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

A new model construction based on the knowledge graph for mining elite polyphenotype genes in crops

Identifying polyphenotype genes that simultaneously regulate important agronomic traits (e.g., plant height, yield, and disease resistance) is critical for developing novel high-quality crop varieties. Predicting the associations between genes and traits requires the organization and analysis of multi-dimensional scientific data. The existing methods for establishing the relationships between genomic data and phenotypic data can only elucidate the associations between genes and individual traits. However, there are relatively few methods for detecting elite polyphenotype genes. In this study, a knowledge graph for traits regulating-genes was constructed by collecting data from the PubMed database and eight other databases related to the staple food crops rice, maize, and wheat as well as the model plant Arabidopsis thaliana. On the basis of the knowledge graph, a model for predicting traits regulating-genes was constructed by combining the data attributes of the gene nodes and the topological relationship attributes of the gene nodes. Additionally, a scoring method for predicting the genes regulating specific traits was developed to screen for elite polyphenotype genes. A total of 125,591 nodes and 547,224 semantic relationships were included in the knowledge graph. The accuracy of the knowledge graph-based model for predicting traits regulating-genes was 0.89, the precision rate was 0.91, the recall rate was 0.96, and the F1 value was 0.94. Moreover, 4,447 polyphenotype genes for 31 trait combinations were identified, among which the rice polyphenotype gene IPA1 and the A. thaliana polyphenotype gene CUC2 were verified via a literature search. Furthermore, the wheat gene TraesCS5A02G275900 was revealed as a potential polyphenotype gene that will need to be further characterized. Meanwhile, the result of venn diagram analysis between the polyphenotype gene datasets (consists of genes that are predicted by our model) and the transcriptome gene datasets (consists of genes that were differential expression in response to disease, drought or salt) showed approximately 70% and 54% polyphenotype genes were identified in the transcriptome datasets of Arabidopsis and rice, respectively. The application of the model driven by knowledge graph for predicting traits regulating-genes represents a novel method for detecting elite polyphenotype genes.

Development of a Knowledge Graph Embeddings Model for Pain

Pain is a complex concept that can interconnect with other concepts such as a disorder that might cause pain, a medication that might relieve pain, and so on. To fully understand the context of pain experienced by either an individual or across a population, we may need to examine all concepts related to pain and the relationships between them. This is especially useful when modeling pain that has been recorded in electronic health records. Knowledge graphs represent concepts and their relations by an interlinked network, enabling semantic and context-based reasoning in a computationally tractable form. These graphs can, however, be too large for efficient computation. Knowledge graph embeddings help to resolve this by representing the graphs in a low-dimensional vector space. These embeddings can then be used in various downstream tasks such as classification and link prediction. The various relations associated with pain which are required to construct such a knowledge graph can be obtained from external medical knowledge bases such as SNOMED CT, a hierarchical systematic nomenclature of medical terms. A knowledge graph built in this way could be further enriched with real-world examples of pain and its relations extracted from electronic health records. This paper describes the construction of such knowledge graph embedding models of pain concepts, extracted from the unstructured text of mental health electronic health records, combined with external knowledge created from relations described in SNOMED CT, and their evaluation on a subject-object link prediction task. The performance of the models was compared with other baseline models.

Hyperbolic hierarchical knowledge graph embeddings for biological entities

Predicting relationships between biological entities can greatly benefit important biomedical problems. Previous studies have attempted to represent biological entities and relationships in Euclidean space using embedding methods, which evaluate their semantic similarity by representing entities as numerical vectors. However, the limitation of these methods is that they cannot prevent the loss of latent hierarchical information when embedding large graph-structured data into Euclidean space, and therefore cannot capture the semantics of entities and relationships accurately. Hyperbolic spaces, such as Poincaré ball, are better suited for hierarchical modeling than Euclidean spaces. This is because hyperbolic spaces exhibit negative curvature, causing distances to grow exponentially as they approach the boundary. In this paper, we propose HEM, a hyperbolic hierarchical knowledge graph embedding model to generate vector representations of bio-entities. By encoding the entities and relations in the hyperbolic space, HEM can capture latent hierarchical information and improve the accuracy of biological entity representation. Notably, HEM can preserve rich information with a low dimension compared with the methods that encode entities in Euclidean space. Furthermore, we explore the performance of HEM in protein-protein interaction prediction and gene-disease association prediction tasks. Experimental results demonstrate the superior performance of HEM over state-of-the-art baselines. The data and code are available at : https://github.com/Nan-ll/HEM.

Predicting disease genes based on multi-head attention fusion

BACKGROUND

The identification of disease-related genes is of great significance for the diagnosis and treatment of human disease. Most studies have focused on developing efficient and accurate computational methods to predict disease-causing genes. Due to the sparsity and complexity of biomedical data, it is still a challenge to develop an effective multi-feature fusion model to identify disease genes.

RESULTS

This paper proposes an approach to predict the pathogenic gene based on multi-head attention fusion (MHAGP). Firstly, the heterogeneous biological information networks of disease genes are constructed by integrating multiple biomedical knowledge databases. Secondly, two graph representation learning algorithms are used to capture the feature vectors of gene-disease pairs from the network, and the features are fused by introducing multi-head attention. Finally, multi-layer perceptron model is used to predict the gene-disease association.

CONCLUSIONS

The MHAGP model outperforms all of other methods in comparative experiments. Case studies also show that MHAGP is able to predict genes potentially associated with diseases. In the future, more biological entity association data, such as gene-drug, disease phenotype-gene ontology and so on, can be added to expand the information in heterogeneous biological networks and achieve more accurate predictions. In addition, MHAGP with strong expansibility can be used for potential tasks such as gene-drug association and drug-disease association prediction.

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.

Hetnet connectivity search provides rapid insights into how two biomedical entities are related

Hetnets, short for "heterogeneous networks", contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet connects 11 types of nodes - including genes, diseases, drugs, pathways, and anatomical structures - with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious not only how metformin is related to breast cancer, but also how the GJA1 gene might be involved in insomnia. We developed a new procedure, termed hetnet connectivity search, that proposes important paths between any two nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). We find that predictions are broadly similar to those from previously described supervised approaches for certain node type pairs. Scoring of individual paths is based on the most specific paths of a given type. Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs. We implemented the method on Hetionet and provide an online interface at https://het.io/search . We provide an open source implementation of these methods in our new Python package named hetmatpy .

Hetnet connectivity search provides rapid insights into how biomedical entities are related

BACKGROUND

Hetnets, short for "heterogeneous networks," contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet, connects 11 types of nodes-including genes, diseases, drugs, pathways, and anatomical structures-with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious about not only how metformin is related to breast cancer but also how a given gene might be involved in insomnia.

FINDINGS

We developed a new procedure, termed hetnet connectivity search, that proposes important paths between any 2 nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs.

CONCLUSION

We implemented the method on Hetionet and provide an online interface at https://het.io/search. We provide an open-source implementation of these methods in our new Python package named hetmatpy.

Integration of Protein-Protein Interaction Networks and Gene Expression Profiles Helps Detect Pancreatic Adenocarcinoma Candidate Genes

More and more cancer-associated genes (CAGs) are being identified with the development of biological mechanism research. Integrative analysis of protein-protein interaction (PPI) networks and co-expression patterns of these genes can help identify new disease-associated genes and clarify their importance in specific diseases. This study proposed a PPI network and co-expression integration analysis model (PRNet) to integrate PPI networks and gene co-expression patterns to identify potential risk causative genes for pancreatic adenocarcinoma (PAAD). We scored the importance of the candidate genes by constructing a high-confidence co-expression-based edge-weighted PPI network, extracting protein regulatory sub-networks by random walk algorithm, constructing disease-specific networks based on known CAGs, and scoring the genes of the sub-networks with the PageRank algorithm. The results showed that our screened top-ranked genes were more critical in tumours relative to the known CAGs list and significantly differentiated the overall survival of PAAD patients. These results suggest that the PRNet method of ranking cancer-associated genes can identify new disease-associated genes and is more informative than the original CAGs list, which can help investigators to screen potential biomarkers for validation and molecular mechanism exploration.

