Gene Prediction Methods Research Articles

Gene expression prediction from histology images via hypergraph neural networks.

Spatial transcriptomics reveals the spatial distribution of genes in complex tissues, providing crucial insights into biological processes, disease mechanisms, and drug development. The prediction of gene expression based on cost-effective histology images is a promising yet challenging field of research. Existing methods for gene prediction from histology images exhibit two major limitations. First, they ignore the intricate relationship between cell morphological information and gene expression. Second, these methods do not fully utilize the different latent stages of features extracted from the images. To address these limitations, we propose a novel hypergraph neural network model, HGGEP, to predict gene expressions from histology images. HGGEP includes a gradient enhancement module to enhance the model's perception of cell morphological information. A lightweight backbone network extracts multiple latent stage features from the image, followed by attention mechanisms to refine the representation of features at each latent stage and capture their relations with nearby features. To explore higher-order associations among multiple latent stage features, we stack them and feed into the hypergraph to establish associations among features at different scales. Experimental results on multiple datasets from disease samples including cancers and tumor disease, demonstrate the superior performance of our HGGEP model than existing methods.

Investigating long noncoding RNA HA117 and its possible regulatory network in osteosarcoma

Osteosarcoma, a primary malignant bone tumor, is the third most common cancer in children and adolescents under 20 years old. In recent decades, many osteosarcomar elated molecular targets, including long noncoding RNA (lncRNA), have been discovered or confirmed. This study aims to elucidate the gene expression and possible regulatory mechanisms of lncRNA HA117 in osteosarcoma. To achieve this, we downloaded 51 whole-transcriptome osteosarcoma sequencing samples from the NCBI Sequence Read Archive database and performed bioinformatics analysis. Geneexpression analysis of HA117 revealed no significant difference between the tumor and adjacent tissues. However, HA117 exhibited significant down-regulation in bothfresh and formalin‐fixed paraffin-embedded (FFPE) samples after chemotherapy. Bycombining two target gene prediction methods, we identified 11 and 83 target genes for HA117 in fresh and FFPE samples, respectively. Functional analysis indicated that these target genes are mainly located in the cytoplasm and nucleus, with most related to protein binding. In addition, Reactome analysis demonstrated that these target genes participate in the regulation of multiple metabolic pathways, predominantly in cellular responses to stress. Our findings suggest that chemotherapy may regulate downstream target genes by altering the expression of HA117, thereby inducing cellular stress response. Overall, our results indicate that HA117 may not function as an oncogene but could serve as a therapeutic target in osteosarcoma.

KDGene: knowledge graph completion for disease gene prediction using interactional tensor decomposition.

The accurate identification of disease-associated genes is crucial for understanding the molecular mechanisms underlying various diseases. Most current methods focus on constructing biological networks and utilizing machine learning, particularly deep learning, to identify disease genes. However, these methods overlook complex relations among entities in biological knowledge graphs. Such information has been successfully applied in other areas of life science research, demonstrating their effectiveness. Knowledge graph embedding methods can learn the semantic information of different relations within the knowledge graphs. Nonetheless, the performance of existing representation learning techniques, when applied to domain-specific biological data, remains suboptimal. To solve these problems, we construct a biological knowledge graph centered on diseases and genes, and develop an end-to-end knowledge graph completion framework for disease gene prediction using interactional tensor decomposition named KDGene. KDGene incorporates an interaction module that bridges entity and relation embeddings within tensor decomposition, aiming to improve the representation of semantically similar concepts in specific domains and enhance the ability to accurately predict disease genes. Experimental results show that KDGene significantly outperforms state-of-the-art algorithms, whether existing disease gene prediction methods or knowledge graph embedding methods for general domains. Moreover, the comprehensive biological analysis of the predicted results further validates KDGene's capability to accurately identify new candidate genes. This work proposes a scalable knowledge graph completion framework to identify disease candidate genes, from which the results are promising to provide valuable references for further wet experiments. Data and source codes are available at https://github.com/2020MEAI/KDGene.

Comparative Genome Annotation.

Newly sequenced genomes are being added to the tree of life at an unprecedented fast pace. A large proportion of such new genomes are phylogenetically close to previously sequenced and annotated genomes. In other cases, whole clades of closely related species or strains ought to be annotated simultaneously. Often, in subsequent studies, differences between the closely related species or strains are in the focus of research when the shared gene structures prevail. We here review methods for comparative structural genome annotation. The reviewed methods include classical approaches such as the alignment of protein sequences or protein profiles against the genome and comparative gene prediction methods that exploit a genome alignment to annotate either a single target genome or all input genomes simultaneously. We discuss how the methods depend on the phylogenetic placement of genomes, give advice on the choice of methods, and examine the consistency between gene structure annotations in an example. Furthermore, we provide practical advice on genome annotation in general.

A method to improve the prediction performance of cancer-gene association by screening negative training samples through gene network data

This work focuses on data sampling in cancer-gene association prediction. Currently, researchers are using machine learning methods to predict genes that are more likely to produce cancer-causing mutations. To improve the performance of machine learning models, methods have been proposed, one of which is to improve the quality of the training data. Existing methods focus mainly on positive data, i.e. cancer driver genes, for screening selection. This paper proposes a low-cancer-related gene screening method based on gene network and graph theory algorithms to improve the negative samples selection. Genetic data with low cancer correlation is used as negative training samples. After experimental verification, using the negative samples screened by this method to train the cancer gene classification model can improve prediction performance. The biggest advantage of this method is that it can be easily combined with other methods that focus on enhancing the quality of positive training samples. It has been demonstrated that significant improvement is achieved by combining this method with three state-of-the-arts cancer gene prediction methods.

Addressing the pervasive scarcity of structural annotation in eukaryotic algae

Despite a continuous increase in algal genome sequencing, structural annotations of most algal genome assemblies remain unavailable. This pervasive scarcity of genome annotation has restricted rigorous investigation of these genomic resources and may have precipitated misleading biological interpretations. However, the annotation process for eukaryotic algal species is often challenging as genomic resources and transcriptomic evidence are not always available. To address this challenge, we benchmark the cutting-edge gene prediction methods that can be generalized for a broad range of non-model eukaryotes. Using the most accurate methods selected based on high-quality algal genomes, we predict structural annotations for 135 unannotated algal genomes. Using previously available genomic data pooled together with new data obtained in this study, we identified the core orthologous genes and the multi-gene phylogeny of eukaryotic algae, including of previously unexplored algal species. This study not only provides a benchmark for the use of structural annotation methods on a variety of non-model eukaryotes, but also compensates for missing data in the current spectrum of algal genomic resources. These results bring us one step closer to the full potential of eukaryotic algal genomics.

FTGD: a machine learning method for flowering-time gene prediction

FTGD: a machine learning method for flowering-time gene prediction

Repulsion and attraction in searching: A hybrid algorithm based on gravitational kernel and vital few for cancer driver gene prediction

By taking a new perspective to combine a machine learning method with an evolutionary algorithm, a new hybrid algorithm is developed to predict cancer driver genes. Firstly, inspired by the search strategy with the capability of global search in evolutionary algorithms, a gravitational kernel is proposed to act on the full range of gene features. Constructed by fusing PPI and mutation features, the gravitational kernel is capable to produce repulsion effects. The candidate genes with greater mutation effects and PPI have higher similarity scores. According to repulsion, the similarity score of these promising genes is larger than ordinary genes, which is beneficial to search for these promising genes. Secondly, inspired by the idea of elite populations related to evolutionary algorithms, the concept of vital few is proposed. Targeted at a local scale, it acts on the candidate genes associated with vital few genes. Under attraction effect, these vital few driver genes attract those with similar mutational effects to them, which leads to greater similarity scores. Lastly, the model and parameters are optimized by using an evolutionary algorithm, so as to obtain the optimal model and parameters for cancer driver gene prediction. Herein, a comparison is performed with six other advanced methods of cancer driver gene prediction. According to the experimental results, the method proposed in this study outperforms these six state-of-the-art algorithms on the pan-oncogene dataset.

基于网络和基因差异表达信息的癌症致病基因预测

<p indent="0mm">In genome research, the discovery of disease-causing pathogenic genes is a major challenge in genome research. Recently, using the available biological data, many researchers have employed computational methods for pathogenic gene prediction. However, most of these computational methods are based on gene interaction networks or other similar networks, and the potential connection between the local network of specific genes and their differential expression information is rarely considered. This paper explores the biological properties of cancerous pathogenic genes and their neighbors based on a local network structure and the differential expression information of genes. Furthermore, machine learning methods are employed for predicting cancerous pathogenic genes based on the newly discovered biological properties. First, the expression data of 21 cancers and their pathogenic genes are obtained from the TCGA (The Cancer Genome Atlas) and OMIM (Online Mendelian Inheritance in Man) databases. Human-protein interaction and tissue-specific interaction networks corresponding to each cancer gene are used as background networks to analyze the potential biological properties between the neighborhood information of different networks and the changed information of the gene expression. Then, based on the discovered biological properties, a vector representation method for gene node features is established, and the support vector machine is employed for pathogenic gene prediction. Experimental results are verified using ICGC (International Cancer Genome Consortium), COSMIC (Catalogue Of Somatic Mutations In Cancer), NCG (Network of Cancer Genes), OncoKB (Oncology Knowledge Base), and other standard databases, as well as using related literature, disease annotations and pathway enrichments. Results show that the definition of gene features can be used to distinguish cancerous pathogenic genes from other genes, thus providing powerful hypotheses for cancerous pathogenic gene prediction. Furthermore, reliable pathogenic gene candidates are obtained for related biological experiments to promote research on the pathogenic mechanism of cancer, a complex disease.

Prioritization of cancer driver gene with prize-collecting steiner tree by introducing an edge weighted strategy in the personalized gene interaction network

BackgroundCancer is a heterogeneous disease in which tumor genes cooperate as well as adapt and evolve to the changing conditions for individual patients. It is a meaningful task to discover the personalized cancer driver genes that can provide diagnosis and target drug for individual patients. However, most of existing methods mainly ranks potential personalized cancer driver genes by considering the patient-specific nodes information on the gene/protein interaction network. These methods ignore the personalized edge weight information in gene interaction network, leading to false positive results.ResultsIn this work, we presented a novel algorithm (called PDGPCS) to predict the Personalized cancer Driver Genes based on the Prize-Collecting Steiner tree model by considering the personalized edge weight information. PDGPCS first constructs the personalized weighted gene interaction network by integrating the personalized gene expression data and prior known gene/protein interaction network knowledge. Then the gene mutation data and pathway data are integrated to quantify the impact of each mutant gene on every dysregulated pathway with the prize-collecting Steiner tree model. Finally, according to the mutant gene’s aggregated impact score on all dysregulated pathways, the mutant genes are ranked for prioritizing the personalized cancer driver genes. Experimental results on four TCGA cancer datasets show that PDGPCS has better performance than other personalized driver gene prediction methods. In addition, we verified that the personalized edge weight of gene interaction network can improve the prediction performance.ConclusionsPDGPCS can more accurately identify the personalized driver genes and takes a step further toward personalized medicine and treatment. The source code of PDGPCS can be freely downloaded from https://github.com/NWPU-903PR/PDGPCS.

