Full-text Biomedical Articles Research Articles

NILINKER: Attention-based approach to NIL Entity Linking

The existence of unlinkable (NIL) entities is a major hurdle affecting the performance of Named Entity Linking approaches, and, consequently, the performance of downstream models that depend on them. Existing approaches to deal with NIL entities focus mainly on clustering and prediction and are limited to general entities. However, other domains, such as the biomedical sciences, are also prone to the existence of NIL entities, given the growing nature of scientific literature. We propose NILINKER, a model that includes a candidate retrieval module for biomedical NIL entities and a neural network that leverages the attention mechanism to find the top-k relevant concepts from target Knowledge Bases (MEDIC, CTD-Chemicals, ChEBI, HP, CTD-Anatomy and Gene Ontology-Biological Process) that may partially represent a given NIL entity. We also make available a new evaluation dataset designated by EvaNIL, suitable for training and evaluating models focusing on the NIL entity linking task. This dataset contains 846,165 documents (abstracts and full-text biomedical articles), including 1,071,776 annotations, distributed by six different partitions: EvaNIL-MEDIC, EvaNIL-CTD-Chemicals, EvaNIL-ChEBI, EvaNIL-HP, EvaNIL-CTD-Anatomy and EvaNIL-Gene Ontology-Biological Process. NILINKER was integrated into a graph-based Named Entity Linking model (REEL) and the results of the experiments show that this approach is able to increase the performance of the Named Entity Linking model.

PubTator central: automated concept annotation for biomedical full text articles.

PubTator Central (https://www.ncbi.nlm.nih.gov/research/pubtator/) is a web service for viewing and retrieving bioconcept annotations in full text biomedical articles. PubTator Central (PTC) provides automated annotations from state-of-the-art text mining systems for genes/proteins, genetic variants, diseases, chemicals, species and cell lines, all available for immediate download. PTC annotates PubMed (29 million abstracts) and the PMC Text Mining subset (3 million full text articles). The new PTC web interface allows users to build full text document collections and visualize concept annotations in each document. Annotations are downloadable in multiple formats (XML, JSON and tab delimited) via the online interface, a RESTful web service and bulk FTP. Improved concept identification systems and a new disambiguation module based on deep learning increase annotation accuracy, and the new server-side architecture is significantly faster. PTC is synchronized with PubMed and PubMed Central, with new articles added daily. The original PubTator service has served annotated abstracts for ∼300 million requests, enabling third-party research in use cases such as biocuration support, gene prioritization, genetic disease analysis, and literature-based knowledge discovery. We demonstrate the full text results in PTC significantly increase biomedical concept coverage and anticipate this expansion will both enhance existing downstream applications and enable new use cases.

PMC text mining subset in BioC: about three million full-text articles and growing.

Interest in text mining full-text biomedical research articles is growing. To facilitate automated processing of nearly 3 million full-text articles (in PubMed Central® Open Access and Author Manuscript subsets) and to improve interoperability, we convert these articles to BioC, a community-driven simple data structure in either XML or JavaScript Object Notation format for conveniently sharing text and annotations. The resultant articles can be downloaded via both File Transfer Protocol for bulk access and a Web API for updates or a more focused collection. Since the availability of the Web API in 2017, our BioC collection has been widely used by the research community. https://www.ncbi.nlm.nih.gov/research/bionlp/APIs/BioC-PMC/.

Neural Relevance Model Using Similarities with Elite Documents for Effective Clinical Decision Support

Clinical Decision Support (CDS) is regarded as an information retrieval (IR) task, where medical records are used to retrieve full-text biomedical articles to satisfy the information needs from physicians, aiming at better medical solutions. Recent attempts have introduced the advances of deep learning by employing neural IR methods for CDS, where, however, only the document-query relationship is modelled, resulting in non-optimal results in that a medical record can barely reflect the information included in a relevant biomedical article which is usually much longer. Therefore, in addition to the document-query relationship, we propose a neural relevance model (DNRM) based on similarities to a set of elite documents, addressing the information mismatch by utilising the content of relevant articles as a complete picture of the given medical record. Specifically, our DNRM model evaluates a document relative to a query and to several pseudo relevant documents for the query at the same time, capturing the interactions from both parts with a feed forward network. Experimental results on the standard Text REtrieval Conference (TREC) CDS track dataset confirm the superior performance of the proposed DNRM model.