Combining biomedical knowledge graphs and text to improve predictions for drug-target interactions and drug-indications

Biomedical knowledge is represented in structured databases and published in biomedical literature, and different computational approaches have been developed to exploit each type of information in predictive models. However, the information in structured databases and literature is often complementary. We developed a machine learning method that combines information from literature and databases to predict drug targets and indications. To effectively utilize information in published literature, we integrate knowledge graphs and published literature using named entity recognition and normalization before applying a machine learning model that utilizes the combination of graph and literature. We then use supervised machine learning to show the effects of combining features from biomedical knowledge and published literature on the prediction of drug targets and drug indications. We demonstrate that our approach using datasets for drug-target interactions and drug indications is scalable to large graphs and can be used to improve the ranking of targets and indications by exploiting features from either structure or unstructured information alone.

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.

Gene prediction of aging-related diseases based on DNN and Mashup

Background

At present, the bioinformatics research on the relationship between aging-related diseases and genes is mainly through the establishment of a machine learning multi-label model to classify each gene. Most of the existing methods for predicting pathogenic genes mainly rely on specific types of gene features, or directly encode multiple features with different dimensions, use the same encoder to concatenate and predict the final results, which will be subject to many limitations in the applicability of the algorithm. Possible shortcomings of the above include: incomplete coverage of gene features by a single type of biomics data, overfitting of small dimensional datasets by a single encoder, or underfitting of larger dimensional datasets.

Methods

We use the known gene disease association data and gene descriptors, such as gene ontology terms (GO), protein interaction data (PPI), PathDIP, Kyoto Encyclopedia of genes and genomes Genes (KEGG), etc, as input for deep learning to predict the association between genes and diseases. Our innovation is to use Mashup algorithm to reduce the dimensionality of PPI, GO and other large biological networks, and add new pathway data in KEGG database, and then combine a variety of biological information sources through modular Deep Neural Network (DNN) to predict the genes related to aging diseases.

Result and conclusion

The results show that our algorithm is more effective than the standard neural network algorithm (the Area Under the ROC curve from 0.8795 to 0.9153), gradient enhanced tree classifier and logistic regression classifier. In this paper, we firstly use DNN to learn the similar genes associated with the known diseases from the complex multi-dimensional feature space, and then provide the evidence that the assumed genes are associated with a certain disease.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04518-5.

Mitochondrial-cell cycle cross-talk drives endoreplication in heart disease

[Figure: see text].

Preliminary Analysis of the Risk Factor Identification Embedding Model for Cardiovascular Disease

Cardiovascular Disease (CVD) is responsible for a large part of healthcare costs every year, but susceptibility to it is affected by complex biological and physiological variables including patients' genetics and lifestyles. There has not been much work to develop a framework that incorporates these important and clinically relevant risk factors into a comprehensive model for CVD research. Moreover, the data labeling required to do so, such as annotating gene functions, is an extremely challenging, tedious, and time-consuming process. In this work, our goal was to develop and validate a risk factor embedding model, which incorporates genotype, phenotype without pre-labeled information to identify various risk factors of CVD. We hypothesize that (1) the knowledge background that does not require data labeling could be gathered from published abstract data, (2) the phenotype, genotype risk factors could be represented in an embedding vector space. We collected 1,363,682 published abstracts from PubMed using the keyword "heart" and 19,264 human gene names, then trained our model using the collected abstracts. We evaluated our CVD risk factor identification model using both intrinsic and extrinsic evaluations: for the intrinsic evaluation, we examined whether or not the captured top-10 words and genes have references related to the input query "myocardial infarction", as one of CVDs, and our model correctly identified them. For the extrinsic evaluation, we used our model to the dimensionality reduction task for classifications, and our method outperformed other popular methods. These results show the feasibility of our approach for disease-associated risk factors of CVD which incorporates genotype, phenotype.Clinical Relevance-Our model provides a comprehensive tool to incorporate various risk factors without any a priori data labeling knowledge for CVD. Our approach shows a potential to provide discovered knowledge that contributes to better understanding and treatment of CVD.