GCN-GENE: A novel method for prediction of coronary heart disease-related genes

Coronary heart disease is the most common heart disease, it can induce myocardial infarction, and the cause of the disease has a lot to do with life and eating habits. The results of a large number of epidemiological studies at home and abroad show that the incidence of coronary heart disease has an obvious familial tendency. However, little is known about the genetic factors of coronary heart disease. Although genome-wide association analysis and gene knockout experiments have found some genes related to coronary heart disease, there are still a large number of genes potentially related to coronary heart disease that have not been discovered. If it is confirmed by biological experimental means, the time and money cost is too high. Therefore, it is urgent to identify genes related to coronary heart disease on a large scale by computational means, so as to conduct targeted biological experimental verification. This paper proposes a deep learning method based on biological networks for the identification of coronary heart disease-related genes. We constructed gene interaction networks and extracted gene expression levels in different tissues as features. Through the association information and expression characteristics between genes, we constructed a model of coronary heart disease-related genes. Through cross-validation, we found that our proposed GCN-GENE that has AUC as 0.75 and AUPR as 0.78, which is more accurate than other methods and is a reliable method for predicting coronary heart disease-related genes.

Using an Improved Residual Network to Identify PIK3CA Mutation Status in Breast Cancer on Ultrasound Image.

BackgroundThe detection of phosphatidylinositol-3 kinase catalytic alpha (PIK3CA) gene mutations in breast cancer is a key step to design personalizing an optimal treatment strategy. Traditional genetic testing methods are invasive and time-consuming. It is urgent to find a non-invasive method to estimate the PIK3CA mutation status. Ultrasound (US), one of the most common methods for breast cancer screening, has the advantages of being non-invasive, fast imaging, and inexpensive. In this study, we propose to develop a deep convolutional neural network (DCNN) to identify PIK3CA mutations in breast cancer based on US images.Materials and MethodsWe retrospectively collected 312 patients with pathologically confirmed breast cancer who underwent genetic testing. All US images (n=800) of breast cancer patients were collected and divided into the training set (n=600) and test set (n=200). A DCNN-Improved Residual Network (ImResNet) was designed to identify the PIK3CA mutations. We also compared the ImResNet model with the original ResNet50 model, classical machine learning models, and other deep learning models.ResultsThe proposed ImResNet model has the ability to identify PIK3CA mutations in breast cancer based on US images. Notably, our ImResNet model outperforms the original ResNet50, DenseNet201, Xception, MobileNetv2, and two machine learning models (SVM and KNN), with an average area under the curve (AUC) of 0.775. Moreover, the overall accuracy, average precision, recall rate, and F1-score of the ImResNet model achieved 74.50%, 74.17%, 73.35%, and 73.76%, respectively. All of these measures were significantly higher than other models.ConclusionThe ImResNet model gives an encouraging performance in predicting PIK3CA mutations based on breast US images, providing a new method for noninvasive gene prediction. In addition, this model could provide the basis for clinical adjustments and precision treatment.

XGBG: A Novel Method for Identifying Ovarian Carcinoma Susceptible Genes Based on Deep Learning.

Ovarian carcinomas (OCs) represent a heterogeneous group of neoplasms consisting of several entities with pathogenesis, molecular profiles, multiple risk factors, and outcomes. OC has been regarded as the most lethal cancer among women all around the world. There are at least five main types of OCs classified by the fifth edition of the World Health Organization of tumors: high-/low-grade serous carcinoma, mucinous carcinoma, clear cell carcinoma, and endometrioid carcinoma. With the improved knowledge of genome-wide association study (GWAS) and expression quantitative trait locus (eQTL) analyses, the knowledge of genomic landscape of complex diseases has been uncovered in large measure. Moreover, pathway analyses also play an important role in exploring the underlying mechanism of complex diseases by providing curated pathway models and information about molecular dynamics and cellular processes. To investigate OCs deeper, we introduced a novel disease susceptible gene prediction method, XGBG, which could be used in identifying OC-related genes based on different omics data and deep learning methods. We first employed the graph convolutional network (GCN) to reconstruct the gene features based on both gene feature and network topological structure. Then, a boosting method is utilized to predict OC susceptible genes. As a result, our model achieved a high AUC of 0.7541 and an AUPR of 0.8051, which indicates the effectiveness of the XGPG. Based on the newly predicted OC susceptible genes, we gathered and researched related literatures to provide strong support to the results, which may help in understanding the pathogenesis and mechanisms of the disease.

Pyrodigal: Python bindings and interface to Prodigal, an efficient method for gene prediction in prokaryotes

Larralde, M., (2022). Pyrodigal: Python bindings and interface to Prodigal, an efficient method for gene prediction in prokaryotes. Journal of Open Source Software, 7(72), 4296, https://doi.org/10.21105/joss.04296

A computational method for predicting nucleocapsid protein in retroviruses

Nucleocapsid protein (NC) in the group-specific antigen (gag) of retrovirus is essential in the interactions of most retroviral gag proteins with RNAs. Computational method to predict NCs would benefit subsequent structure analysis and functional study on them. However, no computational method to predict the exact locations of NCs in retroviruses has been proposed yet. The wide range of length variation of NCs also increases the difficulties. In this paper, a computational method to identify NCs in retroviruses is proposed. All available retrovirus sequences with NC annotations were collected from NCBI. Models based on random forest (RF) and weighted support vector machine (WSVM) were built to predict initiation and termination sites of NCs. Factor analysis scales of generalized amino acid information along with position weight matrix were utilized to generate the feature space. Homology based gene prediction methods were also compared and integrated to bring out better predicting performance. Candidate initiation and termination sites predicted were then combined and screened according to their intervals, decision values and alignment scores. All available gag sequences without NC annotations were scanned with the model to detect putative NCs. Geometric means of sensitivity and specificity generated from prediction of initiation and termination sites under fivefold cross-validation are 0.9900 and 0.9548 respectively. 90.91% of all the collected retrovirus sequences with NC annotations could be predicted totally correct by the model combining WSVM, RF and simple alignment. The composite model performs better than the simplex ones. 235 putative NCs in unannotated gags were detected by the model. Our prediction method performs well on NC recognition and could also be expanded to solve other gene prediction problems, especially those whose training samples have large length variations.

A network-based method for brain disease gene prediction by integrating brain connectome and molecular network.

Brain disease gene identification is critical for revealing the biological mechanism and developing drugs for brain diseases. To enhance the identification of brain disease genes, similarity-based computational methods, especially network-based methods, have been adopted for narrowing down the searching space. However, these network-based methods only use molecular networks, ignoring brain connectome data, which have been widely used in many brain-related studies. In our study, we propose a novel framework, named brainMI, for integrating brain connectome data and molecular-based gene association networks to predict brain disease genes. For the consistent representation of molecular-based network data and brain connectome data, brainMI first constructs a novel gene network, called brain functional connectivity (BFC)-based gene network, based on resting-state functional magnetic resonance imaging data and brain region-specific gene expression data. Then, a multiple network integration method is proposed to learn low-dimensional features of genes by integrating the BFC-based gene network and existing protein-protein interaction networks. Finally, these features are utilized to predict brain disease genes based on a support vector machine-based model. We evaluate brainMI on four brain diseases, including Alzheimer's disease, Parkinson's disease, major depressive disorder and autism. brainMI achieves of 0.761, 0.729, 0.728 and 0.744 using the BFC-based gene network alone and enhances the molecular network-based performance by 6.3% on average. In addition, the results show that brainMI achieves higher performance in predicting brain disease genes compared to the existing three state-of-the-art methods.

MOSES: A New Approach to Integrate Interactome Topology and Functional Features for Disease Gene Prediction.

