GFD-Net: A novel semantic similarity methodology for the analysis of gene networks

Since the popularization of biological network inference methods, it has become crucial to create methods to validate the resulting models.Here we present GFD-Net, the first methodology that applies the concept of semantic similarity to gene network analysis. GFD-Net combines the concept of semantic similarity with the use of gene network topology to analyze the functional dissimilarity of gene networks based on Gene Ontology (GO). The main innovation of GFD-Net lies in the way that semantic similarity is used to analyze gene networks taking into account the network topology. GFD-Net selects a functionality for each gene (specified by a GO term), weights each edge according to the dissimilarity between the nodes at its ends and calculates a quantitative measure of the network functional dissimilarity, i.e. a quantitative value of the degree of dissimilarity between the connected genes.The robustness of GFD-Net as a gene network validation tool was demonstrated by performing a ROC analysis on several network repositories. Furthermore, a well-known network was analyzed showing that GFD-Net can also be used to infer knowledge.The relevance of GFD-Net becomes more evident in Section “GFD-Net applied to the study of human diseases” where an example of how GFD-Net can be applied to the study of human diseases is presented.GFD-Net is available as an open-source Cytoscape app which offers a user-friendly interface to configure and execute the algorithm as well as the ability to visualize and interact with the results(http://apps.cytoscape.org/apps/gfdnet).     

Evaluating semantic similarity between Chinese biomedical terms through multiple ontologies with score normalization: An initial study

BackgroundSemantic similarity estimation significantly promotes the understanding of natural language resources and supports medical decision making. Previous studies have investigated semantic similarity and relatedness estimation between biomedical terms through resources in English, such as SNOMED-CT or UMLS. However, very limited studies focused on the Chinese language, and technology on natural language processing and text mining of medical documents in China is urgently needed. Due to the lack of a complete and publicly available biomedical ontology in China, we only have access to several modest-sized ontologies with no overlaps. Although all these ontologies do not constitute a complete coverage of biomedicine, their coverage of their respective domains is acceptable. In this paper, semantic similarity estimations between Chinese biomedical terms using these multiple non-overlapping ontologies were explored as an initial study.MethodsTypical path-based and information content (IC)-based similarity measures were applied on these ontologies. From the analysis of the computed similarity scores, heterogeneity in the statistical distributions of scores derived from multiple ontologies was discovered. This heterogeneity hampers the comparability of scores and the overall accuracy of similarity estimation. This problem was addressed through a novel language-independent method by combining semantic similarity estimation and score normalization. A reference standard was also created in this study.ResultsCompared with the existing task-independent normalization methods, the newly developed method exhibited superior performance on most IC-based similarity measures. The accuracy of semantic similarity estimation was enhanced through score normalization. This enhancement resulted from the mitigation of heterogeneity in the similarity scores derived from multiple ontologies.ConclusionWe demonstrated the potential necessity of score normalization when estimating semantic similarity using ontology-based measures. The results of this study can also be extended to other language systems to implement semantic similarity estimation in biomedicine.     

Prioritization of candidate disease genes by combining topological similarity and semantic similarity

The identification of gene–phenotype relationships is very important for the treatment of human diseases. Studies have shown that genes causing the same or similar phenotypes tend to interact with each other in a protein–protein interaction (PPI) network. Thus, many identification methods based on the PPI network model have achieved good results. However, in the PPI network, some interactions between the proteins encoded by candidate gene and the proteins encoded by known disease genes are very weak. Therefore, some studies have combined the PPI network with other genomic information and reported good predictive performances. However, we believe that the results could be further improved. In this paper, we propose a new method that uses the semantic similarity between the candidate gene and known disease genes to set the initial probability vector of a random walk with a restart algorithm in a human PPI network. The effectiveness of our method was demonstrated by leave-one-out cross-validation, and the experimental results indicated that our method outperformed other methods. Additionally, our method can predict new causative genes of multifactor diseases, including Parkinson’s disease, breast cancer and obesity. The top predictions were good and consistent with the findings in the literature, which further illustrates the effectiveness of our method.     

