Cascaded classifiers for confidence-based chemical named entity recognition

EnzChemRED, a rich enzyme chemistry relation extraction dataset

Expert curation is essential to capture knowledge of enzyme functions from the scientific literature in FAIR open knowledgebases but cannot keep pace with the rate of new discoveries and new publications. In this work we present EnzChemRED, for Enzyme Chemistry Relation Extraction Dataset, a new training and benchmarking dataset to support the development of Natural Language Processing (NLP) methods such as (large) language models that can assist enzyme curation. EnzChemRED consists of 1,210 expert curated PubMed abstracts where enzymes and the chemical reactions they catalyze are annotated using identifiers from the protein knowledgebase UniProtKB and the chemical ontology ChEBI. We show that fine-tuning language models with EnzChemRED significantly boosts their ability to identify proteins and chemicals in text (86.30% F1 score) and to extract the chemical conversions (86.66% F1 score) and the enzymes that catalyze those conversions (83.79% F1 score). We apply our methods to abstracts at PubMed scale to create a draft map of enzyme functions in literature to guide curation efforts in UniProtKB and the reaction knowledgebase Rhea.

Supporting the working life exposome: Annotating occupational exposure for enhanced literature search

An individual's likelihood of developing non-communicable diseases is often influenced by the types, intensities and duration of exposures at work. Job exposure matrices provide exposure estimates associated with different occupations. However, due to their time-consuming expert curation process, job exposure matrices currently cover only a subset of possible workplace exposures and may not be regularly updated. Scientific literature articles describing exposure studies provide important supporting evidence for developing and updating job exposure matrices, since they report on exposures in a variety of occupational scenarios. However, the constant growth of scientific literature is increasing the challenges of efficiently identifying relevant articles and important content within them. Natural language processing methods emulate the human process of reading and understanding texts, but in a fraction of the time. Such methods can increase the efficiency of both finding relevant documents and pinpointing specific information within them, which could streamline the process of developing and updating job exposure matrices. Named entity recognition is a fundamental natural language processing method for language understanding, which automatically identifies mentions of domain-specific concepts (named entities) in documents, e.g., exposures, occupations and job tasks. State-of-the-art machine learning models typically use evidence from an annotated corpus, i.e., a set of documents in which named entities are manually marked up (annotated) by experts, to learn how to detect named entities automatically in new documents. We have developed a novel annotated corpus of scientific articles to support machine learning based named entity recognition relevant to occupational substance exposures. Through incremental refinements to the annotation process, we demonstrate that expert annotators can attain high levels of agreement, and that the corpus can be used to train high-performance named entity recognition models. The corpus thus constitutes an important foundation for the wider development of natural language processing tools to support the study of occupational exposures.

A Narrative Literature Review of Natural Language Processing Applied to the Occupational Exposome

The evolution of the Exposome concept revolutionised the research in exposure assessment and epidemiology by introducing the need for a more holistic approach on the exploration of the relationship between the environment and disease. At the same time, further and more dramatic changes have also occurred on the working environment, adding to the already existing dynamic nature of it. Natural Language Processing (NLP) refers to a collection of methods for identifying, reading, extracting and untimely transforming large collections of language. In this work, we aim to give an overview of how NLP has successfully been applied thus far in Exposome research. Methods: We conduct a literature search on PubMed, Scopus and Web of Science for scientific articles published between 2011 and 2021. We use both quantitative and qualitative methods to screen papers and provide insights into the inclusion and exclusion criteria. We outline our approach for article selection and provide an overview of our findings. This is followed by a more detailed insight into selected articles. Results: Overall, 6420 articles were screened for the suitability of this review, where we review 37 articles in depth. Finally, we discuss future avenues of research and outline challenges in existing work. Conclusions: Our results show that (i) there has been an increase in articles published that focus on applying NLP to exposure and epidemiology research, (ii) most work uses existing NLP tools and (iii) traditional machine learning is the most popular approach.

Quantifying the advantage of domain-specific pre-training on named entity recognition tasks in materials science

A bottleneck in efficiently connecting new materials discoveries to established literature has arisen due to an increase in publications. This problem may be addressed by using named entity recognition (NER) to extract structured summary-level data from unstructured materials science text. We compare the performance of four NER models on three materials science datasets. The four models include a bidirectional long short-term memory (BiLSTM) and three transformer models (BERT, SciBERT, and MatBERT) with increasing degrees of domain-specific materials science pre-training. MatBERT improves over the other two BERT_BASE-based models by 1%∼12%, implying that domain-specific pre-training provides measurable advantages. Despite relative architectural simplicity, the BiLSTM model consistently outperforms BERT, perhaps due to its domain-specific pre-trained word embeddings. Furthermore, MatBERT and SciBERT models outperform the original BERT model to a greater extent in the small data limit. MatBERT’s higher-quality predictions should accelerate the extraction of structured data from materials science literature.

