João D. Ferreira

Semantic Similarity for Automatic Classification of Chemical Compounds

With the increasing amount of data made available in the chemical field, there is a strong need for systems capable of comparing and classifying chemical compounds in an efficient and effective way. The best approaches existing today are based on the structure-activity relationship premise, which states that biological activity of a molecule is strongly related to its structural or physicochemical properties. This work presents a novel approach to the automatic classification of chemical compounds by integrating semantic similarity with existing structural comparison methods. Our approach was assessed based on the Matthews Correlation Coefficient for the prediction, and achieved values of 0.810 when used as a prediction of blood-brain barrier permeability, 0.694 for P-glycoprotein substrate, and 0.673 for estrogen receptor binding activity. These results expose a significant improvement over the currently existing methods, whose best performances were 0.628, 0.591, and 0.647 respectively. It was demonstrated that the integration of semantic similarity is a feasible and effective way to improve existing chemical compound classification systems. Among other possible uses, this tool helps the study of the evolution of metabolic pathways, the study of the correlation of metabolic networks with properties of those networks, or the improvement of ontologies that represent chemical information.

Improving chemical entity recognition through h-index based semantic similarity.

BackgroundOur approach to the BioCreative IV challenge of recognition and classification of drug names (CHEMDNER task) aimed at achieving high levels of precision by applying semantic similarity validation techniques to Chemical Entities of Biological Interest (ChEBI) mappings. Our assumption is that the chemical entities mentioned in the same fragment of text should share some semantic relation. This validation method was further improved by adapting the semantic similarity measure to take into account the h-index of each ancestor. We applied this method in two measures, simUI and simGIC, and validated the results obtained for the competition, comparing each adapted measure to its original version.ResultsFor the competition, we trained a Random Forest classifier that uses various scores provided by our system, including semantic similarity, which improved the F-measure obtained with the Conditional Random Fields classifiers by 4.6%. Using a notion of concept relevance based on the h-index measure, we were able to enhance our validation process so that for a fixed recall, we increased precision by excluding from the results a higher amount of false positives. We plotted precision and recall values for a range of validation thresholds using different similarity measures, obtaining higher precision values for the same recall with the measures based on the h-index.ConclusionsThe semantic similarity measure we introduced was more efficient at validating text mining results from machine learning classifiers than other measures. We improved the results we obtained for the CHEMDNER task by maintaining high precision values while improving the recall and F-measure.

Exploiting disjointness axioms to improve semantic similarity measures

MOTIVATION Representing domain knowledge in biology has traditionally been accomplished by creating simple hierarchies of classes with textual annotations. Recently, expressive ontology languages, such as Web Ontology Language, have become more widely adopted, supporting axioms that express logical relationships other than class-subclass, e.g. disjointness. This is improving the coverage and validity of the knowledge contained in biological ontologies. However, current semantic tools still need to adapt to this more expressive information. In this article, we propose a method to integrate disjointness axioms, which are being incorporated in real-world ontologies, such as the Gene Ontology and the chemical entities of biological interest ontology, into semantic similarity, the measure that estimates the closeness in meaning between classes. RESULTS We present a modification of the measure of shared information content, which extends the base measure to allow the incorporation of disjointness information. To evaluate our approach, we applied it to several randomly selected datasets extracted from the chemical entities of biological interest ontology. In 93.8% of these datasets, our measure performed better than the base measure of shared information content. This supports the idea that semantic similarity is more accurate if it extends beyond the hierarchy of classes of the ontology. CONTACT joao.ferreira@lasige.di.fc.ul.pt. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.

The epidemiology ontology: an ontology for the semantic annotation of epidemiological resources

BackgroundEpidemiology is a data-intensive and multi-disciplinary subject, where data integration, curation and sharing are becoming increasingly relevant, given its global context and time constraints. The semantic annotation of epidemiology resources is a cornerstone to effectively support such activities. Although several ontologies cover some of the subdomains of epidemiology, we identified a lack of semantic resources for epidemiology-specific terms. This paper addresses this need by proposing the Epidemiology Ontology (EPO) and by describing its integration with other related ontologies into a semantic enabled platform for sharing epidemiology resources.ResultsThe EPO follows the OBO Foundry guidelines and uses the Basic Formal Ontology (BFO) as an upper ontology. The first version of EPO models several epidemiology and demography parameters as well as transmission of infection processes, participants and related procedures. It currently has nearly 200 classes and is designed to support the semantic annotation of epidemiology resources and data integration, as well as information retrieval and knowledge discovery activities.ConclusionsEPO is under active development and is freely available at https://code.google.com/p/epidemiology-ontology/. We believe that the annotation of epidemiology resources with EPO will help researchers to gain a better understanding of global epidemiological events by enhancing data integration and sharing.

On the usefulness of ontologies in epidemiology research and practice

Epidemiology research is a truly multidisciplinary subject, relying on areas of knowledge as diverse as medicine, biology, statistics, sociology and geography.1 The creation of large-scale epidemiological models and the development of effective model-based prediction methods can only be achieved if efficient data collection techniques based on reliable policies for data sharing between research communities and health authorities are adopted.2 As a research domain that so strongly depends on heterogeneous data from diverse origins, epidemiology greatly requires a proper integrative framework to cope with its inherent multidisciplinarity. One promising way to meet these requirements is the adoption by the epidemiology community of Semantic Web technologies. The Semantic Web is a vision of information management and sharing that promotes intelligent access to data on the world wide web, both by human beings and by computers.3 The adoption of the Semantic Web is not new in biomedical research: for instance, in molecular biology, it has been applied in the past with intent to create successful applications. One of these is GoPubMed, a platform that enables a deep and structured exploration of PubMed abstracts4; another one is a method to identify gene functions associated with specific biological phenomena.5 The remainder of this manuscript will illustrate the advantages of adopting this paradigm for epidemiological studies, together with a brief introduction of standard Semantic Web concepts and practices, that could be useful for current and prospective epidemiologists. We also present the Epidemic Marketplace, a case study for storing and describing epidemiological resources following the Semantic Web vision. The world wide web is, by itself, an extremely useful content-sharing platform, but the content of its resources is not expressed through a common data format and is mainly directed at human users. To achieve machine-readability, the Semantic Web perceives information as resources …

Chemical Named Entity Recognition: Improving Recall Using a Comprehensive List of Lexical Features

As the number of published scientific papers grows everyday, there is also an increasing necessity for automated named entity recognition (NER) systems capable of identifying relevant entities mentioned in a given text, such as chemical entities. Since high precision values are crucial to deliver useful results, we developed a NER method, Identifying Chemical Entities (ICE), which was tuned for precision. Thus, ICE achieved the second highest precision value in the BioCreative IV CHEMDNER task, but with significant low recall values. However, this paper shows how the use of simple lexical features was able to improve the recall of ICE while maintaining high levels of precision. Using a selection of the best features tested, ICE obtained a best recall of 27.2% for a precision of 92.4%.

Assessing Public Metabolomics Metadata, Towards Improving Quality

Abstract Public resources need to be appropriately annotated with metadata in order to make them discoverable, reproducible and traceable, further enabling them to be interoperable or integrated with other datasets. While data-sharing policies exist to promote the annotation process by data owners, these guidelines are still largely ignored. In this manuscript, we analyse automatic measures of metadata quality, and suggest their application as a mean to encourage data owners to increase the metadata quality of their resources and submissions, thereby contributing to higher quality data, improved data sharing, and the overall accountability of scientific publications. We analyse these metadata quality measures in the context of a real-world repository of metabolomics data (i.e. MetaboLights), including a manual validation of the measures, and an analysis of their evolution over time. Our findings suggest that the proposed measures can be used to mimic a manual assessment of metadata quality.

Metadata Analyser: Measuring Metadata Quality

Scientific research is increasingly dependent on publicly available information and data sharing. So far, the best practices to ensure that data is accessible and shareable has been to deposit it in public repositories. However, these repositories often fail to implement mechanisms that measure data quality, which could lead to improving the discoverability of existing data, and contribute to its future integration. In light of this, we present Metadata Analyser, a tool that measures metadata quality. It assesses the quality of metadata by considering the proportion of terms actually linked to ontology concepts, as well as the specificity of the terms used in the metadata. Metadata Analyser applied to Metabolights, a real-world repository of metabolomics data, and results show that the tool successfully implements the proposed measures, that there is indeed a lack of effort in the annotation task, and that our tool can be used to improve this situation. Metadata Analyser’s frontend is available at http://masterweb-metadataanalyser.rhcloud.com.

Toponym disambiguation using ontology-based semantic similarity

We propose a new heuristic for toponym sense disambiguation, to be used when mapping toponyms in text to ontology concepts, using techniques based on semantic similarity measures. We evaluated the proposed approach using a collection of Portuguese news articles from which the geographic entity names were extracted and then manually mapped to concepts in a geospatial ontology covering the territory of Portugal. The results suggest that using semantic similarity to disambiguate toponyms in text produces good results, in comparison with a baseline method.

Generating a Tolerogenic Cell Therapy Knowledge Graph from Literature

Tolerogenic cell therapies provide an alternative to conventional immunosuppressive treatments of autoimmune disease and address, among other goals, the rejection of organ or stem cell transplants. Since various methodologies can be followed to develop tolerogenic therapies, it is important to be aware and up to date on all available studies that may be relevant to their improvement. Recently, knowledge graphs have been proposed to link various sources of information, using text mining techniques. Knowledge graphs facilitate the automatic retrieval of information about the topics represented in the graph. The objective of this work was to automatically generate a knowledge graph for tolerogenic cell therapy from biomedical literature. We developed a system, ICRel, based on machine learning to extract relations between cells and cytokines from abstracts. Our system retrieves related documents from PubMed, annotates each abstract with cell and cytokine named entities, generates the possible combinations of cell–cytokine pairs cooccurring in the same sentence, and identifies meaningful relations between cells and cytokines. The extracted relations were used to generate a knowledge graph, where each edge was supported by one or more documents. We obtained a graph containing 647 cell–cytokine relations, based on 3,264 abstracts. The modules of ICRel were evaluated with cross-validation and manual evaluation of the relations extracted. The relation extraction module obtained an F-measure of 0.789 in a reference database, while the manual evaluation obtained an accuracy of 0.615. Even though the knowledge graph is based on information that was already published in other articles about immunology, the system we present is more efficient than the laborious task of manually reading all the literature to find indirect or implicit relations. The ICRel graph will help experts identify implicit relations that may not be evident in published studies.