Search

Molecular biology has become heavily dependent on biological knowledge encoded in expert curated biological databases. As the volume of biological literature increases, biocurators need help in keeping up with the literature; (semi-) automated aids for biocuration would seem to be an ideal application for natural language processing and text mining. However, to date, there have been few documented successes for improving biocuration throughput using text mining. Our initial investigations took place for the workshop on ‘Text Mining for the BioCuration Workflow’ at the third International Biocuration Conference (Berlin, 2009). We interviewed biocurators to obtain workflows from eight biological databases. This initial study revealed high-level commonalities, including (i) selection of documents for curation; (ii) indexing of documents with biologically relevant entities (e.g. genes); and (iii) detailed curation of specific relations (e.g. interactions); however, the detailed workflows also showed many variabilities. Following the workshop, we conducted a survey of biocurators. The survey identified biocurator priorities, including the handling of full text indexed with biological entities and support for the identification and prioritization of documents for curation. It also indicated that two-thirds of the biocuration teams had experimented with text mining and almost half were using text mining at that time. Analysis of our interviews and survey provide a set of requirements for the integration of text mining into the biocuration workflow. These can guide the identification of common needs across curated databases and encourage joint experimentation involving biocurators, text mining developers and the larger biomedical research community. [ABSTRACT FROM AUTHOR]

"P-hacking" is the repeated analysis of data until a statistically significant result is achieved. We show that p-hacking can also occur during data generation, sometimes unintentionally. We use the type-token ratio to demonstrate that differences in the definitions of "type" and "token" can produce significantly different results. Since these terms are rarely defined in the biomedical literature, the result is an inability to meaningfully interpret the body of literature that makes use of this measure.

Despite considerable recent attention to problems with reproducibility of scientific research, there is a striking lack of agreement about the definition of the term. That is a problem, because the lack of a consensus definition makes it difficult to compare studies of reproducibility, and thus to have even a broad overview of the state of the issue in natural language processing. This paper proposes an ontology of reproducibility in that field. Its goal is to enhance both future research and communication about the topic, and retrospective meta-analyses. We show that three dimensions of reproducibility, corresponding to three kinds of claims in natural language processing papers, can account for a variety of types of research reports. These dimensions are reproducibility of a conclusion , of a finding , and of a value. Three biomedical natural language processing papers by the authors of this paper are analyzed with respect to these dimensions.

Most natural language processing applications exhibit a trade-off between precision and recall. In some use cases for natural language processing, there are reasons to prefer to tilt that trade-off toward high precision. Relying on the Zipfian distribution of false positive results, we describe a strategy for increasing precision, using a variety of both pre-processing and post-processing methods. They draw on both knowledge-based and frequentist approaches to modeling language. Based on an existing high-performance biomedical concept recognition pipeline and a previously published manually annotated corpus, we apply this hybrid rationalist/empiricist strategy to concept normalization for eight different ontologies. Which approaches did and did not improve precision varied widely between the ontologies.

Prior knowledge of the distributional characteristics of linguistic phenomena can be useful for a variety of language processing tasks. This paper describes the distribution of negation in two types of biomedical texts: scientific journal articles and progress notes. Two types of negation are examined: explicit negation at the syntactic level and affixal negation at the sub-word level. The data show that the distribution of negation is significantly different in the two document types, with explicit negation more frequent in the clinical documents than in the scientific publications and affixal negation more frequent in the journal articles at the type level and token levels. All code is available on GitHub https://github.com/KevinBretonnelCohen/NegationDistribution .

This paper reports on Task 2 of the 2016 CLEF eHealth evaluation lab which extended the previous information extraction tasks of ShARe/CLEF eHealth evaluation labs. The task continued with named entity recognition and normalization in French narratives, as offered in CLEF eHealth 2015. Named entity recognition involved ten types of entities including disorders that were defined according to Semantic Groups in the Unified Medical Language System ® (UMLS ® ), which was also used for normalizing the entities. In addition, we introduced a large-scale classification task in French death certificates, which consisted of extracting causes of death as coded in the International Classification of Diseases, tenth revision (ICD10). Participant systems were evaluated against a blind reference standard of 832 titles of scientific articles indexed in MEDLINE, 4 drug monographs published by the European Medicines Agency (EMEA) and 27,850 death certificates using Precision, Recall and F-measure. In total, seven teams participated, including five in the entity recognition and normalization task, and five in the death certificate coding task. Three teams submitted their systems to our newly offered reproducibility track. For entity recognition, the highest performance was achieved on the EMEA corpus, with an overall F-measure of 0.702 for plain entities recognition and 0.529 for normalized entity recognition. For entity normalization, the highest performance was achieved on the MEDLINE corpus, with an overall F-measure of 0.552. For death certificate coding, the highest performance was 0.848 F-measure.

Ethical issues reported with paid crowdsourcing include unfairly low wages. It is assumed that such issues are under the control of the task requester. Can one control the amount that a worker earns by controlling the amount that one pays? 412 linguistic data development tasks were submitted to Amazon Mechanical Turk. The pay per HIT was manipulated through a range of values. We examined the relationship between the pay that is offered per HIT and the effective pay rate. There is no such relationship. Paying more per HIT does not cause workers to earn more: the higher the pay per HIT, the more time workers spend on them ( R = 0.92). So, the effective hourly rate stays roughly the same. The finding has clear implications for language resource builders who want to behave ethically: other means must be found in order to compensate workers fairly. The findings of this paper should not be taken as an endorsement of unfairly low pay rates for crowdsourcing workers. Rather, the intention is to point out that additional measures, such as pre-calculating and communicating to the workers an average hourly, rather than per-task, rate must be found in order to ensure an ethical rate of pay.

This paper reports SuperCAT, a corpus analysis toolkit. It is a radical extension of SubCAT, the Sublanguage Corpus Analysis Toolkit, from sublanguage analysis to corpus analysis in general. The idea behind SuperCAT is that representative corpora have no tendency towards closure-that is, they tend towards infinity. In contrast, non-representative corpora have a tendency towards closure-roughly, finiteness. SuperCAT focuses on general techniques for the quantitative description of the characteristics of any corpus (or other language sample), particularly concerning the characteristics of lexical distributions. Additionally, SuperCAT features a complete re-engineering of the previous SubCAT architecture.

There is currently a crisis in science related to highly publicized failures to reproduce large numbers of published studies. The current work proposes, by way of case studies, a methodology for moving the study of reproducibility in computational work to a full stage beyond that of earlier work. Specifically, it presents a case study in attempting to reproduce the reports of two R libraries for doing text mining of the PubMed/MEDLINE repository of scientific publications. The main findings are that a rational paradigm for reproduction of natural language processing papers can be established; the advertised functionality was difficult, but not impossible, to reproduce; and reproducibility studies can produce additional insights into the functioning of the published system. Additionally, the work on reproducibility lead to the production of novel user-centered documentation that has been accessed 260 times since its publication-an average of once a day per library.

Sublanguages are varieties of language that form "subsets" of the general language, typically exhibiting particular types of lexical, semantic, and other restrictions and deviance. SubCAT, the Sublanguage Corpus Analysis Toolkit, assesses the representativeness and closure properties of corpora to analyze the extent to which they are either sublanguages, or representative samples of the general language. The current version of SubCAT contains scripts and applications for assessing lexical closure, morphological closure, sentence type closure, over-represented words, and syntactic deviance. Its operation is illustrated with three case studies concerning scientific journal articles, patents, and clinical records. Materials from two language families are analyzed-English (Germanic), and Bulgarian (Slavic). The software is available at sublanguage.sourceforge.net under a liberal Open Source license.

The application of semantic technologies to the integration of biological data and the interoperability of bioinformatics analysis and visualization tools has been the common theme of a series of annual BioHackathons hosted in Japan for the past five years. Here we provide a review of the activities and outcomes from the BioHackathons held in 2011 in Kyoto and 2012 in Toyama. In order to efficiently implement semantic technologies in the life sciences, participants formed various sub-groups and worked on the following topics: Resource Description Framework (RDF) models for specific domains, text mining of the literature, ontology development, essential metadata for biological databases, platforms to enable efficient Semantic Web technology development and interoperability, and the development of applications for Semantic Web data. In this review, we briefly introduce the themes covered by these sub-groups. The observations made, conclusions drawn, and software development projects that emerged from these activities are discussed.