•

Efficient extraction of information from materials science literature is needed

•

Domain-specific materials science pre-training improves results

•

Even simpler domain-specific models can outperform more complex general models

A bottleneck in efficiently connecting new materials discoveries to established literature has arisen due to a massive increase in publications. Four different language models are trained to automatically collect important information from materials science articles. We compare a simple model (BiLSTM) with materials science knowledge to three variants of a more complex model: one with general knowledge (BERT), one with general scientific knowledge (SciBERT), and one with materials science knowledge (MatBERT). We find that MatBERT performs the best overall. This implies that language models with greater extents of materials science knowledge will perform better on materials science-related tasks. The simpler model even consistently outperforms BERT. Furthermore, the performance gaps grow when the models are given fewer examples of information extraction to learn from. MatBERT’s higher-quality results should accelerate the collection of information from materials science literature.

Opportunities and challenges of text mining in aterials research

Research publications are the major repository of scientific knowledge. However, their unstructured and highly heterogenous format creates a significant obstacle to large-scale analysis of the information contained within. Recent progress in natural language processing (NLP) has provided a variety of tools for high-quality information extraction from unstructured text. These tools are primarily trained on non-technical text and struggle to produce accurate results when applied to scientific text, involving specific technical terminology. During the last years, significant efforts in information retrieval have been made for biomedical and biochemical publications. For materials science, text mining (TM) methodology is still at the dawn of its development. In this review, we survey the recent progress in creating and applying TM and NLP approaches to materials science field. This review is directed at the broad class of researchers aiming to learn the fundamentals of TM as applied to the materials science publications.

Adverse drug event and medication extraction in electronic health records via a cascading architecture with different sequence labeling models and word embeddings

OBJECTIVE

An adverse drug event (ADE) refers to an injury resulting from medical intervention related to a drug including harm caused by drugs or from the usage of drugs. Extracting ADEs from clinical records can help physicians associate adverse events to targeted drugs.

MATERIALS AND METHODS

We proposed a cascading architecture to recognize medical concepts including ADEs, drug names, and entities related to drugs. The architecture includes a preprocessing method and an ensemble of conditional random fields (CRFs) and neural network-based models to respectively address the challenges of surrogate string and overlapping annotation boundaries observed in the employed ADEs and medication extraction (ADME) corpus. The effectiveness of applying different pretrained and postprocessed word embeddings for the ADME task was also studied.

RESULTS

The empirical results showed that both CRFs and neural network-based models provide promising solution for the ADME task. The neural network-based models particularly outperformed CRFs in concept types involving narrative descriptions. Our best run achieved an overall micro F-score of 0.919 on the employed corpus. Our results also suggested that the Global Vectors for word representation embedding in general domain provides a very strong baseline, which can be further improved by applying the principal component analysis to generate more isotropic vectors.

CONCLUSIONS

We have demonstrated that the proposed cascading architecture can handle the problem of overlapped annotations and further improve the overall recall and F-scores because the architecture enables the developed models to exploit more context information and forms an ensemble for creating a stronger recognizer.

Chemlistem: chemical named entity recognition using recurrent neural networks

Chemical named entity recognition (NER) has traditionally been dominated by conditional random fields (CRF)-based approaches but given the success of the artificial neural network techniques known as “deep learning” we decided to examine them as an alternative to CRFs. We present here several chemical named entity recognition systems. The first system translates the traditional CRF-based idioms into a deep learning framework, using rich per-token features and neural word embeddings, and producing a sequence of tags using bidirectional long short term memory (LSTM) networks—a type of recurrent neural net. The second system eschews the rich feature set—and even tokenisation—in favour of character labelling using neural character embeddings and multiple LSTM layers. The third system is an ensemble that combines the results of the first two systems. Our original BioCreative V.5 competition entry was placed in the top group with the highest F scores, and subsequent using transfer learning have achieved a final F score of 90.33% on the test data (precision 91.47%, recall 89.21%).

Information Retrieval and Text Mining Technologies for Chemistry

Efficient access to chemical information contained in scientific literature, patents, technical reports, or the web is a pressing need shared by researchers and patent attorneys from different chemical disciplines. Retrieval of important chemical information in most cases starts with finding relevant documents for a particular chemical compound or family. Targeted retrieval of chemical documents is closely connected to the automatic recognition of chemical entities in the text, which commonly involves the extraction of the entire list of chemicals mentioned in a document, including any associated information. In this Review, we provide a comprehensive and in-depth description of fundamental concepts, technical implementations, and current technologies for meeting these information demands. A strong focus is placed on community challenges addressing systems performance, more particularly CHEMDNER and CHEMDNER patents tasks of BioCreative IV and V, respectively. Considering the growing interest in the construction of automatically annotated chemical knowledge bases that integrate chemical information and biological data, cheminformatics approaches for mapping the extracted chemical names into chemical structures and their subsequent annotation together with text mining applications for linking chemistry with biological information are also presented. Finally, future trends and current challenges are highlighted as a roadmap proposal for research in this emerging field.

A framework for ontology-based question answering with application to parasite immunology

Background

Large quantities of biomedical data are being produced at a rapid pace for a variety of organisms. With ontologies proliferating, data is increasingly being stored using the RDF data model and queried using RDF based querying languages. While existing systems facilitate the querying in various ways, the scientist must map the question in his or her mind to the interface used by the systems. The field of natural language processing has long investigated the challenges of designing natural language based retrieval systems. Recent efforts seek to bring the ability to pose natural language questions to RDF data querying systems while leveraging the associated ontologies. These analyze the input question and extract triples (subject, relationship, object), if possible, mapping them to RDF triples in the data. However, in the biomedical context, relationships between entities are not always explicit in the question and these are often complex involving many intermediate concepts.

Results

We present a new framework, OntoNLQA, for querying RDF data annotated using ontologies which allows posing questions in natural language. OntoNLQA offers five steps in order to answer natural language questions. In comparison to previous systems, OntoNLQA differs in how some of the methods are realized. In particular, it introduces a novel approach for discovering the sophisticated semantic associations that may exist between the key terms of a natural language question, in order to build an intuitive query and retrieve precise answers. We apply this framework to the context of parasite immunology data, leading to a system called AskCuebee that allows parasitologists to pose genomic, proteomic and pathway questions in natural language related to the parasite, Trypanosoma cruzi. We separately evaluate the accuracy of each component of OntoNLQA as implemented in AskCuebee and the accuracy of the whole system. AskCuebee answers 68 % of the questions in a corpus of 125 questions, and 60 % of the questions in a new previously unseen corpus. If we allow simple corrections by the scientists, this proportion increases to 92 %.

Conclusions

We introduce a novel framework for question answering and apply it to parasite immunology data. Evaluations of translating the questions to RDF triple queries by combining machine learning, lexical similarity matching with ontology classes, properties and instances for specificity, and discovering associations between them demonstrate that the approach performs well and improves on previous systems. Subsequently, OntoNLQA offers a viable framework for building question answering systems in other biomedical domains.

Electronic supplementary material

The online version of this article (doi:10.1186/s13326-015-0029-x) contains supplementary material, which is available to authorized users.

Overview of the Cancer Genetics and Pathway Curation tasks of BioNLP Shared Task 2013

BACKGROUND

Since their introduction in 2009, the BioNLP Shared Task events have been instrumental in advancing the development of methods and resources for the automatic extraction of information from the biomedical literature. In this paper, we present the Cancer Genetics (CG) and Pathway Curation (PC) tasks, two event extraction tasks introduced in the BioNLP Shared Task 2013. The CG task focuses on cancer, emphasizing the extraction of physiological and pathological processes at various levels of biological organization, and the PC task targets reactions relevant to the development of biomolecular pathway models, defining its extraction targets on the basis of established pathway representations and ontologies.

RESULTS

Six groups participated in the CG task and two groups in the PC task, together applying a wide range of extraction approaches including both established state-of-the-art systems and newly introduced extraction methods. The best-performing systems achieved F-scores of 55% on the CG task and 53% on the PC task, demonstrating a level of performance comparable to the best results achieved in similar previously proposed tasks.

CONCLUSIONS

The results indicate that existing event extraction technology can generalize to meet the novel challenges represented by the CG and PC task settings, suggesting that extraction methods are capable of supporting the construction of knowledge bases on the molecular mechanisms of cancer and the curation of biomolecular pathway models. The CG and PC tasks continue as open challenges for all interested parties, with data, tools and resources available from the shared task homepage.

