power.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04950-1.

Multi-Modal Imaging Genetics Data Fusion via a Hypergraph-Based Manifold Regularization: Application to Schizophrenia Study

Recent studies show that multi-modal data fusion techniques combine information from diverse sources for comprehensive diagnosis and prognosis of complex brain disorder, often resulting in improved accuracy compared to single-modality approaches. However, many existing data fusion methods extract features from homogeneous networs, ignoring heterogeneous structural information among multiple modalities. To this end, we propose a Hypergraph-based Multi-modal data Fusion algorithm, namely HMF. Specifically, we first generate a hypergraph similarity matrix to represent the high-order relationships among subjects, and then enforce the regularization term based upon both the inter- and intra-modality relationships of the subjects. Finally, we apply HMF to integrate imaging and genetics datasets. Validation of the proposed method is performed on both synthetic data and real samples from schizophrenia study. Results show that our algorithm outperforms several competing methods, and reveals significant interactions among risk genes, environmental factors and abnormal brain regions.

Deep learning-based transcription factor activity for stratification of breast cancer patients

Transcription factors directly bind to DNA and regulate the expression of the gene, causing epigenetic modification of the DNA. They often mediate epigenetic parameters of transcriptional and posttranscriptional mechanisms, and their expression activities can be used to characterize genomic aberrations in cancer cell. In this study, the activity profile of transcription factors inferred by VIPER algorithm. The autoencoder model was applied for compressing the transcription factor activity profile for obtaining more useful transformed features for stratifying patients into two different breast cancer subtypes. The deep learning-based subtypes exhibited superior prognostic value and yielded better risk-stratification than the transcription factor activity-based method. Importantly, according to transformed features, a deep neural network was constructed to predict the subtypes, and achieved the accuracy of 94.98% and area under the ROC curve of 0.9663, respectively. The proposed subtypes were found to be significantly associated with immune infiltration, tumor immunogenicity and so on. Furthermore, the ceRNA network was constructed for the breast cancer subtypes. Besides, 11 master regulators were found to be associated with patients in cluster 1. Given the robustness performance of our deep learning model over multiple breast cancer cohorts, we expected this model may be useful in the area of prognosis prediction and lead some possibility for personalized medicine in breast cancer patients.

IKBKE phosphorylates and stabilizes Snail to promote breast cancer invasion and metastasis

IKBKE, a non-canonical inflammatory kinase, is frequently amplified or activated, and plays predominantly oncogenic roles in human cancers, especially in breast cancer. However, the potential function and underlying mechanism of IKBKE contributing to breast cancer metastasis remain largely elusive. Here, we report that depletion of Ikbke markedly decreases polyoma virus middle T antigen (PyVMT)-induced mouse mammary tumorigenesis and subsequent lung metastasis. Biologically, ectopic expression of IKBKE accelerates, whereas depletion of IKBKE attenuates breast cancer invasiveness and migration in vitro and tumor metastasis in vivo. Mechanistically, IKBKE tightly controls the stability of transcriptional factor Snail in different layers, in particular by directly phosphorylating Snail, which markedly blocks the E3 ligase β-TRCP1-mediated Snail degradation, resulting in breast cancer epithelial-mesenchymal transition (EMT) and metastasis. These findings together reveal a novel oncogenic function of IKBKE in promoting breast cancer metastasis by governing Snail abundance, and highlight the potential of targeting IKBKE for metastatic breast cancer therapies.

Prospective Analysis of Proteins Carried in Extracellular Vesicles with Clinical Outcome in Hepatocellular Carcinoma

Background: Extracellular vehicles (EVs) contain different proteins that relay information between tumor cells, thus promoting tumorigenesis. Therefore, EVs can serve as an ideal marker for tumor pathogenesis and clinical application. Objective: Here, we characterised EV-specific proteins in hepatocellular carcinoma (HCC) samples and established their potential protein-protein interaction (PPI) networks. Materials and Methods: We used multi-dimensional bioinformatics methods to mine a network module to use as a prognostic signature and validated the model's prediction using additional datasets. The relationship between the prognostic model and tumor immune cells or the tumor microenvironment status was also examined. Results: 1134 proteins from 316 HCC samples were mapped to the exoRBase database. HCC-specific EVs specifically expressed a total of 437 proteins. The PPI network revealed 321 proteins and 938 interaction pathways, which were mined to identify a three network module (3NM) with significant prognostic prediction ability. Validation of the 3NM in two more datasets demonstrated that the model outperformed the other signatures in prognostic prediction ability. Functional analysis revealed that the network proteins were involved in various tumor-related pathways. Additionally, these findings demonstrated a favorable association between the 3NM signature and macrophages, dendritic, and mast cells. Besides, the 3NM revealed the tumor microenvironment status, including hypoxia and inflammation. Conclusion: These findings demonstrate that the 3NM signature reliably predicts HCC pathogenesis. Therefore, the model may be used as an effective prognostic biomarker in managing patients with HCC.

Emerging landscape of molecular interaction networks: Opportunities, challenges and prospects

Network biology finds application in interpreting molecular interaction networks and providing insightful inferences using graph theoretical analysis of biological systems. The integration of computational bio-modelling approaches with different hybrid network-based techniques provides additional information about the behaviour of complex systems. With increasing advances in high-throughput technologies in biological research, attempts have been made to incorporate this information into network structures, which has led to a continuous update of network biology approaches over time. The newly minted centrality measures accommodate the details of omics data and regulatory network structure information. The unification of graph network properties with classical mathematical and computational modelling approaches and technologically advanced approaches like machine-learning- and artificial intelligence-based algorithms leverages the potential application of these techniques. These computational advances prove beneficial and serve various applications such as essential gene prediction, identification of drug–disease interaction and gene prioritization. Hence, in this review, we have provided a comprehensive overview of the emerging landscape of molecular interaction networks using graph theoretical approaches. With the aim to provide information on the wide range of applications of network biology approaches in understanding the interaction and regulation of genes, proteins, enzymes and metabolites at different molecular levels, we have reviewed the methods that utilize network topological properties, emerging hybrid network-based approaches and applications that integrate machine learning techniques to analyse molecular interaction networks. Further, we have discussed the applications of these approaches in biomedical research with a note on future prospects.

Multi-level attention graph neural network based on co-expression gene modules for disease diagnosis and prognosis

MOTIVATION

Advanced deep learning techniques have been widely applied in disease diagnosis and prognosis with clinical omics, especially gene expression data. In the regulation of biological processes and disease progression, genes often work interactively rather than individually. Therefore, investigating gene association information and co-functional gene modules can facilitate disease state prediction.

RESULTS

To explore the gene modules and inter-gene relational information contained in the omics data, we propose a novel multi-level attention graph neural network (MLA-GNN) for disease diagnosis and prognosis. Specifically, we format omics data into co-expression graphs via weighted correlation network analysis, and then construct multi-level graph features, finally fuse them through a well-designed multi-level graph feature fully fusion module to conduct predictions. For model interpretation, a novel full-gradient graph saliency mechanism is developed to identify the disease-relevant genes. MLA-GNN achieves state-of-the-art performance on transcriptomic data from TCGA-LGG/TCGA-GBM and proteomic data from coronavirus disease 2019 (COVID-19)/non-COVID-19 patient sera. More importantly, the relevant genes selected by our model are interpretable and are consistent with the clinical understanding.

AVAILABILITYAND IMPLEMENTATION

The codes are available at https://github.com/TencentAILabHealthcare/MLA-GNN.

Molecular characterization of chronic liver disease dynamics: from liver fibrosis to acute-on-chronic liver failure

Background & Aims

The molecular mechanisms driving the progression from early-chronic liver disease (CLD) to cirrhosis and, finally, acute-on-chronic liver failure (ACLF) are largely unknown. Our aim was to develop a protein network-based approach to investigate molecular pathways driving progression from early-CLD to ACLF.

Methods

Transcriptome analysis was performed on liver biopsies from patients at different liver disease stages, including fibrosis, compensated cirrhosis, decompensated cirrhosis and ACLF, and control healthy livers. We created 9 liver-specific disease-related protein-protein interaction networks capturing key pathophysiological processes potentially related to CLD. We used these networks as a framework and performed gene set-enrichment analysis (GSEA) to identify dynamic gene profiles of disease progression.

Results

Principal component analyses revealed that samples clustered according to the disease stage. GSEA of the defined processes showed an upregulation of inflammation, fibrosis and apoptosis networks throughout disease progression. Interestingly, we did not find significant gene expression differences between compensated and decompensated cirrhosis, while ACLF showed acute expression changes in all the defined liver disease-related networks. The analyses of disease progression patterns identified ascending and descending expression profiles associated with ACLF onset. Functional analyses showed that ascending profiles were associated with inflammation, fibrosis, apoptosis, senescence and carcinogenesis networks, while descending profiles were mainly related to oxidative stress and genetic factors. We confirmed by qPCR the upregulation of genes of the ascending profile and validated our findings in an independent patient cohort.

Conclusion

ACLF is characterized by a specific hepatic gene expression pattern related to inflammation, fibrosis, apoptosis, senescence and carcinogenesis. Moreover, the observed profile is significantly different from that of compensated and decompensated cirrhosis, supporting the hypothesis that ACLF should be considered a distinct entity.

Lay summary

By using transjugular biopsies obtained from patients at different stages of chronic liver disease, we unveil the molecular pathogenic mechanisms implicated in the progression of chronic liver disease to cirrhosis and acute-on-chronic liver failure. The most relevant finding in this study is that patients with acute-on-chronic liver failure present a specific hepatic gene expression pattern distinct from that of patients at earlier disease stages. This gene expression pattern is mostly related to inflammation, fibrosis, angiogenesis, and senescence and apoptosis pathways in the liver.

•

We unveiled the molecular pathogenic mechanisms implicated in the progression of chronic liver disease to cirrhosis and ACLF.

•

ACLF presents a specific hepatic gene expression pattern distinct from that of patients at earlier disease stages.

•

Gene expression pattern of ACLF is mostly related to inflammation, fibrosis, angiogenesis, senescence and apoptosis pathways in the liver.

Gene and Protein Interaction Network Analysis in Epithelial-Mesenchymal Transition of Hertwig's Epithelial Root Sheath reveals periodontal regenerative drug targets - An in silico study

Background and aim

Hertwig’s Εpithelial Root Sheath (HΕRS) has a major function in the developing tooth roots. Earlier research revealed that it undergoes epithelial–mesenchymal transition, a vital process for the morphogenesis and complete development of the tooth and its surrounding periodontium. Few studies have demonstrated the role of HERS in cementogenesis through ΕMΤ. The background of this in-silico system biology approach is to find a hub protein and gene involved in the EMT of HERS that may uncover novel insights in periodontal regenerative drug targets.

Materials and methods

The protein and gene list involved in epithelial–mesenchymal transition were obtained from literature sources. The protein interaction was constructed using STRING software and the protein interaction network was analyzed. Molecular docking simulation checks the binding energy and stability of protein-ligand complex.

Results

Results revealed the hub gene to be DYRK1A(Hepcidin), and the ligand was identified as isoetharine. SΤRIΝG results showed a confidence cutoff of 0.9 in sensitivity analysis with a condensed protein interaction network. Overall, 98 nodes from 163 nodes of expected edges were found with an average node degree of 11.9. Docking results show binding energy of −4.70, and simulation results show an RMSD value of 5.6 Å at 50 ns.

Conclusion

Isoetharine could be a potential drug for periodontal regeneration.

The DOMINO web-server for active module identification analysis

MOTIVATION

Active module identification (AMI) is an essential step in many omics analyses. Such algorithms receive a gene network and a gene activity profile as input and report subnetworks that show significant over-representation of accrued activity signal ('active modules'). Such modules can point out key molecular processes in the analyzed biological conditions.

RESULTS

We recently introduced a novel AMI algorithm called DOMINO and demonstrated that it detects active modules that capture biological signals with markedly improved rate of empirical validation. Here, we provide an online server that executes DOMINO, making it more accessible and user-friendly. To help the interpretation of solutions, the server provides GO enrichment analysis, module visualizations and accessible output formats for customized downstream analysis. It also enables running DOMINO with various gene identifiers of different organisms.

AVAILABILITY AND IMPLEMENTATION

The server is available at http://domino.cs.tau.ac.il. Its codebase is available at https://github.com/Shamir-Lab.

Deep graph representations embed network information for robust disease marker identification

MOTIVATION

Accurate disease diagnosis and prognosis based on omics data rely on the effective identification of robust prognostic and diagnostic markers that reflect the states of the biological processes underlying the disease pathogenesis and progression. In this article, we present GCNCC, a Graph Convolutional Network-based approach for Clustering and Classification, that can identify highly effective and robust network-based disease markers. Based on a geometric deep learning framework, GCNCC learns deep network representations by integrating gene expression data with protein interaction data to identify highly reproducible markers with consistently accurate prediction performance across independent datasets possibly from different platforms. GCNCC identifies these markers by clustering the nodes in the protein interaction network based on latent similarity measures learned by the deep architecture of a graph convolutional network, followed by a supervised feature selection procedure that extracts clusters that are highly predictive of the disease state.

RESULTS

By benchmarking GCNCC based on independent datasets from different diseases (psychiatric disorder and cancer) and different platforms (microarray and RNA-seq), we show that GCNCC outperforms other state-of-the-art methods in terms of accuracy and reproducibility.

AVAILABILITY AND IMPLEMENTATION

https://github.com/omarmaddouri/GCNCC.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Empowering differential networks using Bayesian analysis

Differential networks (DN) are important tools for modeling the changes in conditional dependencies between multiple samples. A Bayesian approach for estimating DNs, from the classical viewpoint, is introduced with a computationally efficient threshold selection for graphical model determination. The algorithm separately estimates the precision matrices of the DN using the Bayesian adaptive graphical lasso procedure. Synthetic experiments illustrate that the Bayesian DN performs exceptionally well in numerical accuracy and graphical structure determination in comparison to state of the art methods. The proposed method is applied to South African COVID-19 data to investigate the change in DN structure between various phases of the pandemic.

An Algorithm to Mine Therapeutic Motifs for Cancer from Networks of Genetic Interactions

Study of pairwise genetic interactions, such as mutually exclusive mutations, has led to understanding of underlying mechanisms in cancer. Investigation of various combinatorial motifs within networks of such interactions can lead to deeper insights into its mutational landscape and inform therapy development. One such motif called the Between-Pathway Model (BPM) represents redundant or compensatory pathways that can be therapeutically exploited. Finding such BPM motifs is challenging since most formulations require solving variants of the NP-complete maximum weight bipartite subgraph problem. In this paper we design an algorithm based on Integer Linear Programming (ILP) to solve this problem. In our experiments, our approach outperforms the best previous method to mine BPM motifs. Further, our ILP-based approach allows us to easily model additional application-specific constraints. We illustrate this advantage through a new application of BPM motifs that can potentially aid in finding combination therapies to combat cancer.

Identification of condition-specific biomarker systems in uterine cancer

Uterine cancer is the fourth most common cancer among women, projected to affect 66,000 US women in 2021. Uterine cancer often arises in the inner lining of the uterus, known as the endometrium, but can present as several different types of cancer, including endometrioid cancer, serous adenocarcinoma, and uterine carcinosarcoma. Previous studies have analyzed the genetic changes between normal and cancerous uterine tissue to identify specific genes of interest, including TP53 and PTEN. Here we used Gaussian Mixture Models to build condition-specific gene coexpression networks for endometrial cancer, uterine carcinosarcoma, and normal uterine tissue. We then incorporated uterine regulatory edges and investigated potential coregulation relationships. These networks were further validated using differential expression analysis, functional enrichment, and a statistical analysis comparing the expression of transcription factors and their target genes across cancerous and normal uterine samples. These networks allow for a more comprehensive look into the biological networks and pathways affected in uterine cancer compared with previous singular gene analyses. We hope this study can be incorporated into existing knowledge surrounding the genetics of uterine cancer and soon become clinical biomarkers as a tool for better prognosis and treatment.

Improving Analysis and Annotation of Microarray Data with Protein Interactions

Gene expression microarrays are one of the most widely used high-throughput technologies in molecular biology, with applications such as identification of disease mechanisms and development of diagnostic and prognostic gene signatures. However, the success of these tasks is often limited because microarray analysis does not account for the complex relationships among genes, their products, and overall signaling and regulatory cascades. Incorporating protein-protein interaction data into microarray analysis can help address these challenges. This chapter reviews how protein-protein interactions can help with microarray analysis, leading to benefits such as better explanations of disease mechanisms, more complete gene annotations, improved prioritization of genes for future experiments, and gene signatures that generalize better to new data.

Bimolecular Fluorescence Complementation to Visualize Protein-Protein Interactions in Cells

Examining protein-protein interactions provides critical insight into numerous human diseases and infections. Here we describe a protocol for bimolecular fluorescence complementation, which can be used to directly visualize and characterize intracellular protein-protein interactions and ascertain their localization using fluorescence microscopy.

Relating Translation Efficiency to Protein Networks Provides Evolutionary Insights in Shewanella and Its Implications for Extracellular Electron Transfer

Shewanella species are well-known for their extracellular electron transfer (EET) capacity, by which these microorganisms can transfer the electrons from intracellular environment to extracellular space for the reduction of the extracellular insoluble electron acceptors. Using a time-stamped data for the paired protein-mRNA, we investigate the impact of differential translation on the EET process of Shewanella oneidensis MR-1. Firstly, differentially translated proteins when O₂ levels are switched from high-O₂ to low-O₂ are identified by using a soft clustering method, 629 up-regulated translated proteins and 767 down-regulated translated proteins are considered to reflect the changes from inactivated to activated EET process. Then, we showed that the degrees of connectivity of differentially translated proteins were significantly larger than those of non-differentially translated proteins, and thereby these differentially translated proteins will be more important in the protein networks. After that, we networked these differentially translated proteins to construct the differentially translated sub-networks, and discussed the most important proteins that are involved in the EET process with the help of centralization analysis of these differentially translated networks. Furthermore, we also studied the differentially translated operonic genes. Taking together, this work searches the key proteins that potentially activated the EET process from a translational efficiency viewpoint.

Temporal and sequential order of nonoverlapping gene networks unraveled in mated female Drosophila

Mating triggers successive waves of temporal transcriptomic changes within independent gene networks in female Drosophila, suggesting a recruitment of interconnected modules that vanish in late life.

In this study, we reanalyzed available datasets of gene expression changes in female Drosophila head induced by mating. Mated females present metabolic phenotypic changes and display behavioral characteristics that are not observed in virgin females, such as repulsion to male sexual aggressiveness, fidelity to food spots selected for oviposition, and restriction to the colonization of new niches. We characterize gene networks that play a role in female brain plasticity after mating using AMINE, a novel algorithm to find dysregulated modules of interacting genes. The uncovered networks of altered genes revealed a strong specificity for each successive period of life span after mating in the female head, with little conservation between them. This finding highlights a temporal order of recruitment of waves of interconnected genes which are apparently transiently modified: the first wave disappears before the emergence of the second wave in a reversible manner and ends with few consolidated gene expression changes at day 20. This analysis might document an extended field of a programmatic control of female phenotypic traits by male seminal fluid.

An Entropy-based Directed Random Walk for Pathway Activity Inference Using Topological Importance and Gene Interactions.. [DOI: 10.1101/2021.11.05.467449] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

The integration of microarray technologies and machine learning methods has become popular in predicting pathological condition of diseases and discovering risk genes. The traditional microarray analysis considers pathways as simple gene sets, treating all genes in the pathway identically while ignoring the pathway network’s structure information. This study, however, proposed an entropy-based directed random walk (e-DRW) method to infer pathway activity. This study aims (1) To enhance the gene-weighting method in Directed Random Walk (DRW) by incorporating t-test statistic scores and correlation coefficient values, (2) To implement entropy as a parameter variable for random walking in a biological network, and (3) To apply Entropy Weight Method (EWM) in DRW pathway activity inference. To test the objectives, the gene expression dataset was used as input datasets while the pathway dataset was used as reference datasets to build a directed graph. An equation was proposed to assess the connectivity of nodes in the directed graph via probability values calculated from the Shannon entropy formula. A direct proof of calculation based on the proposed mathematical formula was presented using e-DRW with gene expression data. Based on the results, there was an improvement in terms of sensitivity of prediction and accuracy of cancer classification between e-DRW and conventional DRW. The within-dataset experiments indicated that our novel method demonstrated robust and superior performance in terms of accuracy and number of predicted risk-active pathways compared to the other DRW methods. In conclusion, the results revealed that e-DRW not only improved prediction performance, but also effectively extracted topologically important pathways and genes that are specifically related to the corresponding cancer types.

Active Module Identification From Multilayer Weighted Gene Co-Expression Networks: A Continuous Optimization Approach

Searching for active modules, i.e., regions showing striking changes in molecular activity in biological networks is important to reveal regulatory and signaling mechanisms of biological systems. Most existing active modules identification methods are based on protein-protein interaction networks or metabolic networks, which require comprehensive and accurate prior knowledge. On the other hand, weighted gene co-expression networks (WGCNs) are purely constructed from gene expression profiles. However, existing WGCN analysis methods are designed for identifying functional modules but not capable of identifying active modules. There is an urgent need to develop an active module identification algorithm for WGCNs to discover regulatory and signaling mechanism associating with a given cellular response. To address this urgent need, we propose a novel algorithm called active modules on the multi-layer weighted (co-expression gene) network, based on a continuous optimization approach (AMOUNTAIN). The algorithm is capable of identifying active modules not only from single-layer WGCNs but also from multilayer WGCNs such as cross-species and dynamic WGCNs. We first validate AMOUNTAIN on a synthetic benchmark dataset. We then apply AMOUNTAIN to WGCNs constructed from Th17 differentiation gene expression datasets of human and mouse, which include a single layer, a cross-species two-layer and a multilayer dynamic WGCNs. The identified active modules from WGCNs are enriched by known protein-protein interactions, and more importantly, they reveal some interesting and important regulatory and signaling mechanisms of Th17 cell differentiation.

Analysis of multiple gene co-expression networks to discover interactions favoring CFTR biogenesis and ΔF508-CFTR rescue

BACKGROUND

We previously reported that expression of a miR-138 mimic or knockdown of SIN3A in primary cultures of cystic fibrosis (CF) airway epithelia increased ΔF508-CFTR mRNA and protein levels, and partially restored CFTR-dependent chloride transport. Global mRNA transcript profiling in ΔF508-CFBE cells treated with miR-138 mimic or SIN3A siRNA identified two genes, SYVN1 and NEDD8, whose inhibition significantly increased ΔF508-CFTR trafficking, maturation, and function. Little is known regarding the dynamic changes in the CFTR gene network during such rescue events. We hypothesized that analysis of condition-specific gene networks from transcriptomic data characterizing ΔF508-CFTR rescue could help identify dynamic gene modules associated with CFTR biogenesis.

METHODS

We applied a computational method, termed M-module, to analyze multiple gene networks, each of which exhibited differential activity compared to a baseline condition. In doing so, we identified both unique and shared gene pathways across multiple differential networks. To construct differential networks, gene expression data from CFBE cells were divided into three groups: (1) siRNA inhibition of NEDD8 and SYVN1; (2) miR-138 mimic and SIN3A siRNA; and (3) temperature (27 °C for 24 h, 40 °C for 24 h, and 27 °C for 24 h followed by 40 °C for 24 h).

RESULTS

Interrogation of individual networks (e.g., NEDD8/SYVN1 network), combinations of two networks (e.g., NEDD8/SYVN1 + temperature networks), and all three networks yielded sets of 1-modules, 2-modules, and 3-modules, respectively. Gene ontology analysis revealed significant enrichment of dynamic modules in pathways including translation, protein metabolic/catabolic processes, protein complex assembly, and endocytosis. Candidate CFTR effectors identified in the analysis included CHURC1, GZF1, and RPL15, and siRNA-mediated knockdown of these genes partially restored CFTR-dependent transepithelial chloride current to ΔF508-CFBE cells.

CONCLUSIONS

The ability of the M-module to identify dynamic modules involved in ΔF508 rescue provides a novel approach for studying CFTR biogenesis and identifying candidate suppressors of ΔF508.

Regulation of Long Non-coding RNA KCNQ1OT1 Network in Colorectal Cancer Immunity

Over the past few decades, researchers have become aware of the importance of non-coding RNA, which makes up the vast majority of the transcriptome. Long non-coding RNAs (lncRNAs) in turn constitute the largest fraction of non-coding transcripts. Increasing evidence has been found for the crucial roles of lncRNAs in both tissue homeostasis and development, and for their functional contributions to and regulation of the development and progression of various human diseases such as cancers. However, so far, only few findings with regards to functional lncRNAs in cancers have been translated into clinical applications. Based on multiple factors such as binding affinity of miRNAs to their lncRNA sponges, we analyzed the competitive endogenous RNA (ceRNA) network for the colorectal cancer RNA-seq datasets from The Cancer Genome Atlas (TCGA). After performing the ceRNA network construction and survival analysis, the lncRNA KCNQ1OT1 was found to be significantly upregulated in colorectal cancer tissues and associated with the survival of patients. A KCNQ1OT1-related lncRNA-miRNA-mRNA ceRNA network was constructed. A gene set variation analysis (GSVA) indicated that the expression of the KCNQ1OT1 ceRNA network in colorectal cancer tissues and normal tissues were significantly different, not only in the TCGA-COAD dataset but also in three other GEO datasets used as validation. By predicting comprehensive immune cell subsets from gene expression data, in samples grouped by differential expression levels of the KCNQ1OT1 ceRNA network in a cohort of patients, we found that CD4⁺, CD8⁺, and cytotoxic T cells and 14 other immune cell subsets were at different levels in the high- and low-KCNQ1OT1 ceRNA network score groups. These results indicated that the KCNQ1OT1 ceRNA network could be involved in the regulation of the tumor microenvironment, which would provide the rationale to further exploit KCNQ1OT1 as a possible functional contributor to and therapeutic target for colorectal cancer.