HiG2Vec: hierarchical representations of Gene Ontology and genes in the Poincaré ball

MOTIVATION

Knowledge manipulation of Gene Ontology (GO) and Gene Ontology Annotation (GOA) can be done primarily by using vector representation of GO terms and genes. Previous studies have represented GO terms and genes or gene products in Euclidean space to measure their semantic similarity using an embedding method such as the Word2Vec-based method to represent entities as numeric vectors. However, this method has the limitation that embedding large graph-structured data in the Euclidean space cannot prevent a loss of information of latent hierarchies, thus precluding the semantics of GO and GOA from being captured optimally. On the other hand, hyperbolic spaces such as the Poincaré balls are more suitable for modeling hierarchies, as they have a geometric property in which the distance increases exponentially as it nears the boundary because of negative curvature.

RESULTS

In this article, we propose hierarchical representations of GO and genes (HiG2Vec) by applying Poincaré embedding specialized in the representation of hierarchy through a two-step procedure: GO embedding and gene embedding. Through experiments, we show that our model represents the hierarchical structure better than other approaches and predicts the interaction of genes or gene products similar to or better than previous studies. The results indicate that HiG2Vec is superior to other methods in capturing the GO and gene semantics and in data utilization as well. It can be robustly applied to manipulate various biological knowledge.

AVAILABILITYAND IMPLEMENTATION

https://github.com/JaesikKim/HiG2Vec.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Catalyzing Knowledge-Driven Discovery in Environmental Health Sciences through a Community-Driven Harmonized Language

Harmonized language is critical for helping researchers to find data, collecting scientific data to facilitate comparison, and performing pooled and meta-analyses. Using standard terms to link data to knowledge systems facilitates knowledge-driven analysis, allows for the use of biomedical knowledge bases for scientific interpretation and hypothesis generation, and increasingly supports artificial intelligence (AI) and machine learning. Due to the breadth of environmental health sciences (EHS) research and the continuous evolution in scientific methods, the gaps in standard terminologies, vocabularies, ontologies, and related tools hamper the capabilities to address large-scale, complex EHS research questions that require the integration of disparate data and knowledge sources. The results of prior workshops to advance a harmonized environmental health language demonstrate that future efforts should be sustained and grounded in scientific need. We describe a community initiative whose mission was to advance integrative environmental health sciences research via the development and adoption of a harmonized language. The products, outcomes, and recommendations developed and endorsed by this community are expected to enhance data collection and management efforts for NIEHS and the EHS community, making data more findable and interoperable. This initiative will provide a community of practice space to exchange information and expertise, be a coordination hub for identifying and prioritizing activities, and a collaboration platform for the development and adoption of semantic solutions. We encourage anyone interested in advancing this mission to engage in this community.

KnetMiner: a comprehensive approach for supporting evidence-based gene discovery and complex trait analysis across species

The generation of new ideas and scientific hypotheses is often the result of extensive literature and database searches, but, with the growing wealth of public and private knowledge, the process of searching diverse and interconnected data to generate new insights into genes, gene networks, traits and diseases is becoming both more complex and more time-consuming. To guide this technically challenging data integration task and to make gene discovery and hypotheses generation easier for researchers, we have developed a comprehensive software package called KnetMiner which is open-source and containerized for easy use. KnetMiner is an integrated, intelligent, interactive gene and gene network discovery platform that supports scientists explore and understand the biological stories of complex traits and diseases across species. It features fast algorithms for generating rich interactive gene networks and prioritizing candidate genes based on knowledge mining approaches. KnetMiner is used in many plant science institutions and has been adopted by several plant breeding organizations to accelerate gene discovery. The software is generic and customizable and can therefore be readily applied to new species and data types; for example, it has been applied to pest insects and fungal pathogens; and most recently repurposed to support COVID-19 research. Here, we give an overview of the main approaches behind KnetMiner and we report plant-centric case studies for identifying genes, gene networks and trait relationships in Triticum aestivum (bread wheat), as well as, an evidence-based approach to rank candidate genes under a large Arabidopsis thaliana QTL. KnetMiner is available at: https://knetminer.org.

