A knowledge-based approach for predicting gene-disease associations

SciLinker: a large-scale text mining framework for mapping associations among biological entities

Introduction

The biomedical literature is the go-to source of information regarding relationships between biological entities, including genes, diseases, cell types, and drugs, but the rapid pace of publication makes an exhaustive manual exploration impossible. In order to efficiently explore an up-to-date repository of millions of abstracts, we constructed an efficient and modular natural language processing pipeline and applied it to the entire PubMed abstract corpora.

Methods

We developed SciLinker using open-source libraries and pre-trained named entity recognition models to identify human genes, diseases, cell types and drugs, normalizing these biological entities to the Unified Medical Language System (UMLS). We implemented a scoring schema to quantify the statistical significance of entity co-occurrences and applied a fine-tuned PubMedBERT model for gene-disease relationship extraction.

Results

We identified and analyzed over 30 million association sentences, including more than 11 million gene-disease co-occurrence sentences, revealing more than 1.25 million unique gene-disease associations. We demonstrate SciLinker's ability to extract specific gene-disease relationships using osteoporosis as a case study. We show how such an analysis benefits target identification as clinically validated targets are enriched in SciLinker-derived disease-associated genes. Moreover, this co-occurrence data can be used to construct disease-specific networks, providing insights into significant relationships among biological entities from scientific literature.

Conclusion

SciLinker represents a novel text mining approach that extracts and quantifies associations between biomedical entities through co-occurrence analysis and relationship extraction from PubMed abstracts. Its modular design enables expansion to additional entities and text corpora, making it a versatile tool for transforming unstructured biomedical data into actionable insights for drug discovery.

Graph Artificial Intelligence in Medicine

In clinical artificial intelligence (AI), graph representation learning, mainly through graph neural networks and graph transformer architectures, stands out for its capability to capture intricate relationships and structures within clinical datasets. With diverse data-from patient records to imaging-graph AI models process data holistically by viewing modalities and entities within them as nodes interconnected by their relationships. Graph AI facilitates model transfer across clinical tasks, enabling models to generalize across patient populations without additional parameters and with minimal to no retraining. However, the importance of human-centered design and model interpretability in clinical decision-making cannot be overstated. Since graph AI models capture information through localized neural transformations defined on relational datasets, they offer both an opportunity and a challenge in elucidating model rationale. Knowledge graphs can enhance interpretability by aligning model-driven insights with medical knowledge. Emerging graph AI models integrate diverse data modalities through pretraining, facilitate interactive feedback loops, and foster human-AI collaboration, paving the way toward clinically meaningful predictions.

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.

A Comprehensive Bioinformatics Approach to Identify Molecular Signatures and Key Pathways for the Huntington Disease

Huntington disease (HD) is a degenerative brain disease caused by the expansion of CAG (cytosine-adenine-guanine) repeats, which is inherited as a dominant trait and progressively worsens over time possessing threat. Although HD is monogenetic, the specific pathophysiology and biomarkers are yet unknown specifically, also, complex to diagnose at an early stage, and identification is restricted in accuracy and precision. This study combined bioinformatics analysis and network-based system biology approaches to discover the biomarker, pathways, and drug targets related to molecular mechanism of HD etiology. The gene expression profile data sets GSE64810 and GSE95343 were analyzed to predict the molecular markers in HD where 162 mutual differentially expressed genes (DEGs) were detected. Ten hub genes among them (DUSP1, NKX2-5, GLI1, KLF4, SCNN1B, NPHS1, SGK2, PITX2, S100A4, and MSX1) were identified from protein-protein interaction (PPI) network which were mostly expressed as down-regulated. Following that, transcription factors (TFs)-DEGs interactions (FOXC1, GATA2, etc), TF-microRNA (miRNA) interactions (hsa-miR-340, hsa-miR-34a, etc), protein-drug interactions, and disorders associated with DEGs were predicted. Furthermore, we used gene set enrichment analysis (GSEA) to emphasize relevant gene ontology terms (eg, TF activity, sequence-specific DNA binding) linked to DEGs in HD. Disease interactions revealed the diseases that are linked to HD, and the prospective small drug molecules like cytarabine and arsenite was predicted against HD. This study reveals molecular biomarkers at the RNA and protein levels that may be beneficial to improve the understanding of molecular mechanisms, early diagnosis, as well as prospective pharmacologic targets for designing beneficial HD treatment.

MGREL: A multi-graph representation learning-based ensemble learning method for gene-disease association prediction

The identification of gene-disease associations plays an important role in the exploration of pathogenic mechanisms and therapeutic targets. Computational methods have been regarded as an effective way to discover the potential gene-disease associations in recent years. However, most of them ignored the combination of abundant genetic, therapeutic information, and gene-disease network topology. To this end, we re-organized the current gene-disease association benchmark dataset by extracting the newest gene-disease associations from the OMIM database. Then, we developed a multi-graph representation learning-based ensemble model, named MGREL to predict gene-disease associations. MGREL integrated two feature generation channels to extract gene and disease features, including a knowledge extraction channel which learned high-order representations from genetic and therapeutic information, and a graph learning channel which acquired network topological representations through multiple advanced graph representation learning methods. Then, an ensemble learning method with 5 machine learning models was used as the classifier to predict the gene-disease association. Comprehensive experiments have demonstrated the significant performance achieved by MGREL compared to 5 state-of-the-art methods. For the major measurements (AUC = 0.925, AUPR = 0.935), the relative improvements of MGREL compared to the suboptimal methods are 3.24%, and 2.75%, respectively. MGREL also achieved impressive improvements in the challenging tasks of predicting potential associations for unknown genes/diseases. In addition, case studies implied potential applications for MGREL in the discovery of potential therapeutic targets.

HetIG-PreDiG: A Heterogeneous Integrated Graph Model for Predicting Human Disease Genes based on gene expression

Graph analytical approaches permit identifying novel genes involved in complex diseases, but are limited by (i) inferring structural network similarity of connected gene nodes, ignoring potentially relevant unconnected nodes; (ii) using homogeneous graphs, missing gene-disease associations' complexity; (iii) relying on disease/gene-phenotype associations' similarities, involving highly incomplete data; (iv) using binary classification, with gene-disease edges as positive training samples, and non-associated gene and disease nodes as negative samples that may include currently unknown disease genes; or (v) reporting predicted novel associations without systematically evaluating their accuracy. Addressing these limitations, we develop the Heterogeneous Integrated Graph for Predicting Disease Genes (HetIG-PreDiG) model that includes gene-gene, gene-disease, and gene-tissue associations. We predict novel disease genes using low-dimensional representation of nodes accounting for network structure, and extending beyond network structure using the developed Gene-Disease Prioritization Score (GDPS) reflecting the degree of gene-disease association via gene co-expression data. For negative training samples, we select non-associated gene and disease nodes with lower GDPS that are less likely to be affiliated. We evaluate the developed model's success in predicting novel disease genes by analyzing the prediction probabilities of gene-disease associations. HetIG-PreDiG successfully predicts (Micro-F1 = 0.95) gene-disease associations, outperforming baseline models, and is validated using published literature, thus advancing our understanding of complex genetic diseases.

Artificial Intelligence, Healthcare, Clinical Genomics, and Pharmacogenomics Approaches in Precision Medicine

Precision medicine has greatly aided in improving health outcomes using earlier diagnosis and better prognosis for chronic diseases. It makes use of clinical data associated with the patient as well as their multi-omics/genomic data to reach a conclusion regarding how a physician should proceed with a specific treatment. Compared to the symptom-driven approach in medicine, precision medicine considers the critical fact that all patients do not react to the same treatment or medication in the same way. When considering the intersection of traditionally distinct arenas of medicine, that is, artificial intelligence, healthcare, clinical genomics, and pharmacogenomics—what ties them together is their impact on the development of precision medicine as a field and how they each contribute to patient-specific, rather than symptom-specific patient outcomes. This study discusses the impact and integration of these different fields in the scope of precision medicine and how they can be used in preventing and predicting acute or chronic diseases. Additionally, this study also discusses the advantages as well as the current challenges associated with artificial intelligence, healthcare, clinical genomics, and pharmacogenomics.

CIPHER-SC: Disease-Gene Association Inference Using Graph Convolution on a Context-Aware Network With Single-Cell Data

Inference of disease-gene associations helps unravel the pathogenesis of diseases and contributes to the treatment. Although many machine learning-based methods have been developed to predict causative genes, accurate association inference remains challenging. One major reason is the inaccurate feature selection and accumulation of error brought by commonly used multi-stage training architecture. In addition, the existing methods do not incorporate cell-type-specific information, thus fail to study gene functions at a higher resolution. Therefore, we introduce single-cell transcriptome data and construct a context-aware network to unbiasedly integrate all data sources. Then we develop a graph convolution-based approach named CIPHER-SC to realize a complete end-to-end learning architecture. Our approach outperforms four state-of-the-art approaches in five-fold cross-validations on three distinct test sets with the best AUC of 0.9501, demonstrating its stable ability either to predict the novel genes or to predict with genetic basis. The ablation study shows that our complete end-to-end design and unbiased data integration boost the performance from 0.8727 to 0.9443 in AUC. The addition of single-cell data further improves the prediction accuracy and makes our results be enriched for cell-type-specific genes. These results confirm the ability of CIPHER-SC to discover reliable disease genes. Our implementation is available at http://github.com/YidingZhang117/CIPHER-SC.

PDGNet: Predicting Disease Genes Using a Deep Neural Network With Multi-View Features

The knowledge of phenotype-genotype associations is crucial for the understanding of disease mechanisms. Numerous studies have focused on developing efficient and accurate computing approaches to predict disease genes. However, owing to the sparseness and complexity of medical data, developing an efficient deep neural network model to identify disease genes remains a huge challenge. Therefore, we develop a novel deep neural network model that fuses the multi-view features of phenotypes and genotypes to identify disease genes (termed PDGNet). Our model integrated the multi-view features of diseases and genes and leveraged the feedback information of training samples to optimize the parameters of deep neural network and obtain the deep vector features of diseases and genes. The evaluation experiments on a large data set indicated that PDGNet obtained higher performance than the state-of-the-art method (precision and recall improved by 9.55 and 9.63 percent). The analysis results for the candidate genes indicated that the predicted genes have strong functional homogeneity and dense interactions with known genes. We validated the top predicted genes of Parkinson's disease based on external curated data and published medical literatures, which indicated that the candidate genes have a huge potential to guide the selection of causal genes in the 'wet experiment'. The source codes and the data of PDGNet are available at https://github.com/yangkuoone/PDGNet.

Molecular tissue profiling by MALDI imaging: recent progress and applications in cancer research

Matrix-assisted laser desorption/ionization (MALDI) imaging is an emergent technology that has been increasingly adopted in cancer research. MALDI imaging is capable of providing global molecular mapping of the abundance and spatial information of biomolecules directly in the tissues without labeling. It enables the characterization of a wide spectrum of analytes, including proteins, peptides, glycans, lipids, drugs, and metabolites and is well suited for both discovery and targeted analysis. An advantage of MALDI imaging is that it maintains tissue integrity, which allows correlation with histological features. It has proven to be a valuable tool for probing tumor heterogeneity and has been increasingly applied to interrogate molecular events associated with cancer. It provides unique insights into both the molecular content and spatial details that are not accessible by other techniques, and it has allowed considerable progress in the field of cancer research. In this review, we first provide an overview of the MALDI imaging workflow and approach. We then highlight some useful applications in various niches of cancer research, followed by a discussion of the challenges, recent developments and future prospect of this technique in the field.

Identifying potential association on gene-disease network via dual hypergraph regularized least squares

BACKGROUND

Identifying potential associations between genes and diseases via biomedical experiments must be the time-consuming and expensive research works. The computational technologies based on machine learning models have been widely utilized to explore genetic information related to complex diseases. Importantly, the gene-disease association detection can be defined as the link prediction problem in bipartite network. However, many existing methods do not utilize multiple sources of biological information; Additionally, they do not extract higher-order relationships among genes and diseases.

RESULTS

In this study, we propose a novel method called Dual Hypergraph Regularized Least Squares (DHRLS) with Centered Kernel Alignment-based Multiple Kernel Learning (CKA-MKL), in order to detect all potential gene-disease associations. First, we construct multiple kernels based on various biological data sources in gene and disease spaces respectively. After that, we use CAK-MKL to obtain the optimal kernels in the two spaces respectively. To specific, hypergraph can be employed to establish higher-order relationships. Finally, our DHRLS model is solved by the Alternating Least squares algorithm (ALSA), for predicting gene-disease associations.

CONCLUSION

Comparing with many outstanding prediction tools, DHRLS achieves best performance on gene-disease associations network under two types of cross validation. To verify robustness, our proposed approach has excellent prediction performance on six real-world networks. Our research work can effectively discover potential disease-associated genes and provide guidance for the follow-up verification methods of complex diseases.

Graph Neural Networks and Their Current Applications in Bioinformatics

Graph neural networks (GNNs), as a branch of deep learning in non-Euclidean space, perform particularly well in various tasks that process graph structure data. With the rapid accumulation of biological network data, GNNs have also become an important tool in bioinformatics. In this research, a systematic survey of GNNs and their advances in bioinformatics is presented from multiple perspectives. We first introduce some commonly used GNN models and their basic principles. Then, three representative tasks are proposed based on the three levels of structural information that can be learned by GNNs: node classification, link prediction, and graph generation. Meanwhile, according to the specific applications for various omics data, we categorize and discuss the related studies in three aspects: disease prediction, drug discovery, and biomedical imaging. Based on the analysis, we provide an outlook on the shortcomings of current studies and point out their developing prospect. Although GNNs have achieved excellent results in many biological tasks at present, they still face challenges in terms of low-quality data processing, methodology, and interpretability and have a long road ahead. We believe that GNNs are potentially an excellent method that solves various biological problems in bioinformatics research.

IsoDA: Isoform-Disease Association Prediction by Multiomics Data Fusion

A gene can be spliced into different isoforms by alternative splicing, which contributes to the functional diversity of protein species. Computational prediction of gene-disease associations (GDAs) has been studied for decades. However, the process of identifying the isoform-disease associations (IDAs) at a large scale is rarely explored, which can decipher the pathology at a more granular level. The main bottleneck is the lack of IDAs in current databases and the multilevel omics data fusion. To bridge this gap, we propose a computational approach called Isoform-Disease Association prediction by multiomics data fusion (IsoDA) to predict IDAs. Based on the relationship between a gene and its spliced isoforms, IsoDA first introduces a dispatch and aggregation term to dispatch gene-disease associations to individual isoforms, and reversely aggregate these dispatched associations to their hosting genes. At the same time, it fuses the genome, transcriptome, and proteome data by joint matrix factorization to improve the prediction of IDAs. Experimental results show that IsoDA significantly outperforms the related state-of-the-art methods at both the gene level and isoform level. A case study further shows that IsoDA credibly identifies three isoforms spliced from apolipoprotein E, which have individual associations with Alzheimer's disease, and two isoforms spliced from vascular endothelial growth factor A, which have different associations with coronary heart disease. The codes of IsoDA are available at http://mlda.swu.edu.cn/codes.php?name=IsoDA.

Predicting disease‐associated genes: Computational methods, databases, and evaluations

Complex diseases are associated with a set of genes (called disease genes), the identification of which can help scientists uncover the mechanisms of diseases and develop new drugs and treatment strategies. Due to the huge cost and time of experimental identification techniques, many computational algorithms have been proposed to predict disease genes. Although several review publications in recent years have discussed many computational methods, some of them focus on cancer driver genes while others focus on biomolecular networks, which only cover a specific aspect of existing methods. In this review, we summarize existing methods and classify them into three categories based on their rationales. Then, the algorithms, biological data, and evaluation methods used in the computational prediction are discussed. Finally, we highlight the limitations of existing methods and point out some future directions for improving these algorithms. This review could help investigators understand the principles of existing methods, and thus develop new methods to advance the computational prediction of disease genes.

This article is categorized under:

A network-based machine-learning framework to identify both functional modules and disease genes

Disease gene identification is a critical step towards uncovering the molecular mechanisms of diseases and systematically investigating complex disease phenotypes. Despite considerable efforts to develop powerful computing methods, candidate gene identification remains a severe challenge owing to the connectivity of an incomplete interactome network, which hampers the discovery of true novel candidate genes. We developed a network-based machine-learning framework to identify both functional modules and disease candidate genes. In this framework, we designed a semi-supervised non-negative matrix factorization model to obtain the functional modules related to the diseases and genes. Of note, we proposed a disease gene-prioritizing method called MapGene that integrates the correlations from both functional modules and network closeness. Our framework identified a set of functional modules with highly functional homogeneity and close gene interactions. Experiments on a large-scale benchmark dataset showed that MapGene performs significantly better than the state-of-the-art algorithms. Further analysis demonstrates MapGene can effectively relieve the impact of the incompleteness of interactome networks and obtain highly reliable rankings of candidate genes. In addition, disease cases on Parkinson's disease and diabetes mellitus confirmed the generalization of MapGene for novel candidate gene identification. This work proposed, for the first time, an integrated computing framework to predict both functional modules and disease candidate genes. The methodology and results support that our framework has the potential to help discover underlying functional modules and reliable candidate genes in human disease.

A Knowledge-Based Machine Learning Approach to Gene Prioritisation in Amyotrophic Lateral Sclerosis

Amyotrophic lateral sclerosis is a neurodegenerative disease of the upper and lower motor neurons resulting in death from neuromuscular respiratory failure, typically within two to five years of first symptoms. Several rare disruptive gene variants have been associated with ALS and are responsible for about 15% of all cases. Although our knowledge of the genetic landscape of this disease is improving, it remains limited. Machine learning models trained on the available protein-protein interaction and phenotype-genotype association data can use our current knowledge of the disease genetics for the prediction of novel candidate genes. Here, we describe a knowledge-based machine learning method for this purpose. We trained our model on protein-protein interaction data from IntAct, gene function annotation from Gene Ontology, and known disease-gene associations from DisGeNet. Using several sets of known ALS genes from public databases and a manual review as input, we generated a list of new candidate genes for each input set. We investigated the relevance of the predicted genes in ALS by using the available summary statistics from the largest ALS genome-wide association study and by performing functional and phenotype enrichment analysis. The predicted sets were enriched for genes associated with other neurodegenerative diseases known to overlap with ALS genetically and phenotypically, as well as for biological processes associated with the disease. Moreover, using ALS genes from ClinVar and our manual review as input, the predicted sets were enriched for ALS-associated genes (ClinVar p = 0.038 and manual review p = 0.060) when used for gene prioritisation in a genome-wide association study.

Consistent gene signature of schizophrenia identified by a novel feature selection strategy from comprehensive sets of transcriptomic data

The etiology of schizophrenia (SCZ) is regarded as one of the most fundamental puzzles in current medical research, and its diagnosis is limited by the lack of objective molecular criteria. Although plenty of studies were conducted, SCZ gene signatures identified by these independent studies are found highly inconsistent. As one of the most important factors contributing to this inconsistency, the feature selection methods used currently do not fully consider the reproducibility among the signatures discovered from different datasets. Therefore, it is crucial to develop new bioinformatics tools of novel strategy for ensuring a stable discovery of gene signature for SCZ. In this study, a novel feature selection strategy (1) integrating repeated random sampling with consensus scoring and (2) evaluating the consistency of gene rank among different datasets was constructed. By systematically assessing the identified SCZ signature comprising 135 differentially expressed genes, this newly constructed strategy demonstrated significantly enhanced stability and better differentiating ability compared with the feature selection methods popular in current SCZ research. Based on a first-ever assessment on methods' reproducibility cross-validated by independent datasets from three representative studies, the new strategy stood out among the popular methods by showing superior stability and differentiating ability. Finally, 2 novel and 17 previously reported transcription factors were identified and showed great potential in revealing the etiology of SCZ. In sum, the SCZ signature identified in this study would provide valuable clues for discovering diagnostic molecules and potential targets for SCZ.

MEDICASCY: A Machine Learning Approach for Predicting Small-Molecule Drug Side Effects, Indications, Efficacy, and Modes of Action

To improve the drug discovery yield, a method which is implemented at the beginning of drug discovery that accurately predicts drug side effects, indications, efficacy, and mode of action based solely on the input of the drug's chemical structure is needed. In contrast, extant predictive methods do not comprehensively address these aspects of drug discovery and rely on features derived from extensive, often unavailable experimental information for novel molecules. To address these issues, we developed MEDICASCY, a multilabel-based boosted random forest machine learning method that only requires the small molecule's chemical structure for the drug side effect, indication, efficacy, and probable mode of action target predictions; however, it has comparable or even significantly better performance than existing approaches requiring far more information. In retrospective benchmarking on high confidence predictions, MEDICASCY shows about 78% precision and recall for predicting at least one severe side effect and 72% precision drug efficacy. Experimental validation of MEDICASCY's efficacy predictions on novel molecules shows close to 80% precision for the inhibition of growth in ovarian, breast, and prostate cancer cell lines. Thus, MEDICASCY should improve the success rate for new drug approval. A web service for academic users is available at http://pwp.gatech.edu/cssb/MEDICASCY.

Constructing Disease Similarity Networks Based on Disease Module Theory

Quantifying the associations between diseases is now playing an important role in modern biology and medicine. Actually discovering associations between diseases could help us gain deeper insights into pathogenic mechanisms of complex diseases, thus could lead to improvements in disease diagnosis, drug repositioning, and drug development. Due to the growing body of high-throughput biological data, a number of methods have been developed for computing similarity between diseases during the past decade. However, these methods rarely consider the interconnections of genes related to each disease in protein-protein interaction network (PPIN). Recently, the disease module theory has been proposed, which states that disease-related genes or proteins tend to interact with each other in the same neighborhood of a PPIN. In this study, we propose a new method called ModuleSim to measure associations between diseases by using disease-gene association data and PPIN data based on disease module theory. The experimental results show that by considering the interactions between disease modules and their modularity, the disease similarity calculated by ModuleSim has a significant correlation with disease classification of Disease Ontology (DO). Furthermore, ModuleSim outperforms other four popular methods which are all using disease-gene association data and PPIN data to measure disease-disease associations. In addition, the disease similarity network constructed by MoudleSim suggests that ModuleSim is capable of finding potential associations between diseases.

Differential kinase activity of ACVR1 G328V and R206H mutations with implications to possible TβRI cross-talk in diffuse intrinsic pontine glioma

Diffuse intrinsic pontine glioma (DIPG) is a lethal pediatric brain cancer whose median survival time is under one year. The possible roles of the two most common DIPG associated cytoplasmic ACVR1 receptor kinase domain mutants, G328V and R206H, are reexamined in the context of new biochemical results regarding their intrinsic relative ATPase activities. At 37 °C, the G328V mutant displays a 1.8-fold increase in intrinsic kinase activity over wild-type, whereas the R206H mutant shows similar activity. The higher G328V mutant intrinsic kinase activity is consistent with the statistically significant longer overall survival times of DIPG patients harboring ACVR1 G328V tumors. Based on the potential cross-talk between ACVR1 and TβRI pathways and known and predicted off-targets of ACVR1 inhibitors, we further validated the inhibition effects of several TβRI inhibitors on ACVR1 wild-type and G328V mutant patient tumor derived DIPG cell lines at 20–50 µM doses. SU-DIPG-IV cells harboring the histone H3.1K27M and activating ACVR1 G328V mutations appeared to be less susceptible to TβRI inhibition than SF8628 cells harboring the H3.3K27M mutation and wild-type ACVR1. Thus, inhibition of hidden oncogenic signaling pathways in DIPG such as TβRI that are not limited to ACVR1 itself may provide alternative entry points for DIPG therapeutics.

Context-Specific Coordinately Regulatory Network Prioritize Breast Cancer Genetic Risk Factors

Breast cancer (BC) is one of the most common tumors, leading the causes of cancer death in women. However, the pathogenesis of BC still remains unclear, and the atlas of BC-associated risk factors is far from complete. In this study, we constructed a BC-specific coordinately regulatory network (CRN) to prioritize potential BC-associated protein-coding genes (PCGs) and non-coding RNAs (ncRNAs). We integrated 813 BC sample transcriptome data from The Cancer Genome Atlas (TCGA) and eight types of regulatory relationships to construct BC-specific CRN, including 387 transcription factors (TFs), 174 microRNAs (miRNAs), 407 long non-coding RNAs (lncRNAs), and 905 PCGs. After that, the random walk with restart (RWR) method was performed on the CRN by using the known BC-associated factors as seeds, and potential BC-associated risk factors were prioritized. The leave-one-out cross-validation (LOOCV) was utilized on the BC-specific CRN and achieved an area under the curve (AUC) of 0.92. The performances of common CRN, common protein-protein interaction (PPI) network, and BC-specific PPI network were also evaluated, demonstrating that the context-specific CRN prioritizes BC risk factors. Functional analysis for the top 100-ranked risk factors in the candidate list revealed that these factors were significantly enriched in cancer-related functions and had significant semantic similarity with BC-related gene ontology (GO) terms. Differential expression analysis and survival analysis proved that the prioritized risk factors significantly associated with BC progression and prognosis. In total, we provided a computational method to predict reliable BC-associated risk factors, which would help improve the understanding of the pathology of BC and benefit disease diagnosis and prognosis.

Dynamic incorporation of prior knowledge from multiple domains in biomarker discovery

Background

In biomarker discovery, applying domain knowledge is an effective approach to eliminating false positive features, prioritizing functionally impactful markers and facilitating the interpretation of predictive signatures. Several computational methods have been developed that formulate the knowledge-based biomarker discovery as a feature selection problem guided by prior information. These methods often require that prior information is encoded as a single score and the algorithms are optimized for biological knowledge of a specific type. However, in practice, domain knowledge from diverse resources can provide complementary information. But no current methods can integrate heterogeneous prior information for biomarker discovery. To address this problem, we developed the Know-GRRF (know-guided regularized random forest) method that enables dynamic incorporation of domain knowledge from multiple disciplines to guide feature selection.

Results

Know-GRRF embeds domain knowledge in a regularized random forest framework. It combines prior information from multiple domains in a linear model to derive a composite score, which, together with other tuning parameters, controls the regularization of the random forests model. Know-GRRF concurrently optimizes the weight given to each type of domain knowledge and other tuning parameters to minimize the AIC of out-of-bag predictions. The objective is to select a compact feature subset that has a high discriminative power and strong functional relevance to the biological phenotype.

Via rigorous simulations, we show that Know-GRRF guided by multiple-domain prior information outperforms feature selection methods guided by single-domain prior information or no prior information. We then applied Known-GRRF to a real-world study to identify prognostic biomarkers of prostate cancers. We evaluated the combination of cancer-related gene annotations, evolutionary conservation and pre-computed statistical scores as the prior knowledge to assemble a panel of biomarkers. We discovered a compact set of biomarkers with significant improvements on prediction accuracies.

Conclusions

Know-GRRF is a powerful novel method to incorporate knowledge from multiple domains for feature selection. It has a broad range of applications in biomarker discoveries. We implemented this method and released a KnowGRRF package in the R/CRAN archive.

HerGePred: Heterogeneous Network Embedding Representation for Disease Gene Prediction

The discovery of disease-causing genes is a critical step towards understanding the nature of a disease and determining a possible cure for it. In recent years, many computational methods to identify disease genes have been proposed. However, making full use of disease-related (e.g., symptoms) and gene-related (e.g., gene ontology and protein-protein interactions) information to improve the performance of disease gene prediction is still an issue. Here, we develop a heterogeneous disease-gene-related network (HDGN) embedding representation framework for disease gene prediction (called HerGePred). Based on this framework, a low-dimensional vector representation (LVR) of the nodes in the HDGN can be obtained. Then, we propose two specific algorithms, namely, an LVR-based similarity prediction and a random walk with restart on a reconstructed heterogeneous disease-gene network (RW-RDGN), to predict disease genes with high performance. First, to validate the rationality of the framework, we analyze the similarity-based overlap distribution of disease pairs and design an experiment for disease-gene association recovery, the results of which revealed that the LVR of nodes performs well at preserving the local and global network structure of the HDGN. Then, we apply tenfold cross validation and external validation to compare our methods with other well-known disease gene prediction algorithms. The experimental results show that the RW-RDGN performs better than the state-of-the-art algorithm. The prediction results of disease candidate genes are essential for molecular mechanism investigation and experimental validation. The source codes of HerGePred and experimental data are available at https://github.com/yangkuoone/HerGePred.

A novel one-class classification approach to accurately predict disease-gene association in acute myeloid leukemia cancer

Disease causing gene identification is considered as an important step towards drug design and drug discovery. In disease gene identification and classification, the main aim is to identify disease genes while identifying non-disease genes are of less or no significant. Hence, this task can be defined as a one-class classification problem. Existing machine learning methods typically take into consideration known disease genes as positive training set and unknown genes as negative samples to build a binary-class classification model. Here we propose a new One-class Classification Support Vector Machines (OCSVM) method to precisely classify candidate disease genes. Our aim is to build a model that concentrate its focus on detecting known disease-causing gene to increase sensitivity and precision. We investigate the impact of our proposed model using a benchmark consisting of the gene expression dataset for Acute Myeloid Leukemia (AML) cancer. Compared with the traditional methods, our experimental result shows the superiority of our proposed method in terms of precision, recall, and F-measure to detect disease causing genes for AML. OCSVM codes and our extracted AML benchmark are publicly available at: https://github.com/imandehzangi/OCSVM.

Semantic Disease Gene Embeddings (SmuDGE): phenotype-based disease gene prioritization without phenotypes

Motivation

In the past years, several methods have been developed to incorporate information about phenotypes into computational disease gene prioritization methods. These methods commonly compute the similarity between a disease’s (or patient’s) phenotypes and a database of gene-to-phenotype associations to find the phenotypically most similar match. A key limitation of these methods is their reliance on knowledge about phenotypes associated with particular genes which is highly incomplete in humans as well as in many model organisms such as the mouse.

Results

We developed SmuDGE, a method that uses feature learning to generate vector-based representations of phenotypes associated with an entity. SmuDGE can be used as a trainable semantic similarity measure to compare two sets of phenotypes (such as between a disease and gene, or a disease and patient). More importantly, SmuDGE can generate phenotype representations for entities that are only indirectly associated with phenotypes through an interaction network; for this purpose, SmuDGE exploits background knowledge in interaction networks comprised of multiple types of interactions. We demonstrate that SmuDGE can match or outperform semantic similarity in phenotype-based disease gene prioritization, and furthermore significantly extends the coverage of phenotype-based methods to all genes in a connected interaction network.