Clustering clinical models from local electronic health records based on semantic similarity

BackgroundClinical models in electronic health records are typically expressed as templates which support the multiple clinical workflows in which the system is used. The templates are often designed using local rather than standard information models and terminology, which hinders semantic interoperability. Semantic challenges can be solved by harmonizing and standardizing clinical models. However, methods supporting harmonization based on existing clinical models are lacking. One approach is to explore semantic similarity estimation as a basis of an analytical framework. Therefore, the aim of this study is to develop and apply methods for intrinsic similarity-estimation based analysis that can compare and give an overview of multiple clinical models.MethodFor a similarity estimate to be intrinsic it should be based on an established ontology, for which SNOMED CT was chosen. In this study, Lin similarity estimates and Sokal and Sneath similarity estimates were used together with two aggregation techniques (average and best-match-average respectively) resulting in a total of four methods. The similarity estimations are used to hierarchically cluster templates. The test material consists of templates from Danish and Swedish EHR systems. The test material was used to evaluate how the four different methods perform.Result and discussionThe best-match-average aggregation technique performed better in terms of clustering similar templates than the average aggregation technique. No difference could be seen in terms of the choice of similarity estimate in this study, but the finding may be different for other datasets. The dendrograms resulting from the hierarchical clustering gave an overview of the templates and a basis of further analysis.ConclusionHierarchical clustering of templates based on SNOMED CT and semantic similarity estimation with best-match-average aggregation technique can be used for comparison and summarization of multiple templates. Consequently, it can provide a valuable tool for harmonization and standardization of clinical models.     

Bridging the gap: Incorporating a semantic similarity measure for effectively mapping PubMed queries to documents

The main approach of traditional information retrieval (IR) is to examine how many words from a query appear in a document. A drawback of this approach, however, is that it may fail to detect relevant documents where no or only few words from a query are found. The semantic analysis methods such as LSA (latent semantic analysis) and LDA (latent Dirichlet allocation) have been proposed to address the issue, but their performance is not superior compared to common IR approaches. Here we present a query-document similarity measure motivated by the Word Mover’s Distance. Unlike other similarity measures, the proposed method relies on neural word embeddings to compute the distance between words. This process helps identify related words when no direct matches are found between a query and a document. Our method is efficient and straightforward to implement. The experimental results on TREC Genomics data show that our approach outperforms the BM25 ranking function by an average of 12% in mean average precision. Furthermore, for a real-world dataset collected from the PubMed^® search logs, we combine the semantic measure with BM25 using a learning to rank method, which leads to improved ranking scores by up to 25%. This experiment demonstrates that the proposed approach and BM25 nicely complement each other and together produce superior performance.     

Measures of semantic similarity and relatedness in the biomedical domain

Measures of semantic similarity between concepts are widely used in Natural Language Processing. In this article, we show how six existing domain-independent measures can be adapted to the biomedical domain. These measures were originally based on WordNet, an English lexical database of concepts and relations. In this research, we adapt these measures to the SNOMED-CT ontology of medical concepts. The measures include two path-based measures, and three measures that augment path-based measures with information content statistics from corpora. We also derive a context vector measure based on medical corpora that can be used as a measure of semantic relatedness. These six measures are evaluated against a newly created test bed of 30 medical concept pairs scored by three physicians and nine medical coders. We find that the medical coders and physicians differ in their ratings, and that the context vector measure correlates most closely with the physicians, while the path-based measures and one of the information content measures correlates most closely with the medical coders. We conclude that there is a role both for more flexible measures of relatedness based on information derived from corpora, as well as for measures that rely on existing ontological structures.     