Interpretation of cancer mutations using a multiscale map of protein systems

A major goal of cancer research is to understand how mutations distributed across diverse genes affect common cellular systems, including multiprotein complexes and assemblies. Two challenges—how to comprehensively map such systems and how to identify which are under mutational selection—have hindered this understanding. Accordingly, we created a comprehensive map of cancer protein systems integrating both new and published multi-omic interaction data at multiple scales of analysis. We then developed a unified statistical model that pinpoints 395 specific systems under mutational selection across 13 cancer types. This map, called NeST (Nested Systems in Tumors), incorporates canonical processes and notable discoveries, including a PIK3CA-actomyosin complex that inhibits phosphatidylinositol 3-kinase signaling and recurrent mutations in collagen complexes that promote tumor proliferation. These systems can be used as clinical biomarkers and implicate a total of 548 genes in cancer evolution and progression. This work shows how disparate tumor mutations converge on protein assemblies at different scales.

Prospects and challenges of cancer systems medicine: from genes to disease networks

It is becoming evident that holistic perspectives toward cancer are crucial in deciphering the overwhelming complexity of tumors. Single-layer analysis of genome-wide data has greatly contributed to our understanding of cellular systems and their perturbations. However, fundamental gaps in our knowledge persist and hamper the design of effective interventions. It is becoming more apparent than ever, that cancer should not only be viewed as a disease of the genome but as a disease of the cellular system. Integrative multilayer approaches are emerging as vigorous assets in our endeavors to achieve systemic views on cancer biology. Herein, we provide a comprehensive review of the approaches, methods and technologies that can serve to achieve systemic perspectives of cancer. We start with genome-wide single-layer approaches of omics analyses of cellular systems and move on to multilayer integrative approaches in which in-depth descriptions of proteogenomics and network-based data analysis are provided. Proteogenomics is a remarkable example of how the integration of multiple levels of information can reduce our blind spots and increase the accuracy and reliability of our interpretations and network-based data analysis is a major approach for data interpretation and a robust scaffold for data integration and modeling. Overall, this review aims to increase cross-field awareness of the approaches and challenges regarding the omics-based study of cancer and to facilitate the necessary shift toward holistic approaches.

A multi-objective genetic algorithm to find active modules in multiplex biological networks

The identification of subnetworks of interest—or active modules—by integrating biological networks with molecular profiles is a key resource to inform on the processes perturbed in different cellular conditions. We here propose MOGAMUN, a Multi-Objective Genetic Algorithm to identify active modules in MUltiplex biological Networks. MOGAMUN optimizes both the density of interactions and the scores of the nodes (e.g., their differential expression). We compare MOGAMUN with state-of-the-art methods, representative of different algorithms dedicated to the identification of active modules in single networks. MOGAMUN identifies dense and high-scoring modules that are also easier to interpret. In addition, to our knowledge, MOGAMUN is the first method able to use multiplex networks. Multiplex networks are composed of different layers of physical and functional relationships between genes and proteins. Each layer is associated to its own meaning, topology, and biases; the multiplex framework allows exploiting this diversity of biological networks. We applied MOGAMUN to identify cellular processes perturbed in Facio-Scapulo-Humeral muscular Dystrophy, by integrating RNA-seq expression data with a multiplex biological network. We identified different active modules of interest, thereby providing new angles for investigating the pathomechanisms of this disease.

Availability: MOGAMUN is available at https://github.com/elvanov/MOGAMUN and as a Bioconductor package at https://bioconductor.org/packages/release/bioc/html/MOGAMUN.html.

Contact:anais.baudot@univ-amu.fr

Integrating different sources of biological information is a powerful way to uncover the functioning of biological systems. In network biology, in particular, integrating interaction data with expression profiles helps contextualizing the networks and identifying subnetworks of interest, aka active modules. We here propose MOGAMUN, a multi-objective genetic algorithm that optimizes both the overall deregulation and the density to identify active modules, considering jointly multiple sources of biological interactions. We demonstrate the performance of MOGAMUN over state-of-the-art methods, and illustrate its usefulness in unveiling perturbed biological processes in Facio-Scapulo-Humeral muscular Dystrophy.

Identifying cancer patient subgroups by finding co-modules from the driver mutation profiles and downstream gene expression profiles

Identifying cancer subtypes shed new light on effective personalized cancer medicine, future therapeutic strategies and minimizing treatment-related costs. Recently, there are many clustering methods have been proposed in categorizing cancer patients. However, these methods still fail to fully use the prior known biological information in the model designing process to improve precision and efficiency. It is acknowledged that the driver gene always regulates its downstream genes in the net-work to perform a certain function. By analyzing the known clinic cancer subtype data, we found some special co-pathways between the driver genes and the downstream genes in the cancer patients of the same subgroup. Hence, we proposed a novel model named DDCMNMF(Driver and Downstream gene Co-Module Assisted Multiple Non-negative Matrix Factorization model) that first stratify cancer sub-types by identifying co-modules of driver genes and downstream genes. We applied our model on lung and breast cancer datasets and compared it with the other four state-of-the-art models. The final results show that our model could identify the cancer subtypes with high compactness and separateness and achieve a high degree of consistency with the known cancer subtypes. The survival time analysis further proves the significant clinical characteristic of identified cancer subgroups by our model.