Neural relevance model using similarities with elite documents for effective clinical decision support

Clinical Decision Support (CDS) is regarded as an information retrieval (IR) task, where medical records are used to retrieve full-text biomedical articles to satisfy the information needs from physicians, aiming at better medical solutions. Recent attempts have introduced the advances of deep learning by employing neural IR methods for CDS, where, however, only the document-query relationship is modelled, resulting in non-optimal results in that a medical record can barely reflect the information included in a relevant biomedical article which is usually much longer. Therefore, in addition to the document-query relationship, we propose a neural relevance model (DNRM) based on similarities to a set of elite documents, addressing the information mismatch by utilising the content of relevant articles as a complete picture of the given medical record. Specifically, our DNRM model evaluates a document relative to a query and to several pseudo relevant documents for the query at the same time, capturing the interactions from both parts with a feed forward network. Experimental results on the standard Text REtrieval Conference (TREC) CDS track dataset confirm the superior performance of the proposed DNRM model.

DeTEXT: A Database for Evaluating Text Extraction from Biomedical Literature Figures.

Hundreds of millions of figures are available in biomedical literature, representing important biomedical experimental evidence. Since text is a rich source of information in figures, automatically extracting such text may assist in the task of mining figure information. A high-quality ground truth standard can greatly facilitate the development of an automated system. This article describes DeTEXT: A database for evaluating text extraction from biomedical literature figures. It is the first publicly available, human-annotated, high quality, and large-scale figure-text dataset with 288 full-text articles, 500 biomedical figures, and 9308 text regions. This article describes how figures were selected from open-access full-text biomedical articles and how annotation guidelines and annotation tools were developed. We also discuss the inter-annotator agreement and the reliability of the annotations. We summarize the statistics of the DeTEXT data and make available evaluation protocols for DeTEXT. Finally we lay out challenges we observed in the automated detection and recognition of figure text and discuss research directions in this area. DeTEXT is publicly available for downloading at http://prir.ustb.edu.cn/DeTEXT/.

Database citation in supplementary data linked to Europe PubMed Central full text biomedical articles.

BackgroundIn this study, we present an analysis of data citation practices in full text research articles and their corresponding supplementary data files, made available in the Open Access set of articles from Europe PubMed Central. Our aim is to investigate whether supplementary data files should be considered as a source of information for integrating the literature with biomolecular databases.ResultsUsing text-mining methods to identify and extract a variety of core biological database accession numbers, we found that the supplemental data files contain many more database citations than the body of the article, and that those citations often take the form of a relatively small number of articles citing large collections of accession numbers in text-based files. Moreover, citation of value-added databases derived from submission databases (such as Pfam, UniProt or Ensembl) is common, demonstrating the reuse of these resources as datasets in themselves. All the database accession numbers extracted from the supplementary data are publicly accessible from http://dx.doi.org/10.5281/zenodo.11771.ConclusionsOur study suggests that supplementary data should be considered when linking articles with data, in curation pipelines, and in information retrieval tasks in order to make full use of the entire research article. These observations highlight the need to improve the management of supplemental data in general, in order to make this information more discoverable and useful.

Tagtog: interactive and text-mining-assisted annotation of gene mentions in PLOS full-text articles

The breadth and depth of biomedical literature are increasing year upon year. To keep abreast of these increases, FlyBase, a database for Drosophila genomic and genetic information, is constantly exploring new ways to mine the published literature to increase the efficiency and accuracy of manual curation and to automate some aspects, such as triaging and entity extraction. Toward this end, we present the ‘tagtog’ system, a web-based annotation framework that can be used to mark up biological entities (such as genes) and concepts (such as Gene Ontology terms) in full-text articles. tagtog leverages manual user annotation in combination with automatic machine-learned annotation to provide accurate identification of gene symbols and gene names. As part of the BioCreative IV Interactive Annotation Task, FlyBase has used tagtog to identify and extract mentions of Drosophila melanogaster gene symbols and names in full-text biomedical articles from the PLOS stable of journals. We show here the results of three experiments with different sized corpora and assess gene recognition performance and curation speed. We conclude that tagtog-named entity recognition improves with a larger corpus and that tagtog-assisted curation is quicker than manual curation.Database URL: www.tagtog.net, www.flybase.org

CiteGraph: a citation network system for MEDLINE articles and analysis.

This paper details the development and implementation of CiteGraph, a system for constructing large-scale citation and co-authorship networks from full-text biomedical articles. CiteGraph represents articles and authors by uniquely identified nodes, and connects those nodes through citation and co-authorship relations. CiteGraph network encompasses over 1.65 million full-text articles and 6.35 million citations by 1.37 million unique authors from the Elsevier full-text articles. Our evaluation shows 98% 99% F1-score for mapping a citation to the corresponding article and identifying MEDLINE articles. We further analyzed the characteristics of CiteGraph and found that they are consistent with assumptions made using small-scale bibliometric analysis. We also developed several novel network-based methods for analyzing publication, citation and collaboration patterns. This is the first work to develop a completely automated system for the creation of a large-scale citation network in the biomedical domain, and also to introduce novel findings in researcher publication histories. CiteGraph can be a useful resource to both the biomedical community, and bibliometric research.

PubMed Central: An Essential Resource for Information Professionals and Researchers

Objective – A review of the journals containing research listed in PubMed Central (PMC), but not selected for inclusion in the National Library of Medicine (NLM) collection. The authors identified reasons why journals had not been included in the collection and if any met the NLM selection criteria and were appropriate for inclusion.
 
 Design – Descriptive study.
 
 Setting – National Library of Medicine, United States.
 
 Subjects – 571 journals that were not included in the NLM collection but had research articles in PMC.
 Methods – In October 2009, a report was produced from the NLM library system listing journals tagged as having articles in PMC and not being in the NLM collection. Information was gathered on the journals identified and these were checked against the Collection Development Manual of the NLM and the NLM checklist used for selecting electronic journals. The reason for non-selection of the journal was recorded and the subject category, according to the Library of Congress Classification, was noted.
 
 Recorded reasons why journals were not selected:
 
 • Less than 15% of articles were within scope of NLM collection
 • Not enough articles published
 • Coverage (lacking original research or not for a scholarly audience)
 • Insufficient information to determine reason
 
 For journals where the criteria seemed to be met, the decision on selection to the NLM collection was reviewed.
 
 Main Results – The authors identified 571 journals that had articles in PMC but did not meet the criteria for inclusion in the NLM journal collection. The majority of these journals (73%) were outside the NLM scope and a further 10% had not published a sufficient number of articles to be considered. A further 3% were assessed as not intended for a scholarly audience or lacked original research and another 3% could not be reviewed due to lack of information available. There were 65 journals (11%) that were referred for further review as the selection criteria seemed to be met and 11 of these journals have subsequently been added to the NLM collection. This is in relation to 482 new print and electronic journals in total that were added to the NLM collection in 2009.
 
 However, only 369 of the 571 journals (65%) had one or more articles included in PMC; of these, 238 had one article and 33 had more than four articles in the archive. The reason that some journals had no articles in PMC at the time of this review was due to the time it takes to process new articles and embargos set by the publishers that restrict immediate listing on open access databases such as PMC. A number of these journals may also be new and may not have had a sufficient number of articles or enough information available to be able to include them in the NLM collection. To add context, the authors state that PMC contained over 115,000 NIH-funded articles by the end of November 2010.
 
 The subject areas these non-selected journals were classified under included Engineering (15%); Medicine (14%); Mathematics (10%); Chemistry (10%); and Computer Science (9%). Library Science was assigned to 2% of the journals. The Medicine journals were more likely than those in the other subject areas to be new journals without sufficient articles to be included in the NLM collection.
 
 Conclusion – When the journal title is out of the scope of the NLM collection, an individual article in that journal can still be included in PMC. This provides a solution to the problem of how to collect biomedical research that is not published in biomedical journals. This may be more important in the future as the field becomes more interdisciplinary. This also provides a useful resource for libraries and researchers searching for full-text biomedical articles.
 
 The authors conclude that analyzing the articles from the journals not selected for inclusion in the NLM collection will provide helpful information about the types of biomedical research being published in non-biomedical journals. This will highlight particular areas the NLM should pay attention to in the future.

Using cited references to improve the retrieval of related biomedical documents

BackgroundA popular query from scientists reading a biomedical abstract is to search for topic-related documents in bibliographic databases. Such a query is challenging because the amount of information attached to a single abstract is little, whereas classification-based retrieval algorithms are optimally trained with large sets of relevant documents. As a solution to this problem, we propose a query expansion method that extends the information related to a manuscript using its cited references.ResultsData on cited references and text sections in 249,108 full-text biomedical articles was extracted from the Open Access subset of the PubMed Central® database (PMC-OA). Of the five standard sections of a scientific article, the Introduction and Discussion sections contained most of the citations (mean = 10.2 and 9.9 citations, respectively). A large proportion of articles (98.4%) and their cited references (79.5%) were indexed in the PubMed® database.Using the MedlineRanker abstract classification tool, cited references allowed accurate retrieval of the citing document in a test set of 10,000 documents and also of documents related to six biomedical topics defined by particular MeSH® terms from the entire PMC-OA (p-value<0.01).Classification performance was sensitive to the topic and also to the text sections from which the references were selected. Classifiers trained on the baseline (i.e., only text from the query document and not from the references) were outperformed in almost all the cases. Best performance was often obtained when using all cited references, though using the references from Introduction and Discussion sections led to similarly good results. This query expansion method performed significantly better than pseudo relevance feedback in 4 out of 6 topics.ConclusionsThe retrieval of documents related to a single document can be significantly improved by using the references cited by this document (p-value<0.01). Using references from Introduction and Discussion performs almost as well as using all references, which might be useful for methods that require reduced datasets due to computational limitations. Cited references from particular sections might not be appropriate for all topics. Our method could be a better alternative to pseudo relevance feedback though it is limited by full text availability.

BioCause: Annotating and analysing causality in the biomedical domain

BackgroundBiomedical corpora annotated with event-level information represent an important resource for domain-specific information extraction (IE) systems. However, bio-event annotation alone cannot cater for all the needs of biologists. Unlike work on relation and event extraction, most of which focusses on specific events and named entities, we aim to build a comprehensive resource, covering all statements of causal association present in discourse. Causality lies at the heart of biomedical knowledge, such as diagnosis, pathology or systems biology, and, thus, automatic causality recognition can greatly reduce the human workload by suggesting possible causal connections and aiding in the curation of pathway models. A biomedical text corpus annotated with such relations is, hence, crucial for developing and evaluating biomedical text mining.ResultsWe have defined an annotation scheme for enriching biomedical domain corpora with causality relations. This schema has subsequently been used to annotate 851 causal relations to form BioCause, a collection of 19 open-access full-text biomedical journal articles belonging to the subdomain of infectious diseases. These documents have been pre-annotated with named entity and event information in the context of previous shared tasks. We report an inter-annotator agreement rate of over 60% for triggers and of over 80% for arguments using an exact match constraint. These increase significantly using a relaxed match setting. Moreover, we analyse and describe the causality relations in BioCause from various points of view. This information can then be leveraged for the training of automatic causality detection systems.ConclusionAugmenting named entity and event annotations with information about causal discourse relations could benefit the development of more sophisticated IE systems. These will further influence the development of multiple tasks, such as enabling textual inference to detect entailments, discovering new facts and providing new hypotheses for experimental work.

Automatic discourse connective detection in biomedical text

Relation extraction in biomedical text mining systems has largely focused on identifying clause-level relations, but increasing sophistication demands the recognition of relations at discourse level. A first step in identifying discourse relations involves the detection of discourse connectives: words or phrases used in text to express discourse relations. In this study supervised machine-learning approaches were developed and evaluated for automatically identifying discourse connectives in biomedical text. Two supervised machine-learning models (support vector machines and conditional random fields) were explored for identifying discourse connectives in biomedical literature. In-domain supervised machine-learning classifiers were trained on the Biomedical Discourse Relation Bank, an annotated corpus of discourse relations over 24 full-text biomedical articles (~112,000 word tokens), a subset of the GENIA corpus. Novel domain adaptation techniques were also explored to leverage the larger open-domain Penn Discourse Treebank (~1 million word tokens). The models were evaluated using the standard evaluation metrics of precision, recall and F1 scores. Supervised machine-learning approaches can automatically identify discourse connectives in biomedical text, and the novel domain adaptation techniques yielded the best performance: 0.761 F1 score. A demonstration version of the fully implemented classifier BioConn is available at: http://bioconn.askhermes.org.

