Research into event-based text mining from the biomedical literature has been growing in popularity to facilitate the development of advanced biomedical text mining systems. Such technology permits advanced search, which goes beyond document or sentence-based retrieval. However, existing event-based systems typically ignore additional information within the textual context of events that can determine, amongst other things, whether an event represents a fact, hypothesis, experimental result or analysis of results, whether it describes new or previously reported knowledge, and whether it is speculated or negated. We refer to such contextual information as meta-knowledge. The automatic recognition of such information can permit the training of systems allowing finer-grained searching of events according to the meta-knowledge that is associated with them.
Based on a corpus of 1,000 MEDLINE abstracts, fully manually annotated with both events and associated meta-knowledge, we have constructed a machine learning-based system that automatically assigns meta-knowledge information to events. This system has been integrated into EventMine, a state-of-the-art event extraction system, in order to create a more advanced system (EventMine-MK) that not only extracts events from text automatically, but also assigns five different types of meta-knowledge to these events. The meta-knowledge assignment module of EventMine-MK performs with macro-averaged F-scores in the range of 57-87% on the BioNLP’09 Shared Task corpus. EventMine-MK has been evaluated on the BioNLP’09 Shared Task subtask of detecting negated and speculated events. Our results show that EventMine-MK can outperform other state-of-the-art systems that participated in this task.
We have constructed the first practical system that extracts both events and associated, detailed meta-knowledge information from biomedical literature. The automatically assigned meta-knowledge information can be used to refine search systems, in order to provide an extra search layer beyond entities and assertions, dealing with phenomena such as rhetorical intent, speculations, contradictions and negations. This finer grained search functionality can assist in several important tasks, e.g., database curation (by locating new experimental knowledge) and pathway enrichment (by providing information for inference). To allow easy integration into text mining systems, EventMine-MK is provided as a UIMA component that can be used in the interoperable text mining infrastructure, U-Compare.
Biomedical events are key to understanding physiological processes and disease, and wide coverage extraction is required for comprehensive automatic analysis of statements describing biomedical systems in the literature. In turn, the training and evaluation of extraction methods requires manually annotated corpora. However, as manual annotation is time-consuming and expensive, any single event-annotated corpus can only cover a limited number of semantic types. Although combined use of several such corpora could potentially allow an extraction system to achieve broad semantic coverage, there has been little research into learning from multiple corpora with partially overlapping semantic annotation scopes.
We propose a method for learning from multiple corpora with partial semantic annotation overlap, and implement this method to improve our existing event extraction system, EventMine. An evaluation using seven event annotated corpora, including 65 event types in total, shows that learning from overlapping corpora can produce a single, corpus-independent, wide coverage extraction system that outperforms systems trained on single corpora and exceeds previously reported results on two established event extraction tasks from the BioNLP Shared Task 2011.
The proposed method allows the training of a wide-coverage, state-of-the-art event extraction system from multiple corpora with partial semantic annotation overlap. The resulting single model makes broad-coverage extraction straightforward in practice by removing the need to either select a subset of compatible corpora or semantic types, or to merge results from several models trained on different individual corpora. Multi-corpus learning also allows annotation efforts to focus on covering additional semantic types, rather than aiming for exhaustive coverage in any single annotation effort, or extending the coverage of semantic types annotated in existing corpora.
Current research has shown that major difficulties in event extraction for the biomedical domain are traceable to coreference. Therefore, coreference resolution is believed to be useful for improving event extraction. To address coreference resolution in molecular biology literature, the Protein Coreference (COREF) task was arranged in the BioNLP Shared Task (BioNLP-ST, hereafter) 2011, as a supporting task. However, the shared task results indicated that transferring coreference resolution methods developed for other domains to the biological domain was not a straight-forward task, due to the domain differences in the coreference phenomena.
We analyzed the contribution of domain-specific information, including the information that indicates the protein type, in a rule-based protein coreference resolution system. In particular, the domain-specific information is encoded into semantic classification modules for which the output is used in different components of the coreference resolution. We compared our system with the top four systems in the BioNLP-ST 2011; surprisingly, we found that the minimal configuration had outperformed the best system in the BioNLP-ST 2011. Analysis of the experimental results revealed that semantic classification, using protein information, has contributed to an increase in performance by 2.3% on the test data, and 4.0% on the development data, in F-score.
The use of domain-specific information in semantic classification is important for effective coreference resolution. Since it is difficult to transfer domain-specific information across different domains, we need to continue seek for methods to utilize such information in coreference resolution.
We present a system for extracting biomedical events (detailed descriptions of biomolecular interactions) from research articles, developed for the BioNLP'11 Shared Task. Our goal is to develop a system easily adaptable to different event schemes, following the theme of the BioNLP'11 Shared Task: generalization, the extension of event extraction to varied biomedical domains. Our system extends our BioNLP'09 Shared Task winning Turku Event Extraction System, which uses support vector machines to first detect event-defining words, followed by detection of their relationships.
Our current system successfully predicts events for every domain case introduced in the BioNLP'11 Shared Task, being the only system to participate in all eight tasks and all of their subtasks, with best performance in four tasks. Following the Shared Task, we improve the system on the Infectious Diseases task from 42.57% to 53.87% F-score, bringing performance into line with the similar GENIA Event Extraction and Epigenetics and Post-translational Modifications tasks. We evaluate the machine learning performance of the system by calculating learning curves for all tasks, detecting areas where additional annotated data could be used to improve performance. Finally, we evaluate the use of system output on external articles as additional training data in a form of self-training.
We show that the updated Turku Event Extraction System can easily be adapted to all presently available event extraction targets, with competitive performance in most tasks. The scope of the performance gains between the 2009 and 2011 BioNLP Shared Tasks indicates event extraction is still a new field requiring more work. We provide several analyses of event extraction methods and performance, highlighting potential future directions for continued development.
In recent years, biological event extraction has emerged as a key natural language processing task, aiming to address the information overload problem in accessing the molecular biology literature. The BioNLP shared task competitions have contributed to this recent interest considerably. The first competition (BioNLP'09) focused on extracting biological events from Medline abstracts from a narrow domain, while the theme of the latest competition (BioNLP-ST'11) was generalization and a wider range of text types, event types, and subject domains were considered. We view event extraction as a building block in larger discourse interpretation and propose a two-phase, linguistically-grounded, rule-based methodology. In the first phase, a general, underspecified semantic interpretation is composed from syntactic dependency relations in a bottom-up manner. The notion of embedding underpins this phase and it is informed by a trigger dictionary and argument identification rules. Coreference resolution is also performed at this step, allowing extraction of inter-sentential relations. The second phase is concerned with constraining the resulting semantic interpretation by shared task specifications. We evaluated our general methodology on core biological event extraction and speculation/negation tasks in three main tracks of BioNLP-ST'11 (GENIA, EPI, and ID).
We achieved competitive results in GENIA and ID tracks, while our results in the EPI track leave room for improvement. One notable feature of our system is that its performance across abstracts and articles bodies is stable. Coreference resolution results in minor improvement in system performance. Due to our interest in discourse-level elements, such as speculation/negation and coreference, we provide a more detailed analysis of our system performance in these subtasks.
The results demonstrate the viability of a robust, linguistically-oriented methodology, which clearly distinguishes general semantic interpretation from shared task specific aspects, for biological event extraction. Our error analysis pinpoints some shortcomings, which we plan to address in future work within our incremental system development methodology.
Text mining is increasingly used in the biomedical domain because of its ability to automatically gather information from large amount of scientific articles. One important task in biomedical text mining is relation extraction, which aims to identify designated relations among biological entities reported in literature. A relation extraction system achieving high performance is expensive to develop because of the substantial time and effort required for its design and implementation. Here, we report a novel framework to facilitate the development of a pattern-based biomedical relation extraction system. It has several unique design features: (1) leveraging syntactic variations possible in a language and automatically generating extraction patterns in a systematic manner, (2) applying sentence simplification to improve the coverage of extraction patterns, and (3) identifying referential relations between a syntactic argument of a predicate and the actual target expected in the relation extraction task.
A relation extraction system derived using the proposed framework achieved overall F-scores of 72.66% for the Simple events and 55.57% for the Binding events on the BioNLP-ST 2011 GE test set, comparing favorably with the top performing systems that participated in the BioNLP-ST 2011 GE task. We obtained similar results on the BioNLP-ST 2013 GE test set (80.07% and 60.58%, respectively). We conducted additional experiments on the training and development sets to provide a more detailed analysis of the system and its individual modules. This analysis indicates that without increasing the number of patterns, simplification and referential relation linking play a key role in the effective extraction of biomedical relations.
In this paper, we present a novel framework for fast development of relation extraction systems. The framework requires only a list of triggers as input, and does not need information from an annotated corpus. Thus, we reduce the involvement of domain experts, who would otherwise have to provide manual annotations and help with the design of hand crafted patterns. We demonstrate how our framework is used to develop a system which achieves state-of-the-art performance on a public benchmark corpus.
Negation occurs frequently in scientific literature, especially in biomedical literature. It has previously been reported that around 13% of sentences found in biomedical research articles contain negation. Historically, the main motivation for identifying negated events has been to ensure their exclusion from lists of extracted interactions. However, recently, there has been a growing interest in negative results, which has resulted in negation detection being identified as a key challenge in biomedical relation extraction. In this article, we focus on the problem of identifying negated bio-events, given gold standard event annotations.
We have conducted a detailed analysis of three open access bio-event corpora containing negation information (i.e., GENIA Event, BioInfer and BioNLP’09 ST), and have identified the main types of negated bio-events. We have analysed the key aspects of a machine learning solution to the problem of detecting negated events, including selection of negation cues, feature engineering and the choice of learning algorithm. Combining the best solutions for each aspect of the problem, we propose a novel framework for the identification of negated bio-events. We have evaluated our system on each of the three open access corpora mentioned above. The performance of the system significantly surpasses the best results previously reported on the BioNLP’09 ST corpus, and achieves even better results on the GENIA Event and BioInfer corpora, both of which contain more varied and complex events.
Recently, in the field of biomedical text mining, the development and enhancement of event-based systems has received significant interest. The ability to identify negated events is a key performance element for these systems. We have conducted the first detailed study on the analysis and identification of negated bio-events. Our proposed framework can be integrated with state-of-the-art event extraction systems. The resulting systems will be able to extract bio-events with attached polarities from textual documents, which can serve as the foundation for more elaborate systems that are able to detect mutually contradicting bio-events.
The Genia task, when it was introduced in 2009, was the first community-wide effort to address a fine-grained, structural information extraction from biomedical literature. Arranged for the second time as one of the main tasks of BioNLP Shared Task 2011, it aimed to measure the progress of the community since 2009, and to evaluate generalization of the technology to full text papers. The Protein Coreference task was arranged as one of the supporting tasks, motivated from one of the lessons of the 2009 task that the abundance of coreference structures in natural language text hinders further improvement with the Genia task.
The Genia task received final submissions from 15 teams. The results show that the community has made a significant progress, marking 74% of the best F-score in extracting bio-molecular events of simple structure, e.g., gene expressions, and 45% ~ 48% in extracting those of complex structure, e.g., regulations. The Protein Coreference task received 6 final submissions. The results show that the coreference resolution performance in biomedical domain is lagging behind that in newswire domain, cf. 50% vs. 66% in MUC score. Particularly, in terms of protein coreference resolution the best system achieved 34% in F-score.
Detailed analysis performed on the results improves our insight into the problem and suggests the directions for further improvements.
We present the preparation, resources, results and analysis of three tasks of the BioNLP Shared Task 2011: the main tasks on Infectious Diseases (ID) and Epigenetics and Post-translational Modifications (EPI), and the supporting task on Entity Relations (REL). The two main tasks represent extensions of the event extraction model introduced in the BioNLP Shared Task 2009 (ST'09) to two new areas of biomedical scientific literature, each motivated by the needs of specific biocuration tasks. The ID task concerns the molecular mechanisms of infection, virulence and resistance, focusing in particular on the functions of a class of signaling systems that are ubiquitous in bacteria. The EPI task is dedicated to the extraction of statements regarding chemical modifications of DNA and proteins, with particular emphasis on changes relating to the epigenetic control of gene expression. By contrast to these two application-oriented main tasks, the REL task seeks to support extraction in general by separating challenges relating to part-of relations into a subproblem that can be addressed by independent systems. Seven groups participated in each of the two main tasks and four groups in the supporting task. The participating systems indicated advances in the capability of event extraction methods and demonstrated generalization in many aspects: from abstracts to full texts, from previously considered subdomains to new ones, and from the ST'09 extraction targets to other entities and events. The highest performance achieved in the supporting task REL, 58% F-score, is broadly comparable with levels reported for other relation extraction tasks. For the ID task, the highest-performing system achieved 56% F-score, comparable to the state-of-the-art performance at the established ST'09 task. In the EPI task, the best result was 53% F-score for the full set of extraction targets and 69% F-score for a reduced set of core extraction targets, approaching a level of performance sufficient for user-facing applications. In this study, we extend on previously reported results and perform further analyses of the outputs of the participating systems. We place specific emphasis on aspects of system performance relating to real-world applicability, considering alternate evaluation metrics and performing additional manual analysis of system outputs. We further demonstrate that the strengths of extraction systems can be combined to improve on the performance achieved by any system in isolation. The manually annotated corpora, supporting resources, and evaluation tools for all tasks are available from http://www.bionlp-st.org and the tasks continue as open challenges for all interested parties.
This article reports the use of the BioC standard format in our sentence simplification system, iSimp, and demonstrates its general utility. iSimp is designed to simplify complex sentences commonly found in the biomedical text, and has been shown to improve existing text mining applications that rely on the analysis of sentence structures. By adopting the BioC format, we aim to make iSimp readily interoperable with other applications in the biomedical domain. To examine the utility of iSimp in BioC, we implemented a rule-based relation extraction system that uses iSimp as a preprocessing module and BioC for data exchange. Evaluation on the training corpus of BioNLP-ST 2011 GENIA Event Extraction (GE) task showed that iSimp sentence simplification improved the recall by 3.2% without reducing precision. The iSimp simplification-annotated corpora, both our previously used corpus and the GE corpus in the current study, have been converted into the BioC format and made publicly available at the project’s Web site: http://research.bioinformatics.udel.edu/isimp/.
Motivation: To create, verify and maintain pathway models, curators must discover and assess knowledge distributed over the vast body of biological literature. Methods supporting these tasks must understand both the pathway model representations and the natural language in the literature. These methods should identify and order documents by relevance to any given pathway reaction. No existing system has addressed all aspects of this challenge.
Method: We present novel methods for associating pathway model reactions with relevant publications. Our approach extracts the reactions directly from the models and then turns them into queries for three text mining-based MEDLINE literature search systems. These queries are executed, and the resulting documents are combined and ranked according to their relevance to the reactions of interest. We manually annotate document-reaction pairs with the relevance of the document to the reaction and use this annotation to study several ranking methods, using various heuristic and machine-learning approaches.
Results: Our evaluation shows that the annotated document-reaction pairs can be used to create a rule-based document ranking system, and that machine learning can be used to rank documents by their relevance to pathway reactions. We find that a Support Vector Machine-based system outperforms several baselines and matches the performance of the rule-based system. The success of the query extraction and ranking methods are used to update our existing pathway search system, PathText.
Availability: An online demonstration of PathText 2 and the annotated corpus are available for research purposes at http://www.nactem.ac.uk/pathtext2/.
Supplementary data are available at Bioinformatics online.
We present the BioNLP 2011 Shared Task Bacteria Track, the first Information Extraction challenge entirely dedicated to bacteria. It includes three tasks that cover different levels of biological knowledge. The Bacteria Gene Renaming supporting task is aimed at extracting gene renaming and gene name synonymy in PubMed abstracts. The Bacteria Gene Interaction is a gene/protein interaction extraction task from individual sentences. The interactions have been categorized into ten different sub-types, thus giving a detailed account of genetic regulations at the molecular level. Finally, the Bacteria Biotopes task focuses on the localization and environment of bacteria mentioned in textbook articles.
We describe the process of creation for the three corpora, including document acquisition and manual annotation, as well as the metrics used to evaluate the participants' submissions.
Three teams submitted to the Bacteria Gene Renaming task; the best team achieved an F-score of 87%. For the Bacteria Gene Interaction task, the only participant's score had reached a global F-score of 77%, although the system efficiency varies significantly from one sub-type to another. Three teams submitted to the Bacteria Biotopes task with very different approaches; the best team achieved an F-score of 45%. However, the detailed study of the participating systems efficiency reveals the strengths and weaknesses of each participating system.
The three tasks of the Bacteria Track offer participants a chance to address a wide range of issues in Information Extraction, including entity recognition, semantic typing and coreference resolution. We found commond trends in the most efficient systems: the systematic use of syntactic dependencies and machine learning. Nevertheless, the originality of the Bacteria Biotopes task encouraged the use of interesting novel methods and techniques, such as term compositionality, scopes wider than the sentence.
Text mining tools have gained popularity to process the vast amount of available research articles in the biomedical literature. It is crucial that such tools extract information with a sufficient level of detail to be applicable in real life scenarios. Studies of mining non-causal molecular relations attribute to this goal by formally identifying the relations between genes, promoters, complexes and various other molecular entities found in text. More importantly, these studies help to enhance integration of text mining results with database facts.
We describe, compare and evaluate two frameworks developed for the prediction of non-causal or 'entity' relations (REL) between gene symbols and domain terms. For the corresponding REL challenge of the BioNLP Shared Task of 2011, these systems ranked first (57.7% F-score) and second (41.6% F-score). In this paper, we investigate the performance discrepancy of 16 percentage points by benchmarking on a related and more extensive dataset, analysing the contribution of both the term detection and relation extraction modules. We further construct a hybrid system combining the two frameworks and experiment with intersection and union combinations, achieving respectively high-precision and high-recall results. Finally, we highlight extremely high-performance results (F-score >90%) obtained for the specific subclass of embedded entity relations that are essential for integrating text mining predictions with database facts.
The results from this study will enable us in the near future to annotate semantic relations between molecular entities in the entire scientific literature available through PubMed. The recent release of the EVEX dataset, containing biomolecular event predictions for millions of PubMed articles, is an interesting and exciting opportunity to overlay these entity relations with event predictions on a literature-wide scale.
Biomedical 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.
We 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.
Augmenting 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.
Manually annotated corpora are critical for the training and evaluation of automated methods to identify concepts in biomedical text.
This paper presents the concept annotations of the Colorado Richly Annotated Full-Text (CRAFT) Corpus, a collection of 97 full-length, open-access biomedical journal articles that have been annotated both semantically and syntactically to serve as a research resource for the biomedical natural-language-processing (NLP) community. CRAFT identifies all mentions of nearly all concepts from nine prominent biomedical ontologies and terminologies: the Cell Type Ontology, the Chemical Entities of Biological Interest ontology, the NCBI Taxonomy, the Protein Ontology, the Sequence Ontology, the entries of the Entrez Gene database, and the three subontologies of the Gene Ontology. The first public release includes the annotations for 67 of the 97 articles, reserving two sets of 15 articles for future text-mining competitions (after which these too will be released). Concept annotations were created based on a single set of guidelines, which has enabled us to achieve consistently high interannotator agreement.
As the initial 67-article release contains more than 560,000 tokens (and the full set more than 790,000 tokens), our corpus is among the largest gold-standard annotated biomedical corpora. Unlike most others, the journal articles that comprise the corpus are drawn from diverse biomedical disciplines and are marked up in their entirety. Additionally, with a concept-annotation count of nearly 100,000 in the 67-article subset (and more than 140,000 in the full collection), the scale of conceptual markup is also among the largest of comparable corpora. The concept annotations of the CRAFT Corpus have the potential to significantly advance biomedical text mining by providing a high-quality gold standard for NLP systems. The corpus, annotation guidelines, and other associated resources are freely available at http://bionlp-corpora.sourceforge.net/CRAFT/index.shtml.
Cellular events play a central role in the understanding of biological processes and functions, providing insight on both physiological and pathogenesis mechanisms. Automatic extraction of mentions of such events from the literature represents an important contribution to the progress of the biomedical domain, allowing faster updating of existing knowledge. The identification of trigger words indicating an event is a very important step in the event extraction pipeline, since the following task(s) rely on its output. This step presents various complex and unsolved challenges, namely the selection of informative features, the representation of the textual context, and the selection of a specific event type for a trigger word given this context.
We propose TrigNER, a machine learning-based solution for biomedical event trigger recognition, which takes advantage of Conditional Random Fields (CRFs) with a high-end feature set, including linguistic-based, orthographic, morphological, local context and dependency parsing features. Additionally, a completely configurable algorithm is used to automatically optimize the feature set and training parameters for each event type. Thus, it automatically selects the features that have a positive contribution and automatically optimizes the CRF model order, n-grams sizes, vertex information and maximum hops for dependency parsing features. The final output consists of various CRF models, each one optimized to the linguistic characteristics of each event type.
TrigNER was tested in the BioNLP 2009 shared task corpus, achieving a total F-measure of 62.7 and outperforming existing solutions on various event trigger types, namely gene expression, transcription, protein catabolism, phosphorylation and binding. The proposed solution allows researchers to easily apply complex and optimized techniques in the recognition of biomedical event triggers, making its application a simple routine task. We believe this work is an important contribution to the biomedical text mining community, contributing to improved and faster event recognition on scientific articles, and consequent hypothesis generation and knowledge discovery. This solution is freely available as open source at http://bioinformatics.ua.pt/trigner.
Biomedical papers contain rich information about entities, facts and events of biological relevance. To discover these automatically, we use text mining techniques, which rely on annotated corpora for training. In order to extract protein-protein interactions, genotype-phenotype/gene-disease associations, etc., we rely on event corpora that are annotated with classified, structured representations of important facts and findings contained within text. These provide an important resource for the training of domain-specific information extraction (IE) systems, to facilitate semantic-based searching of documents. Correct interpretation of these events is not possible without additional information, e.g., does an event describe a fact, a hypothesis, an experimental result or an analysis of results? How confident is the author about the validity of her analyses? These and other types of information, which we collectively term meta-knowledge, can be derived from the context of the event.
We have designed an annotation scheme for meta-knowledge enrichment of biomedical event corpora. The scheme is multi-dimensional, in that each event is annotated for 5 different aspects of meta-knowledge that can be derived from the textual context of the event. Textual clues used to determine the values are also annotated. The scheme is intended to be general enough to allow integration with different types of bio-event annotation, whilst being detailed enough to capture important subtleties in the nature of the meta-knowledge expressed in the text. We report here on both the main features of the annotation scheme, as well as its application to the GENIA event corpus (1000 abstracts with 36,858 events). High levels of inter-annotator agreement have been achieved, falling in the range of 0.84-0.93 Kappa.
By augmenting event annotations with meta-knowledge, more sophisticated IE systems can be trained, which allow interpretative information to be specified as part of the search criteria. This can assist in a number of important tasks, e.g., finding new experimental knowledge to facilitate database curation, enabling textual inference to detect entailments and contradictions, etc. To our knowledge, our scheme is unique within the field with regards to the diversity of meta-knowledge aspects annotated for each event.
We consider the task of automatically extracting DNA methylation events from the biomedical domain literature. DNA methylation is a key mechanism of epigenetic control of gene expression and implicated in many cancers, but there has been little study of automatic information extraction for DNA methylation.
We present an annotation scheme for DNA methylation following the representation of the BioNLP shared task on event extraction, select a set of 200 abstracts including a representative sample of all PubMed citations relevant to DNA methylation, and introduce manual annotation for this corpus marking nearly 3000 gene/protein mentions and 1500 DNA methylation and demethylation events. We retrain a state-of-the-art event extraction system on the corpus and find that automatic extraction of DNA methylation events, the methylated genes, and their methylation sites can be performed at 78% precision and 76% recall.
Our results demonstrate that reliable extraction methods for DNA methylation events can be created through corpus annotation and straightforward retraining of a general event extraction system. The introduced resources are freely available for use in research from the GENIA project homepage http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA.
Event extraction following the GENIA Event corpus and BioNLP shared task models has been a considerable focus of recent work in biomedical information extraction. This work includes efforts applying event extraction methods to the entire PubMed literature database, far beyond the narrow subdomains of biomedicine for which annotated resources for extraction method development are available.
In the present study, our aim is to estimate the coverage of all statements of gene/protein associations in PubMed that existing resources for event extraction can provide. We base our analysis on a recently released corpus automatically annotated for gene/protein entities and syntactic analyses covering the entire PubMed, and use named entity co-occurrence, shortest dependency paths and an unlexicalized classifier to identify likely statements of gene/protein associations. A set of high-frequency/high-likelihood association statements are then manually analyzed with reference to the GENIA ontology.
We present a first estimate of the overall coverage of gene/protein associations provided by existing resources for event extraction. Our results suggest that for event-type associations this coverage may be over 90%. We also identify several biologically significant associations of genes and proteins that are not addressed by these resources, suggesting directions for further extension of extraction coverage.
A major challenge for functional and comparative genomics resource development is the extraction of data from the biomedical literature. Although text mining for biological data is an active research field, few applications have been integrated into production literature curation systems such as those of the model organism databases (MODs). Not only are most available biological natural language (bioNLP) and information retrieval and extraction solutions difficult to adapt to existing MOD curation workflows, but many also have high error rates or are unable to process documents available in those formats preferred by scientific journals.
In September 2008, Mouse Genome Informatics (MGI) at The Jackson Laboratory initiated a search for dictionary-based text mining tools that we could integrate into our biocuration workflow. MGI has rigorous document triage and annotation procedures designed to identify appropriate articles about mouse genetics and genome biology. We currently screen ∼1000 journal articles a month for Gene Ontology terms, gene mapping, gene expression, phenotype data and other key biological information. Although we do not foresee that curation tasks will ever be fully automated, we are eager to implement named entity recognition (NER) tools for gene tagging that can help streamline our curation workflow and simplify gene indexing tasks within the MGI system. Gene indexing is an MGI-specific curation function that involves identifying which mouse genes are being studied in an article, then associating the appropriate gene symbols with the article reference number in the MGI database.
Here, we discuss our search process, performance metrics and success criteria, and how we identified a short list of potential text mining tools for further evaluation. We provide an overview of our pilot projects with NCBO's Open Biomedical Annotator and Fraunhofer SCAI's ProMiner. In doing so, we prove the potential for the further incorporation of semi-automated processes into the curation of the biomedical literature.
The biomedical text mining community has focused on developing techniques to automatically extract important relations between biological components and semantic events involving genes or proteins from literature. In this paper, we propose a novel approach for mining relations and events in the biomedical literature using approximate subgraph matching. Extraction of such knowledge is performed by searching for an approximate subgraph isomorphism between key contextual dependencies and input sentence graphs. Our approach significantly increases the chance of retrieving relations or events encoded within complex dependency contexts by introducing error tolerance into the graph matching process, while maintaining the extraction precision at a high level. When evaluated on practical tasks, it achieves a 51.12% F-score in extracting nine types of biological events on the GE task of the BioNLP-ST 2011 and an 84.22% F-score in detecting protein-residue associations. The performance is comparable to the reported systems across these tasks, and thus demonstrates the generalizability of our proposed approach.
Gene function curation via Gene Ontology (GO) annotation is a common task among Model Organism Database groups. Owing to its manual nature, this task is considered one of the bottlenecks in literature curation. There have been many previous attempts at automatic identification of GO terms and supporting information from full text. However, few systems have delivered an accuracy that is comparable with humans. One recognized challenge in developing such systems is the lack of marked sentence-level evidence text that provides the basis for making GO annotations. We aim to create a corpus that includes the GO evidence text along with the three core elements of GO annotations: (i) a gene or gene product, (ii) a GO term and (iii) a GO evidence code. To ensure our results are consistent with real-life GO data, we recruited eight professional GO curators and asked them to follow their routine GO annotation protocols. Our annotators marked up more than 5000 text passages in 200 articles for 1356 distinct GO terms. For evidence sentence selection, the inter-annotator agreement (IAA) results are 9.3% (strict) and 42.7% (relaxed) in F1-measures. For GO term selection, the IAAs are 47% (strict) and 62.9% (hierarchical). Our corpus analysis further shows that abstracts contain ∼10% of relevant evidence sentences and 30% distinct GO terms, while the Results/Experiment section has nearly 60% relevant sentences and >70% GO terms. Further, of those evidence sentences found in abstracts, less than one-third contain enough experimental detail to fulfill the three core criteria of a GO annotation. This result demonstrates the need of using full-text articles for text mining GO annotations. Through its use at the BioCreative IV GO (BC4GO) task, we expect our corpus to become a valuable resource for the BioNLP research community.
Bioinformatics tools for automatic processing of biomedical literature are invaluable for both the design and interpretation of large-scale experiments. Many information extraction (IE) systems that incorporate natural language processing (NLP) techniques have thus been developed for use in the biomedical field. A key IE task in this field is the extraction of biomedical relations, such as protein-protein and gene-disease interactions. However, most biomedical relation extraction systems usually ignore adverbial and prepositional phrases and words identifying location, manner, timing, and condition, which are essential for describing biomedical relations. Semantic role labeling (SRL) is a natural language processing technique that identifies the semantic roles of these words or phrases in sentences and expresses them as predicate-argument structures. We construct a biomedical SRL system called BIOSMILE that uses a maximum entropy (ME) machine-learning model to extract biomedical relations. BIOSMILE is trained on BioProp, our semi-automatic, annotated biomedical proposition bank. Currently, we are focusing on 30 biomedical verbs that are frequently used or considered important for describing molecular events.
To evaluate the performance of BIOSMILE, we conducted two experiments to (1) compare the performance of SRL systems trained on newswire and biomedical corpora; and (2) examine the effects of using biomedical-specific features. The experimental results show that using BioProp improves the F-score of the SRL system by 21.45% over an SRL system that uses a newswire corpus. It is noteworthy that adding automatically generated template features improves the overall F-score by a further 0.52%. Specifically, ArgM-LOC, ArgM-MNR, and Arg2 achieve statistically significant performance improvements of 3.33%, 2.27%, and 1.44%, respectively.
We demonstrate the necessity of using a biomedical proposition bank for training SRL systems in the biomedical domain. Besides the different characteristics of biomedical and newswire sentences, factors such as cross-domain framesets and verb usage variations also influence the performance of SRL systems. For argument classification, we find that NE (named entity) features indicating if the target node matches with NEs are not effective, since NEs may match with a node of the parsing tree that does not have semantic role labels in the training set. We therefore incorporate templates composed of specific words, NE types, and POS tags into the SRL system. As a result, the classification accuracy for adjunct arguments, which is especially important for biomedical SRL, is improved significantly.
Motivation: In the field of biomolecular text mining, black box behavior of machine learning systems currently limits understanding of the true nature of the predictions. However, feature selection (FS) is capable of identifying the most relevant features in any supervised learning setting, providing insight into the specific properties of the classification algorithm. This allows us to build more accurate classifiers while at the same time bridging the gap between the black box behavior and the end-user who has to interpret the results.
Results: We show that our FS methodology successfully discards a large fraction of machine-generated features, improving classification performance of state-of-the-art text mining algorithms. Furthermore, we illustrate how FS can be applied to gain understanding in the predictions of a framework for biomolecular event extraction from text. We include numerous examples of highly discriminative features that model either biological reality or common linguistic constructs. Finally, we discuss a number of insights from our FS analyses that will provide the opportunity to considerably improve upon current text mining tools.
Availability: The FS algorithms and classifiers are available in Java-ML (http://java-ml.sf.net). The datasets are publicly available from the BioNLP'09 Shared Task web site (http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA/SharedTask/).
The TREC 2004 Genomics Track focused on applying information retrieval and text mining techniques to improve the use of genomic information in biomedicine. The Genomics Track consisted of two main tasks, ad hoc retrieval and document categorization. In this paper, we describe the categorization task, which focused on the classification of full-text documents, simulating the task of curators of the Mouse Genome Informatics (MGI) system and consisting of three subtasks. One subtask of the categorization task required the triage of articles likely to have experimental evidence warranting the assignment of GO terms, while the other two subtasks were concerned with the assignment of the three top-level GO categories to each paper containing evidence for these categories.
The track had 33 participating groups. The mean and maximum utility measure for the triage subtask was 0.3303, with a top score of 0.6512. No system was able to substantially improve results over simply using the MeSH term Mice. Analysis of significant feature overlap between the training and test sets was found to be less than expected. Sample coverage of GO terms assigned to papers in the collection was very sparse. Determining papers containing GO term evidence will likely need to be treated as separate tasks for each concept represented in GO, and therefore require much denser sampling than was available in the data sets.
The annotation subtask had a mean F-measure of 0.3824, with a top score of 0.5611. The mean F-measure for the annotation plus evidence codes subtask was 0.3676, with a top score of 0.4224. Gene name recognition was found to be of benefit for this task.
Automated classification of documents for GO annotation is a challenging task, as was the automated extraction of GO code hierarchies and evidence codes. However, automating these tasks would provide substantial benefit to biomedical curation, and therefore work in this area must continue. Additional experience will allow comparison and further analysis about which algorithmic features are most useful in biomedical document classification, and better understanding of the task characteristics that make automated classification feasible and useful for biomedical document curation. The TREC Genomics Track will be continuing in 2005 focusing on a wider range of triage tasks and improving results from 2004.