Facilitating the development of controlled vocabularies for metabolomics technologies with text mining

Cognitive analysis of metabolomics data for systems biology

Cognitive computing is revolutionizing the way big data are processed and integrated, with artificial intelligence (AI) natural language processing (NLP) platforms helping researchers to efficiently search and digest the vast scientific literature. Most available platforms have been developed for biomedical researchers, but new NLP tools are emerging for biologists in other fields and an important example is metabolomics. NLP provides literature-based contextualization of metabolic features that decreases the time and expert-level subject knowledge required during the prioritization, identification and interpretation steps in the metabolomics data analysis pipeline. Here, we describe and demonstrate four workflows that combine metabolomics data with NLP-based literature searches of scientific databases to aid in the analysis of metabolomics data and their biological interpretation. The four procedures can be used in isolation or consecutively, depending on the research questions. The first, used for initial metabolite annotation and prioritization, creates a list of metabolites that would be interesting for follow-up. The second workflow finds literature evidence of the activity of metabolites and metabolic pathways in governing the biological condition on a systems biology level. The third is used to identify candidate biomarkers, and the fourth looks for metabolic conditions or drug-repurposing targets that the two diseases have in common. The protocol can take 1-4 h or more to complete, depending on the processing time of the various software used.

Using ontologies to map between research data and policymakers’ presumptions: the experience of the KNOWMAK project

Understanding knowledge co-creation in key emerging areas of European research is critical for policy makers wishing to analyze impact and make strategic decisions. However, purely data-driven methods for characterising policy topics have limitations relating to the broad nature of such topics and the differences in language and topic structure between the political language and scientific and technological outputs. In this paper, we discuss the use of ontologies and semantic technologies as a means to bridge the linguistic and conceptual gap between policy questions and data sources for characterising European knowledge production. Our experience suggests that the integration between advanced techniques for language processing and expert assessment at critical junctures in the process is key for the success of this endeavour.

Bridging the food security gap: an information-led approach to connect dietary nutrition, food composition and crop production

BACKGROUND

Food security is recognized as a major global challenge, yet human food-chain systems are inherently not geared towards nutrition, with decisions on crop and cultivar choice not informed by dietary composition. Currently, food compositional tables and databases (FCT/FCDB) are the primary information sources for decisions relating to dietary intake. However, these only present single mean values representing major components. Establishment of a systematic controlled vocabulary to fill this gap requires representation of a more complex set of semantic relationships between terms used to describe nutritional composition and dietary function.

RESULTS

We carried out a survey of 11 FCT/FCDB and 177 peer-reviewed papers describing variation in nutritional composition and dietary function for food crops to identify a comprehensive set of terms to construct a controlled vocabulary. We used this information to generate a Crop Dietary Nutrition Data Framework (CDN-DF), which incorporates controlled vocabularies systematically organized into major classes representing nutritional components and dietary functions. We demonstrate the value of the CDN-DF for comparison of equivalent components between crop species or cultivars, for identifying data gaps and potential for formal meta-analysis. The CDN-DF also enabled us to explore relationships between nutritional components and the functional attributes of food.

CONCLUSION

We have generated a structured crop dietary nutrition data framework, which is generally applicable to the collation and comparison of data relevant to crop researchers, breeders, and other stakeholders, and will facilitate dialogue with nutritionists. It is currently guiding the establishment of a more robust formal ontology. © 2019 Society of Chemical Industry.

Improved ontology for eukaryotic single-exon coding sequences in biological databases

Efficient extraction of knowledge from biological data requires the development of structured vocabularies to unambiguously define biological terms. This paper proposes descriptions and definitions to disambiguate the term 'single-exon gene'. Eukaryotic Single-Exon Genes (SEGs) have been defined as genes that do not have introns in their protein coding sequences. They have been studied not only to determine their origin and evolution but also because their expression has been linked to several types of human cancer and neurological/developmental disorders and many exhibit tissue-specific transcription. Unfortunately, the term 'SEGs' is rife with ambiguity, leading to biological misinterpretations. In the classic definition, no distinction is made between SEGs that harbor introns in their untranslated regions (UTRs) versus those without. This distinction is important to make because the presence of introns in UTRs affects transcriptional regulation and post-transcriptional processing of the mRNA. In addition, recent whole-transcriptome shotgun sequencing has led to the discovery of many examples of single-exon mRNAs that arise from alternative splicing of multi-exon genes, these single-exon isoforms are being confused with SEGs despite their clearly different origin. The increasing expansion of RNA-seq datasets makes it imperative to distinguish the different SEG types before annotation errors become indelibly propagated in biological databases. This paper develops a structured vocabulary for their disambiguation, allowing a major reassessment of their evolutionary trajectories, regulation, RNA processing and transport, and provides the opportunity to improve the detection of gene associations with disorders including cancers, neurological and developmental diseases.

Ranking Medical Terms to Support Expansion of Lay Language Resources for Patient Comprehension of Electronic Health Record Notes: Adapted Distant Supervision Approach

Background

Medical terms are a major obstacle for patients to comprehend their electronic health record (EHR) notes. Clinical natural language processing (NLP) systems that link EHR terms to lay terms or definitions allow patients to easily access helpful information when reading through their EHR notes, and have shown to improve patient EHR comprehension. However, high-quality lay language resources for EHR terms are very limited in the public domain. Because expanding and curating such a resource is a costly process, it is beneficial and even necessary to identify terms important for patient EHR comprehension first.

Objective

We aimed to develop an NLP system, called adapted distant supervision (ADS), to rank candidate terms mined from EHR corpora. We will give EHR terms ranked as high by ADS a higher priority for lay language annotation—that is, creating lay definitions for these terms.

Methods

Adapted distant supervision uses distant supervision from consumer health vocabulary and transfer learning to adapt itself to solve the problem of ranking EHR terms in the target domain. We investigated 2 state-of-the-art transfer learning algorithms (ie, feature space augmentation and supervised distant supervision) and designed 5 types of learning features, including distributed word representations learned from large EHR data for ADS. For evaluating ADS, we asked domain experts to annotate 6038 candidate terms as important or nonimportant for EHR comprehension. We then randomly divided these data into the target-domain training data (1000 examples) and the evaluation data (5038 examples). We compared ADS with 2 strong baselines, including standard supervised learning, on the evaluation data.

Results

The ADS system using feature space augmentation achieved the best average precision, 0.850, on the evaluation set when using 1000 target-domain training examples. The ADS system using supervised distant supervision achieved the best average precision, 0.819, on the evaluation set when using only 100 target-domain training examples. The 2 ADS systems both performed significantly better than the baseline systems (P<.001 for all measures and all conditions). Using a rich set of learning features contributed to ADS’s performance substantially.

Conclusions

ADS can effectively rank terms mined from EHRs. Transfer learning improved ADS’s performance even with a small number of target-domain training examples. EHR terms prioritized by ADS were used to expand a lay language resource that supports patient EHR comprehension. The top 10,000 EHR terms ranked by ADS are available upon request.

Updating controlled vocabularies by analysing query logs

Purpose

– Controlled vocabularies play an important role in information retrieval. Numerous studies have shown that conceptual searches based on vocabularies are more effective than keyword searches, at least in certain contexts. Consequently, new ways must be found to improve controlled vocabularies. The purpose of this paper is to present a semi-automatic model for updating controlled vocabularies through the use of a text corpus and the analysis of query logs.

Design/methodology/approach

– An experimental development is presented in which, first, the suitability of a controlled vocabulary to a text corpus is examined. The keywords entered by users to access the text corpus are then compared with the descriptors used to index it. Finally, both the query logs and text corpus are processed to obtain a set of candidate terms to update the controlled vocabulary.

Findings

– This paper describes a model applicable both in the context of the text corpus of an online academic journal and to repositories and intranets. The model is able to: first, identify the queries that led users from a search engine to a relevant document; and second, process these queries to identify candidate terms for inclusion in a controlled vocabulary.

Research limitations/implications

– Ideally, the model should be used in controlled web environments, such as repositories, intranets or academic journals.

Social implications

– The proposed model directly improves the indexing process by facilitating the maintenance and updating of controlled vocabularies. It so doing, it helps to optimise access to information.

Originality/value

– The proposed model takes into account the perspective of users by mining queries in order to propose candidate terms for inclusion in a controlled vocabulary.

Evaluation and cross-comparison of lexical entities of biological interest (LexEBI)

MOTIVATION

Biomedical entities, their identifiers and names, are essential in the representation of biomedical facts and knowledge. In the same way, the complete set of biomedical and chemical terms, i.e. the biomedical "term space" (the "Lexeome"), forms a key resource to achieve the full integration of the scientific literature with biomedical data resources: any identified named entity can immediately be normalized to the correct database entry. This goal does not only require that we are aware of all existing terms, but would also profit from knowing all their senses and their semantic interpretation (ambiguities, nestedness).

RESULT

This study compiles a resource for lexical terms of biomedical interest in a standard format (called "LexEBI"), determines the overall number of terms, their reuse in different resources and the nestedness of terms. LexEBI comprises references for protein and gene entries and their term variants and chemical entities amongst other terms. In addition, disease terms have been identified from Medline and PubmedCentral and added to LexEBI. Our analysis demonstrates that the baseforms of terms from the different semantic types show only little polysemous use. Nonetheless, the term variants of protein and gene names (PGNs) frequently contain species mentions, which should have been avoided according to protein annotation guidelines. Furthermore, the protein and gene entities as well as the chemical entities, both do comprise enzymes leading to hierarchical polysemy, and a large portion of PGNs make reference to a chemical entity. Altogether, according to our analysis based on the Medline distribution, 401,869 unique PGNs in the documents contain a reference to 25,022 chemical entities, 3,125 disease terms or 1,576 species mentions.

CONCLUSION

LexEBI delivers the complete biomedical and chemical Lexeome in a standardized representation (http://www.ebi.ac.uk/Rebholz-srv/LexEBI/). The resource provides the disease terms as open source content, and fully interlinks terms across resources.

How to link ontologies and protein-protein interactions to literature: text-mining approaches and the BioCreative experience

There is an increasing interest in developing ontologies and controlled vocabularies to improve the efficiency and consistency of manual literature curation, to enable more formal biocuration workflow results and ultimately to improve analysis of biological data. Two ontologies that have been successfully used for this purpose are the Gene Ontology (GO) for annotating aspects of gene products and the Molecular Interaction ontology (PSI-MI) used by databases that archive protein–protein interactions. The examination of protein interactions has proven to be extremely promising for the understanding of cellular processes. Manual mapping of information from the biomedical literature to bio-ontology terms is one of the most challenging components in the curation pipeline. It requires that expert curators interpret the natural language descriptions contained in articles and infer their semantic equivalents in the ontology (controlled vocabulary). Since manual curation is a time-consuming process, there is strong motivation to implement text-mining techniques to automatically extract annotations from free text. A range of text mining strategies has been devised to assist in the automated extraction of biological data. These strategies either recognize technical terms used recurrently in the literature and propose them as candidates for inclusion in ontologies, or retrieve passages that serve as evidential support for annotating an ontology term, e.g. from the PSI-MI or GO controlled vocabularies. Here, we provide a general overview of current text-mining methods to automatically extract annotations of GO and PSI-MI ontology terms in the context of the BioCreative (Critical Assessment of Information Extraction Systems in Biology) challenge. Special emphasis is given to protein–protein interaction data and PSI-MI terms referring to interaction detection methods.

Using statistical text mining to supplement the development of an ontology

Statistical text mining was used to supplement efforts to develop a clinical vocabulary for post-traumatic stress disorder (PTSD) in the VA. A set of outpatient progress notes was collected for a cohort of 405 unique veterans with PTSD and a comparison group of 392 with other psychological conditions at one VA hospital. Two methods were employed: (1) "multi-model term scoring" used stepwise logistic regression to develop 21 separate models by varying three frequency weight and seven term weight options and (2) "iterative term refinement" which used a standard stop list followed by clinical review to eliminate non-clinical terms and terms not related to PTSD. Combined results of the two methods were reviewed by two clinicians resulting in 226 unique PTSD related terms. Results of the statistical text mining methods were compared with ongoing efforts to identify terms based on literature review, focus groups with clinicians treating PTSD and review of an existing vocabulary, lending support to the contributions of the STM analyses.

Computer-assisted update of a consumer health vocabulary through mining of social network data

Background

Consumer health vocabularies (CHVs) have been developed to aid consumer health informatics applications. This purpose is best served if the vocabulary evolves with consumers’ language.

Objective

Our objective was to create a computer assisted update (CAU) system that works with live corpora to identify new candidate terms for inclusion in the open access and collaborative (OAC) CHV.

Methods

The CAU system consisted of three main parts: a Web crawler and an HTML parser, a candidate term filter that utilizes natural language processing tools including term recognition methods, and a human review interface. In evaluation, the CAU system was applied to the health-related social network website PatientsLikeMe.com. The system’s utility was assessed by comparing the candidate term list it generated to a list of valid terms hand extracted from the text of the crawled webpages.

Results

The CAU system identified 88,994 unique terms 1- to 7-grams (“n-grams” are n consecutive words within a sentence) in 300 crawled PatientsLikeMe.com webpages. The manual review of the crawled webpages identified 651 valid terms not yet included in the OAC CHV or the Unified Medical Language System (UMLS) Metathesaurus, a collection of vocabularies amalgamated to form an ontology of medical terms, (ie, 1 valid term per 136.7 candidate n-grams). The term filter selected 774 candidate terms, of which 237 were valid terms, that is, 1 valid term among every 3 or 4 candidates reviewed.

Conclusion

The CAU system is effective for generating a list of candidate terms for human review during CHV development.

Systems level studies of mammalian metabolomes: the roles of mass spectrometry and nuclear magnetic resonance spectroscopy

The study of biological systems in a holistic manner (systems biology) is increasingly being viewed as a necessity to provide qualitative and quantitative descriptions of the emergent properties of the complete system. Systems biology performs studies focussed on the complex interactions of system components; emphasising the whole system rather than the individual parts. Many perturbations to mammalian systems (diet, disease, drugs) are multi-factorial and the study of small parts of the system is insufficient to understand the complete phenotypic changes induced. Metabolomics is one functional level tool being employed to investigate the complex interactions of metabolites with other metabolites (metabolism) but also the regulatory role metabolites provide through interaction with genes, transcripts and proteins (e.g. allosteric regulation). Technological developments are the driving force behind advances in scientific knowledge. Recent advances in the two analytical platforms of mass spectrometry (MS) and nuclear magnetic resonance (NMR) spectroscopy have driven forward the discipline of metabolomics. In this critical review, an introduction to metabolites, metabolomes, metabolomics and the role of MS and NMR spectroscopy will be provided. The applications of metabolomics in mammalian systems biology for the study of the health-disease continuum, drug efficacy and toxicity and dietary effects on mammalian health will be reviewed. The current limitations and future goals of metabolomics in systems biology will also be discussed (374 references).

EnvMine: a text-mining system for the automatic extraction of contextual information

BACKGROUND

For ecological studies, it is crucial to count on adequate descriptions of the environments and samples being studied. Such a description must be done in terms of their physicochemical characteristics, allowing a direct comparison between different environments that would be difficult to do otherwise. Also the characterization must include the precise geographical location, to make possible the study of geographical distributions and biogeographical patterns. Currently, there is no schema for annotating these environmental features, and these data have to be extracted from textual sources (published articles). So far, this had to be performed by manual inspection of the corresponding documents. To facilitate this task, we have developed EnvMine, a set of text-mining tools devoted to retrieve contextual information (physicochemical variables and geographical locations) from textual sources of any kind.

RESULTS

EnvMine is capable of retrieving the physicochemical variables cited in the text, by means of the accurate identification of their associated units of measurement. In this task, the system achieves a recall (percentage of items retrieved) of 92% with less than 1% error. Also a Bayesian classifier was tested for distinguishing parts of the text describing environmental characteristics from others dealing with, for instance, experimental settings.Regarding the identification of geographical locations, the system takes advantage of existing databases such as GeoNames to achieve 86% recall with 92% precision. The identification of a location includes also the determination of its exact coordinates (latitude and longitude), thus allowing the calculation of distance between the individual locations.

CONCLUSION

EnvMine is a very efficient method for extracting contextual information from different text sources, like published articles or web pages. This tool can help in determining the precise location and physicochemical variables of sampling sites, thus facilitating the performance of ecological analyses. EnvMine can also help in the development of standards for the annotation of environmental features.

Exploitation of ontological resources for scientific literature analysis: searching genes and related diseases

Ontological resources such as controlled vocabularies, taxonomies and ontologies from the OBO foundry are used to represent biomedical domain knowledge. The development of such resources is a time consuming task. Once they are finished they contribute to standardization of information representation, interoperability of IT solutions, literature analysis and knowledge discovery. Text mining comprises IT solutions for information retrieval (IR) and information extraction (IE). IR technology exploits ontological resources to select documents that fit best to the processed query, for example, through indexing of the literature content with concept ids or through disambiguation of terms in the query. IE solutions make use of the ontological labels to identify concepts in the text. The text passages that denote conceptual entries are then used either to annotate named entities or to relate the named entities to each other. For knowledge discovery (KD) solutions the identified concepts in the scientific literature are used to relate entities to each other, e.g. to identify gene-disease relations based on shared molecular functions.

Analysis of biological processes and diseases using text mining approaches

A number of biomedical text mining systems have been developed to extract biologically relevant information directly from the literature, complementing bioinformatics methods in the analysis of experimentally generated data. We provide a short overview of the general characteristics of natural language data, existing biomedical literature databases, and lexical resources relevant in the context of biomedical text mining. A selected number of practically useful systems are introduced together with the type of user queries supported and the results they generate. The extraction of biological relationships, such as protein-protein interactions as well as metabolic and signaling pathways using information extraction systems, will be discussed through example cases of cancer-relevant proteins. Basic strategies for detecting associations of genes to diseases together with literature mining of mutations, SNPs, and epigenetic information (methylation) are described. We provide an overview of disease-centric and gene-centric literature mining methods for linking genes to phenotypic and genotypic aspects. Moreover, we discuss recent efforts for finding biomarkers through text mining and for gene list analysis and prioritization. Some relevant issues for implementing a customized biomedical text mining system will be pointed out. To demonstrate the usefulness of literature mining for the molecular oncology domain, we implemented two cancer-related applications. The first tool consists of a literature mining system for retrieving human mutations together with supporting articles. Specific gene mutations are linked to a set of predefined cancer types. The second application consists of a text categorization system supporting breast cancer-specific literature search and document-based breast cancer gene ranking. Future trends in text mining emphasize the importance of community efforts such as the BioCreative challenge for the development and integration of multiple systems into a common platform provided by the BioCreative Metaserver.

Pathway enrichment based on text mining and its validation on carotenoid and vitamin A metabolism

Carotenoid metabolism is relevant to the prevention of various diseases. Although the main actors in this metabolic pathway are known, our understanding of the pathway is still incomplete. The information on the carotenoids is scattered in the large and growing body of scientific literature. We designed a text-mining work flow to enrich existing pathways. It has been validated on the vitamin A pathway, which is a well-studied part of the carotenoid metabolism. In this study we used the vitamin A metabolism pathway as it has been described by an expert team on carotenoid metabolism from the European network of excellence in Nutrigenomics (NuGO). This work flow uses an initial set of publications cited in a review paper (1,191 publications), enlarges this corpus with Medline abstracts (13,579 documents), and then extracts the key terminology from all relevant publications. Domain experts validated the intermediate and final results of our text-mining work flow. With our approach we were able to enrich the pathway representing vitamin A metabolism. We found 37 new and relevant terms from a total of 89,086 terms, which have been qualified for inclusion in the analyzed pathway. These 37 terms have been assessed manually and as a result 13 new terms were then added as entities to the pathway. Another 14 entities belonged to other pathways, which could form the link of these pathways with the vitamin A pathway. The remaining 10 terms were classified as biomarkers or nutrients. Automatic literature analysis improves the enrichment of pathways with entities already described in the scientific literature.

Expanded information retrieval using full-text searching

The value of full text for expanding information retrieval was examined. Two full-text databases were used: Textpresso for neuroscience and ScienceDirect. Queries representing different categories were used to search different text fields (titles, abstracts, full text and, where possible, keywords). Searching the full-text field relative to the commonly used abstracts field increases retrievals by one or more orders of magnitude, depending on the categories selected. For phenomena-type categories (e.g. blood flow, thermodynamic equilibrium, etc.), retrievals are enhanced by about an order of magnitude. For infrastructure-type categories (e.g. equipment types, sponsors, suppliers, databases, etc.), retrievals are enhanced by well over an order of magnitude, and sometimes multiple orders of magnitude. Use of combination terms along with proximity specification capability is a very powerful feature for retrieving relevant records from full-text searching, and can be useful for applications like literature-related discovery.

Reuse of terminological resources for efficient ontological engineering in Life Sciences

This paper is intended to explore how to use terminological resources for ontology engineering. Nowadays there are several biomedical ontologies describing overlapping domains, but there is not a clear correspondence between the concepts that are supposed to be equivalent or just similar. These resources are quite precious but their integration and further development are expensive. Terminologies may support the ontological development in several stages of the lifecycle of the ontology; e.g. ontology integration. In this paper we investigate the use of terminological resources during the ontology lifecycle. We claim that the proper creation and use of a shared thesaurus is a cornerstone for the successful application of the Semantic Web technology within life sciences. Moreover, we have applied our approach to a real scenario, the Health-e-Child (HeC) project, and we have evaluated the impact of filtering and re-organizing several resources. As a result, we have created a reference thesaurus for this project, named HeCTh.

Techniques for integrating -omics data

The challenge for -omics research is to tackle the problem of fragmentation of knowledge by integrating several sources of heterogeneous information into a coherent entity. It is widely recognized that successful data integration is one of the keys to improve productivity for stored data. Through proper data integration tools and algorithms, researchers may correlate relationships that enable them to make better and faster decisions. The need for data integration is essential for present -omics community, because -omics data is currently spread world wide in wide variety of formats. These formats can be integrated and migrated across platforms through different techniques and one of the important techniques often used is XML. XML is used to provide a document markup language that is easier to learn, retrieve, store and transmit. It is semantically richer than HTML. Here, we describe bio warehousing, database federation, controlled vocabularies and highlighting the XML application to store, migrate and validate -omics data.

A consensus yeast metabolic network reconstruction obtained from a community approach to systems biology

Genomic data allow the large-scale manual or semi-automated assembly of metabolic network reconstructions, which provide highly curated organism-specific knowledge bases. Although several genome-scale network reconstructions describe Saccharomyces cerevisiae metabolism, they differ in scope and content, and use different terminologies to describe the same chemical entities. This makes comparisons between them difficult and underscores the desirability of a consolidated metabolic network that collects and formalizes the 'community knowledge' of yeast metabolism. We describe how we have produced a consensus metabolic network reconstruction for S. cerevisiae. In drafting it, we placed special emphasis on referencing molecules to persistent databases or using database-independent forms, such as SMILES or InChI strings, as this permits their chemical structure to be represented unambiguously and in a manner that permits automated reasoning. The reconstruction is readily available via a publicly accessible database and in the Systems Biology Markup Language (http://www.comp-sys-bio.org/yeastnet). It can be maintained as a resource that serves as a common denominator for studying the systems biology of yeast. Similar strategies should benefit communities studying genome-scale metabolic networks of other organisms.