Availability and implementation

https://github.com/bio-ontology-research-group/SmuDGE

Gene multifunctionality scoring using gene ontology

Multifunctional genes are important genes because of their essential roles in human cells. Studying and analyzing multifunctional genes can help understand disease mechanisms and drug discovery. We propose a computational method for scoring gene multifunctionality based on functional annotations of the target gene from the Gene Ontology. The method is based on identifying pairs of GO annotations that represent semantically different biological functions and any gene annotated with two annotations from one pair is considered multifunctional. The proposed method can be employed to identify multifunctional genes in the entire human genome using solely the GO annotations. We evaluated the proposed method in scoring multifunctionality of all human genes using four criteria: gene-disease associations; protein-protein interactions; gene studies with PubMed publications; and published known multifunctional gene sets. The evaluation results confirm the validity and reliability of the proposed method for identifying multifunctional human genes. The results across all four evaluation criteria were statistically significant in determining multifunctionality. For example, the method confirmed that multifunctional genes tend to be associated with diseases more than other genes, with significance [Formula: see text]. Moreover, consistent with all previous studies, proteins encoded by multifunctional genes, based on our method, are involved in protein-protein interactions significantly more ([Formula: see text]) than other proteins.

Prioritizing target-disease associations with novel safety and efficacy scoring methods

Biological target (commonly genes or proteins) identification is still largely a manual process, where experts manually try to collect and combine information from hundreds of data sources, ranging from scientific publications to omics databases. Targeting the wrong gene or protein will lead to failure of the drug development process, as well as incur delays and costs. To improve this process, different software platforms are being developed. These platforms rely strongly on efficacy estimates based on target-disease association scores created by computational methods for drug target prioritization. Here novel computational methods are presented to more accurately evaluate the efficacy and safety of potential drug targets. The proposed efficacy scores utilize existing gene expression data and tissue/disease specific networks to improve the inference of target-disease associations. Conversely, safety scores enable the identification of genes that are essential, potentially susceptible to adverse effects or carcinogenic. Benchmark results demonstrate that our transcriptome-based methods for drug target prioritization can increase the true positive rate of target-disease associations. Additionally, the proposed safety evaluation system enables accurate predictions of targets of withdrawn drugs and targets of drug trials prematurely discontinued.

Enhancing the prediction of disease–gene associations with multimodal deep learning

Motivation

Computationally predicting disease genes helps scientists optimize the in-depth experimental validation and accelerates the identification of real disease-associated genes. Modern high-throughput technologies have generated a vast amount of omics data, and integrating them is expected to improve the accuracy of computational prediction. As an integrative model, multimodal deep belief net (DBN) can capture cross-modality features from heterogeneous datasets to model a complex system. Studies have shown its power in image classification and tumor subtype prediction. However, multimodal DBN has not been used in predicting disease–gene associations.

Results

In this study, we propose a method to predict disease–gene associations by multimodal DBN (dgMDL). Specifically, latent representations of protein-protein interaction networks and gene ontology terms are first learned by two DBNs independently. Then, a joint DBN is used to learn cross-modality representations from the two sub-models by taking the concatenation of their obtained latent representations as the multimodal input. Finally, disease–gene associations are predicted with the learned cross-modality representations. The proposed method is compared with two state-of-the-art algorithms in terms of 5-fold cross-validation on a set of curated disease–gene associations. dgMDL achieves an AUC of 0.969 which is superior to the competing algorithms. Further analysis of the top-10 unknown disease–gene pairs also demonstrates the ability of dgMDL in predicting new disease–gene associations.

Availability and implementation

Prediction results and a reference implementation of dgMDL in Python is available on https://github.com/luoping1004/dgMDL.

Supplementary information

Supplementary data are available at Bioinformatics online.

Heterogeneous network embedding for identifying symptom candidate genes

Objective

Investigating the molecular mechanisms of symptoms is a vital task in precision medicine to refine disease taxonomy and improve the personalized management of chronic diseases. Although there are abundant experimental studies and computational efforts to obtain the candidate genes of diseases, the identification of symptom genes is rarely addressed. We curated a high-quality benchmark dataset of symptom-gene associations and proposed a heterogeneous network embedding for identifying symptom genes.

Methods

We proposed a heterogeneous network embedding representation algorithm, which constructed a heterogeneous symptom-related network that integrated symptom-related associations and applied an embedding representation algorithm to obtain the low-dimensional vector representation of nodes. By measuring the relevance between symptoms and genes via calculating the similarities of their vectors, the candidate genes of given symptoms can be obtained.

Results

A benchmark dataset of 18 270 symptom-gene associations between 505 symptoms and 4549 genes was curated. We compared our method to baseline algorithms (FSGER and PRINCE). The experimental results indicated our algorithm achieved a significant improvement over the state-of-the-art method, with precision and recall improved by 66.80% (0.844 vs 0.506) and 53.96% (0.311 vs 0.202), respectively, for TOP@3 and association precision improved by 37.71% (0.723 vs 0.525) over the PRINCE.

Conclusions

The experimental validation of the algorithms and the literature validation of typical symptoms indicated our method achieved excellent performance. Hence, we curated a prediction dataset of 17 479 symptom-candidate genes. The benchmark and prediction datasets have the potential to promote investigations of the molecular mechanisms of symptoms and provide candidate genes for validation in experimental settings.