Identifying genetic variants that affect drug response or play a role in disease is an important task for clinicians and researchers. Before individual variants can be explored efficiently for effect on drug response or disease relationships, specific candidate genes must be identified. While many methods rank candidate genes through the use of sequence features and network topology, only a few exploit the information contained in the biomedical literature. In this work, we train and test a classifier on known pharmacogenes from PharmGKB and present a classifier that predicts pharmacogenes on a genome-wide scale using only Gene Ontology annotations and simple features mined from the biomedical literature. Performance of F=0.86, AUC=0.860 is achieved. The top 10 predicted genes are analyzed. Additionally, a set of enriched pharmacogenic Gene Ontology concepts is produced.

SPARQL queries have become the standard for querying linked open data knowledge bases, but SPARQL query construction can be challenging and time-consuming even for experts. SPARQL query generation from natural language questions is an attractive modality for interfacing with LOD. However, how to evaluate SPARQL query generation from natural language questions is a mostly open research question. This paper presents some issues that arise in SPARQL query generation from natural language, a test suite for evaluating performance with respect to these issues, and a case study in evaluating a system for SPARQL query generation from natural language questions.

The goal of this work was to establish a reasonable baseline for research in patient cohort retrieval from clinical free text. Much recent work has used Lucene for this purpose. Our approach was to use MetaMap alone. We found that although many TREC 2011 Electronic Medical Records track participants found it difficult to beat a Lucene baseline, our MetaMap-based baseline did outperform a number of Lucene runs. We propose that MetaMap is a more valid baseline than Lucene, providing essential concept extraction, and that failure to make use of this industry-standard tool results in an unfairly low baseline for evaluation of system outputs.

The contents of parentheses in biomedical text have many potential uses in text mining applications. However, making use of them requires the ability to determine what class of contents they are. A system that automatically classifies parenthesized text into one of 20 categories is presented and evaluated here. It performs at a micro-averaged accuracy of 68% and a macro-averaged accuracy of 60% on an annotated corpus. The application is available as a Java class and as a Perl module.

We introduce a system developed for the BioCreative II.5 community evaluation of information extraction of proteins and protein interactions. The paper focuses primarily on the gene normalization task of recognizing protein mentions in text and mapping them to the appropriate database identifiers based on contextual clues. We outline a ""fuzzy" dictionary lookup approach to protein mention detection that matches regularized text to similarly regularized dictionary entries. We describe several different strategies for gene normalization that focus on species or organism mentions in the text, both globally throughout the document and locally in the immediate vicinity of a protein mention, and present the results of experimentation with a series of system variations that explore the effectiveness of the various normalization strategies, as well as the role of external knowledge sources. While our system was neither the best nor the worst performing system in the evaluation, the gene normalization strategies show promise and the system affords the opportunity to explore some of the variables affecting performance on the BCII.5 tasks.

Summary: Due to the increasing number of text mining resources (tools and corpora) available to biologists, interoperability issues between these resources are becoming significant obstacles to using them effectively. UIMA, the Unstructured Information Management Architecture, is an open framework designed to aid in the construction of more interoperable tools. U-Compare is built on top of the UIMA framework, and provides both a concrete framework for out-of-the-box text mining and a sophisticated evaluation platform allowing users to run specific tools on any target text, generating both detailed statistics and instance-based visualizations of outputs. U-Compare is a joint project, providing the world's largest, and still growing, collection of UIMA-compatible resources. These resources, originally developed by different groups for a variety of domains, include many famous tools and corpora. U-Compare can be launched straight from the web, without needing to be manually installed. All U-Compare components are provided ready-to-use and can be combined easily via a drag-and-drop interface without any programming. External UIMA components can also simply be mixed with U-Compare components, without distinguishing between locally and remotely deployed resources., Availability: http://u-compare.org/

Motivation: It is important for the quality of biological ontologies that similar concepts be expressed consistently, or univocally. Univocality is relevant for the usability of the ontology for humans, as well as for computational tools that rely on regularity in the structure of terms. However, in practice terms are not always expressed consistently, and we must develop methods for identifying terms that are not univocal so that they can be corrected., Results: We developed an automated transformation-based clustering methodology for detecting terms that use different linguistic conventions for expressing similar semantics. These term sets represent occurrences of univocality violations. Our method was able to identify 67 examples of univocality violations in the Gene Ontology., Availability: The identified univocality violations are available upon request. We are preparing a release of an open source version of the software to be available at http://bionlp.sourceforge.net.