BioERP: biomedical heterogeneous network-based self-supervised representation learning approach for entity relationship predictions

MOTIVATION

Predicting entity relationship can greatly benefit important biomedical problems. Recently, a large amount of biomedical heterogeneous networks (BioHNs) are generated and offer opportunities for developing network-based learning approaches to predict relationships among entities. However, current researches slightly explored BioHNs-based self-supervised representation learning methods, and are hard to simultaneously capturing local- and global-level association information among entities.

RESULTS

In this study, we propose a biomedical heterogeneous network-based self-supervised representation learning approach for entity relationship predictions, termed BioERP. A self-supervised meta path detection mechanism is proposed to train a deep Transformer encoder model that can capture the global structure and semantic feature in BioHNs. Meanwhile, a biomedical entity mask learning strategy is designed to reflect local associations of vertices. Finally, the representations from different task models are concatenated to generate two-level representation vectors for predicting relationships among entities. The results on eight datasets show BioERP outperforms 30 state-of-the-art methods. In particular, BioERP reveals great performance with results close to 1 in terms of AUC and AUPR on the drug-target interaction predictions. In summary, BioERP is a promising bio-entity relationship prediction approach.

AVAILABILITY

Source code and data can be downloaded from https://github.com/pengsl-lab/BioERP.git.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

A representation model for biological entities by fusing structured axioms with unstructured texts

MOTIVATION

Structured semantic resources, for example, biological knowledge bases and ontologies, formally define biological concepts, entities and their semantic relationships, manifested as structured axioms and unstructured texts (e.g. textual definitions). The resources contain accurate expressions of biological reality and have been used by machine-learning models to assist intelligent applications like knowledge discovery. The current methods use both the axioms and definitions as plain texts in representation learning (RL). However, since the axioms are machine-readable while the natural language is human-understandable, difference in meaning of token and structure impedes the representations to encode desirable biological knowledge.

RESULTS

We propose ERBK, a RL model of bio-entities. Instead of using the axioms and definitions as a textual corpus, our method uses knowledge graph embedding method and deep convolutional neural models to encode the axioms and definitions respectively. The representations could not only encode more underlying biological knowledge but also be further applied to zero-shot circumstance where existing approaches fall short. Experimental evaluations show that ERBK outperforms the existing methods for predicting protein-protein interactions and gene-disease associations. Moreover, it shows that ERBK still maintains promising performance under the zero-shot circumstance. We believe the representations and the method have certain generality and could extend to other types of bio-relation.

AVAILABILITY AND IMPLEMENTATION

The source code is available at the gitlab repository https://gitlab.com/BioAI/erbk.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Predicting candidate genes from phenotypes, functions and anatomical site of expression

Motivation

Over the past years, many computational methods have been developed to incorporate information about phenotypes for disease–gene prioritization task. These methods generally compute the similarity between a patient’s phenotypes and a database of gene-phenotype to find the most phenotypically similar match. The main limitation in these methods is their reliance on knowledge about phenotypes associated with particular genes, which is not complete in humans as well as in many model organisms, such as the mouse and fish. Information about functions of gene products and anatomical site of gene expression is available for more genes and can also be related to phenotypes through ontologies and machine-learning models.

Results

We developed a novel graph-based machine-learning method for biomedical ontologies, which is able to exploit axioms in ontologies and other graph-structured data. Using our machine-learning method, we embed genes based on their associated phenotypes, functions of the gene products and anatomical location of gene expression. We then develop a machine-learning model to predict gene–disease associations based on the associations between genes and multiple biomedical ontologies, and this model significantly improves over state-of-the-art methods. Furthermore, we extend phenotype-based gene prioritization methods significantly to all genes, which are associated with phenotypes, functions or site of expression.

Availability and implementation

Software and data are available at https://github.com/bio-ontology-research-group/DL2Vec.

Supplementary information

Supplementary data are available at Bioinformatics online.

DeepViral: prediction of novel virus-host interactions from protein sequences and infectious disease phenotypes

MOTIVATION

Infectious diseases caused by novel viruses have become a major public health concern. Rapid identification of virus-host interactions can reveal mechanistic insights into infectious diseases and shed light on potential treatments. Current computational prediction methods for novel viruses are based mainly on protein sequences. However, it is not clear to what extent other important features, such as the symptoms caused by the viruses, could contribute to a predictor. Disease phenotypes (i.e., signs and symptoms) are readily accessible from clinical diagnosis and we hypothesize that they may act as a potential proxy and an additional source of information for the underlying molecular interactions between the pathogens and hosts.

RESULTS

We developed DeepViral, a deep learning based method that predicts protein-protein interactions (PPI) between humans and viruses. Motivated by the potential utility of infectious disease phenotypes, we first embedded human proteins and viruses in a shared space using their associated phenotypes and functions, supported by formalized background knowledge from biomedical ontologies. By jointly learning from protein sequences and phenotype features, DeepViral significantly improves over existing sequence-based methods for intra- and inter-species PPI prediction.

AVAILABILITY

Code and datasets for reproduction and customization are available at https://github.com/bio-ontology-research-group/DeepViral. Prediction results for 14 virus families are available at https://doi.org/10.5281/zenodo.4429824.

Application and evaluation of knowledge graph embeddings in biomedical data

Linked data and bio-ontologies enabling knowledge representation, standardization, and dissemination are an integral part of developing biological and biomedical databases. That is, linked data and bio-ontologies are employed in databases to maintain data integrity, data organization, and to empower search capabilities. However, linked data and bio-ontologies are more recently being used to represent information as multi-relational heterogeneous graphs, "knowledge graphs". The reason being, entities and relations in the knowledge graph can be represented as embedding vectors in semantic space, and these embedding vectors have been used to predict relationships between entities. Such knowledge graph embedding methods provide a practical approach to data analytics and increase chances of building machine learning models with high prediction accuracy that can enhance decision support systems. Here, we present a comparative assessment and a standard benchmark for knowledge graph-based representation learning methods focused on the link prediction task for biological relations. We systematically investigated and compared state-of-the-art embedding methods based on the design settings used for training and evaluation. We further tested various strategies aimed at controlling the amount of information related to each relation in the knowledge graph and its effects on the final performance. We also assessed the quality of the knowledge graph features through clustering and visualization and employed several evaluation metrics to examine their uses and differences. Based on this systematic comparison and assessments, we identify and discuss the limitations of knowledge graph-based representation learning methods and suggest some guidelines for the development of more improved methods.

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.

Recent advances in network-based methods for disease gene prediction

Disease-gene association through genome-wide association study (GWAS) is an arduous task for researchers. Investigating single nucleotide polymorphisms that correlate with specific diseases needs statistical analysis of associations. Considering the huge number of possible mutations, in addition to its high cost, another important drawback of GWAS analysis is the large number of false positives. Thus, researchers search for more evidence to cross-check their results through different sources. To provide the researchers with alternative and complementary low-cost disease-gene association evidence, computational approaches come into play. Since molecular networks are able to capture complex interplay among molecules in diseases, they become one of the most extensively used data for disease-gene association prediction. In this survey, we aim to provide a comprehensive and up-to-date review of network-based methods for disease gene prediction. We also conduct an empirical analysis on 14 state-of-the-art methods. To summarize, we first elucidate the task definition for disease gene prediction. Secondly, we categorize existing network-based efforts into network diffusion methods, traditional machine learning methods with handcrafted graph features and graph representation learning methods. Thirdly, an empirical analysis is conducted to evaluate the performance of the selected methods across seven diseases. We also provide distinguishing findings about the discussed methods based on our empirical analysis. Finally, we highlight potential research directions for future studies on disease gene prediction.

Supervised learning is an accurate method for network-based gene classification

Background

Assigning every human gene to specific functions, diseases and traits is a grand challenge in modern genetics. Key to addressing this challenge are computational methods, such as supervised learning and label propagation, that can leverage molecular interaction networks to predict gene attributes. In spite of being a popular machine-learning technique across fields, supervised learning has been applied only in a few network-based studies for predicting pathway-, phenotype- or disease-associated genes. It is unknown how supervised learning broadly performs across different networks and diverse gene classification tasks, and how it compares to label propagation, the widely benchmarked canonical approach for this problem.

Results

In this study, we present a comprehensive benchmarking of supervised learning for network-based gene classification, evaluating this approach and a classic label propagation technique on hundreds of diverse prediction tasks and multiple networks using stringent evaluation schemes. We demonstrate that supervised learning on a gene’s full network connectivity outperforms label propagaton and achieves high prediction accuracy by efficiently capturing local network properties, rivaling label propagation’s appeal for naturally using network topology. We further show that supervised learning on the full network is also superior to learning on node embeddings (derived using node2vec), an increasingly popular approach for concisely representing network connectivity. These results show that supervised learning is an accurate approach for prioritizing genes associated with diverse functions, diseases and traits and should be considered a staple of network-based gene classification workflows.

Availability and implementation

The datasets and the code used to reproduce the results and add new gene classification methods have been made freely available.

Contact

arjun@msu.edu

Supplementary information

Supplementary data are available at Bioinformatics online.

Constructing knowledge graphs and their biomedical applications

Knowledge graphs can support many biomedical applications. These graphs represent biomedical concepts and relationships in the form of nodes and edges. In this review, we discuss how these graphs are constructed and applied with a particular focus on how machine learning approaches are changing these processes. Biomedical knowledge graphs have often been constructed by integrating databases that were populated by experts via manual curation, but we are now seeing a more robust use of automated systems. A number of techniques are used to represent knowledge graphs, but often machine learning methods are used to construct a low-dimensional representation that can support many different applications. This representation is designed to preserve a knowledge graph's local and/or global structure. Additional machine learning methods can be applied to this representation to make predictions within genomic, pharmaceutical, and clinical domains. We frame our discussion first around knowledge graph construction and then around unifying representational learning techniques and unifying applications. Advances in machine learning for biomedicine are creating new opportunities across many domains, and we note potential avenues for future work with knowledge graphs that appear particularly promising.

Supervised learning is an accurate method for network-based gene classification

BACKGROUND

Assigning every human gene to specific functions, diseases and traits is a grand challenge in modern genetics. Key to addressing this challenge are computational methods, such as supervised learning and label propagation, that can leverage molecular interaction networks to predict gene attributes. In spite of being a popular machine-learning technique across fields, supervised learning has been applied only in a few network-based studies for predicting pathway-, phenotype- or disease-associated genes. It is unknown how supervised learning broadly performs across different networks and diverse gene classification tasks, and how it compares to label propagation, the widely benchmarked canonical approach for this problem.

RESULTS

In this study, we present a comprehensive benchmarking of supervised learning for network-based gene classification, evaluating this approach and a classic label propagation technique on hundreds of diverse prediction tasks and multiple networks using stringent evaluation schemes. We demonstrate that supervised learning on a gene's full network connectivity outperforms label propagaton and achieves high prediction accuracy by efficiently capturing local network properties, rivaling label propagation's appeal for naturally using network topology. We further show that supervised learning on the full network is also superior to learning on node embeddings (derived using node2vec), an increasingly popular approach for concisely representing network connectivity. These results show that supervised learning is an accurate approach for prioritizing genes associated with diverse functions, diseases and traits and should be considered a staple of network-based gene classification workflows.

AVAILABILITY AND IMPLEMENTATION

The datasets and the code used to reproduce the results and add new gene classification methods have been made freely available.

CONTACT

arjun@msu.edu.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Heterogeneous networks integration for disease–gene prioritization with node kernels

Motivation

The identification of disease–gene associations is a task of fundamental importance in human health research. A typical approach consists in first encoding large gene/protein relational datasets as networks due to the natural and intuitive property of graphs for representing objects’ relationships and then utilizing graph-based techniques to prioritize genes for successive low-throughput validation assays. Since different types of interactions between genes yield distinct gene networks, there is the need to integrate different heterogeneous sources to improve the reliability of prioritization systems.

Results

We propose an approach based on three phases: first, we merge all sources in a single network, then we partition the integrated network according to edge density introducing a notion of edge type to distinguish the parts and finally, we employ a novel node kernel suitable for graphs with typed edges. We show how the node kernel can generate a large number of discriminative features that can be efficiently processed by linear regularized machine learning classifiers. We report state-of-the-art results on 12 disease–gene associations and on a time-stamped benchmark containing 42 newly discovered associations.

Availability and implementation

Source code: https://github.com/dinhinfotech/DiGI.git.

Supplementary information

Supplementary data are available at Bioinformatics online.

[Epigenomic variations manifesting as a loss of heterozygosity affecting imprinted genes represent a molecular mechanism of autism spectrum disorders and intellectual disability in children]

AIM

Long continuous stretches of homozygosity (LCSH) are regularly detected in studies using molecular karyotyping (SNP array). Despite this type of variation being able to provide meaningful data on the parents' kinship, uniparental disomy and chromosome rearrangements, LCSH are rarely considered as a possible epigenetic cause of neurodevelopmental disorders. Despite their direct relationship to imprinting, LCSH in imprinted loci have not been considered in terms of pathogenicity. The present work is aimed at studying LCSH in chromosomal regions containing imprinted genes previously associated with disease in children with idiopathic intellectual disability, autism, congenital malformations and/or epilepsy.

MATERIAL AND METHODS

Five hundred and four patients with autism spectrum disorders and intellectual disability were examined.

RESULTS

LCSH affecting imprinted loci associated with various diseases were identified in 40 (7.9%) individuals. Chromosomal region 7q21.3 was affected in twenty three cases, 15q11.2 in twelve, 11p15.5 in five, 7q32.2 in four. Four patients had 2 LCSH affecting imprinted loci. Besides one LCSH in 7q31.33q32.3 (~4 Mbp) region, all LCSH were 1-1.6 Mbp. Clinically, these cases resembled the corresponding imprinting diseases (e.g. Silver-Russell, Beckwith-Wiedemann, Prader-Willi, Angelman syndromes). Parental kinship was identified in 8 cases (1.59%), which were not affected by LCSH at imprinted loci.

CONCLUSION

The present study shows that LCSH affecting chromosomal regions 7q21.3, 7q32.2, 11p15.5 and 15p11.2 occur in about 7.9% of children with intellectual disability, autism, congenital malformations and/or epilepsy. Consequently, this type of epigenetic mutations is obviously common in a group of children with neurodevelopmental disorders. LCSH less than 2.5-10 Mbp are usually ignored in molecular karyotyping (SNP array) studies and, therefore, an important epigenetic cause of intellectual disability, autism or epilepsy with high probability remains without attention.

PathoPhenoDB, linking human pathogens to their phenotypes in support of infectious disease research

Understanding the relationship between the pathophysiology of infectious disease, the biology of the causative agent and the development of therapeutic and diagnostic approaches is dependent on the synthesis of a wide range of types of information. Provision of a comprehensive and integrated disease phenotype knowledgebase has the potential to provide novel and orthogonal sources of information for the understanding of infectious agent pathogenesis, and support for research on disease mechanisms. We have developed PathoPhenoDB, a database containing pathogen-to-phenotype associations. PathoPhenoDB relies on manual curation of pathogen-disease relations, on ontology-based text mining as well as manual curation to associate host disease phenotypes with infectious agents. Using Semantic Web technologies, PathoPhenoDB also links to knowledge about drug resistance mechanisms and drugs used in the treatment of infectious diseases. PathoPhenoDB is accessible at http://patho.phenomebrowser.net/ , and the data are freely available through a public SPARQL endpoint.

Quantitative evaluation of ontology design patterns for combining pathology and anatomy ontologies

Data are increasingly annotated with multiple ontologies to capture rich information about the features of the subject under investigation. Analysis may be performed over each ontology separately, but recently there has been a move to combine multiple ontologies to provide more powerful analytical possibilities. However, it is often not clear how to combine ontologies or how to assess or evaluate the potential design patterns available. Here we use a large and well-characterized dataset of anatomic pathology descriptions from a major study of aging mice. We show how different design patterns based on the MPATH and MA ontologies provide orthogonal axes of analysis, and perform differently in over-representation and semantic similarity applications. We discuss how such a data-driven approach might be used generally to generate and evaluate ontology design patterns.