The Human Phenotype Ontology

Robinson PN, Mundlos S. The Human Phenotype Ontology. A standardized, controlled vocabulary allows phenotypic information to be described in an unambiguous fashion in medical publications and databases. The Human Phenotype Ontology (HPO) is being developed in an effort to provide such a vocabulary. The use of an ontology to capture phenotypic information allows the use of computational algorithms that exploit semantic similarity between related phenotypic abnormalities to define phenotypic similarity metrics, which can be used to perform database searches for clinical diagnostics or as a basis for incorporating the human phenome into large‐scale computational analysis of gene expression patterns and other cellular phenomena associated with human disease. The HPO is freely available at http://www.human‐phenotype‐ontology.org .     

Semantic similarity estimation in the biomedical domain: an ontology-based information-theoretic perspective

Semantic similarity estimation is an important component of analysing natural language resources like clinical records. Proper understanding of concept semantics allows for improved use and integration of heterogeneous clinical sources as well as higher information retrieval accuracy. Semantic similarity has been the focus of much research, which has led to the definition of heterogeneous measures using different theoretical principles and knowledge resources in a variety of contexts and application domains. In this paper, we study several of these measures, in addition to other similarity coefficients (not necessarily framed in a semantic context) that may be useful in determining the similarity of sets of terms. In order to make them easier to interpret and improve their applicability and accuracy, we propose a framework grounded in information theory that allows the measures studied to be uniformly redefined. Our framework is based on approximating concept semantics in terms of Information Content (IC). We also propose computing IC in a scalable and efficient manner from the taxonomical knowledge modelled in biomedical ontologies. As a result, new semantic similarity measures expressed in terms of concept Information Content are presented. These measures are evaluated and compared to related works using a benchmark of medical terms and a standard biomedical ontology. We found that an information-theoretical redefinition of well-known semantic measures and similarity coefficients, and an intrinsic estimation of concept IC result in noticeable improvements in their accuracy.     

Developing a similarity searching module for patient safety event reporting system using semantic similarity measures

Background

The most important knowledge in the field of patient safety is regarding the prevention and reduction of patient safety events (PSE) during treatment and care. The similarities and patterns among the events may otherwise go unnoticed if they are not properly reported and analyzed. There is an urgent need for developing a PSE reporting system that can dynamically measure the similarities of the events and thus promote event analysis and learning effect.

Methods

In this study, three prevailing algorithms of semantic similarity were implemented to measure the similarities of the 366 PSE annotated by the taxonomy of The Agency for Healthcare Research and Quality (AHRQ). The performance of each algorithm was then evaluated by a group of domain experts based on a 4-point Likert scale. The consistency between the scales of the algorithms and experts was measured and compared with the scales randomly assigned. The similarity algorithms and scores, as a self-learning and self-updating module, were then integrated into the system.

Results

The result shows that the similarity scores reflect a high consistency with the experts’ review than those randomly assigned. Moreover, incorporating the algorithms into our reporting system enables a mechanism to learn and update based upon PSE similarity.

Conclusion

In conclusion, integrating semantic similarity algorithms into a PSE reporting system can help us learn from previous events and provide timely knowledge support to the reporters. With the knowledge base in the PSE domain, the new generation reporting system holds promise in educating healthcare providers and preventing the recurrence and serious consequences of PSE.

     

Computation of semantic similarity within an ontology of breast pathology to assist inter-observer consensus

Computer-assisted consensus in medical imaging involves automatic comparison of morphological abnormalities observed by physicians in images. We built an ontology of morphological abnormalities in breast pathology to assist inter-observer consensus. Concepts of morphological abnormalities extracted from existing terminologies, published grading systems and medical reports were organized in an taxonomic hierarchy and furthermore linked by the relation "is a diagnostic criterion of" according to diagnostic meaning. We implemented position-based, content-based and mixed semantic similarity measures between concepts in this ontology and compared the results with experts' judgment. The position-based similarity measure using both taxonomic and non-taxonomic relations performed as well as the other measures and was used for automatic comparison of morphological abnormalities within the IDEM computer-assisted consensus platform.     

Similarity classifier using similarity measure derived from Yu's norms in classification of medical data sets

A new approach using a similarity measure based on Yu's norms is presented for the detection of erythemato-squamous diseases, diabetes, breast cancer, lung cancer and lymphography. The domain contains records of patients with known diagnoses. The results are very promising with all data sets and (in conclusion, can be drawn that) a similarity model derived from Yu's norms could be used for the diagnosis of patients taking into consideration the error rate. A similarity classifier derived from Yu's norms was used to detect the six erythemato-squamous diseases when 34 features defining six disease indications were used as inputs. The results confirmed that the proposed model has potential in detecting the erythemato-squamous diseases. The similarity model derived from Yu's norms achieved an accuracy rate (97.8%) which was higher than that of the stand-alone neural network model or the ANFIS model suggested in Ubeyli and Güler [Automatic detection of erythemato-squamous diseases using adaptive neuro-fuzzy inference systems, Comput. Biol. Med. 35 (2005) 421-433] or the similarity model based on ?ukasiewicz similarity [Luukka and Lepp?lampi, Similarity classifier with generalized mean applied to medical data, Comput. Biol. Med. 36 (2006) 1026-1040]. With PIMA Indian diabetes, the detection model has an error rate of about 24% which is much better than the overall rate of 33% for diabetes. Also, a classifier was applied to the lung cancer data set and the results were to my knowledge better than before. When the lung cancer data were preprocessed with an entropy minimization technique and the classifier with similarity based on Yu's norm was applied, 99.99% accuracy was achieved. The use of this preprocessing method enhanced the results over 30%. In lymphography, entropy minimization also enhanced the results remarkably and 86.2% accuracy was achieved.     

Enabling semantic similarity estimation across multiple ontologies: an evaluation in the biomedical domain

The estimation of the semantic similarity between terms provides a valuable tool to enable the understanding of textual resources. Many semantic similarity computation paradigms have been proposed both as general-purpose solutions or framed in concrete fields such as biomedicine. In particular, ontology-based approaches have been very successful due to their efficiency, scalability, lack of constraints and thanks to the availability of large and consensus ontologies (like WordNet or those in the UMLS). These measures, however, are hampered by the fact that only one ontology is exploited and, hence, their recall depends on the ontological detail and coverage. In recent years, some authors have extended some of the existing methodologies to support multiple ontologies. The problem of integrating heterogeneous knowledge sources is tackled by means of simple terminological matchings between ontological concepts. In this paper, we aim to improve these methods by analysing the similarity between the modelled taxonomical knowledge and the structure of different ontologies. As a result, we are able to better discover the commonalities between different ontologies and hence, improve the accuracy of the similarity estimation. Two methods are proposed to tackle this task. They have been evaluated and compared with related works by means of several widely-used benchmarks of biomedical terms using two standard ontologies (WordNet and MeSH). Results show that our methods correlate better, compared to related works, with the similarity assessments provided by experts in biomedicine.     

Recognition of medication information from discharge summaries using ensembles of classifiers

ABSTRACT: BACKGROUND: Extraction of clinical information such as medications or problems from clinical text is an important task of clinical natural language processing (NLP). Rule-based methods are often used in clinical NLP systems because they are easy to adapt and customize. Recently, supervised machine learning methods have proven to be effective in clinical NLP as well. However, combining different classifiers to further improve the performance of clinical entity recognition systems has not been investigated extensively. Combining classifiers into an ensemble classifier presents both challenges and opportunities to improve performance in such NLP tasks. METHODS: We investigated ensemble classifiers that used different voting strategies to combine outputs from three individual classifiers: a rule-based system, a support vector machine (SVM) based system, and a conditional random field (CRF) based system. Three voting methods were proposed and evaluated using the annotated data sets from the 2009 i2b2 NLP challenge: simple majority, local SVM-based voting, and local CRF-based voting. RESULTS: Evaluation on 268 manually annotated discharge summaries from the i2b2 challenge showed that the local CRF-based voting method achieved the best F-score of 90.84% (94.11% Precision, 87.81% Recall) for 10-fold cross-validation. We then compared our systems with the first-ranked system in the challenge by using the same training and test sets. Our system based on majority voting achieved a better F-score of 89.65% (93.91% Precision, 85.76% Recall) than the previously reported F-score of 89.19% (93.78% Precision, 85.03% Recall) by the first-ranked system in the challenge. CONCLUSIONS: Our experimental results using the 2009 i2b2 challenge datasets showed that ensemble classifiers that combine individual classifiers into a voting system could achieve better performance than a single classifier in recognizing medication information from clinical text. It suggests that simple strategies that can be easily implemented such as majority voting could have the potential to significantly improve clinical entity recognition.     

A framework for unifying ontology-based semantic similarity measures: A study in the biomedical domain

Ontologies are widely adopted in the biomedical domain to characterize various resources (e.g. diseases, drugs, scientific publications) with non-ambiguous meanings. By exploiting the structured knowledge that ontologies provide, a plethora of ad hoc and domain-specific semantic similarity measures have been defined over the last years. Nevertheless, some critical questions remain: which measure should be defined/chosen for a concrete application? Are some of the, a priori different, measures indeed equivalent? In order to bring some light to these questions, we perform an in-depth analysis of existing ontology-based measures to identify the core elements of semantic similarity assessment. As a result, this paper presents a unifying framework that aims to improve the understanding of semantic measures, to highlight their equivalences and to propose bridges between their theoretical bases. By demonstrating that groups of measures are just particular instantiations of parameterized functions, we unify a large number of state-of-the-art semantic similarity measures through common expressions. The application of the proposed framework and its practical usefulness is underlined by an empirical analysis of hundreds of semantic measures in a biomedical context.     

Novel phenotype–disease matching tool for rare genetic diseases

PurposeTo improve the accuracy of matching rare genetic diseases based on patient’s phenotypes.MethodsWe introduce new methods to prioritize diagnosis of genetic diseases based on integrated semantic similarity (method 1) and ontological overlap (method 2) between the phenotypes expressed by a patient and phenotypes annotated to known diseases.ResultsWe evaluated the performance of our methods by two sets of simulated data and one set of patient’s data derived from electronic health records. We demonstrated that the two methods achieved significantly improved performance compared with previous methods in correctly prioritizing candidate diseases in all of the three sets. Our methods are freely available as a web application (https://gddp.research.cchmc.org/) to aid diagnosis of genetic diseases.ConclusionOur methods can capture the diagnostic information embedded in the phenotype ontology, consider all phenotypes exhibited by a patient, and are more robust than the existing methods when phenotypes are incorrectly or imprecisely specified. These methods can assist the diagnosis of rare genetic diseases and help the interpretation of the results of DNA tests.     

Predicting gene ontology functions from ProDom and CDD protein domains

A heuristic algorithm for associating Gene Ontology (GO) defined molecular functions to protein domains as listed in the ProDom and CDD databases is described. The algorithm generates rules for function-domain associations based on the intersection of functions assigned to gene products by the GO consortium that contain ProDom and/or CDD domains at varying levels of sequence similarity. The hierarchical nature of GO molecular functions is incorporated into rule generation. Manual review of a subset of the rules generated indicates an accuracy rate of 87% for ProDom rules and 84% for CDD rules. The utility of these associations is that novel sequences can be assigned a putative function if sufficient similarity exists to a ProDom or CDD domain for which one or more GO functions has been associated. Although functional assignments are increasingly being made for gene products from model organisms, it is likely that the needs of investigators will continue to outpace the efforts of curators, particularly for nonmodel organisms. A comparison with other methods in terms of coverage and agreement was performed, indicating the utility of the approach. The domain-function associations and function assignments are available from our website http://www.cbil.upenn.edu/GO.