Decoding competing endogenous RNA networks for cancer biomarker discovery

Crosstalk between competing endogenous RNAs (ceRNAs) is mediated by shared microRNAs (miRNAs) and plays important roles both in normal physiology and tumorigenesis; thus, it is attractive for systems-level decoding of gene regulation. As ceRNA networks link the function of miRNAs with that of transcripts sharing the same miRNA response elements (MREs), e.g. pseudogenes, competing mRNAs, long non-coding RNAs, and circular RNAs, the perturbation of crucial interactions in ceRNA networks may contribute to carcinogenesis by affecting the balance of cellular regulatory system. Therefore, discovering biomarkers that indicate cancer initiation, development, and/or therapeutic responses via reconstructing and analyzing ceRNA networks is of clinical significance. In this review, the regulatory function of ceRNAs in cancer and crucial determinants of ceRNA crosstalk are firstly discussed to gain a global understanding of ceRNA-mediated carcinogenesis. Then, computational and experimental approaches for ceRNA network reconstruction and ceRNA validation, respectively, are described from a systems biology perspective. We focus on strategies for biomarker identification based on analyzing ceRNA networks and highlight the translational applications of ceRNA biomarkers for cancer management. This article will shed light on the significance of miRNA-mediated ceRNA interactions and provide important clues for discovering ceRNA network-based biomarker in cancer biology, thereby accelerating the pace of precision medicine and healthcare for cancer patients.

Diverse transcriptional regulation and functional effects revealed by CRISPR/Cas9-directed epigenetic editing

DNA methylation is an epigenetic process that controls DNA accessibility and serves as a transcriptomic switch when deposited at regulatory regions. The adequate functioning of this process is indispensable for tissue homeostasis and cell fate determination. Conversely, altered DNA methylation patterns result in abnormal gene transcription profiles that contribute to tumor initiation and progression. However, whether the consequence of DNA methylation on gene expression and cell fate is uniform regardless of the cell type or state could so far not been tested due to the lack of technologies to target DNA methylation in-situ. Here, we have taken advantage of CRISPR/dCas9 technology adapted for epigenetic editing through site-specific targeting of DNA methylation to characterize the transcriptional changes of the candidate gene and the functional effects on cell fate in different tumor settings. As a proof-of-concept, we were able to induce de-novo site-specific methylation of the gene promoter of IGFBP2 up to 90% with long-term and bona-fide inheritance by daughter cells. Strikingly, this modification led to opposing expression profiles of the target gene in different cancer cell models and affected the expression of mesenchymal genes CDH1, VIM1, TGFB1 and apoptotic marker BCL2. Moreover, methylation-induced changes in expression profiles was also accompanied by a phenotypic switch in cell migration and cell morphology. We conclude that in different cell types the consequence of DNA methylation on gene expression and cell fate can be completely different.

Mechanism-Centric Approaches for Biomarker Detection and Precision Therapeutics in Cancer

Biomarker discovery is at the heart of personalized treatment planning and cancer precision therapeutics, encompassing disease classification and prognosis, prediction of treatment response, and therapeutic targeting. However, many biomarkers represent passenger rather than driver alterations, limiting their utilization as functional units for therapeutic targeting. We suggest that identification of driver biomarkers through mechanism-centric approaches, which take into account upstream and downstream regulatory mechanisms, is fundamental to the discovery of functionally meaningful markers. Here, we examine computational approaches that identify mechanism-centric biomarkers elucidated from gene co-expression networks, regulatory networks (e.g., transcriptional regulation), protein-protein interaction (PPI) networks, and molecular pathways. We discuss their objectives, advantages over gene-centric approaches, and known limitations. Future directions highlight the importance of input and model interpretability, method and data integration, and the role of recently introduced technological advantages, such as single-cell sequencing, which are central for effective biomarker discovery and time-cautious precision therapeutics.

A graph convolutional neural network for gene expression data analysis with multiple gene networks

Spectral graph convolutional neural networks (GCN) are proposed to incorporate important information contained in graphs such as gene networks. In a standard spectral GCN, there is only one gene network to describe the relationships among genes. However, for genomic applications, due to condition- or tissue-specific gene function and regulation, multiple gene networks may be available; it is unclear how to apply GCNs to disease classification with multiple networks. Besides, which gene networks may provide more effective prior information for a given learning task is unknown a priori and is not straightforward to discover in many cases. A deep multiple graph convolutional neural network is therefore developed here to meet the challenge. The new approach not only computes a feature of a gene as the weighted average of those of itself and its neighbors through spectral GCNs, but also extracts features from gene-specific expression (or other feature) profiles via a feed-forward neural networks (FNN). We also provide two measures, the importance of a given gene and the relative importance score of each gene network, for the genes' and gene networks' contributions, respectively, to the learning task. To evaluate the new method, we conduct real data analyses using several breast cancer and diffuse large B-cell lymphoma datasets and incorporating multiple gene networks obtained from "GIANT 2.0" Compared with the standard FNN, GCN, and random forest, the new method not only yields high classification accuracy but also prioritizes the most important genes confirmed to be highly associated with cancer, strongly suggesting the usefulness of the new method in incorporating multiple gene networks.

Differential network analysis by simultaneously considering changes in gene interactions and gene expression

MOTIVATION

Differential network analysis is an important tool to investigate the rewiring of gene interactions under different conditions. Several computational methods have been developed to estimate differential networks from gene expression data, but most of them do not consider that gene network rewiring may be driven by the differential expression of individual genes. New differential network analysis methods that simultaneously take account of the changes in gene interactions and changes in expression levels are needed.

