Evaluating the effect of annotation size on measures of semantic similarity

Prioritizing genomic variants through neuro-symbolic, knowledge-enhanced learning

MOTIVATION

Whole-exome and genome sequencing have become common tools in diagnosing patients with rare diseases. Despite their success, this approach leaves many patients undiagnosed. A common argument is that more disease variants still await discovery, or the novelty of disease phenotypes results from a combination of variants in multiple disease-related genes. Interpreting the phenotypic consequences of genomic variants relies on information about gene functions, gene expression, physiology, and other genomic features. Phenotype-based methods to identify variants involved in genetic diseases combine molecular features with prior knowledge about the phenotypic consequences of altering gene functions. While phenotype-based methods have been successfully applied to prioritizing variants, such methods are based on known gene-disease or gene-phenotype associations as training data and are applicable to genes that have phenotypes associated, thereby limiting their scope. In addition, phenotypes are not assigned uniformly by different clinicians, and phenotype-based methods need to account for this variability.

RESULTS

We developed an Embedding-based Phenotype Variant Predictor (EmbedPVP), a computational method to prioritize variants involved in genetic diseases by combining genomic information and clinical phenotypes. EmbedPVP leverages a large amount of background knowledge from human and model organisms about molecular mechanisms through which abnormal phenotypes may arise. Specifically, EmbedPVP incorporates phenotypes linked to genes, functions of gene products, and the anatomical site of gene expression, and systematically relates them to their phenotypic effects through neuro-symbolic, knowledge-enhanced machine learning. We demonstrate EmbedPVP's efficacy on a large set of synthetic genomes and genomes matched with clinical information.

AVAILABILITY AND IMPLEMENTATION

EmbedPVP and all evaluation experiments are freely available at https://github.com/bio-ontology-research-group/EmbedPVP.

How much do model organism phenotypes contribute to the computational identification of human disease genes?

Computing phenotypic similarity helps identify new disease genes and diagnose rare diseases. Genotype–phenotype data from orthologous genes in model organisms can compensate for lack of human data and increase genome coverage. In the past decade, cross-species phenotype comparisons have proven valuble, and several ontologies have been developed for this purpose. The relative contribution of different model organisms to computational identification of disease-associated genes is not fully explored. We used phenotype ontologies to semantically relate phenotypes resulting from loss-of-function mutations in model organisms to disease-associated phenotypes in humans. Semantic machine learning methods were used to measure the contribution of different model organisms to the identification of known human gene–disease associations. We found that mouse genotype–phenotype data provided the most important dataset in the identification of human disease genes by semantic similarity and machine learning over phenotype ontologies. Other model organisms' data did not improve identification over that obtained using the mouse alone, and therefore did not contribute significantly to this task. Our work impacts on the development of integrated phenotype ontologies, as well as for the use of model organism phenotypes in human genetic variant interpretation.

This article has an associated First Person interview with the first author of the paper.

Editor's choice: We investigated the use of model organism phenotypes in the computational identification of disease genes, identifying several data biases and concluding that mouse model phenotypes contribute most to computational disease gene identification.

TransformerGO: predicting protein-protein interactions by modelling the attention between sets of gene ontology terms

MOTIVATION

Protein-protein interactions (PPIs) play a key role in diverse biological processes but only a small subset of the interactions has been experimentally identified. Additionally, high-throughput experimental techniques that detect PPIs are known to suffer various limitations, such as exaggerated false positives and negatives rates. The semantic similarity derived from the Gene Ontology (GO) annotation is regarded as one of the most powerful indicators for protein interactions. However, while computational approaches for prediction of PPIs have gained popularity in recent years, most methods fail to capture the specificity of GO terms.

RESULTS

We propose TransformerGO, a model that is capable of capturing the semantic similarity between GO sets dynamically using an attention mechanism. We generate dense graph embeddings for GO terms using an algorithmic framework for learning continuous representations of nodes in networks called node2vec. TransformerGO learns deep semantic relations between annotated terms and can distinguish between negative and positive interactions with high accuracy. TransformerGO outperforms classic semantic similarity measures on gold standard PPI datasets and state-of-the-art machine-learning-based approaches on large datasets from Saccharomyces cerevisiae and Homo sapiens. We show how the neural attention mechanism embedded in the transformer architecture detects relevant functional terms when predicting interactions.

AVAILABILITY AND IMPLEMENTATION

https://github.com/Ieremie/TransformerGO.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Evaluating semantic similarity methods for comparison of text-derived phenotype profiles

Background

Semantic similarity is a valuable tool for analysis in biomedicine. When applied to phenotype profiles derived from clinical text, they have the capacity to enable and enhance ‘patient-like me’ analyses, automated coding, differential diagnosis, and outcome prediction. While a large body of work exists exploring the use of semantic similarity for multiple tasks, including protein interaction prediction, and rare disease differential diagnosis, there is less work exploring comparison of patient phenotype profiles for clinical tasks. Moreover, there are no experimental explorations of optimal parameters or better methods in the area.

Methods

We develop a platform for reproducible benchmarking and comparison of experimental conditions for patient phentoype similarity. Using the platform, we evaluate the task of ranking shared primary diagnosis from uncurated phenotype profiles derived from all text narrative associated with admissions in the medical information mart for intensive care (MIMIC-III).

Results

300 semantic similarity configurations were evaluated, as well as one embedding-based approach. On average, measures that did not make use of an external information content measure performed slightly better, however the best-performing configurations when measured by area under receiver operating characteristic curve and Top Ten Accuracy used term-specificity and annotation-frequency measures.

Conclusion

We identified and interpreted the performance of a large number of semantic similarity configurations for the task of classifying diagnosis from text-derived phenotype profiles in one setting. We also provided a basis for further research on other settings and related tasks in the area.

Multi-faceted semantic clustering with text-derived phenotypes

Identification of ontology concepts in clinical narrative text enables the creation of phenotype profiles that can be associated with clinical entities, such as patients or drugs. Constructing patient phenotype profiles using formal ontologies enables their analysis via semantic similarity, in turn enabling the use of background knowledge in clustering or classification analyses. However, traditional semantic similarity approaches collapse complex relationships between patient phenotypes into a unitary similarity scores for each pair of patients. Moreover, single scores may be based only on matching terms with the greatest information content (IC), ignoring other dimensions of patient similarity. This process necessarily leads to a loss of information in the resulting representation of patient similarity, and is especially apparent when using very large text-derived and highly multi-morbid phenotype profiles. Moreover, it renders finding a biological explanation for similarity very difficult; the black box problem. In this article, we explore the generation of multiple semantic similarity scores for patients based on different facets of their phenotypic manifestation, which we define through different sub-graphs in the Human Phenotype Ontology. We further present a new methodology for deriving sets of qualitative class descriptions for groups of entities described by ontology terms. Leveraging this strategy to obtain meaningful explanations for our semantic clusters alongside other evaluation techniques, we show that semantic clustering with ontology-derived facets enables the representation, and thus identification of, clinically relevant phenotype relationships not easily recoverable using overall clustering alone. In this way, we demonstrate the potential of faceted semantic clustering for gaining a deeper and more nuanced understanding of text-derived patient phenotypes.

Semantic similarity and machine learning with ontologies

Ontologies have long been employed in the life sciences to formally represent and reason over domain knowledge and they are employed in almost every major biological database. Recently, ontologies are increasingly being used to provide background knowledge in similarity-based analysis and machine learning models. The methods employed to combine ontologies and machine learning are still novel and actively being developed. We provide an overview over the methods that use ontologies to compute similarity and incorporate them in machine learning methods; in particular, we outline how semantic similarity measures and ontology embeddings can exploit the background knowledge in ontologies and how ontologies can provide constraints that improve machine learning models. The methods and experiments we describe are available as a set of executable notebooks, and we also provide a set of slides and additional resources at https://github.com/bio-ontology-research-group/machine-learning-with-ontologies.

Similarity Calculation, Enrichment Analysis, and Ontology Visualization of Biomedical Ontologies using UFO

The rapid growth of biomedical ontologies observed in recent years has been reported to be useful in various applications. In this article, we propose two main-function protocols-term-related and entity-related-with the three most common ontology analyses, including similarity calculation, enrichment analysis, and ontology visualization, which can be done by separate methods. Many previously developed tools implementing those methods run on different platforms and implement a limited number of the methods for similarity calculation and enrichment analysis tools for a specific type of biomedical ontology, although any type can be acceptable. Moreover, depending on each application, methods have distinct advantages; thus, the greater the number of methods a tool has, the better decisions that users make. The protocol here implements all the analyses above using an advanced popular tool called UFO. UFO is a Cytoscape app that unifies most of the semantic similarity measures for between-term and between-entity similarity calculation for biomedical ontologies in OBO format, which can calculate the similarity between two sets of entities and weigh imported entity networks, as well as generate functional similarity networks. The complete protocol can be performed in 30 min and is designed for use by biologists with no prior bioinformatics training. © 2021 Wiley Periodicals LLC. Basic Protocol: Running UFO using a list of input Gene Ontology, Disease Ontology, or Human Phenotype Ontology data.

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:

UFO: A tool for unifying biomedical ontology-based semantic similarity calculation, enrichment analysis and visualization

Background

Biomedical ontologies have been growing quickly and proven to be useful in many biomedical applications. Important applications of those data include estimating the functional similarity between ontology terms and between annotated biomedical entities, analyzing enrichment for a set of biomedical entities. Many semantic similarity calculation and enrichment analysis methods have been proposed for such applications. Also, a number of tools implementing the methods have been developed on different platforms. However, these tools have implemented a small number of the semantic similarity calculation and enrichment analysis methods for a certain type of biomedical ontology. Note that the methods can be applied to all types of biomedical ontologies. More importantly, each method can be dominant in different applications; thus, users have more choice with more number of methods implemented in tools. Also, more functions would facilitate their task with ontology.

Results

In this study, we developed a Cytoscape app, named UFO, which unifies most of the semantic similarity measures for between-term and between-entity similarity calculation for all types of biomedical ontologies in OBO format. Based on the similarity calculation, UFO can calculate the similarity between two sets of entities and weigh imported entity networks as well as generate functional similarity networks. Besides, it can perform enrichment analysis of a set of entities by different methods. Moreover, UFO can visualize structural relationships between ontology terms, annotating relationships between entities and terms, and functional similarity between entities. Finally, we demonstrated the ability of UFO through some case studies on finding the best semantic similarity measures for assessing the similarity between human disease phenotypes, constructing biomedical entity functional similarity networks for predicting disease-associated biomarkers, and performing enrichment analysis on a set of similar phenotypes.

Conclusions

Taken together, UFO is expected to be a tool where biomedical ontologies can be exploited for various biomedical applications.

Availability

UFO is distributed as a Cytoscape app, and can be downloaded freely at Cytoscape App (http://apps.cytoscape.org/apps/ufo) for non-commercial use

Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotations

Motivation

Biological knowledge is widely represented in the form of ontology-based annotations: ontologies describe the phenomena assumed to exist within a domain, and the annotations associate a (kind of) biological entity with a set of phenomena within the domain. The structure and information contained in ontologies and their annotations make them valuable for developing machine learning, data analysis and knowledge extraction algorithms; notably, semantic similarity is widely used to identify relations between biological entities, and ontology-based annotations are frequently used as features in machine learning applications.

Results

We propose the Onto2Vec method, an approach to learn feature vectors for biological entities based on their annotations to biomedical ontologies. Our method can be applied to a wide range of bioinformatics research problems such as similarity-based prediction of interactions between proteins, classification of interaction types using supervised learning, or clustering. To evaluate Onto2Vec, we use the gene ontology (GO) and jointly produce dense vector representations of proteins, the GO classes to which they are annotated, and the axioms in GO that constrain these classes. First, we demonstrate that Onto2Vec-generated feature vectors can significantly improve prediction of protein-protein interactions in human and yeast. We then illustrate how Onto2Vec representations provide the means for constructing data-driven, trainable semantic similarity measures that can be used to identify particular relations between proteins. Finally, we use an unsupervised clustering approach to identify protein families based on their Enzyme Commission numbers. Our results demonstrate that Onto2Vec can generate high quality feature vectors from biological entities and ontologies. Onto2Vec has the potential to significantly outperform the state-of-the-art in several predictive applications in which ontologies are involved.

Availability and implementation

https://github.com/bio-ontology-research-group/onto2vec.

Supplementary information

Supplementary data are available at Bioinformatics online.

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.

Ontology based text mining of gene-phenotype associations: application to candidate gene prediction

Gene-phenotype associations play an important role in understanding the disease mechanisms which is a requirement for treatment development. A portion of gene-phenotype associations are observed mainly experimentally and made publicly available through several standard resources such as MGI. However, there is still a vast amount of gene-phenotype associations buried in the biomedical literature. Given the large amount of literature data, we need automated text mining tools to alleviate the burden in manual curation of gene-phenotype associations and to develop comprehensive resources. In this study, we present an ontology-based approach in combination with statistical methods to text mine gene-phenotype associations from the literature. Our method achieved AUC values of 0.90 and 0.75 in recovering known gene-phenotype associations from HPO and MGI respectively. We posit that candidate genes and their relevant diseases should be expressed with similar phenotypes in publications. Thus, we demonstrate the utility of our approach by predicting disease candidate genes based on the semantic similarities of phenotypes associated with genes and diseases. To the best of our knowledge, this is the first study using an ontology based approach to extract gene-phenotype associations from the literature. We evaluated our disease candidate prediction model on the gene-disease associations from MGI. Our model achieved AUC values of 0.90 and 0.87 on OMIM (human) and MGI (mouse) datasets of gene-disease associations respectively. Our manual analysis on the text mined data revealed that our method can accurately extract gene-phenotype associations which are not currently covered by the existing public gene-phenotype resources. Overall, results indicate that our method can precisely extract known as well as new gene-phenotype associations from literature. All the data and methods are available at https://github.com/bio-ontology-research-group/genepheno.

Improved ontology-based similarity calculations using a study-wise annotation model

A typical use case of ontologies is the calculation of similarity scores between items that are annotated with classes of the ontology. For example, in differential diagnostics and disease gene prioritization, the human phenotype ontology (HPO) is often used to compare a query phenotype profile against gold-standard phenotype profiles of diseases or genes. The latter have long been constructed as flat lists of ontology classes, which, as we show in this work, can be improved by exploiting existing structure and information in annotation datasets or full text disease descriptions. We derive a study-wise annotation model of diseases and genes and show that this can improve the performance of semantic similarity measures. Inferred weights of individual annotations are one reason for this improvement, but more importantly using the study-wise structure further boosts the results of the algorithms according to precision-recall analyses. We test the study-wise annotation model for diseases annotated with classes from the HPO and for genes annotated with gene ontology (GO) classes. We incorporate this annotation model into similarity algorithms and show how this leads to improved performance. This work adds weight to the need for enhancing simple list-based representations of disease or gene annotations. We show how study-wise annotations can be automatically derived from full text summaries of disease descriptions and from the annotation data provided by the GO Consortium and how semantic similarity measure can utilize this extended annotation model.

Database URL: https://phenomics.github.io/

As Ontologies Reach Maturity, Artificial Intelligence Starts Being Fully Efficient: Findings from the Section on Knowledge Representation and Management for the Yearbook 2018

Objectives:  To select, present, and summarize the best papers published in 2017 in the field of Knowledge Representation and Management (KRM).

Methods:  A comprehensive and standardized review of the medical informatics literature was performed to select the most interesting papers of KRM published in 2017, based on a PubMed query.