Disease gene prediction is to date one of the main computational challenges of precision medicine. It is still uncertain if disease genes have unique functional properties that distinguish them from other non-disease genes or, from a network perspective, if they are located randomly in the interactome or show specific patterns in the network topology. In this study, we propose a new method for disease gene prediction based on the use of biological knowledge-bases (gene-disease associations, genes functional annotations, etc.) and interactome network topology. The proposed algorithm called MOSES is based on the definition of two somewhat opposing sets of genes both disease-specific from different perspectives: warm seeds (i.e., disease genes obtained from databases) and cold seeds (genes far from the disease genes on the interactome and not involved in their biological functions). The application of MOSES to a set of 40 diseases showed that the suggested putative disease genes are significantly enriched in their reference disease. Reassuringly, known and predicted disease genes together, tend to form a connected network module on the human interactome, mitigating the scattered distribution of disease genes which is probably due to both the paucity of disease-gene associations and the incompleteness of the interactome.

Computational and Bioinformatics Methods for MicroRNA Gene Prediction.

MicroRNAs (miRNAs) are 20-24-nucleotide-long noncoding RNAs that bind to the untranslated region (3' UTR) of their target mRNAs. The importance of miRNAs in medicine has grown rapidly in the 20years since the discovery of them. As the regulatory function of miRNAs on biological processes was discovered, they were advocated to play a role in the underlying mechanisms of human pathogenesis. Functional studies have confirmed that miRNAs are promising in preclinical development through deregulation of genes targeted by miRNAs in many cancer cases. In this chapter, we summarize the miRNAs identified for some specific types of cancer and their functions. Besides, miRNAs function as cancer biomarker and their benefits to diagnosis and treatment of cancer are also discussed.

An Ovarian Cancer Susceptible Gene Prediction Method Based on Deep Learning Methods.

Ovarian cancer (OC) is one of the most fatal diseases among women all around the world. It is highly lethal because it is usually diagnosed at an advanced stage which may reduce the survival rate greatly. Even though most of the patients are treated timely and effectively, the survival rate is still low due to the high recurrence rate of OC. With a large number of genome-wide association analysis (GWAS)-discovered risk regions of OC, expression quantitative trait locus (eQTL) analyses can explore candidate susceptible genes based on these risk loci. However, a large number of OC-related genes remain unknown. In this study, we proposed a novel gene prediction method based on different omics data and deep learning methods to identify OC causal genes. We first employed graph attention network (GAT) to obtain a compact gene feature representation, then a deep neural network (DNN) is utilized to predict OC-related genes. As a result, our model achieved a high AUC of 0.761 and AUPR of 0.788, which proved the accuracy and effectiveness of our proposed method. At last, we conducted a gene-set enrichment analysis to further explore the mechanism of OC. Finally, we predicted 245 novel OC causal genes and 10 top related KEGG pathways.

Genome assembly and annotation of the white spot syndrome virus - infected pacific white shrimp (Ltopenaeus vannamei) in Vietnam

Pacific white shrimp (Penaeus vannamei or Litopenaeus vannamei) is native to South America, high economic value, and widely cultivated in the world and Vietnam. Over the last two decades, viral diseases have seriously threatened the shrimp aquaculture industry. Among the viral diseases, white spot syndrome virus (WSSV) is the most important viral pathogens of shrimp farming. WSSV causes a cumulative mortality can reach 100% within 3–10 days. Genome sequencing and assembly has been an important step for deciphering molecular mechanisms and accelerating genetic improvements of traits of interest in economically important species. This study aims at constructing and annotating the genome of white spot syndrome virus - infected Pacific white shrimp in Vietnam. The whole genome sequencing data was de novo assembled using SOAP denovo2 to obtained draft genome of WSSV- infected L. vannamei shrimp. The draft genome contained 3,180,049 scaffolds (genome size ~1.67 Gb) with the length arranging from 200 bp to 137,569 bp and with N50 as 616 bp. Applying gene prediction method, we have been able to identify 187,948 putative genes. The results have shown that 33,611 genes were annotate in NT database and 133,548 genes were annotated in UniProtKB/Swissprot database. These results are only the initial information about white spot syndrome virus - infected Pacific white shrimp but they are really important for future studies relating to white spot syndrome virus – resistance L. vannamei shrimp in Vietnam.