http://precedings.nature.com/tags/text%20mining Recently posted documents tagged with 'text mining' Nature Publishing Group en Nature Precedings http://precedings.nature.com/images/header_logo.gif http://precedings.nature.com http://dx.doi.org/10.1038/npre.2009.3322.1 The identification of a chemical compound solely based on its name requires comprehensive chemical knowledge and often extensive searches in chemical databases. However, it is crucial for the integration of biochemical data extracted from the literature, since many publications exclusively describe a compound by its name. We have developed an application which matches synonymic names of chemical compounds and thereby facilitates the bundling of corresponding data referring to the same compound.The tool that we have developed is based on natural language processing (NLP) methods and applies rules to systematically normalize chemical compound names. Matching of synonymous names is achieved by comparison of the normalized name forms. It is capable of normalizing a given name of a chemical compound and matching it against names in (bio-)chemical databases (e.g. SABIO-RK, ChEBI or PubChem), even when there is no exact name-to-name-match. The tool is also able to match a complete list of compound names against these databases which makes it useful for the automatic annotation of chemical data.This normalization and matching of various synonyms of a chemical compound constitutes a platform for the unambiguous identification of compounds described in the literature or in databases. http://dx.doi.org/10.1038/npre.2009.3322.1 Fri, 05 Jun 2009 20:06:57 UTC Normalization and Matching of Chemical Compound Names doi:10.1038/npre.2009.3322.1 2009-06-05 Martin Golebiewski Nature Precedings 2009-06-05T20:06:57Z Poster Chemistry Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://dx.doi.org/10.1038/npre.2009.3302.1 Ten years ago WormBase1 started as a repository for sequence data for the modelorganism Caenorhabditis elegans and has since striven to include the curation of allgenetic and molecular data published for this nematode. With a publication rate in the C.elegans field of approximately 800 papers per year, WormBase (WB) has the opportunity to include information from every paper published. Currently there are ~11,000 full text research papers (mid-1970’s to the present) downloaded into the WB curation database, from which over 27 data types (i.e. genetic interactions, transgene objects, gene expression patterns, mutant phenotypes etc.) are extracted by curators. Textpresso2 is an open source text-mining tool capable of rapid searches for keywords, as well as concepts, from the full text of research papers. Curators at WB use Textpresso on a daily basis for many aspects of literature curation, from simple keyword searches to semi- or fully automated entity and fact extraction, which feed into curation pipelines or directly into the curation database itself. In addition, Textpresso greatly aids prioritization of literature curation by retrieving papers based on their full contents rather than solely on their abstracts. Such retrievable contents can range from the very particular (such as a gene simply being mentioned in the Materials and Methods section of a paper) to the complex (such as molecular functions that involve cellular components). As WB expands to incorporate the genomes of other nematodes, we will be working with Textpresso developers to set up a library of literature for related nematodes. We expect Textpresso to be crucial for most efficiently directing our efforts in literature curation, and for most quickly providing data to users searching the literature. In this workshop we will show how we use Textpresso in our curation pipeline to help with literature queries, to prioritize our workflow, and to automate data and fact extraction.1 WormBase2 Textpresso http://dx.doi.org/10.1038/npre.2009.3302.1 Tue, 02 Jun 2009 14:49:35 UTC Using Textpresso for Information Retrieval, Fact Extraction doi:10.1038/npre.2009.3302.1 2009-06-02 Kimberly Van Auken Nature Precedings 2009-06-02T14:49:35Z Presentation Genetics & Genomics Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://dx.doi.org/10.1038/npre.2009.3262.1 A major challenge for the development of resources for functional and comparative genomics is the extraction of data from the biomedical literature. Although text retrieval and extraction 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.In September 2008, Mouse Genome Informatics (MGI) at The Jackson Lab initiated a search for dictionary-based text mining tools that we could integrate into our curation workflow. MGI has rigorous document triage and annotation procedures designed to identify articles about mouse genome biology and determine whether those articles should be curated. We currently screens approximately 1000 journal articles a month for Gene Ontology terms, gene mapping, gene expression, phenotype data and other key biological information. Although we don’t foresee that human curation tasks can be fully automated in the near future, we are eager to implement entity name recognition and gene tagging tools that can help streamline our curation workflow and simplify gene indexing tasks in the MGI system. In this presentation, we discuss our search process and the steps we took to identify a short list of potential tools for further evaluation. We present our performance metrics and success criteria, and pilot projects in progress. The primary applications under current review are Fraunhofer SCAI’s ProMiner and NCBO’s Open-Biomedical Annotator. http://dx.doi.org/10.1038/npre.2009.3262.1 Wed, 20 May 2009 21:16:19 UTC Integrating Text Mining into the MGI Biocuration Workflow doi:10.1038/npre.2009.3262.1 2009-05-20 Karen G. Dowell Nature Precedings 2009-05-20T21:16:19Z Presentation Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://dx.doi.org/10.1038/npre.2009.3250.1 As the first phase of a knowledge engineering study of biocuration workflows, we performed a preliminary task-modeling exercise on seven separate bioinformatics systems. This involved constructing UML activity diagrams from detailed interviews with curators in order to understand the organization of the process the biocurators used to populate their system. The objective of this work was to identify common patterns within the workflows where we might apply text mining methods to accelerate curation. We compiled a number of workflows in a common format but were largely unable to consolidate these structures into a formal structure that facilitated comparison across workflows. We presented this work as a slideshow and publish this account of the catalog as supplementary information. http://dx.doi.org/10.1038/npre.2009.3250.1 Wed, 13 May 2009 19:12:22 UTC Biocuration Workflow Catalogue doi:10.1038/npre.2009.3250.1 2009-05-13 Gully Burns Nature Precedings 2009-05-13T19:12:22Z Manuscript Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://precedings.nature.com/documents/3212/version/1 Anyone who regularly reads life science literature often comes across names of genes, proteins, or small molecules that they would like to know more about. To make this process easier, we have developed a new, free service called Reflect (http://reflect.ws) that can be installed as a plug-in to Firefox or Internet Explorer. Reflect tags gene, protein, and small molecule names in any web page, typically within a few seconds, and without affecting document layout. Clicking on a tagged gene or protein name opens a popup showing a concise summary that includes synonyms, database identifiers, sequence, domains, 3D structure, interaction partners, subcellular location, and related literature. Clicking on a tagged small molecule name opens a popup showing 2D structure and interaction partners. The popups also allow navigation to commonly used databases. In the future we plan to add further entity types to Reflect, including outside the life sciences. http://precedings.nature.com/documents/3212/version/1 Mon, 04 May 2009 14:50:53 UTC Reflect: Augmented Browsing for the Life Scientist hdl:10101/npre.2009.3212.1 2009-05-04 Seán I. O'Donoghue Nature Precedings 2009-05-04T14:50:53Z Manuscript Biotechnology Chemistry Genetics & Genomics Molecular Cell Biology Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://dx.doi.org/10.1038/npre.2009.3188.1 The boosting of Biomedical Text Mining (BioTM) research in the last few years has led the way for finally bridging out the gap between text miners and biologists. Beyond the development of enhanced entity recognisers and the construction of relationship extraction systems, now, more than ever, it is the time for applying available tools to real-world scenarios. Moreover, it is crucial to develop end-user tools that can assist biologists in their research activities. Such tools should be able to emulate biologist conventional curation, recurring to the same knowledge bases and making the same assumptions that biologists usually do, whereas delivering automated capabilities. The search and selection of PubMed articles, the construction of dictionaries from the contents of available Molecular Biology repositories, the implementation of description environments for rule specification, the implementation of dictionary- and rule-based entity recognisers, the development of flexible and extensible relationship extraction systems and the development of easy-to-use manual curation environments are of foremost importance.Our software, named @Note, aims to be a framework and a workbench for BioTM, i.e., it has been conceived for delivering end-user applications, whereas enabling collaboration with other BioTM groups. As a framework, it provides a reusable design for BioTM software systems and a set of pre-assembled software building blocks that programmers can use, extend and customise for their specific needs. As a workbench, it helps developing BioTM applications