Results:  In direct line with the research on data integration presented in the KRM section of the 2017 edition of the International Medical Informatics Association (IMIA) Yearbook, the five best papers for 2018 demonstrate even further the added-value of ontology-based integration approaches for phenotype-genotype association mining. Additionally, among the 15 preselected papers, two aspects of KRM are in the spotlight: the design of knowledge bases and new challenges in using ontologies.

Conclusions:  Ontologies are demonstrating their maturity to integrate medical data and begin to support clinical practices. New challenges have emerged: the query on distributed semantically annotated datasets, the efficiency of semantic annotation processes, the semantic representation of large textual datasets, the control of biases associated with semantic annotations, and the computation of Bayesian indicators on data annotated with ontologies.

HPO2GO: prediction of human phenotype ontology term associations for proteins using cross ontology annotation co-occurrences

Analysing the relationships between biomolecules and the genetic diseases is a highly active area of research, where the aim is to identify the genes and their products that cause a particular disease due to functional changes originated from mutations. Biological ontologies are frequently employed in these studies, which provides researchers with extensive opportunities for knowledge discovery through computational data analysis. In this study, a novel approach is proposed for the identification of relationships between biomedical entities by automatically mapping phenotypic abnormality defining HPO terms with biomolecular function defining GO terms, where each association indicates the occurrence of the abnormality due to the loss of the biomolecular function expressed by the corresponding GO term. The proposed HPO2GO mappings were extracted by calculating the frequency of the co-annotations of the terms on the same genes/proteins, using already existing curated HPO and GO annotation sets. This was followed by the filtering of the unreliable mappings that could be observed due to chance, by statistical resampling of the co-occurrence similarity distributions. Furthermore, the biological relevance of the finalized mappings were discussed over selected cases, using the literature. The resulting HPO2GO mappings can be employed in different settings to predict and to analyse novel gene/protein—ontology term—disease relations. As an application of the proposed approach, HPO term—protein associations (i.e., HPO2protein) were predicted. In order to test the predictive performance of the method on a quantitative basis, and to compare it with the state-of-the-art, CAFA2 challenge HPO prediction target protein set was employed. The results of the benchmark indicated the potential of the proposed approach, as HPO2GO performance was among the best (Fmax = 0.35). The automated cross ontology mapping approach developed in this work may be extended to other ontologies as well, to identify unexplored relation patterns at the systemic level. The datasets, results and the source code of HPO2GO are available for download at: https://github.com/cansyl/HPO2GO.

PhenoRank: reducing study bias in gene prioritization through simulation

Motivation

Genome-wide association studies have identified thousands of loci associated with human disease, but identifying the causal genes at these loci is often difficult. Several methods prioritize genes most likely to be disease causing through the integration of biological data, including protein-protein interaction and phenotypic data. Data availability is not the same for all genes however, potentially influencing the performance of these methods.

Results

We demonstrate that whilst disease genes tend to be associated with greater numbers of data, this may be at least partially a result of them being better studied. With this observation we develop PhenoRank, which prioritizes disease genes whilst avoiding being biased towards genes with more available data. Bias is avoided by comparing gene scores generated for the query disease against gene scores generated using simulated sets of phenotype terms, which ensures that differences in data availability do not affect the ranking of genes. We demonstrate that whilst existing prioritization methods are biased by data availability, PhenoRank is not similarly biased. Avoiding this bias allows PhenoRank to effectively prioritize genes with fewer available data and improves its overall performance. PhenoRank outperforms three available prioritization methods in cross-validation (PhenoRank area under receiver operating characteristic curve [AUC]=0.89, DADA AUC = 0.87, EXOMISER AUC = 0.71, PRINCE AUC = 0.83, P < 2.2 × 10-16).

Availability and implementation

PhenoRank is freely available for download at https://github.com/alexjcornish/PhenoRank.

Supplementary information

Supplementary data are available at Bioinformatics online.