BioCreative Challenge Research Articles

Pre-trained models, data augmentation, and ensemble learning for biomedical information extraction and document classification.

Large volumes of publications are being produced in biomedical sciences nowadays with ever-increasing speed. To deal with the large amount of unstructured text data, effective natural language processing (NLP) methods need to be developed for various tasks such as document classification and information extraction. BioCreative Challenge was established to evaluate the effectiveness of information extraction methods in biomedical domain and facilitate their development as a community-wide effort. In this paper, we summarize our work and what we have learned from the latest round, BioCreative Challenge VII, where we participated in all five tracks. Overall, we found three key components for achieving high performance across a variety of NLP tasks: (1) pre-trained NLP models; (2) data augmentation strategies and (3) ensemble modelling. These three strategies need to be tailored towards the specific tasks at hands to achieve high-performing baseline models, which are usually good enough for practical applications. When further combined with task-specific methods, additional improvements (usually rather small) can be achieved, which might be critical for winning competitions. Database URL: https://doi.org/10.1093/database/baac066

Single Concatenated Input is Better than Indenpendent Multiple-input for CNNs to Predict Chemical-induced Disease Relation from Literature

Single Concatenated Input is Better than Indenpendent Multiple-input for CNNs to Predict Chemical-induced Disease Relation from Literature

The Markyt visualisation, prediction and benchmark platform for chemical and gene entity recognition at BioCreative/CHEMDNER challenge.

Biomedical text mining methods and technologies have improved significantly in the last decade. Considerable efforts have been invested in understanding the main challenges of biomedical literature retrieval and extraction and proposing solutions to problems of practical interest. Most notably, community-oriented initiatives such as the BioCreative challenge have enabled controlled environments for the comparison of automatic systems while pursuing practical biomedical tasks. Under this scenario, the present work describes the Markyt Web-based document curation platform, which has been implemented to support the visualisation, prediction and benchmark of chemical and gene mention annotations at BioCreative/CHEMDNER challenge. Creating this platform is an important step for the systematic and public evaluation of automatic prediction systems and the reusability of the knowledge compiled for the challenge. Markyt was not only critical to support the manual annotation and annotation revision process but also facilitated the comparative visualisation of automated results against the manually generated Gold Standard annotations and comparative assessment of generated results. We expect that future biomedical text mining challenges and the text mining community may benefit from the Markyt platform to better explore and interpret annotations and improve automatic system predictions.Database URL: http://www.markyt.org, https://github.com/sing-group/Markyt

PIPE: a protein-protein interaction passage extraction module for BioCreative challenge.

Identifying the interactions between proteins mentioned in biomedical literatures is one of the frequently discussed topics of text mining in the life science field. In this article, we propose PIPE, an interaction pattern generation module used in the Collaborative Biocurator Assistant Task at BioCreative V (http://www.biocreative.org/) to capture frequent protein-protein interaction (PPI) patterns within text. We also present an interaction pattern tree (IPT) kernel method that integrates the PPI patterns with convolution tree kernel (CTK) to extract PPIs. Methods were evaluated on LLL, IEPA, HPRD50, AIMed and BioInfer corpora using cross-validation, cross-learning and cross-corpus evaluation. Empirical evaluations demonstrate that our method is effective and outperforms several well-known PPI extraction methods.Database URL:

Argo: enabling the development of bespoke workflows and services for disease annotation.

Argo (http://argo.nactem.ac.uk) is a generic text mining workbench that can cater to a variety of use cases, including the semi-automatic annotation of literature. It enables its technical users to build their own customised text mining solutions by providing a wide array of interoperable and configurable elementary components that can be seamlessly integrated into processing workflows. With Argo's graphical annotation interface, domain experts can then make use of the workflows' automatically generated output to curate information of interest.With the continuously rising need to understand the aetiology of diseases as well as the demand for their informed diagnosis and personalised treatment, the curation of disease-relevant information from medical and clinical documents has become an indispensable scientific activity. In the Fifth BioCreative Challenge Evaluation Workshop (BioCreative V), there was substantial interest in the mining of literature for disease-relevant information. Apart from a panel discussion focussed on disease annotations, the chemical-disease relations (CDR) track was also organised to foster the sharing and advancement of disease annotation tools and resources.This article presents the application of Argo’s capabilities to the literature-based annotation of diseases. As part of our participation in BioCreative V’s User Interactive Track (IAT), we demonstrated and evaluated Argo’s suitability to the semi-automatic curation of chronic obstructive pulmonary disease (COPD) phenotypes. Furthermore, the workbench facilitated the development of some of the CDR track’s top-performing web services for normalising disease mentions against the Medical Subject Headings (MeSH) database. In this work, we highlight Argo’s support for developing various types of bespoke workflows ranging from ones which enabled us to easily incorporate information from various databases, to those which train and apply machine learning-based concept recognition models, through to user-interactive ones which allow human curators to manually provide their corrections to automatically generated annotations. Our participation in the BioCreative V challenges shows Argo’s potential as an enabling technology for curating disease and phenotypic information from literature.Database URL: http://argo.nactem.ac.uk

Optimising chemical named entity recognition with pre-processing analytics, knowledge-rich features and heuristics.

BackgroundThe development of robust methods for chemical named entity recognition, a challenging natural language processing task, was previously hindered by the lack of publicly available, large-scale, gold standard corpora. The recent public release of a large chemical entity-annotated corpus as a resource for the CHEMDNER track of the Fourth BioCreative Challenge Evaluation (BioCreative IV) workshop greatly alleviated this problem and allowed us to develop a conditional random fields-based chemical entity recogniser. In order to optimise its performance, we introduced customisations in various aspects of our solution. These include the selection of specialised pre-processing analytics, the incorporation of chemistry knowledge-rich features in the training and application of the statistical model, and the addition of post-processing rules.ResultsOur evaluation shows that optimal performance is obtained when our customisations are integrated into the chemical entity recogniser. When its performance is compared with that of state-of-the-art methods, under comparable experimental settings, our solution achieves competitive advantage. We also show that our recogniser that uses a model trained on the CHEMDNER corpus is suitable for recognising names in a wide range of corpora, consistently outperforming two popular chemical NER tools.ConclusionThe contributions resulting from this work are two-fold. Firstly, we present the details of a chemical entity recognition methodology that has demonstrated performance at a competitive, if not superior, level as that of state-of-the-art methods. Secondly, the developed suite of solutions has been made publicly available as a configurable workflow in the interoperable text mining workbench Argo. This allows interested users to conveniently apply and evaluate our solutions in the context of other chemical text mining tasks.

CheNER: a tool for the identification of chemical entities and their classes in biomedical literature.

BackgroundSmall chemical molecules regulate biological processes at the molecular level. Those molecules are often involved in causing or treating pathological states. Automatically identifying such molecules in biomedical text is difficult due to both, the diverse morphology of chemical names and the alternative types of nomenclature that are simultaneously used to describe them. To address these issues, the last BioCreAtIvE challenge proposed a CHEMDNER task, which is a Named Entity Recognition (NER) challenge that aims at labelling different types of chemical names in biomedical text.MethodsTo address this challenge we tested various approaches to recognizing chemical entities in biomedical documents. These approaches range from linear Conditional Random Fields (CRFs) to a combination of CRFs with regular expression and dictionary matching, followed by a post-processing step to tag those chemical names in a corpus of Medline abstracts. We named our best performing systems CheNER.ResultsWe evaluate the performance of the various approaches using the F-score statistics. Higher F-scores indicate better performance. The highest F-score we obtain in identifying unique chemical entities is 72.88%. The highest F-score we obtain in identifying all chemical entities is 73.07%. We also evaluate the F-Score of combining our system with ChemSpot, and find an increase from 72.88% to 73.83%.ConclusionsCheNER presents a valid alternative for automated annotation of chemical entities in biomedical documents. In addition, CheNER may be used to derive new features to train newer methods for tagging chemical entities. CheNER can be downloaded from http://metres.udl.cat and included in text annotation pipelines.

Closing the loop: from paper to protein annotation using supervised Gene Ontology classification.

Gene function curation of the literature with Gene Ontology (GO) concepts is one particularly time-consuming task in genomics, and the help from bioinformatics is highly requested to keep up with the flow of publications. In 2004, the first BioCreative challenge already designed a task of automatic GO concepts assignment from a full text. At this time, results were judged far from reaching the performances required by real curation workflows. In particular, supervised approaches produced the most disappointing results because of lack of training data. Ten years later, the available curation data have massively grown. In 2013, the BioCreative IV GO task revisited the automatic GO assignment task. For this issue, we investigated the power of our supervised classifier, GOCat. GOCat computes similarities between an input text and already curated instances contained in a knowledge base to infer GO concepts. The subtask A consisted in selecting GO evidence sentences for a relevant gene in a full text. For this, we designed a state-of-the-art supervised statistical approach, using a naïve Bayes classifier and the official training set, and obtained fair results. The subtask B consisted in predicting GO concepts from the previous output. For this, we applied GOCat and reached leading results, up to 65% for hierarchical recall in the top 20 outputted concepts. Contrary to previous competitions, machine learning has this time outperformed standard dictionary-based approaches. Thanks to BioCreative IV, we were able to design a complete workflow for curation: given a gene name and a full text, this system is able to select evidence sentences for curation and to deliver highly relevant GO concepts. Contrary to previous competitions, machine learning this time outperformed dictionary-based systems. Observed performances are sufficient for being used in a real semiautomatic curation workflow. GOCat is available at http://eagl.unige.ch/GOCat/.Database URL: http://eagl.unige.ch/GOCat4FT/

Processing biological literature with customizable Web services supporting interoperable formats.

Web services have become a popular means of interconnecting solutions for processing a body of scientific literature. This has fuelled research on high-level data exchange formats suitable for a given domain and ensuring the interoperability of Web services. In this article, we focus on the biological domain and consider four interoperability formats, BioC, BioNLP, XMI and RDF, that represent domain-specific and generic representations and include well-established as well as emerging specifications. We use the formats in the context of customizable Web services created in our Web-based, text-mining workbench Argo that features an ever-growing library of elementary analytics and capabilities to build and deploy Web services straight from a convenient graphical user interface. We demonstrate a 2-fold customization of Web services: by building task-specific processing pipelines from a repository of available analytics, and by configuring services to accept and produce a combination of input and output data interchange formats. We provide qualitative evaluation of the formats as well as quantitative evaluation of automatic analytics. The latter was carried out as part of our participation in the fourth edition of the BioCreative challenge. Our analytics built into Web services for recognizing biochemical concepts in BioC collections achieved the highest combined scores out of 10 participating teams.Database URL: http://argo.nactem.ac.uk.

Biblio-MetReS for user-friendly mining of genes and biological processes in scientific documents.

One way to initiate the reconstruction of molecular circuits is by using automated text-mining techniques. Developing more efficient methods for such reconstruction is a topic of active research, and those methods are typically included by bioinformaticians in pipelines used to mine and curate large literature datasets. Nevertheless, experimental biologists have a limited number of available user-friendly tools that use text-mining for network reconstruction and require no programming skills to use. One of these tools is Biblio-MetReS. Originally, this tool permitted an on-the-fly analysis of documents contained in a number of web-based literature databases to identify co-occurrence of proteins/genes. This approach ensured results that were always up-to-date with the latest live version of the databases. However, this ‘up-to-dateness’ came at the cost of large execution times. Here we report an evolution of the application Biblio-MetReS that permits constructing co-occurrence networks for genes, GO processes, Pathways, or any combination of the three types of entities and graphically represent those entities. We show that the performance of Biblio-MetReS in identifying gene co-occurrence is as least as good as that of other comparable applications (STRING and iHOP). In addition, we also show that the identification of GO processes is on par to that reported in the latest BioCreAtIvE challenge. Finally, we also report the implementation of a new strategy that combines on-the-fly analysis of new documents with preprocessed information from documents that were encountered in previous analyses. This combination simultaneously decreases program run time and maintains ‘up-to-dateness’ of the results. Availability: http://metres.udl.cat/index.php/downloads, Contact: metres.cmb@gmail.com.

How to link ontologies and protein-protein interactions to literature: text-mining approaches and the BioCreative experience

There is an increasing interest in developing ontologies and controlled vocabularies to improve the efficiency and consistency of manual literature curation, to enable more formal biocuration workflow results and ultimately to improve analysis of biological data. Two ontologies that have been successfully used for this purpose are the Gene Ontology (GO) for annotating aspects of gene products and the Molecular Interaction ontology (PSI-MI) used by databases that archive protein–protein interactions. The examination of protein interactions has proven to be extremely promising for the understanding of cellular processes. Manual mapping of information from the biomedical literature to bio-ontology terms is one of the most challenging components in the curation pipeline. It requires that expert curators interpret the natural language descriptions contained in articles and infer their semantic equivalents in the ontology (controlled vocabulary). Since manual curation is a time-consuming process, there is strong motivation to implement text-mining techniques to automatically extract annotations from free text. A range of text mining strategies has been devised to assist in the automated extraction of biological data. These strategies either recognize technical terms used recurrently in the literature and propose them as candidates for inclusion in ontologies, or retrieve passages that serve as evidential support for annotating an ontology term, e.g. from the PSI-MI or GO controlled vocabularies. Here, we provide a general overview of current text-mining methods to automatically extract annotations of GO and PSI-MI ontology terms in the context of the BioCreative (Critical Assessment of Information Extraction Systems in Biology) challenge. Special emphasis is given to protein–protein interaction data and PSI-MI terms referring to interaction detection methods.

BioCreative III interactive task: an overview

BackgroundThe BioCreative challenge evaluation is a community-wide effort for evaluating text mining and information extraction systems applied to the biological domain. The biocurator community, as an active user of biomedical literature, provides a diverse and engaged end user group for text mining tools. Earlier BioCreative challenges involved many text mining teams in developing basic capabilities relevant to biological curation, but they did not address the issues of system usage, insertion into the workflow and adoption by curators. Thus in BioCreative III (BC-III), the InterActive Task (IAT) was introduced to address the utility and usability of text mining tools for real-life biocuration tasks. To support the aims of the IAT in BC-III, involvement of both developers and end users was solicited, and the development of a user interface to address the tasks interactively was requested.ResultsA User Advisory Group (UAG) actively participated in the IAT design and assessment. The task focused on gene normalization (identifying gene mentions in the article and linking these genes to standard database identifiers), gene ranking based on the overall importance of each gene mentioned in the article, and gene-oriented document retrieval (identifying full text papers relevant to a selected gene). Six systems participated and all processed and displayed the same set of articles. The articles were selected based on content known to be problematic for curation, such as ambiguity of gene names, coverage of multiple genes and species, or introduction of a new gene name. Members of the UAG curated three articles for training and assessment purposes, and each member was assigned a system to review. A questionnaire related to the interface usability and task performance (as measured by precision and recall) was answered after systems were used to curate articles. Although the limited number of articles analyzed and users involved in the IAT experiment precluded rigorous quantitative analysis of the results, a qualitative analysis provided valuable insight into some of the problems encountered by users when using the systems. The overall assessment indicates that the system usability features appealed to most users, but the system performance was suboptimal (mainly due to low accuracy in gene normalization). Some of the issues included failure of species identification and gene name ambiguity in the gene normalization task leading to an extensive list of gene identifiers to review, which, in some cases, did not contain the relevant genes. The document retrieval suffered from the same shortfalls. The UAG favored achieving high performance (measured by precision and recall), but strongly recommended the addition of features that facilitate the identification of correct gene and its identifier, such as contextual information to assist in disambiguation.DiscussionThe IAT was an informative exercise that advanced the dialog between curators and developers and increased the appreciation of challenges faced by each group. A major conclusion was that the intended users should be actively involved in every phase of software development, and this will be strongly encouraged in future tasks. The IAT Task provides the first steps toward the definition of metrics and functional requirements that are necessary for designing a formal evaluation of interactive curation systems in the BioCreative IV challenge.

Simple and efficient machine learning frameworks for identifying protein-protein interaction relevant articles and experimental methods used to study the interactions

BackgroundProtein-protein interaction (PPI) is an important biomedical phenomenon. Automatically detecting PPI-relevant articles and identifying methods that are used to study PPI are important text mining tasks. In this study, we have explored domain independent features to develop two open source machine learning frameworks. One performs binary classification to determine whether the given article is PPI relevant or not, named “Simple Classifier”, and the other one maps the PPI relevant articles with corresponding interaction method nodes in a standardized PSI-MI (Proteomics Standards Initiative-Molecular Interactions) ontology, named “OntoNorm”.ResultsWe evaluated our system in the context of BioCreative challenge competition using the standardized data set. Our systems are amongst the top systems reported by the organizers, attaining 60.8% F1-score for identifying relevant documents, and 52.3% F1-score for mapping articles to interaction method ontology.ConclusionOur results show that domain-independent machine learning frameworks can perform competitively well at the tasks of detecting PPI relevant articles and identifying the methods that were used to study the interaction in such articles.AvailabilitySimple Classifier is available at http://sourceforge.net/p/simpleclassify/home/ and OntoNorm at http://sourceforge.net/p/ontonorm/home/.

Benchmarking of the 2010 BioCreative Challenge III text-mining competition by the BioGRID and MINT interaction databases

BackgroundThe vast amount of data published in the primary biomedical literature represents a challenge for the automated extraction and codification of individual data elements. Biological databases that rely solely on manual extraction by expert curators are unable to comprehensively annotate the information dispersed across the entire biomedical literature. The development of efficient tools based on natural language processing (NLP) systems is essential for the selection of relevant publications, identification of data attributes and partially automated annotation. One of the tasks of the Biocreative 2010 Challenge III was devoted to the evaluation of NLP systems developed to identify articles for curation and extraction of protein-protein interaction (PPI) data.ResultsThe Biocreative 2010 competition addressed three tasks: gene normalization, article classification and interaction method identification. The BioGRID and MINT protein interaction databases both participated in the generation of the test publication set for gene normalization, annotated the development and test sets for article classification, and curated the test set for interaction method classification. These test datasets served as a gold standard for the evaluation of data extraction algorithms.ConclusionThe development of efficient tools for extraction of PPI data is a necessary step to achieve full curation of the biomedical literature. NLP systems can in the first instance facilitate expert curation by refining the list of candidate publications that contain PPI data; more ambitiously, NLP approaches may be able to directly extract relevant information from full-text articles for rapid inspection by expert curators. Close collaboration between biological databases and NLP systems developers will continue to facilitate the long-term objectives of both disciplines.

Multi-stage gene normalization for full-text articles with context-based species filtering for dynamic dictionary entry selection

BackgroundGene normalization (GN) is the task of identifying the unique database IDs of genes and proteins in literature. The best-known public competition of GN systems is the GN task of the BioCreative challenge, which has been held four times since 2003. The last two BioCreatives, II.5 & III, had two significant differences from earlier tasks: firstly, they provided full-length articles in addition to abstracts; and secondly, they included multiple species without providing species ID information. Full papers introduce more complex targets for GN processing, while the inclusion of multiple species vastly increases the potential size of dictionaries needed for GN. BioCreative III GN uses Threshold Average Precision at a median of k errors per query (TAP-k), a new measure closely related to the well-known average precision, but also reflecting the reliability of the score provided by each GN system.ResultsTo use full-paper text, we employed a multi-stage GN algorithm and a ranking method which exploit information in different sections and parts of a paper. To handle the inclusion of multiple unknown species, we developed two context-based dynamic strategies to select dictionary entries related to the species that appear in the paper—section-wide and article-wide context. Our originally submitted BioCreative III system uses a static dictionary containing only the most common species entries. It already exceeds the BioCreative III average team performance by at least 24% in every evaluation. However, using our proposed dynamic dictionary strategies, we were able to further improve TAP-5, TAP-10, and TAP-20 by 16.47%, 13.57% and 6.01%, respectively in the Gold 50 test set. Our best dynamic strategy outperforms the best BioCreative III systems in TAP-10 on the Silver 50 test set and in TAP-5 on the Silver 507 set.ConclusionsOur experimental results demonstrate the superiority of our proposed dynamic dictionary selection strategies over our original static strategy and most BioCreative III participant systems. Section-wide dynamic strategy is preferred because it achieves very similar TAP-k scores to article-wide dynamic strategy but it is more efficient.

Collective classification of textual documents by guided self-organization in T-Cell cross-regulation dynamics

We present and study an agent-based model of T-Cell cross-regulation in the adaptive immune system, which we apply to binary classification. Our method expands an existing analytical model of T-cell cross-regulation (Carneiro et al. in Immunol Rev 216(1):48-68, 2007) that was used to study the self-organizing dynamics of a single population of T-Cells in interaction with an idealized antigen presenting cell capable of presenting a single antigen. With agent-based modeling we are able to study the self-organizing dynamics of multiple populations of distinct T-cells which interact via antigen presenting cells that present hundreds of distinct antigens. Moreover, we show that such self-organizing dynamics can be guided to produce an effective binary classification of antigens, which is competitive with existing machine learning methods when applied to biomedical text classification. More specifically, here we test our model on a dataset of publicly available full-text biomedical articles provided by the BioCreative challenge (Krallinger in The biocreative ii. 5 challenge overview, p 19, 2009). We study the robustness of our model's parameter configurations, and show that it leads to encouraging results comparable to state-of-the-art classifiers. Our results help us understand both T-cell cross-regulation as a general principle of guided self-organization, as well as its applicability to document classification. Therefore, we show that our bio-inspired algorithm is a promising novel method for biomedical article classification and for binary document classification in general.

The PPI affix dictionary (PPIAD) and BioMethod Lexicon: importance of affixes and tags for recognition of entity mentions and experimental protein interactions

Substantial text mining efforts are being devoted to detect protein mentions and protein-protein interaction (PPI) relations from scientific articles [1,2]. In this context, the BioCreative challenge showed that the correct identification of the individual interactor proteins is still a challenging task, especially when using full text articles [2]. A systematic analysis of particularities of protein mentions in the context of interaction descriptions was nonetheless missing. Experimental biologists often use specific fusion proteins or protein-tags such as -GST, -His, -Myc, FLAG-, antibodies or fluorescent protein (GFP, YFP, CFP and RFP) tags to detect and visualize interactions. These tags are often mentioned as affixes of the target proteins in the literature. The importance of affixes in biomedical text mining had been addressed in case of affixal negation expressions [3], to consider general posttranslational modifications of proteins [4] and can be observed in trigger verbs used for interaction extraction [5]. We carried out a detailed study on the presence of common affixes belonging to interactor protein mentions in full text sentences considered by database curators as evidential support for experimentally characterized physical protein interactions. Furthermore, we tried to determine whether specific affixes might be useful to detect PPI relevant articles and to correlate affix mentions with particular interaction detection methods. Based on examination of over 3,000 of the previously referred interaction evidence passages we have compiled a collection of 277 interaction relevant affixes (89 suffixes, 176 prefixes and 12 that could be both), which were structured into 36 affix tag classes (26 super-affix and 10 combined or sub-affix classes). Figure 1A shows the frequency of mention of each of the affix tag classes. In the resulting PPI affix dictionary (PPIAD), each affix tag class has been manually linked to experimental qualifiers represented by associated PSI-MI ontology [5] concepts by considering their concept definitions. Additionally, statistical associations of affix tag classes to PSI-MI interaction detection method concepts have been derived through curator-based annotations of the evidence passages. To overcome the limited scope and lexical coverage of terms contained in the PSI-MI ontology we build the BioMethod Lexicon, a collection of experimental method terms important for protein interaction and gene regulation relations, and characterized method term co-mentions with affix tag classes. Within a total set of 6,300 interaction evidence sentences, 1,946 (31 %) mentioned at least one interaction relevant affix, which shows that it is a relatively common feature of interaction descriptions. Using statistical analysis of associations between affix classes and interaction detection method annotations (Chi-square test) we discovered that some of the affix classes showed strong associations to interaction methods, such as between: MI:0096 AF_21 (MI: pull down and PPIAD: gst_pull_down_tag), MI:0676 AF_6 (tandem affinity purification and Tandem_Affinity_Purification_tag), MI:0018 AF_10 (two hybrid and Gal4_tag), MI:0006 AF_4 (anti bait coimmunoprecipitation and Antibody_tag), MI:0055 AF_15 (fluorescent * Correspondence: mkrallinger@cnio.es Structural Biology and BioComputing Programme, Spanish National Cancer Research Centre, Madrid, Spain Full list of author information is available at the end of the article Krallinger et al. BMC Bioinformatics 2010, 11(Suppl 5):O1 http://www.biomedcentral.com/1471-2105/11/S5/O1

Linking genes to literature: text mining, information extraction, and retrieval applications for biology

Efficient access to information contained in online scientific literature collections is essential for life science research, playing a crucial role from the initial stage of experiment planning to the final interpretation and communication of the results. The biological literature also constitutes the main information source for manual literature curation used by expert-curated databases. Following the increasing popularity of web-based applications for analyzing biological data, new text-mining and information extraction strategies are being implemented. These systems exploit existing regularities in natural language to extract biologically relevant information from electronic texts automatically. The aim of the BioCreative challenge is to promote the development of such tools and to provide insight into their performance. This review presents a general introduction to the main characteristics and applications of currently available text-mining systems for life sciences in terms of the following: the type of biological information demands being addressed; the level of information granularity of both user queries and results; and the features and methods commonly exploited by these applications. The current trend in biomedical text mining points toward an increasing diversification in terms of application types and techniques, together with integration of domain-specific resources such as ontologies. Additional descriptions of some of the systems discussed here are available on the internet .

Evaluation of text-mining systems for biology: overview of the Second BioCreative community challenge

Background:Genome sciences have experienced an increasing demand for efficient text-processing tools that can extract biologically relevant information from the growing amount of published literature. In response, a range of text-mining and information-extraction tools have recently been developed specifically for the biological domain. Such tools are only useful if they are designed to meet real-life tasks and if their performance can be estimated and compared. The BioCreative challenge (Critical Assessment of Information Extraction in Biology) consists of a collaborative initiative to provide a common evaluation framework for monitoring and assessing the state-of-the-art of text-mining systems applied to biologically relevant problems.Results:The Second BioCreative assessment (2006 to 2007) attracted 44 teams from 13 countries worldwide, with the aim of evaluating current information-extraction/text-mining technologies developed for one or more of the three tasks defined for this challenge evaluation. These tasks included the recognition of gene mentions in abstracts (gene mention task); the extraction of a list of unique identifiers for human genes mentioned in abstracts (gene normalization task); and finally the extraction of physical protein-protein interaction annotation-relevant information (protein-protein interaction task). The 'gold standard' data used for evaluating submissions for the third task was provided by the interaction databases MINT (Molecular Interaction Database) and IntAct.Conclusion:The Second BioCreative assessment almost doubled the number of participants for each individual task when compared with the first BioCreative assessment. An overall improvement in terms of balanced precision and recall was observed for the best submissions for the gene mention (F score 0.87); for the gene normalization task, the best results were comparable (F score 0.81) compared with results obtained for similar tasks posed at the first BioCreative challenge. In case of the protein-protein interaction task, the importance and difficulties of experimentally confirmed annotation extraction from full-text articles were explored, yielding different results depending on the step of the annotation extraction workflow. A common characteristic observed in all three tasks was that the combination of system outputs could yield better results than any single system. Finally, the development of the first text-mining meta-server was promoted within the context of this community challenge.

Uncovering protein interaction in abstracts and text using a novel linear model and word proximity networks

Background:We participated in three of the protein-protein interaction subtasks of the Second BioCreative Challenge: classification of abstracts relevant for protein-protein interaction (interaction article subtask [IAS]), discovery of protein pairs (interaction pair subtask [IPS]), and identification of text passages characterizing protein interaction (interaction sentences subtask [ISS]) in full-text documents. We approached the abstract classification task with a novel, lightweight linear model inspired by spam detection techniques, as well as an uncertainty-based integration scheme. We also used a support vector machine and singular value decomposition on the same features for comparison purposes. Our approach to the full-text subtasks (protein pair and passage identification) includes a feature expansion method based on word proximity networks.Results:Our approach to the abstract classification task (IAS) was among the top submissions for this task in terms of measures of performance used in the challenge evaluation (accuracy, F-score, and area under the receiver operating characteristic curve). We also report on a web tool that we produced using our approach: the Protein Interaction Relevance Evaluator (PIARE). Our approach to the full-text tasks resulted in one of the highest recall rates as well as mean reciprocal rank of correct passages.Conclusion:Our approach to abstract classification shows that a simple linear model, using relatively few features, can generalize and uncover the conceptual nature of protein-protein interactions from the bibliome. Because the novel approach is based on a rather lightweight linear model, it can easily be ported and applied to similar problems. In full-text problems, the expansion of word features with word proximity networks is shown to be useful, although the need for some improvements is discussed.