RESULTS

In this paper, we propose a differential network analysis method that considers the differential expression of individual genes when identifying differential edges. First, two hypothesis test statistics are used to quantify changes in partial correlations between gene pairs and changes in expression levels for individual genes. Then, an optimization framework is proposed to combine the two test statistics so that the resulting differential network has a hierarchical property, where a differential edge can be considered only if at least one of the two involved genes is differentially expressed. Simulation results indicate that our method outperforms current state-of-the-art methods. We apply our method to identify the differential networks between the luminal A and basal-like subtypes of breast cancer and those between acute myeloid leukemia and normal samples. Hub nodes in the differential networks estimated by our method, including both differentially and non-differentially expressed genes, have important biological functions.

AVAILABILITY

The source code is available at https://github.com/Zhangxf-ccnu/chNet.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Integrative Analysis of Next-Generation Sequencing for Next-Generation Cancer Research toward Artificial Intelligence

The rapid improvement of next-generation sequencing (NGS) technologies and their application in large-scale cohorts in cancer research led to common challenges of big data. It opened a new research area incorporating systems biology and machine learning. As large-scale NGS data accumulated, sophisticated data analysis methods became indispensable. In addition, NGS data have been integrated with systems biology to build better predictive models to determine the characteristics of tumors and tumor subtypes. Therefore, various machine learning algorithms were introduced to identify underlying biological mechanisms. In this work, we review novel technologies developed for NGS data analysis, and we describe how these computational methodologies integrate systems biology and omics data. Subsequently, we discuss how deep neural networks outperform other approaches, the potential of graph neural networks (GNN) in systems biology, and the limitations in NGS biomedical research. To reflect on the various challenges and corresponding computational solutions, we will discuss the following three topics: (i) molecular characteristics, (ii) tumor heterogeneity, and (iii) drug discovery. We conclude that machine learning and network-based approaches can add valuable insights and build highly accurate models. However, a well-informed choice of learning algorithm and biological network information is crucial for the success of each specific research question.

Pan-Cancer Metastasis Prediction Based on Graph Deep Learning Method

Tumor metastasis is the major cause of mortality from cancer. From this perspective, detecting cancer gene expression and transcriptome changes is important for exploring tumor metastasis molecular mechanisms and cellular events. Precisely estimating a patient’s cancer state and prognosis is the key challenge to develop a patient’s therapeutic schedule. In the recent years, a variety of machine learning techniques widely contributed to analyzing real-world gene expression data and predicting tumor outcomes. In this area, data mining and machine learning techniques have widely contributed to gene expression data analysis by supplying computational models to support decision-making on real-world data. Nevertheless, limitation of real-world data extremely restricted model predictive performance, and the complexity of data makes it difficult to extract vital features. Besides these, the efficacy of standard machine learning pipelines is far from being satisfactory despite the fact that diverse feature selection strategy had been applied. To address these problems, we developed directed relation-graph convolutional network to provide an advanced feature extraction strategy. We first constructed gene regulation network and extracted gene expression features based on relational graph convolutional network method. The high-dimensional features of each sample were regarded as an image pixel, and convolutional neural network was implemented to predict the risk of metastasis for each patient. Ten cross-validations on 1,779 cases from The Cancer Genome Atlas show that our model’s performance (area under the curve, AUC = 0.837; area under precision recall curve, AUPRC = 0.717) outstands that of an existing network-based method (AUC = 0.707, AUPRC = 0.555).

PRER: A patient representation with pairwise relative expression of proteins on biological networks

Changes in protein and gene expression levels are often used as features in predictive modeling such as survival prediction. A common strategy to aggregate information contained in individual proteins is to integrate the expression levels with the biological networks. In this work, we propose a novel patient representation where we integrate proteins’ expression levels with the protein-protein interaction (PPI) networks: Patient representation with PRER (Pairwise Relative Expressions with Random walks). PRER captures the dysregulation patterns of proteins based on the neighborhood of a protein in the PPI network. Specifically, PRER computes a feature vector for a patient by comparing the source protein’s expression level with other proteins’ levels that are within its neighborhood. The neighborhood of the source protein is derived by biased random-walk strategy on the network. We test PRER’s performance in survival prediction task in 10 different cancers using random forest survival models. PRER yields a statistically significant predictive performance in 9 out of 10 cancers when compared to the same model trained with features based on individual protein expressions. Furthermore, we identified the pairs of proteins that their interactions are predictive of patient survival but their individual expression levels are not. The set of identified relations provides a valuable collection of protein biomarkers with high prognostic value. PRER can be used for other complex diseases and prediction tasks that use molecular expression profiles as input. PRER is freely available at: https://github.com/hikuru/PRER.

Cancer remains to be one of the most prevalent and challenging diseases to treat. Cancer is a complex disease with several disrupted molecular mechanisms at play. The protein expression level is a fundamental indicator of how the molecular mechanisms are altered in each tumor. Predicting patient survival based on the changes is essential for understanding the cancer mechanisms and arriving at patient-specific treatment plans. For this task, existing machine learning models are used, such as random survival forest, which requires a feature-based representation of each patient based on her tumors. Most of these models use the individual molecular quantities of the tumors. However, cancer is a complex disease in which molecular mechanisms are dysregulated in various ways. In this work, we present a new patient representation scheme in which we integrate each tumor’s protein expression levels with their neighboring proteins’ expression levels in a protein-protein interaction network to capture patient-specific dysregulation patterns. Our results suggest that proteins’ relative expressions are more predictive than their individual expressions. We also analyze which of the protein interactions are more predictive of patient survival. The identified set of important protein interactions can be potentially used for cancer prognosis.