BioLemmatizer: a lemmatization tool for morphological processing of biomedical text.

BackgroundThe wide variety of morphological variants of domain-specific technical terms contributes to the complexity of performing natural language processing of the scientific literature related to molecular biology. For morphological analysis of these texts, lemmatization has been actively applied in the recent biomedical research.ResultsIn this work, we developed a domain-specific lemmatization tool, BioLemmatizer, for the morphological analysis of biomedical literature. The tool focuses on the inflectional morphology of English and is based on the general English lemmatization tool MorphAdorner. The BioLemmatizer is further tailored to the biological domain through incorporation of several published lexical resources. It retrieves lemmas based on the use of a word lexicon, and defines a set of rules that transform a word to a lemma if it is not encountered in the lexicon. An innovative aspect of the BioLemmatizer is the use of a hierarchical strategy for searching the lexicon, which enables the discovery of the correct lemma even if the input Part-of-Speech information is inaccurate. The BioLemmatizer achieves an accuracy of 97.5% in lemmatizing an evaluation set prepared from the CRAFT corpus, a collection of full-text biomedical articles, and an accuracy of 97.6% on the LLL05 corpus. The contribution of the BioLemmatizer to accuracy improvement of a practical information extraction task is further demonstrated when it is used as a component in a biomedical text mining system.ConclusionsThe BioLemmatizer outperforms other tools when compared with eight existing lemmatizers. The BioLemmatizer is released as an open source software and can be downloaded from http://biolemmatizer.sourceforge.net.

BioN∅T: A searchable database of biomedical negated sentences

BackgroundNegated biomedical events are often ignored by text-mining applications; however, such events carry scientific significance. We report on the development of BioN∅T, a database of negated sentences that can be used to extract such negated events.DescriptionCurrently BioN∅T incorporates ≈32 million negated sentences, extracted from over 336 million biomedical sentences from three resources: ≈2 million full-text biomedical articles in Elsevier and the PubMed Central, as well as ≈20 million abstracts in PubMed. We evaluated BioN∅T on three important genetic disorders: autism, Alzheimer's disease and Parkinson's disease, and found that BioN∅T is able to capture negated events that may be ignored by experts.ConclusionsThe BioN∅T database can be a useful resource for biomedical researchers. BioN∅T is freely available at http://bionot.askhermes.org/. In future work, we will develop semantic web related technologies to enrich BioN∅T.

The Health Internetwork Access to Research Initiative (HINARI) in eligible American countries: Benefits, challenges and relationship to Internet use

The Health Internetwork Access to Research Initiative (HINARI) aims to reduce financial and legal barriers to scholarship by providing Internet access to full text biomedical and health research articles for scholars in economically developing countries. In this study citation data was used to evaluate if HINARI journals have had greater use since the initiation of the program in eligible American countries. Also considered was if a relationship exists between the use of HINARI journals and Internet user statistics. While an increase of journal use is apparent in two of three sub-regions (Caribbean America and Central America), only one of three sub-regions (South America) suggests a correlation between Internet use and HINARI citation frequency. The benefits, challenges and future considerations for HINARI are discussed, as they pertain to scholars and program administrators.

The biomedical discourse relation bank

BackgroundIdentification of discourse relations, such as causal and contrastive relations, between situations mentioned in text is an important task for biomedical text-mining. A biomedical text corpus annotated with discourse relations would be very useful for developing and evaluating methods for biomedical discourse processing. However, little effort has been made to develop such an annotated resource.ResultsWe have developed the Biomedical Discourse Relation Bank (BioDRB), in which we have annotated explicit and implicit discourse relations in 24 open-access full-text biomedical articles from the GENIA corpus. Guidelines for the annotation were adapted from the Penn Discourse TreeBank (PDTB), which has discourse relations annotated over open-domain news articles. We introduced new conventions and modifications to the sense classification. We report reliable inter-annotator agreement of over 80% for all sub-tasks. Experiments for identifying the sense of explicit discourse connectives show the connective itself as a highly reliable indicator for coarse sense classification (accuracy 90.9% and F1 score 0.89). These results are comparable to results obtained with the same classifier on the PDTB data. With more refined sense classification, there is degradation in performance (accuracy 69.2% and F1 score 0.28), mainly due to sparsity in the data. The size of the corpus was found to be sufficient for identifying the sense of explicit connectives, with classifier performance stabilizing at about 1900 training instances. Finally, the classifier performs poorly when trained on PDTB and tested on BioDRB (accuracy 54.5% and F1 score 0.57).ConclusionOur work shows that discourse relations can be reliably annotated in biomedical text. Coarse sense disambiguation of explicit connectives can be done with high reliability by using just the connective as a feature, but more refined sense classification requires either richer features or more annotated data. The poor performance of a classifier trained in the open domain and tested in the biomedical domain suggests significant differences in the semantic usage of connectives across these domains, and provides robust evidence for a biomedical sublanguage for discourse and the need to develop a specialized biomedical discourse annotated corpus. The results of our cross-domain experiments are consistent with related work on identifying connectives in BioDRB.

Collective classification of textual documents by guided self-organization in T-Cell cross-regulation dynamics

We present and study an agent-based model of T-Cell cross-regulation in the adaptive immune system, which we apply to binary classification. Our method expands an existing analytical model of T-cell cross-regulation (Carneiro et al. in Immunol Rev 216(1):48-68, 2007) that was used to study the self-organizing dynamics of a single population of T-Cells in interaction with an idealized antigen presenting cell capable of presenting a single antigen. With agent-based modeling we are able to study the self-organizing dynamics of multiple populations of distinct T-cells which interact via antigen presenting cells that present hundreds of distinct antigens. Moreover, we show that such self-organizing dynamics can be guided to produce an effective binary classification of antigens, which is competitive with existing machine learning methods when applied to biomedical text classification. More specifically, here we test our model on a dataset of publicly available full-text biomedical articles provided by the BioCreative challenge (Krallinger in The biocreative ii. 5 challenge overview, p 19, 2009). We study the robustness of our model's parameter configurations, and show that it leads to encouraging results comparable to state-of-the-art classifiers. Our results help us understand both T-cell cross-regulation as a general principle of guided self-organization, as well as its applicability to document classification. Therefore, we show that our bio-inspired algorithm is a promising novel method for biomedical article classification and for binary document classification in general.

Desiderata for ontologies to be used in semantic annotation of biomedical documents

A wealth of knowledge valuable to the translational research scientist is contained within the vast biomedical literature, but this knowledge is typically in the form of natural language. Sophisticated natural-language-processing systems are needed to translate text into unambiguous formal representations grounded in high-quality consensus ontologies, and these systems in turn rely on gold-standard corpora of annotated documents for training and testing. To this end, we are constructing the Colorado Richly Annotated Full-Text (CRAFT) Corpus, a collection of 97 full-text biomedical journal articles that are being manually annotated with the entire sets of terms from select vocabularies, predominantly from the Open Biomedical Ontologies (OBO) library. Our efforts in building this corpus has illuminated infelicities of these ontologies with respect to the semantic annotation of biomedical documents, and we propose desiderata whose implementation could substantially improve their utility in this task; these include the integration of overlapping terms across OBOs, the resolution of OBO-specific ambiguities, the integration of the BFO with the OBOs and the use of mid-level ontologies, the inclusion of noncanonical instances, and the expansion of relations and realizable entities.

Beyond genes, proteins, and abstracts: Identifying scientific claims from full-text biomedical articles

Massive increases in electronically available text have spurred a variety of natural language processing methods to automatically identify relationships from text; however, existing annotated collections comprise only bioinformatics (gene–protein) or clinical informatics (treatment–disease) relationships. This paper introduces the Claim Framework that reflects how authors across biomedical spectrum communicate findings in empirical studies. The Framework captures different levels of evidence by differentiating between explicit and implicit claims, and by capturing under-specified claims such as correlations, comparisons, and observations. The results from 29 full-text articles show that authors report fewer than 7.84% of scientific claims in an abstract, thus revealing the urgent need for text mining systems to consider the full-text of an article rather than just the abstract. The results also show that authors typically report explicit claims (77.12%) rather than an observations (9.23%), correlations (5.39%), comparisons (5.11%) or implicit claims (2.7%). Informed by the initial manual annotations, we introduce an automated approach that uses syntax and semantics to identify explicit claims automatically and measure the degree to which each feature contributes to the overall precision and recall. Results show that a combination of semantics and syntax is required to achieve the best system performance.