There is an urgent need to capture metadata on the rapidly growing number of genomic, metagenomic and related sequences, such as 16S ribosomal genes. This need is a major focus within the Genomic Standards Consortium (GSC), and Habitat is a key metadata descriptor in the proposed "Minimum Information about a Genome Sequence" (MIGS) specification. The goal of the work described here is to provide a light-weight, easy-to-use (small) set of terms ("Habitat-Lite") that captures high-level information about habitat while preserving a mapping to the recently launched Environment Ontology (EnvO). Our motivation for building Habitat-Lite is to meet the needs of multiple users, such as annotators curating these data, database providers hosting the data, and biologists and bioinformaticians alike who need to search and employ such data in comparative analyses. Here, we report a case study based on semiautomated identification of terms from GenBank and GOLD. We estimate that the terms in the initial version of Habitat-Lite would provide useful labels for over 60% of the kinds of information found in the GenBank isolation_source field, and around 85% of the terms in the GOLD habitat field. We present a revised version of Habitat-Lite defined within the EnvO Environmental Ontology through a new category, EnvO-Lite-GSC. We invite the community's feedback on its further development to provide a minimum list of terms to capture high-level habitat information and to provide classification bins needed for future studies.

Biomedical text mining and other automated techniques are beginning to achieve performance which suggests that they could be applied to aid database curators. However, few studies have evaluated how these systems might work in practice. In this article we focus on the problem of annotating mutations in Protein Data Bank (PDB) entries, and evaluate the relationship between performance of two automated techniques, a text-mining-based approach (MutationFinder) and an alignment-based approach, in intrinsic versus extrinsic evaluations. We find that high performance on gold standard data (an intrinsic evaluation) does not necessarily translate to high performance for database annotation (an extrinsic evaluation). We show that this is in part a result of lack of access to the full text of journal articles, which appears to be critical for comprehensive database annotation by text mining. Additionally, we evaluate the accuracy and completeness of manually annotated mutation data in the PDB, and find that it is far from perfect. We conclude that currently the most cost-effective and reliable approach for database annotation might incorporate manual and automatic annotation methods.

Discussion of point mutations is ubiquitous in biomedical literature, and manually compiling databases or literature on mutations in specific genes or proteins is tedious. We present an open-source, rule-based system, MutationFinder, for extracting point mutation mentions from text. On blind test data, it achieves nearly perfect precision and a markedly improved recall over a baseline., Availability: MutationFinder, along with a high-quality gold standard data set, and a scoring script for mutation extraction systems have been made publicly available. Implementations, source code and unit tests are available in Python, Perl and Java. MutationFinder can be used as a stand-alone script, or imported by other applications., Project Url: http://bionlp.sourceforge.net.

Motivation: Knowledge base construction has been an area of intense activity and great importance in the growth of computational biology. However, there is little or no history of work on the subject of evaluation of knowledge bases, either with respect to their contents or with respect to the processes by which they are constructed. This article proposes the application of a metric from software engineering known as the found/fixed graph to the problem of evaluating the processes by which genomic knowledge bases are built, as well as the completeness of their contents., Results: Well-understood patterns of change in the found/fixed graph are found to occur in two large publicly available knowledge bases. These patterns suggest that the current manual curation processes will take far too long to complete the annotations of even just the most important model organisms, and that at their current rate of production, they will never be sufficient for completing the annotation of all currently available proteomes.

There has been much work devoted to the mapping, alignment, and linking of ontologies (MALO), but little has been published about how to evaluate systems that do this. A fault model for conducting fine-grained evaluations of MALO systems is proposed, and its application to the system described in Johnson et al. [15] is illustrated. Two judges categorized errors according to the model, and inter-judge agreement was calculated by error category. Overall inter-judge agreement was 98% after dispute resolution, suggesting that the model is consistently applicable. The results of applying the model to the system described in [15] reveal the reason for a puzzling set of results in that paper, and also suggest a number of avenues and techniques for improving the state of the art in MALO, including the development of biomedical domain specific language processing tools, filtering of high frequency matching results, and word sense disambiguation.

Like the primary scientific literature, GeneRIFs exhibit both growth and obsolescence. NLM's control over the contents of the Entrez Gene database provides a mechanism for dealing with obsolete data: GeneRIFs are removed from the database when they are found to be of low quality. However, the rapid and extensive growth of Entrez Gene makes manual location of low-quality GeneRIFs problematic. This paper presents a system that takes advantage of the summary-like quality of GeneRIFs to detect low-quality GeneRIFs via a summary revision approach, achieving precision of 89% and recall of 77%. Aspects of the system have been adopted by NLM as a quality assurance mechanism.

Background: Propositional representations of biomedical knowledge are a critical component of most aspects of semantic mining in biomedicine. However, the proper set of propositions has yet to be determined. Recently, the PASBio project proposed a set of propositions and argument structures for biomedical verbs. This initial set of representations presents an opportunity for evaluating the suitability of predicate-argument structures as a scheme for representing verbal semantics in the biomedical domain. Here, we quantitatively evaluate several dimensions of the initial PASBio propositional structure repository., Results: We propose a number of metrics and heuristics related to arity, role labelling, argument realization, and corpus coverage for evaluating large-scale predicate-argument structure proposals. We evaluate the metrics and heuristics by applying them to PASBio 1.0., Conclusion: PASBio demonstrates the suitability of predicate-argument structures for representing aspects of the semantics of biomedical verbs. Metrics related to theta-criterion violations and to the distribution of arguments are able to detect flaws in semantic representations, given a set of predicate-argument structures and a relatively small corpus annotated with them.

A Gene Reference Into Function (GeneRIF) is a concise phrase describing a function of a gene in the Entrez Gene database. Applying techniques from the area of natural language processing known as automatic summarization, it is possible to link the Entrez Gene database, the Gene Ontology, and the biomedical literature. A system was implemented that automatically suggests a sentence from a PubMed/MEDLINE abstract as a candidate GeneRIF by exploiting a gene's GO annotations along with location features and cue words. Results suggest that the method can significantly increase the number of GeneRIF annotations in Entrez Gene, and that it produces qualitatively more useful GeneRIFs than other methods.

We used exact term matching, stemming, and inclusion of synonyms, implemented via the Lucene information retrieval library, to discover relationships between the Gene Ontology and three other OBO ontologies: ChEBI, Cell Type, and BRENDA Tissue. Proposed relationships were evaluated by domain experts. We discovered 91,385 relationships between the ontologies. Various methods had a wide range of correctness. Based on these results, we recommend careful evaluation of all matching strategies before use, including exact string matching. The full set of relationships is available at compbio.uchsc.edu/dependencies.

In this paper we argue that a richer underlying representational model for the Gene Ontology that captures the implicit compositional structure of GO terms could have a positive impact on two activities crucial to the success of GO: ontology curation and database annotation. We show that many of the new terms added to GO in a one-year span appear to be compositional variations of other terms. We found that 90.2% of the 3,652 new terms added between July 2003 and July 2004 exhibited characteristics of compositionality. We also examine annotations available from the GO Consortium website that are either manually curated or automatically generated. We found that 74.5% and 63.2% of GO terms are seldom, if ever, used in manual and automatic annotations, respectively. We show that there are features that tend to distinguish terms that are used from those that are not. In order to characterize the effect of compositionality on the combinatorial properties of GO, we employ finite state automata that represent sets of GO terms. This representational tool demonstrates how ontologies can grow very fast, and also shows that small conceptual changes can directly result in a large number of changes to the terminology. We argue that the curation and annotation findings we report are influenced by the combinatorial properties that present themselves in an ontology that does not have a model that properly captures the compositional structure of its terms.

This paper describes the design of six publicly available biomedical corpora. We then present usage data for the six corpora. We show that corpora that are carefully annotated with respect to structural and linguistic characteristics and that are distributed in standard formats are more widely used than corpora that are not. These findings have implications for the design of the next generation of biomedical corpora.

Background: Our approach to Task 1A was inspired by Tanabe and Wilbur's ABGene system. Like Tanabe and Wilbur, we approached the problem as one of part-of-speech tagging, adding a GENE tag to the standard tag set. Where their system uses the Brill tagger, we used TnT, the Trigrams 'n' Tags HMM-based part-of-speech tagger. Based on careful error analysis, we implemented a set of post-processing rules to correct both false positives and false negatives. We participated in both the open and the closed divisions; for the open division, we made use of data from NCBI., Results: Our base system without post-processing achieved a precision and recall of 68.0% and 77.2%, respectively, giving an F-measure of 72.3%. The full system with post-processing achieved a precision and recall of 80.3% and 80.5% giving an F-measure of 80.4%. We achieved a slight improvement (F-measure = 80.9%) by employing a dictionary-based post-processing step for the open division. We placed third in both the open and the closed division., Conclusion: Our results show that a part-of-speech tagger can be augmented with post-processing rules resulting in an entity identification system that competes well with other approaches.