Automatic extraction of gene-disease associations from literature using joint ensemble learning

A wealth of knowledge concerning relations between genes and its associated diseases is present in biomedical literature. Mining these biological associations from literature can provide immense support to research ranging from drug-targetable pathways to biomarker discovery. However, time and cost of manual curation heavily slows it down. In this current scenario one of the crucial technologies is biomedical text mining, and relation extraction shows the promising result to explore the research of genes associated with diseases. By developing automatic extraction of gene-disease associations from the literature using joint ensemble learning we addressed this problem from a text mining perspective. In the proposed work, we employ a supervised machine learning approach in which a rich feature set covering conceptual, syntax and semantic properties jointly learned with word embedding are trained using ensemble support vector machine for extracting gene-disease relations from four gold standard corpora. Upon evaluating the machine learning approach shows promised results of 85.34%, 83.93%,87.39% and 85.57% of F-measure on EUADR, GAD, CoMAGC and PolySearch corpora respectively. We strongly believe that the presented novel approach combining rich syntax and semantic feature set with domain-specific word embedding through ensemble support vector machines evaluated on four gold standard corpora can act as a new baseline for future works in gene-disease relation extraction from literature.

ENTPRISE-X: Predicting disease-associated frameshift and nonsense mutations

To exploit the plethora of information provided by Next Generation Sequencing, the identification of the genetic mutations responsible for disease in general or cancer in particular, among the thousands of neutral germline or somatic variations is a crucial task. Genome-wide association studies for the detection of disease-associated genes or cancer drivers can only identify common variations or driver genes in a cohort of patients. Thus, they cannot discover unique disease-associated mutations or cancer driver genes on a personal basis. Moreover, even when there are such common variations, their significance is unknown. Here, we extend the machine learning based approach ENTPRISE developed for predicting the disease association of missense mutations to frameshift and nonsense mutations. The new approach, ENTPRISE-X, is shown to outperform the state-of-the-art methods VEST-indel and DDIG-in for predicting the disease association of germline frameshift mutations in terms of balanced measure Matthew’s correlation coefficient, MCC, with a MCC of 0.586 for ENTPRISE-X, versus 0.412 by VEST-indel and 0.321 by DDIG-in, respectively. Large scale testing on the ExAC dataset shows ENTPRISE-X has a much lower fraction of 16% of variations classified as disease causing, as compared to VEST-indel’s 26% and DDIG-in’s 65% of predictions as being disease-associated. A web server for ENTPRISE-X is freely available for academic users at http://cssb2.biology.gatech.edu/entprise-x.

Large-scale analysis of disease pathways in the human interactome

Discovering disease pathways, which can be defined as sets of proteins associated with a given disease, is an important problem that has the potential to provide clinically actionable insights for disease diagnosis, prognosis, and treatment. Computational methods aid the discovery by relying on protein-protein interaction (PPI) networks. They start with a few known disease-associated proteins and aim to find the rest of the pathway by exploring the PPI network around the known disease proteins. However, the success of such methods has been limited, and failure cases have not been well understood. Here we study the PPI network structure of 519 disease pathways. We find that 90% of pathways do not correspond to single well-connected components in the PPI network. Instead, proteins associated with a single disease tend to form many separate connected components/regions in the network. We then evaluate state-of-the-art disease pathway discovery methods and show that their performance is especially poor on diseases with disconnected pathways. Thus, we conclude that network connectivity structure alone may not be sufficient for disease pathway discovery. However, we show that higher-order network structures, such as small subgraphs of the pathway, provide a promising direction for the development of new methods.

Constructing an integrated gene similarity network for the identification of disease genes

BACKGROUND

Discovering novel genes that are involved human diseases is a challenging task in biomedical research. In recent years, several computational approaches have been proposed to prioritize candidate disease genes. Most of these methods are mainly based on protein-protein interaction (PPI) networks. However, since these PPI networks contain false positives and only cover less half of known human genes, their reliability and coverage are very low. Therefore, it is highly necessary to fuse multiple genomic data to construct a credible gene similarity network and then infer disease genes on the whole genomic scale.

RESULTS

We proposed a novel method, named RWRB, to infer causal genes of interested diseases. First, we construct five individual gene (protein) similarity networks based on multiple genomic data of human genes. Then, an integrated gene similarity network (IGSN) is reconstructed based on similarity network fusion (SNF) method. Finally, we employee the random walk with restart algorithm on the phenotype-gene bilayer network, which combines phenotype similarity network, IGSN as well as phenotype-gene association network, to prioritize candidate disease genes. We investigate the effectiveness of RWRB through leave-one-out cross-validation methods in inferring phenotype-gene relationships. Results show that RWRB is more accurate than state-of-the-art methods on most evaluation metrics. Further analysis shows that the success of RWRB is benefited from IGSN which has a wider coverage and higher reliability comparing with current PPI networks. Moreover, we conduct a comprehensive case study for Alzheimer's disease and predict some novel disease genes that supported by literature.

CONCLUSIONS

RWRB is an effective and reliable algorithm in prioritizing candidate disease genes on the genomic scale. Software and supplementary information are available at http://nclab.hit.edu.cn/~tianzhen/RWRB/ .