by integrating Natural Language Processing and Data Mining tools and supporting major Information Retrieval and Information Extraction processes. Moreover, it encompasses a flexible and extensible manual curation environment that enables the interaction with biologists, correcting former annotations and enhancing dictionary contents. We successfully applied @Note in the study of the stringent response on Escherichia coli, an important subject within the analysis of stress responses in bacteria. This joint effort allowed biologists to contribute to the enhancement of our manual curation environment and to identify new functionalities for the existing plug-ins and the specification of new plug-ins. http://dx.doi.org/10.1038/npre.2009.3188.1 Tue, 28 Apr 2009 18:31:15 UTC Bringing Text Miners and Biologists Closer Together doi:10.1038/npre.2009.3188.1 2009-04-28 Anália Lourenço Nature Precedings 2009-04-28T18:31:15Z Presentation Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://dx.doi.org/10.1038/npre.2009.3176.1 OBJECTIVES: We report on a experiment to functionally annotate PubChem assays using the Gene Ontology Categorizer (GOCat). METHODS and MATERIALS: The assays are processed to filter out non functional information, then the textual content is sent to the categorizer, which provide a ranked list of GO descriptors based on a GOA-learned association model. RESULTS: The GO descriptors are regarded as irrelevant for only 18% of the assays. CONCLUSION: Semantic enrichment of PubChem assays with functional genomics categories seems effective at least to navigate PubChem assays. AVAILABILITIES: the database is hosted by the University of Indiana at http://goassay.rguha.net/index.html the GO categorizer interface and service is available at the University of Geneva http://eagl.unige.ch/EAGLi/. http://dx.doi.org/10.1038/npre.2009.3176.1 Tue, 28 Apr 2009 08:47:47 UTC GOAssay: from Gene Ontology to Assays IDentifiers – Towards Automatic Functional Annotation of PubChem BioAssays doi:10.1038/npre.2009.3176.1 2009-04-28 Patrick Ruch Nature Precedings 2009-04-28T08:47:47Z Poster Chemistry Genetics & Genomics Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://dx.doi.org/10.1038/npre.2009.3171.1 As collaborating partners, Barcelona Media Innovation Centre and GRIB (Universitat Pompeu Fabra) seek to combine strengths from Computational Linguistics and Biomedicine to produce a robust Text Mining system to generate data that will help biocurators in their daily work. The first version of this system will focus on the discovery of relationships between genes, SNPs (Single Nucleotide Polymorphisms) and diseases from the literature.A first challenge that we were faced with during the setup of this project is the fact that most current tools that support the curation workflow are complex, ad-hoc built applications which sometimes make difficult the interoperability and results sharing between research groups from different and unrelated expert fields. Often, biologists (even computer-savvy ones) are hard pressed to use and adapt sophisticated Natural Language Processing systems, and computational linguists are challenged by the intricacies of biology in applying their processing pipelines to elicit knowledge from texts. The flow of knowledge (needed to develop a usable, practical tool) to and from the parties involved in the development of such systems is not always easy or straightforward.The modular and versatile architecture of UIMA (Unstructed Information Management Architecture) provides a framework to address these challenges. UIMA is a component architecture and software framework implementation (including a UIMA SDK) to develop applications that analyse large volumes of unstructured information, and has been increasingly adopted by a significant part of the BioNLP community that needs industrial-grade and robust applications to exploit the whole bibliome. The use of UIMA to develop Text Mining applications useful for curation purposes allows the combination of diverse expertises which is beyond the individual know-how of biologists, computer scientists or linguists in isolation. A good synergy and circulation of knowledge between these experts is fundamental to the development of a successful curation tool. http://dx.doi.org/10.1038/npre.2009.3171.1 Fri, 24 Apr 2009 22:20:13 UTC UIMA in the Biocuration Workflow: A coherent framework for cooperation between biologists and computational linguists doi:10.1038/npre.2009.3171.1 2009-04-24 Laura Ines Furlong Nature Precedings 2009-04-24T22:20:13Z Poster Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://dx.doi.org/10.1038/npre.2009.3164.1 Oryzabase (http://www.shigen.nig.ac.jp/rice/oryzabase/) is a comprehensive rice science database 1. It houses a variety of genetic resources, relevant literatures, gene dictionary, DNA sequences, and basic information such as developmental biology and anatomy. In order to keep the gene dictionary up-to-date, literature annotation has been conducted manually since 1995. However as the publication of journal articles increases year by year after genomic sequences were released, it became more difficult to update the dictionary timely and in high quality without sufficient annotators. To overcome this difficulty, we applied machine learning and text-mining to extract known and unknown genes from journals. The machine extraction followed by manual annotation achieved promising results and increased efficiency in manual annotation. Furthermore a direct submission system where rice researchers can deposit new genes according to the standardized nomenclature 2 became operational in 2008. Recent advances will be introduced.[1] Kurata, N. and Y. Yamazaki., Oryzabase, An Integrated Biological and Genome Information Database for Rice. Plant Physiology (2006) 140, 12-17 [2] Susan R. McCouch, Gene Nomenclature System for Rice, Rice (2008) 1:72-84 http://dx.doi.org/10.1038/npre.2009.3164.1 Fri, 24 Apr 2009 15:47:57 UTC Direct submission system and literature annotation of rice genes in Oryzabase doi:10.1038/npre.2009.3164.1 2009-04-24 Yukiko Yamazaki Nature Precedings 2009-04-24T15:47:57Z Poster Genetics & Genomics Bioinformatics Plant Biology http://creativecommons.org/licenses/by/3.0/ http://dx.doi.org/10.1038/npre.2009.3166.1 A text mining group has been set up at the Swiss Institute of Bioinformatics, with objective to develop and adapt information retrieval and extraction tools to help Swiss-Prot curators in their daily annotation work. After over 7 year activities, this group has gathered a significant amount of experience about the need in text mining for biocuration.The first observation we made is that there is no “in-a-box” solution which can satisfy every needs. Each curator has his/her own strategy to find information from the literature and none of the existing information retrieval systems is able to compete with it, more for reason of habits than for reason of performance. Second observation: to be completely operative, an information retrieval system should be embedded in the annotation platform. For instance, it should be possible to copy/paste information, such as the article reference or some interesting sentences, directly in the database format. Most of the existing online programs are hardly adaptable for this task and their use usually results in additional editing efforts for the curators. From this observation, we can derive the fact that integrating text mining services is usually more costly than expected since wrappers and user interfaces need significant developments sometimes fairly user-specific.After noticing these problems in the design and use of a generic information retrieval system for the Swiss-Prot curators, we focused our effort on text mining applications for database update. The follow-up of the literature is essential in the process of database maintenance and there are needs for automatic information extraction tools on a large panel of topics. We developed several IE applications in the field of:- PTM information (phosphorylation, glycosylation, disulfide bridge)- Subcellular localization- Variant/mutation detection and characterization- New sequence with enzymatic activities- New characterization of enzymes.These tools are integrated into pipelines which follow PubMed daily outcomes and generate list of selected abstracts with highlights on the relevant sentences. These procedures are done independently of the usual annotation workflow, so that curators can mine these preselected data whenever they work on database entry updates.To conclude, we have identified big challenges in text mining services after discussion with the curators. One of them is the detection of novel information, especially those related to a new function or a new characterization of a protein or one of its close homologues. We are currently working on this task in the framework of the collaborative project “EAGL”. Another challenge is definitely the large-scale screening of newly published full-text papers to complement the often incomplete information in abstracts. This becomes more and more indispensable, not really for the annotation of widely studied “hot” proteins, but to find new data on uncharacterized ones. For instance, when no gene name has been attributed to a sequence, the only way to retrieve information is to use the orf names, which are never provided in abstracts.Finally, one should definitely stress that many of these information retrieval and extraction tasks could be greatly simplified with the requirement of metadata at the article submission time, such as an official HGNC gene name or a UniProt reference. http://dx.doi.org/10.1038/npre.2009.3166.1 Fri, 24 Apr 2009 14:31:04 UTC Text mining for Swiss-Prot curation: A story of success and failure doi:10.1038/npre.2009.3166.1 2009-04-24 Anne-Lise Veuthey Nature Precedings 2009-04-24T14:31:04Z Presentation Bioinformatics http://creativecommons.org/licenses/by/3.0/