Dataset Information

Hybrid curation of gene-mutation relations combining automated extraction and crowdsourcing.

ABSTRACT: BACKGROUND:This article describes capture of biological information using a hybrid approach that combines natural language processing to extract biological entities and crowdsourcing with annotators recruited via Amazon Mechanical Turk to judge correctness of candidate biological relations. These techniques were applied to extract gene- mutation relations from biomedical abstracts with the goal of supporting production scale capture of gene-mutation-disease findings as an open source resource for personalized medicine. RESULTS:The hybrid system could be configured to provide good performance for gene-mutation extraction (precision ?82%; recall ?70% against an expert-generated gold standard) at a cost of $0.76 per abstract. This demonstrates that crowd labor platforms such as Amazon Mechanical Turk can be used to recruit quality annotators, even in an application requiring subject matter expertise; aggregated Turker judgments for gene-mutation relations exceeded 90% accuracy. Over half of the precision errors were due to mismatches against the gold standard hidden from annotator view (e.g., incorrect EntrezGene identifier or incorrect mutation position extracted), or incomplete task instructions (e.g., the need to exclude nonhuman mutations). CONCLUSIONS:The hybrid curation model provides a readily scalable cost-effective approach to curation, particularly if coupled with expert human review to filter precision errors. We plan to generalize the framework and make it available as open source software. DATABASE URL:http://www.mitre.org/publications/technical-papers/hybrid-curation-of-gene-mutation-relations-combining-automated.

SUBMITTER: Burger JD

PROVIDER: S-EPMC4170591 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Hybrid curation of gene-mutation relations combining automated extraction and crowdsourcing.

Burger John D JD Doughty Emily E Khare Ritu R Wei Chih-Hsuan CH Mishra Rajashree R Aberdeen John J Tresner-Kirsch David D Wellner Ben B Kann Maricel G MG Lu Zhiyong Z Hirschman Lynette L

Database : the journal of biological databases and curation 20140922

<h4>Background</h4>This article describes capture of biological information using a hybrid approach that combines natural language processing to extract biological entities and crowdsourcing with annotators recruited via Amazon Mechanical Turk to judge correctness of candidate biological relations. These techniques were applied to extract gene- mutation relations from biomedical abstracts with the goal of supporting production scale capture of gene-mutation-disease findings as an open source res ...[more]

PMID: 25246425

Similar Datasets

Project description:BackgroundAutomated gene-calling is still an error-prone process, particularly for the highly plastic genomes of fungal species. Improvement through quality control and manual curation of gene models is a time-consuming process that requires skilled biologists and is only marginally performed. The wealth of available fungal genomes has not yet been exploited by an automated method that applies quality control of gene models in order to obtain more accurate genome annotations.ResultsWe provide a novel method named alignment-based fungal gene prediction (ABFGP) that is particularly suitable for plastic genomes like those of fungi. It can assess gene models on a gene-by-gene basis making use of informant gene loci. Its performance was benchmarked on 6,965 gene models confirmed by full-length unigenes from ten different fungi. 79.4% of all gene models were correctly predicted by ABFGP. It improves the output of ab initio gene prediction software due to a higher sensitivity and precision for all gene model components. Applicability of the method was shown by revisiting the annotations of six different fungi, using gene loci from up to 29 fungal genomes as informants. Between 7,231 and 8,337 genes were assessed by ABFGP and for each genome between 1,724 and 3,505 gene model revisions were proposed. The reliability of the proposed gene models is assessed by an a posteriori introspection procedure of each intron and exon in the multiple gene model alignment. The total number and type of proposed gene model revisions in the six fungal genomes is correlated to the quality of the genome assembly, and to sequencing strategies used in the sequencing centre, highlighting different types of errors in different annotation pipelines. The ABFGP method is particularly successful in discovering sequence errors and/or disruptive mutations causing truncated and erroneous gene models.ConclusionsThe ABFGP method is an accurate and fully automated quality control method for fungal gene catalogues that can be easily implemented into existing annotation pipelines. With the exponential release of new genomes, the ABFGP method will help decreasing the number of gene models that require additional manual curation.

Project description:BackgroundAdvances in the next generation sequencing technology has accelerated the pace of individualized medicine (IM), which aims to incorporate genetic/genomic information into medicine. One immediate need in interpreting sequencing data is the assembly of information about genetic variants and their corresponding associations with other entities (e.g., diseases or medications). Even with dedicated effort to capture such information in biological databases, much of this information remains 'locked' in the unstructured text of biomedical publications. There is a substantial lag between the publication and the subsequent abstraction of such information into databases. Multiple text mining systems have been developed, but most of them focus on the sentence level association extraction with performance evaluation based on gold standard text annotations specifically prepared for text mining systems.ResultsWe developed and evaluated a text mining system, MutD, which extracts protein mutation-disease associations from MEDLINE abstracts by incorporating discourse level analysis, using a benchmark data set extracted from curated database records. MutD achieves an F-measure of 64.3% for reconstructing protein mutation disease associations in curated database records. Discourse level analysis component of MutD contributed to a gain of more than 10% in F-measure when compared against the sentence level association extraction. Our error analysis indicates that 23 of the 64 precision errors are true associations that were not captured by database curators and 68 of the 113 recall errors are caused by the absence of associated disease entities in the abstract. After adjusting for the defects in the curated database, the revised F-measure of MutD in association detection reaches 81.5%.ConclusionsOur quantitative analysis reveals that MutD can effectively extract protein mutation disease associations when benchmarking based on curated database records. The analysis also demonstrates that incorporating discourse level analysis significantly improved the performance of extracting the protein-mutation-disease association. Future work includes the extension of MutD for full text articles.

Project description:BackgroundManual curation of experimental data from the biomedical literature is an expensive and time-consuming endeavor. Nevertheless, most biological knowledge bases still rely heavily on manual curation for data extraction and entry. Text mining software that can semi- or fully automate information retrieval from the literature would thus provide a significant boost to manual curation efforts.ResultsWe employ the Textpresso category-based information retrieval and extraction system (http://www.textpresso.org), developed by WormBase to explore how Textpresso might improve the efficiency with which we manually curate C. elegans proteins to the Gene Ontology's Cellular Component Ontology. Using a training set of sentences that describe results of localization experiments in the published literature, we generated three new curation task-specific categories (Cellular Components, Assay Terms, and Verbs) containing words and phrases associated with reports of experimentally determined subcellular localization. We compared the results of manual curation to that of Textpresso queries that searched the full text of articles for sentences containing terms from each of the three new categories plus the name of a previously uncurated C. elegans protein, and found that Textpresso searches identified curatable papers with recall and precision rates of 79.1% and 61.8%, respectively (F-score of 69.5%), when compared to manual curation. Within those documents, Textpresso identified relevant sentences with recall and precision rates of 30.3% and 80.1% (F-score of 44.0%). From returned sentences, curators were able to make 66.2% of all possible experimentally supported GO Cellular Component annotations with 97.3% precision (F-score of 78.8%). Measuring the relative efficiencies of Textpresso-based versus manual curation we find that Textpresso has the potential to increase curation efficiency by at least 8-fold, and perhaps as much as 15-fold, given differences in individual curatorial speed.ConclusionTextpresso is an effective tool for improving the efficiency of manual, experimentally based curation. Incorporating a Textpresso-based Cellular Component curation pipeline at WormBase has allowed us to transition from strictly manual curation of this data type to a more efficient pipeline of computer-assisted validation. Continued development of curation task-specific Textpresso categories will provide an invaluable resource for genomics databases that rely heavily on manual curation.

Project description:BackgroundCurrently, there exists tens of different microbial and eukaryotic metabolic reconstructions (e.g., Escherichia coli, Saccharomyces cerevisiae, Bacillus subtilis) with many more under development. All of these reconstructions are inherently incomplete with some functionalities missing due to the lack of experimental and/or homology information. A key challenge in the automated generation of genome-scale reconstructions is the elucidation of these gaps and the subsequent generation of hypotheses to bridge them.ResultsIn this work, an optimization based procedure is proposed to identify and eliminate network gaps in these reconstructions. First we identify the metabolites in the metabolic network reconstruction which cannot be produced under any uptake conditions and subsequently we identify the reactions from a customized multi-organism database that restores the connectivity of these metabolites to the parent network using four mechanisms. This connectivity restoration is hypothesized to take place through four mechanisms: a) reversing the directionality of one or more reactions in the existing model, b) adding reaction from another organism to provide functionality absent in the existing model, c) adding external transport mechanisms to allow for importation of metabolites in the existing model and d) restore flow by adding intracellular transport reactions in multi-compartment models. We demonstrate this procedure for the genome- scale reconstruction of Escherichia coli and also Saccharomyces cerevisiae wherein compartmentalization of intra-cellular reactions results in a more complex topology of the metabolic network. We determine that about 10% of metabolites in E. coli and 30% of metabolites in S. cerevisiae cannot carry any flux. Interestingly, the dominant flow restoration mechanism is directionality reversals of existing reactions in the respective models.ConclusionWe have proposed systematic methods to identify and fill gaps in genome-scale metabolic reconstructions. The identified gaps can be filled both by making modifications in the existing model and by adding missing reactions by reconciling multi-organism databases of reactions with existing genome-scale models. Computational results provide a list of hypotheses to be queried further and tested experimentally.

Project description:BACKGROUND: Mutations as sources of evolution have long been the focus of attention in the biomedical literature. Accessing the mutational information and their impacts on protein properties facilitates research in various domains, such as enzymology and pharmacology. However, manually curating the rich and fast growing repository of biomedical literature is expensive and time-consuming. As a solution, text mining approaches have increasingly been deployed in the biomedical domain. While the detection of single-point mutations is well covered by existing systems, challenges still exist in grounding impacts to their respective mutations and recognizing the affected protein properties, in particular kinetic and stability properties together with physical quantities. RESULTS: We present an ontology model for mutation impacts, together with a comprehensive text mining system for extracting and analysing mutation impact information from full-text articles. Organisms, as sources of proteins, are extracted to help disambiguation of genes and proteins. Our system then detects mutation series to correctly ground detected impacts using novel heuristics. It also extracts the affected protein properties, in particular kinetic and stability properties, as well as the magnitude of the effects and validates these relations against the domain ontology. The output of our system can be provided in various formats, in particular by populating an OWL-DL ontology, which can then be queried to provide structured information. The performance of the system is evaluated on our manually annotated corpora. In the impact detection task, our system achieves a precision of 70.4%-71.1%, a recall of 71.3%-71.5%, and grounds the detected impacts with an accuracy of 76.5%-77%. The developed system, including resources, evaluation data and end-user and developer documentation is freely available under an open source license at http://www.semanticsoftware.info/open-mutation-miner. CONCLUSION: We present Open Mutation Miner (OMM), the first comprehensive, fully open-source approach to automatically extract impacts and related relevant information from the biomedical literature. We assessed the performance of our work on manually annotated corpora and the results show the reliability of our approach. The representation of the extracted information into a structured format facilitates knowledge management and aids in database curation and correction. Furthermore, access to the analysis results is provided through multiple interfaces, including web services for automated data integration and desktop-based solutions for end user interactions.

Dataset Information

Hybrid curation of gene-mutation relations combining automated extraction and crowdsourcing.

Publications

Hybrid curation of gene-mutation relations combining automated extraction and crowdsourcing.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets