Dataset Information

Simple tricks for improving pattern-based information extraction from the biomedical literature.

ABSTRACT:

Background

Pattern-based approaches to relation extraction have shown very good results in many areas of biomedical text mining. However, defining the right set of patterns is difficult; approaches are either manual, incurring high cost, or automatic, often resulting in large sets of noisy patterns.

Results

We propose several techniques for filtering sets of automatically generated patterns and analyze their effectiveness for different extraction tasks, as defined in the recent BioNLP 2009 shared task. We focus on simple methods that only take into account the complexity of the pattern and the complexity of the texts the patterns are applied to. We show that our techniques, despite their simplicity, yield large improvements in all tasks we analyzed. For instance, they raise the F-score for the task of extraction gene expression events from 24.8% to 51.9%.

Conclusions

Already very simple filtering techniques may improve the F-score of an information extraction method based on automatically generated patterns significantly. Furthermore, the application of such methods yields a considerable speed-up, as fewer matches need to be analysed. Due to their simplicity, the proposed filtering techniques also should be applicable to other methods using linguistic patterns for information extraction.

SUBMITTER: Nguyen QL

PROVIDER: S-EPMC2955645 | biostudies-literature | 2010 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Simple tricks for improving pattern-based information extraction from the biomedical literature.

Nguyen Quang Long QL Tikk Domonkos D Leser Ulf U

Journal of biomedical semantics 20100924 1

<h4>Background</h4>Pattern-based approaches to relation extraction have shown very good results in many areas of biomedical text mining. However, defining the right set of patterns is difficult; approaches are either manual, incurring high cost, or automatic, often resulting in large sets of noisy patterns.<h4>Results</h4>We propose several techniques for filtering sets of automatically generated patterns and analyze their effectiveness for different extraction tasks, as defined in the recent Bi ...[more]

PMID: 20868467

Similar Datasets

Project description:BackgroundFor selection and evaluation of potential biomarkers, inclusion of already published information is of utmost importance. In spite of significant advancements in text- and data-mining techniques, the vast knowledge space of biomarkers in biomedical text has remained unexplored. Existing named entity recognition approaches are not sufficiently selective for the retrieval of biomarker information from the literature. The purpose of this study was to identify textual features that enhance the effectiveness of biomarker information retrieval for different indication areas and diverse end user perspectives.MethodsA biomarker terminology was created and further organized into six concept classes. Performance of this terminology was optimized towards balanced selectivity and specificity. The information retrieval performance using the biomarker terminology was evaluated based on various combinations of the terminology's six classes. Further validation of these results was performed on two independent corpora representing two different neurodegenerative diseases.ResultsThe current state of the biomarker terminology contains 119 entity classes supported by 1890 different synonyms. The result of information retrieval shows improved retrieval rate of informative abstracts, which is achieved by including clinical management terms and evidence of gene/protein alterations (e.g. gene/protein expression status or certain polymorphisms) in combination with disease and gene name recognition. When additional filtering through other classes (e.g. diagnostic or prognostic methods) is applied, the typical high number of unspecific search results is significantly reduced. The evaluation results suggest that this approach enables the automated identification of biomarker information in the literature. A demo version of the search engine SCAIView, including the biomarker retrieval, is made available to the public through http://www.scaiview.com/scaiview-academia.html.ConclusionsThe approach presented in this paper demonstrates that using a dedicated biomarker terminology for automated analysis of the scientific literature maybe helpful as an aid to finding biomarker information in text. Successful extraction of candidate biomarkers information from published resources can be considered as the first step towards developing novel hypotheses. These hypotheses will be valuable for the early decision-making in the drug discovery and development process.

Project description:BackgroundInformation Extraction (IE) is a component of text mining that facilitates knowledge discovery by automatically locating instances of interesting biomedical events from huge document collections. As events are usually centred on verbs and nominalised verbs, understanding the syntactic and semantic behaviour of these words is highly important. Corpora annotated with information concerning this behaviour can constitute a valuable resource in the training of IE components and resources.ResultsWe have defined a new scheme for annotating sentence-bound gene regulation events, centred on both verbs and nominalised verbs. For each event instance, all participants (arguments) in the same sentence are identified and assigned a semantic role from a rich set of 13 roles tailored to biomedical research articles, together with a biological concept type linked to the Gene Regulation Ontology. To our knowledge, our scheme is unique within the biomedical field in terms of the range of event arguments identified. Using the scheme, we have created the Gene Regulation Event Corpus (GREC), consisting of 240 MEDLINE abstracts, in which events relating to gene regulation and expression have been annotated by biologists. A novel method of evaluating various different facets of the annotation task showed that average inter-annotator agreement rates fall within the range of 66% - 90%.ConclusionThe GREC is a unique resource within the biomedical field, in that it annotates not only core relationships between entities, but also a range of other important details about these relationships, e.g., location, temporal, manner and environmental conditions. As such, it is specifically designed to support bio-specific tool and resource development. It has already been used to acquire semantic frames for inclusion within the BioLexicon (a lexical, terminological resource to aid biomedical text mining). Initial experiments have also shown that the corpus may viably be used to train IE components, such as semantic role labellers. The corpus and annotation guidelines are freely available for academic purposes.

Project description:BackgroundIn systems biology, it is of great interest to identify previously unreported associations between genes. Recently, biomedical literature has been considered as a valuable resource for this purpose. While classical clustering algorithms have popularly been used to investigate associations among genes, they are not tuned for the literature mining data and are also based on strong assumptions, which are often violated in this type of data. For example, these approaches often assume homogeneity and independence among observations. However, these assumptions are often violated due to both redundancies in functional descriptions and biological functions shared among genes. Latent block models can be alternatives in this case but they also often show suboptimal performances, especially when signals are weak. In addition, they do not allow to utilize valuable prior biological knowledge, such as those available in existing databases.ResultsIn order to address these limitations, here we propose PALMER, a constrained latent block model that allows to identify indirect relationships among genes based on the biomedical literature mining data. By automatically associating relevant Gene Ontology terms, PALMER facilitates biological interpretation of novel findings without laborious downstream analyses. PALMER also allows researchers to utilize prior biological knowledge about known gene-pathway relationships to guide identification of gene-gene associations. We evaluated PALMER with simulation studies and applications to studies of pathway-modulating genes relevant to cancer signaling pathways, while utilizing biological pathway annotations available in the KEGG database as prior knowledge.ConclusionsWe showed that PALMER outperforms traditional latent block models and it provides reliable identification of novel gene-gene associations by utilizing prior biological knowledge, especially when signals are weak in the biomedical literature mining dataset. We believe that PALMER and its relevant user-friendly software will be powerful tools that can be used to improve existing pathway annotations and identify novel pathway-modulating genes.

Project description:The detection of bacterial antibiotic resistance phenotypes is important when carrying out clinical decisions for patient treatment. Conventional phenotypic testing involves culturing bacteria which requires a significant amount of time and work. Whole-genome sequencing is emerging as a fast alternative to resistance prediction, by considering the presence/absence of certain genes. A lot of research has focused on determining which bacterial genes cause antibiotic resistance and efforts are being made to consolidate these facts in knowledge bases (KBs). KBs are usually manually curated by domain experts to be of the highest quality. However, this limits the pace at which new facts are added. Automated relation extraction of gene-antibiotic resistance relations from the biomedical literature is one solution that can simplify the curation process. This paper reports on the development of a text mining pipeline that takes in English biomedical abstracts and outputs genes that are predicted to cause resistance to antibiotics. To test the generalisability of this pipeline it was then applied to predict genes associated with Helicobacter pylori antibiotic resistance, that are not present in common antibiotic resistance KBs or publications studying H. pylori. These genes would be candidates for further lab-based antibiotic research and inclusion in these KBs. For relation extraction, state-of-the-art deep learning models were used. These models were trained on a newly developed silver corpus which was generated by distant supervision of abstracts using the facts obtained from KBs. The top performing model was superior to a co-occurrence model, achieving a recall of 95%, a precision of 60% and F1-score of 74% on a manually annotated holdout dataset. To our knowledge, this project was the first attempt at developing a complete text mining pipeline that incorporates deep learning models to extract gene-antibiotic resistance relations from the literature. Additional related data can be found at https://github.com/AndreBrincat/Gene-Antibiotic-Resistance-Relation-Extraction.

Dataset Information

Simple tricks for improving pattern-based information extraction from the biomedical literature.

Background

Results

Conclusions

Publications

Simple tricks for improving pattern-based information extraction from the biomedical literature.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure