TopoFun: a machine learning method to improve the functional similarity of gene co-expression modules
Ontology highlight
ABSTRACT:
SUBMITTER: Janbain A
PROVIDER: S-EPMC8573820 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Asthma is a heterogeneous respiratory disease characterized by airway inflammation and obstruction. Despite recent advances, the genetic regulation of asthma pathogenesis is still largely unknown. Gene expression profiling techniques are well suited to study complex diseases including asthma. In this study, differentially expressed genes (DEGs) followed by weighted gene co-expression network analysis (WGCNA) and machine learning techniques using dataset generated from airway epithelial cells (AECs) and nasal epithelial cells (NECs) were used to identify candidate genes and pathways and to develop asthma classification and predictive models. The models were validated using bronchial epithelial cells (BECs), airway smooth muscle (ASM) and whole blood (WB) datasets. DEG and WGCNA followed by least absolute shrinkage and selection operator (LASSO) method identified 30 and 34 gene signatures and these gene signatures with support vector machine (SVM) discriminated asthmatic subjects from controls in AECs (Area under the curve: AUC = 1) and NECs (AUC = 1), respectively. We further validated AECs derived gene-signature in BECs (AUC = 0.72), ASM (AUC = 0.74) and WB (AUC = 0.66). Similarly, NECs derived gene-signature were validated in BECs (AUC = 0.75), ASM (AUC = 0.82) and WB (AUC = 0.69). Both AECs and NECs based gene-signatures showed a strong diagnostic performance with high sensitivity and specificity. Functional annotation of gene-signatures from AECs and NECs were enriched in pathways associated with IL-13, PI3K/AKT and apoptosis signaling. Several asthma related genes were prioritized including SERPINB2 and CTSC genes, which showed functional relevance in multiple tissue/cell types and related to asthma pathogenesis. Taken together, epithelium gene signature-based model could serve as robust surrogate model for hard-to-get tissues including BECs to improve the molecular etiology of asthma.
| S-EPMC10338542 | biostudies-literature
Project description:BACKGROUND: Biological networks characterize the interactions of biomolecules at a systems-level. One important property of biological networks is the modular structure, in which nodes are densely connected with each other, but between which there are only sparse connections. In this report, we attempted to find the relationship between the network topology and formation of modular structure by comparing gene co-expression networks with random networks. The organization of gene functional modules was also investigated. RESULTS: We constructed a genome-wide Arabidopsis gene co-expression network (AGCN) by using 1094 microarrays. We then analyzed the topological properties of AGCN and partitioned the network into modules by using an efficient graph clustering algorithm. In the AGCN, 382 hub genes formed a clique, and they were densely connected only to a small subset of the network. At the module level, the network clustering results provide a systems-level understanding of the gene modules that coordinate multiple biological processes to carry out specific biological functions. For instance, the photosynthesis module in AGCN involves a very large number (> 1000) of genes which participate in various biological processes including photosynthesis, electron transport, pigment metabolism, chloroplast organization and biogenesis, cofactor metabolism, protein biosynthesis, and vitamin metabolism. The cell cycle module orchestrated the coordinated expression of hundreds of genes involved in cell cycle, DNA metabolism, and cytoskeleton organization and biogenesis. We also compared the AGCN constructed in this study with a graphical Gaussian model (GGM) based Arabidopsis gene network. The photosynthesis, protein biosynthesis, and cell cycle modules identified from the GGM network had much smaller module sizes compared with the modules found in the AGCN, respectively. CONCLUSION: This study reveals new insight into the topological properties of biological networks. The preferential hub-hub connections might be necessary for the formation of modular structure in gene co-expression networks. The study also reveals new insight into the organization of gene functional modules.
| S-EPMC2772859 | biostudies-other
Project description:Molecular subtyping of cancer is recognized as a critical and challenging step towards individualized therapy. Most existing computational methods solve this problem via multi-classification of gene-expressions of cancer samples. Although these methods, especially deep learning, perform well in data classification, they usually require large amounts of data for model training and have limitations in interpretability. Besides, as cancer is a complex systemic disease, the phenotypic difference between cancer samples can hardly be fully understood by only analyzing single molecules, and differential expression-based molecular subtyping methods are reportedly not conserved. To address the above issues, we present here a new framework for molecular subtyping of cancer through identifying a robust specific co-expression module for each subtype of cancer, generating network features for each sample by perturbing correlation levels of specific edges, and then training a deep neural network for multi-class classification. When applied to breast cancer (BRCA) and stomach adenocarcinoma (STAD) molecular subtyping, it has superior classification performance over existing methods. In addition to improving classification performance, we consider the specific co-expressed modules selected for subtyping to be biologically meaningful, which potentially offers new insight for diagnostic biomarker design, mechanistic studies of cancer, and individualized treatment plan selection.
| S-EPMC9108363 | biostudies-literature
Project description:BackgroundThe relationships between the gene functional similarity and gene expression profile, and between gene function annotation and gene sequence have been studied extensively. However, not much work has considered the connection between gene functions and location of a gene's expression in the mammalian tissues. On the other hand, although unsupervised learning methods have been commonly used in functional genomics, supervised learning cannot be directly applied to a set of normal genes without having a target (class) attribute.ResultsHere, we propose a supervised learning methodology to predict pair-wise gene functional similarity from multiplex gene expression maps that provide information about the location of gene expression. The features are extracted from expression maps and the labels denote the functional similarities of pairs of genes. We make use of wavelet features, original expression values, difference and average values of neighboring voxels and other features to perform boosting analysis. The experimental results show that with increasing similarities of gene expression maps, the functional similarities are increased too. The model predicts the functional similarities between genes to a certain degree. The weights of the features in the model indicate the features that are more significant for this prediction.ConclusionsBy considering pairs of genes, we propose a supervised learning methodology to predict pair-wise gene functional similarity from multiplex gene expression maps. We also explore the relationship between similarities of gene maps and gene functions. By using AdaBoost coupled with our proposed weak classifier we analyze a large-scale gene expression dataset and predict gene functional similarities. We also detect the most significant single voxels and pairs of neighboring voxels and visualize them in the expression map image of a mouse brain. This work is very important for predicting functions of unknown genes. It also has broader applicability since the methodology can be applied to analyze any large-scale dataset without a target attribute and is not restricted to gene expressions.
| S-EPMC3375633 | biostudies-literature
Project description:BACKGROUND:The inference of homology between proteins is a key problem in molecular biology The current best approaches only identify approximately 50% of homologies (with a false positive rate set at 1/1000). RESULTS:We present Homology Induction (HI), a new approach to inferring homology. HI uses machine learning to bootstrap from standard sequence similarity search methods. First a standard method is run, then HI learns rules which are true for sequences of high similarity to the target (assumed homologues) and not true for general sequences, these rules are then used to discriminate sequences in the twilight zone. To learn the rules HI describes the sequences in a novel way based on a bioinformatic knowledge base, and the machine learning method of inductive logic programming. To evaluate HI we used the PDB40D benchmark which lists sequences of known homology but low sequence similarity. We compared the HI methodology with PSI-BLAST alone and found HI performed significantly better. In addition, Receiver Operating Characteristic (ROC) curve analysis showed that these improvements were robust for all reasonable error costs. The predictive homology rules learnt by HI by can be interpreted biologically to provide insight into conserved features of homologous protein families. CONCLUSIONS:HI is a new technique for the detection of remote protein homology--a central bioinformatic problem. HI with PSI-BLAST is shown to outperform PSI-BLAST for all error costs. It is expect that similar improvements would be obtained using HI with any sequence similarity method.
| S-EPMC107726 | biostudies-literature
Project description:The coronavirus disease-2019 (COVID-19) pandemic has caused an enormous loss of lives. Various clinical trials of vaccines and drugs are being conducted worldwide; nevertheless, as of today, no effective drug exists for COVID-19. The identification of key genes and pathways in this disease may lead to finding potential drug targets and biomarkers. Here, we applied weighted gene co-expression network analysis and LIME as an explainable artificial intelligence algorithm to comprehensively characterize transcriptional changes in bronchial epithelium cells (primary human lung epithelium (NHBE) and transformed lung alveolar (A549) cells) during severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. Our study detected a network that significantly correlated to the pathogenicity of COVID-19 infection based on identified hub genes in each cell line separately. The novel hub gene signature that was detected in our study, including PGLYRP4 and HEPHL1, may shed light on the pathogenesis of COVID-19, holding promise for future prognostic and therapeutic approaches. The enrichment analysis of hub genes showed that the most relevant biological process and KEGG pathways were the type I interferon signaling pathway, IL-17 signaling pathway, cytokine-mediated signaling pathway, and defense response to virus categories, all of which play significant roles in restricting viral infection. Moreover, according to the drug-target network, we identified 17 novel FDA-approved candidate drugs, which could potentially be used to treat COVID-19 patients through the regulation of four hub genes of the co-expression network. In conclusion, the aforementioned hub genes might play potential roles in translational medicine and might become promising therapeutic targets. Further in vitro and in vivo experimental studies are needed to evaluate the role of these hub genes in COVID-19.
| S-EPMC8397209 | biostudies-literature
Project description:Schizophrenia (SCZ) and bipolar disorder (BD) are highly heritable psychiatric disorders. Associated genetic and gene expression changes have been identified, but many have not been replicated and have unknown functions. We identified groups of genes whose expressions varied together, that is co-expression modules, then tested them for association with SCZ. Using weighted gene co-expression network analysis, we show that two modules were differentially expressed in patients versus controls. One, upregulated in cerebral cortex, was enriched with neuron differentiation and neuron development genes, as well as disease genome-wide association study genetic signals; the second, altered in cerebral cortex and cerebellum, was enriched with genes involved in neuron protection functions. The findings were preserved in five expression data sets, including sets from three brain regions, from a different microarray platform, and from BD patients. From those observations, we propose neuron differentiation and development pathways may be involved in etiologies of both SCZ and BD, and neuron protection function participates in pathological process of the diseases.
| S-EPMC4018461 | biostudies-literature
Project description:Ovarian cancer (OV) is an extremely lethal disease. However, the evolutionary machineries of OV are still largely unknown. Here, we used a method that combines phylostratigraphy information with gene co-expression networks to extensively study the evolutionary compositions of OV. The present co-expression network construction yielded 18,549 nodes and 114,985 edges based on 307 OV expression samples obtained from the Genome Data Analysis Centers database. A total of 20 modules were identified as OV related clusters. The human genome sequences were divided into 19 phylostrata (PS), the majority (67.45%) of OV genes was already present in the eukaryotic ancestor. There were two strong peaks of the emergence of OV genes screened by hypergeometric test: the evolution of the multicellular metazoan organisms (PS5 and PS6, P value = 0.002) and the emergence of bony fish (PS11 and PS12, P value = 0.009). Hence, the origin of OV is far earlier than its emergence. The integrated analysis of the topology of OV modules and the phylogenetic data revealed an evolutionary pattern of OV in human, namely, OV modules have arisen step by step during the evolution of the respective lineages. New genes have evolved and become locked into a pathway, where more and more biological pathways are fixed into OV modules by recruiting new genes during human evolution.
| S-EPMC6384884 | biostudies-literature
Project description:BACKGROUND: Endothelial progenitor cells (EPCs) have been implicated in different processes crucial to vasculature repair, which may offer the basis for new therapeutic strategies in cardiovascular disease. Despite advances facilitated by functional genomics, there is a lack of systems-level understanding of treatment response mechanisms of EPCs. In this research we aimed to characterize the EPCs response to adenosine (Ado), a cardioprotective factor, based on the systems-level integration of gene expression data and prior functional knowledge. Specifically, we set out to identify novel biosignatures of Ado-treatment response in EPCs. RESULTS: The predictive integration of gene expression data and standardized functional similarity information enabled us to identify new treatment response biosignatures. Gene expression data originated from Ado-treated and -untreated EPCs samples, and functional similarity was estimated with Gene Ontology (GO)-based similarity information. These information sources enabled us to implement and evaluate an integrated prediction approach based on the concept of k-nearest neighbours learning (kNN). The method can be executed by expert- and data-driven input queries to guide the search for biologically meaningful biosignatures. The resulting integrated kNN system identified new candidate EPC biosignatures that can offer high classification performance (areas under the operating characteristic curve>0.8). We also showed that the proposed models can outperform those discovered by standard gene expression analysis. Furthermore, we report an initial independent in vitro experimental follow-up, which provides additional evidence of the potential validity of the top biosignature. CONCLUSION: Response to Ado treatment in EPCs can be accurately characterized with a new method based on the combination of gene co-expression data and GO-based similarity information. It also exploits the incorporation of human expert-driven queries as a strategy to guide the automated search for candidate biosignatures. The proposed biosignature improves the systems-level characterization of EPCs. The new integrative predictive modeling approach can also be applied to other phenotype characterization or biomarker discovery problems.
| S-EPMC3080295 | biostudies-literature
Project description:Ontologies have long been employed in the life sciences to formally represent and reason over domain knowledge and they are employed in almost every major biological database. Recently, ontologies are increasingly being used to provide background knowledge in similarity-based analysis and machine learning models. The methods employed to combine ontologies and machine learning are still novel and actively being developed. We provide an overview over the methods that use ontologies to compute similarity and incorporate them in machine learning methods; in particular, we outline how semantic similarity measures and ontology embeddings can exploit the background knowledge in ontologies and how ontologies can provide constraints that improve machine learning models. The methods and experiments we describe are available as a set of executable notebooks, and we also provide a set of slides and additional resources at https://github.com/bio-ontology-research-group/machine-learning-with-ontologies.
| S-EPMC8293838 | biostudies-literature