Curatable Named-Entity Recognition Using Semantic Relations

Named-entity recognition (NER) plays an important role in the development of biomedical databases. However, the existing NER tools produce multifarious named-entities which may result in both curatable and non-curatable markers. To facilitate biocuration with a straightforward approach, classifying curatable named-entities is helpful with regard to accelerating the biocuration workflow. Co-occurrence Interaction Nexus with Named-entity Recognition (CoINNER) is a web-based tool that allows users to identify genes, chemicals, diseases, and action term mentions in the Comparative Toxicogenomic Database (CTD). To further discover interactions, CoINNER uses multiple advanced algorithms to recognize the mentions in the BioCreative IV CTD Track. CoINNER is developed based on a prototype system that annotated gene, chemical, and disease mentions in PubMed abstracts at BioCreative 2012 Track I (literature triage). We extended our previous system in developing CoINNER. The pre-tagging results of CoINNER were developed based on the state-of-the-art named entity recognition tools in BioCreative III. Next, a method based on conditional random fields (CRFs) is proposed to predict chemical and disease mentions in the articles. Finally, action term mentions were collected by latent Dirichlet allocation (LDA). At the BioCreative IV CTD Track, the best F-measures reached for gene/protein, chemical/drug and disease NER were 54 percent while CoINNER achieved a 61.5 percent F-measure. System URL: http://ikmbio.csie.ncku.edu.tw/coinner/ introduction.htm.

Application of text mining in the biomedical domain

In recent years the amount of experimental data that is produced in biomedical research and the number of papers that are being published in this field have grown rapidly. In order to keep up to date with developments in their field of interest and to interpret the outcome of experiments in light of all available literature, researchers turn more and more to the use of automated literature mining. As a consequence, text mining tools have evolved considerably in number and quality and nowadays can be used to address a variety of research questions ranging from de novo drug target discovery to enhanced biological interpretation of the results from high throughput experiments. In this paper we introduce the most important techniques that are used for a text mining and give an overview of the text mining tools that are currently being used and the type of problems they are typically applied for.

Enhancing of chemical compound and drug name recognition using representative tag scheme and fine-grained tokenization

Background

The functions of chemical compounds and drugs that affect biological processes and their particular effect on the onset and treatment of diseases have attracted increasing interest with the advancement of research in the life sciences. To extract knowledge from the extensive literatures on such compounds and drugs, the organizers of BioCreative IV administered the CHEMical Compound and Drug Named Entity Recognition (CHEMDNER) task to establish a standard dataset for evaluating state-of-the-art chemical entity recognition methods.

Methods

This study introduces the approach of our CHEMDNER system. Instead of emphasizing the development of novel feature sets for machine learning, this study investigates the effect of various tag schemes on the recognition of the names of chemicals and drugs by using conditional random fields. Experiments were conducted using combinations of different tokenization strategies and tag schemes to investigate the effects of tag set selection and tokenization method on the CHEMDNER task.

Results

This study presents the performance of CHEMDNER of three more representative tag schemes-IOBE, IOBES, and IOB₁₂E-when applied to a widely utilized IOB tag set and combined with the coarse-/fine-grained tokenization methods. The experimental results thus reveal that the fine-grained tokenization strategy performance best in terms of precision, recall and F-scores when the IOBES tag set was utilized. The IOBES model with fine-grained tokenization yielded the best-F-scores in the six chemical entity categories other than the "Multiple" entity category. Nonetheless, no significant improvement was observed when a more representative tag schemes was used with the coarse or fine-grained tokenization rules. The best F-scores that were achieved using the developed system on the test dataset of the CHEMDNER task were 0.833 and 0.815 for the chemical documents indexing and the chemical entity mention recognition tasks, respectively.

Conclusions

The results herein highlight the importance of tag set selection and the use of different tokenization strategies. Fine-grained tokenization combined with the tag set IOBES most effectively recognizes chemical and drug names. To the best of the authors' knowledge, this investigation is the first comprehensive investigation use of various tag set schemes combined with different tokenization strategies for the recognition of chemical entities.

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

Background

The 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.

Results

Our 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.

Conclusion

The 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.

The CHEMDNER corpus of chemicals and drugs and its annotation principles

The automatic extraction of chemical information from text requires the recognition of chemical entity mentions as one of its key steps. When developing supervised named entity recognition (NER) systems, the availability of a large, manually annotated text corpus is desirable. Furthermore, large corpora permit the robust evaluation and comparison of different approaches that detect chemicals in documents. We present the CHEMDNER corpus, a collection of 10,000 PubMed abstracts that contain a total of 84,355 chemical entity mentions labeled manually by expert chemistry literature curators, following annotation guidelines specifically defined for this task. The abstracts of the CHEMDNER corpus were selected to be representative for all major chemical disciplines. Each of the chemical entity mentions was manually labeled according to its structure-associated chemical entity mention (SACEM) class: abbreviation, family, formula, identifier, multiple, systematic and trivial. The difficulty and consistency of tagging chemicals in text was measured using an agreement study between annotators, obtaining a percentage agreement of 91. For a subset of the CHEMDNER corpus (the test set of 3,000 abstracts) we provide not only the Gold Standard manual annotations, but also mentions automatically detected by the 26 teams that participated in the BioCreative IV CHEMDNER chemical mention recognition task. In addition, we release the CHEMDNER silver standard corpus of automatically extracted mentions from 17,000 randomly selected PubMed abstracts. A version of the CHEMDNER corpus in the BioC format has been generated as well. We propose a standard for required minimum information about entity annotations for the construction of domain specific corpora on chemical and drug entities. The CHEMDNER corpus and annotation guidelines are available at: http://www.biocreative.org/resources/biocreative-iv/chemdner-corpus/.

A document processing pipeline for annotating chemical entities in scientific documents

Background

The recognition of drugs and chemical entities in text is a very important task within the field of biomedical information extraction, given the rapid growth in the amount of published texts (scientific papers, patents, patient records) and the relevance of these and other related concepts. If done effectively, this could allow exploiting such textual resources to automatically extract or infer relevant information, such as drug profiles, relations and similarities between drugs, or associations between drugs and potential drug targets. The objective of this work was to develop and validate a document processing and information extraction pipeline for the identification of chemical entity mentions in text.

Results

We used the BioCreative IV CHEMDNER task data to train and evaluate a machine-learning based entity recognition system. Using a combination of two conditional random field models, a selected set of features, and a post-processing stage, we achieved F-measure results of 87.48% in the chemical entity mention recognition task and 87.75% in the chemical document indexing task.

Conclusions

We present a machine learning-based solution for automatic recognition of chemical and drug names in scientific documents. The proposed approach applies a rich feature set, including linguistic, orthographic, morphological, dictionary matching and local context features. Post-processing modules are also integrated, performing parentheses correction, abbreviation resolution and filtering erroneous mentions using an exclusion list derived from the training data. The developed methods were implemented as a document annotation tool and web service, freely available at http://bioinformatics.ua.pt/becas-chemicals/.

Incorporating domain knowledge in chemical and biomedical named entity recognition with word representations

Background

Chemical and biomedical Named Entity Recognition (NER) is an essential prerequisite task before effective text mining can begin for biochemical-text data. Exploiting unlabeled text data to leverage system performance has been an active and challenging research topic in text mining due to the recent growth in the amount of biomedical literature.

We present a semi-supervised learning method that efficiently exploits unlabeled data in order to incorporate domain knowledge into a named entity recognition model and to leverage system performance. The proposed method includes Natural Language Processing (NLP) tasks for text preprocessing, learning word representation features from a large amount of text data for feature extraction, and conditional random fields for token classification. Other than the free text in the domain, the proposed method does not rely on any lexicon nor any dictionary in order to keep the system applicable to other NER tasks in bio-text data.

Results

We extended BANNER, a biomedical NER system, with the proposed method. This yields an integrated system that can be applied to chemical and drug NER or biomedical NER. We call our branch of the BANNER system BANNER-CHEMDNER, which is scalable over millions of documents, processing about 530 documents per minute, is configurable via XML, and can be plugged into other systems by using the BANNER Unstructured Information Management Architecture (UIMA) interface.

BANNER-CHEMDNER achieved an 85.68% and an 86.47% F-measure on the testing sets of CHEMDNER Chemical Entity Mention (CEM) and Chemical Document Indexing (CDI) subtasks, respectively, and achieved an 87.04% F-measure on the official testing set of the BioCreative II gene mention task, showing remarkable performance in both chemical and biomedical NER. BANNER-CHEMDNER system is available at: https://bitbucket.org/tsendeemts/banner-chemdner.

Text-mining-assisted biocuration workflows in Argo

Biocuration activities have been broadly categorized into the selection of relevant documents, the annotation of biological concepts of interest and identification of interactions between the concepts. Text mining has been shown to have a potential to significantly reduce the effort of biocurators in all the three activities, and various semi-automatic methodologies have been integrated into curation pipelines to support them. We investigate the suitability of Argo, a workbench for building text-mining solutions with the use of a rich graphical user interface, for the process of biocuration. Central to Argo are customizable workflows that users compose by arranging available elementary analytics to form task-specific processing units. A built-in manual annotation editor is the single most used biocuration tool of the workbench, as it allows users to create annotations directly in text, as well as modify or delete annotations created by automatic processing components. Apart from syntactic and semantic analytics, the ever-growing library of components includes several data readers and consumers that support well-established as well as emerging data interchange formats such as XMI, RDF and BioC, which facilitate the interoperability of Argo with other platforms or resources. To validate the suitability of Argo for curation activities, we participated in the BioCreative IV challenge whose purpose was to evaluate Web-based systems addressing user-defined biocuration tasks. Argo proved to have the edge over other systems in terms of flexibility of defining biocuration tasks. As expected, the versatility of the workbench inevitably lengthened the time the curators spent on learning the system before taking on the task, which may have affected the usability of Argo. The participation in the challenge gave us an opportunity to gather valuable feedback and identify areas of improvement, some of which have already been introduced. Database URL: http://argo.nactem.ac.uk.

Chemical named entities recognition: a review on approaches and applications

The rapid increase in the flow rate of published digital information in all disciplines has resulted in a pressing need for techniques that can simplify the use of this information. The chemistry literature is very rich with information about chemical entities. Extracting molecules and their related properties and activities from the scientific literature to "text mine" these extracted data and determine contextual relationships helps research scientists, particularly those in drug development. One of the most important challenges in chemical text mining is the recognition of chemical entities mentioned in the texts. In this review, the authors briefly introduce the fundamental concepts of chemical literature mining, the textual contents of chemical documents, and the methods of naming chemicals in documents. We sketch out dictionary-based, rule-based and machine learning, as well as hybrid chemical named entity recognition approaches with their applied solutions. We end with an outlook on the pros and cons of these approaches and the types of chemical entities extracted.

Text mining effectively scores and ranks the literature for improving chemical-gene-disease curation at the comparative toxicogenomics database

The Comparative Toxicogenomics Database (CTD; http://ctdbase.org/) is a public resource that curates interactions between environmental chemicals and gene products, and their relationships to diseases, as a means of understanding the effects of environmental chemicals on human health. CTD provides a triad of core information in the form of chemical-gene, chemical-disease, and gene-disease interactions that are manually curated from scientific articles. To increase the efficiency, productivity, and data coverage of manual curation, we have leveraged text mining to help rank and prioritize the triaged literature. Here, we describe our text-mining process that computes and assigns each article a document relevancy score (DRS), wherein a high DRS suggests that an article is more likely to be relevant for curation at CTD. We evaluated our process by first text mining a corpus of 14,904 articles triaged for seven heavy metals (cadmium, cobalt, copper, lead, manganese, mercury, and nickel). Based upon initial analysis, a representative subset corpus of 3,583 articles was then selected from the 14,094 articles and sent to five CTD biocurators for review. The resulting curation of these 3,583 articles was analyzed for a variety of parameters, including article relevancy, novel data content, interaction yield rate, mean average precision, and biological and toxicological interpretability. We show that for all measured parameters, the DRS is an effective indicator for scoring and improving the ranking of literature for the curation of chemical-gene-disease information at CTD. Here, we demonstrate how fully incorporating text mining-based DRS scoring into our curation pipeline enhances manual curation by prioritizing more relevant articles, thereby increasing data content, productivity, and efficiency.

ChemEx: information extraction system for chemical data curation

Background

Manual chemical data curation from publications is error-prone, time consuming, and hard to maintain up-to-date data sets. Automatic information extraction can be used as a tool to reduce these problems. Since chemical structures usually described in images, information extraction needs to combine structure image recognition and text mining together.

Results

We have developed ChemEx, a chemical information extraction system. ChemEx processes both text and images in publications. Text annotator is able to extract compound, organism, and assay entities from text content while structure image recognition enables translation of chemical raster images to machine readable format. A user can view annotated text along with summarized information of compounds, organism that produces those compounds, and assay tests.

Conclusions

ChemEx facilitates and speeds up chemical data curation by extracting compounds, organisms, and assays from a large collection of publications. The software and corpus can be downloaded from http://www.biotec.or.th/isl/ChemEx.

Collaborative biocuration--text-mining development task for document prioritization for curation

The Critical Assessment of Information Extraction systems in Biology (BioCreAtIvE) challenge evaluation is a community-wide effort for evaluating text mining and information extraction systems for the biological domain. The 'BioCreative Workshop 2012' subcommittee identified three areas, or tracks, that comprised independent, but complementary aspects of data curation in which they sought community input: literature triage (Track I); curation workflow (Track II) and text mining/natural language processing (NLP) systems (Track III). Track I participants were invited to develop tools or systems that would effectively triage and prioritize articles for curation and present results in a prototype web interface. Training and test datasets were derived from the Comparative Toxicogenomics Database (CTD; http://ctdbase.org) and consisted of manuscripts from which chemical-gene-disease data were manually curated. A total of seven groups participated in Track I. For the triage component, the effectiveness of participant systems was measured by aggregate gene, disease and chemical 'named-entity recognition' (NER) across articles; the effectiveness of 'information retrieval' (IR) was also measured based on 'mean average precision' (MAP). Top recall scores for gene, disease and chemical NER were 49, 65 and 82%, respectively; the top MAP score was 80%. Each participating group also developed a prototype web interface; these interfaces were evaluated based on functionality and ease-of-use by CTD's biocuration project manager. In this article, we present a detailed description of the challenge and a summary of the results.

Mining the pharmacogenomics literature--a survey of the state of the art

This article surveys efforts on text mining of the pharmacogenomics literature, mainly from the period 2008 to 2011. Pharmacogenomics (or pharmacogenetics) is the field that studies how human genetic variation impacts drug response. Therefore, publications span the intersection of research in genotypes, phenotypes and pharmacology, a topic that has increasingly become a focus of active research in recent years. This survey covers efforts dealing with the automatic recognition of relevant named entities (e.g. genes, gene variants and proteins, diseases and other pathological phenomena, drugs and other chemicals relevant for medical treatment), as well as various forms of relations between them. A wide range of text genres is considered, such as scientific publications (abstracts, as well as full texts), patent texts and clinical narratives. We also discuss infrastructure and resources needed for advanced text analytics, e.g. document corpora annotated with corresponding semantic metadata (gold standards and training data), biomedical terminologies and ontologies providing domain-specific background knowledge at different levels of formality and specificity, software architectures for building complex and scalable text analytics pipelines and Web services grounded to them, as well as comprehensive ways to disseminate and interact with the typically huge amounts of semiformal knowledge structures extracted by text mining tools. Finally, we consider some of the novel applications that have already been developed in the field of pharmacogenomic text mining and point out perspectives for future research.

ChemSpot: a hybrid system for chemical named entity recognition

MOTIVATION

The accurate identification of chemicals in text is important for many applications, including computer-assisted reconstruction of metabolic networks or retrieval of information about substances in drug development. But due to the diversity of naming conventions and traditions for such molecules, this task is highly complex and should be supported by computational tools.

RESULTS

We present ChemSpot, a named entity recognition (NER) tool for identifying mentions of chemicals in natural language texts, including trivial names, drugs, abbreviations, molecular formulas and International Union of Pure and Applied Chemistry entities. Since the different classes of relevant entities have rather different naming characteristics, ChemSpot uses a hybrid approach combining a Conditional Random Field with a dictionary. It achieves an F(1) measure of 68.1% on the SCAI corpus, outperforming the only other freely available chemical NER tool, OSCAR4, by 10.8 percentage points.

AVAILABILITY

ChemSpot is freely available at: http://www.informatik.hu-berlin.de/wbi/resources.

Chemical Entity Recognition and Resolution to ChEBI

Chemical entities are ubiquitous through the biomedical literature and the development of text-mining systems that can efficiently identify those entities are required. Due to the lack of available corpora and data resources, the community has focused its efforts in the development of gene and protein named entity recognition systems, but with the release of ChEBI and the availability of an annotated corpus, this task can be addressed. We developed a machine-learning-based method for chemical entity recognition and a lexical-similarity-based method for chemical entity resolution and compared them with Whatizit, a popular-dictionary-based method. Our methods outperformed the dictionary-based method in all tasks, yielding an improvement in F-measure of 20% for the entity recognition task, 2–5% for the entity-resolution task, and 15% for combined entity recognition and resolution tasks.

OSCAR4: a flexible architecture for chemical text-mining

The Open-Source Chemistry Analysis Routines (OSCAR) software, a toolkit for the recognition of named entities and data in chemistry publications, has been developed since 2002. Recent work has resulted in the separation of the core OSCAR functionality and its release as the OSCAR4 library. This library features a modular API (based on reduction of surface coupling) that permits client programmers to easily incorporate it into external applications. OSCAR4 offers a domain-independent architecture upon which chemistry specific text-mining tools can be built, and its development and usage are discussed.

Mining chemical information from open patents

Linked Open Data presents an opportunity to vastly improve the quality of science in all fields by increasing the availability and usability of the data upon which it is based. In the chemical field, there is a huge amount of information available in the published literature, the vast majority of which is not available in machine-understandable formats. PatentEye, a prototype system for the extraction and semantification of chemical reactions from the patent literature has been implemented and is discussed. A total of 4444 reactions were extracted from 667 patent documents that comprised 10 weeks' worth of publications from the European Patent Office (EPO), with a precision of 78% and recall of 64% with regards to determining the identity and amount of reactants employed and an accuracy of 92% with regards to product identification. NMR spectra reported as product characterisation data are additionally captured.

Text Mining for Drugs and Chemical Compounds: Methods, Tools and Applications

Providing prior knowledge about biological properties of chemicals, such as kinetic values, protein targets, or toxic effects, can facilitate many aspects of drug development. Chemical information is rapidly accumulating in all sorts of free text documents like patents, industry reports, or scientific articles, which has motivated the development of specifically tailored text mining applications. Despite the potential gains, chemical text mining still faces significant challenges. One of the most salient is the recognition of chemical entities mentioned in text. To help practitioners contribute to this area, a good portion of this review is devoted to this issue, and presents the basic concepts and principles underlying the main strategies. The technical details are introduced and accompanied by relevant bibliographic references. Other tasks discussed are retrieving relevant articles, identifying relationships between chemicals and other entities, or determining the chemical structures of chemicals mentioned in text. This review also introduces a number of published applications that can be used to build pipelines in topics like drug side effects, toxicity, and protein-disease-compound network analysis. We conclude the review with an outlook on how we expect the field to evolve, discussing its possibilities and its current limitations.

Using workflows to explore and optimise named entity recognition for chemistry

Chemistry text mining tools should be interoperable and adaptable regardless of system-level implementation, installation or even programming issues. We aim to abstract the functionality of these tools from the underlying implementation via reconfigurable workflows for automatically identifying chemical names. To achieve this, we refactored an established named entity recogniser (in the chemistry domain), OSCAR and studied the impact of each component on the net performance. We developed two reconfigurable workflows from OSCAR using an interoperable text mining framework, U-Compare. These workflows can be altered using the drag-&-drop mechanism of the graphical user interface of U-Compare. These workflows also provide a platform to study the relationship between text mining components such as tokenisation and named entity recognition (using maximum entropy Markov model (MEMM) and pattern recognition based classifiers). Results indicate that, for chemistry in particular, eliminating noise generated by tokenisation techniques lead to a slightly better performance than others, in terms of named entity recognition (NER) accuracy. Poor tokenisation translates into poorer input to the classifier components which in turn leads to an increase in Type I or Type II errors, thus, lowering the overall performance. On the Sciborg corpus, the workflow based system, which uses a new tokeniser whilst retaining the same MEMM component, increases the F-score from 82.35% to 84.44%. On the PubMed corpus, it recorded an F-score of 84.84% as against 84.23% by OSCAR.

ChemicalTagger: A tool for semantic text-mining in chemistry

Background

The primary method for scientific communication is in the form of published scientific articles and theses which use natural language combined with domain-specific terminology. As such, they contain free owing unstructured text. Given the usefulness of data extraction from unstructured literature, we aim to show how this can be achieved for the discipline of chemistry. The highly formulaic style of writing most chemists adopt make their contributions well suited to high-throughput Natural Language Processing (NLP) approaches.

Results

We have developed the ChemicalTagger parser as a medium-depth, phrase-based semantic NLP tool for the language of chemical experiments. Tagging is based on a modular architecture and uses a combination of OSCAR, domain-specific regex and English taggers to identify parts-of-speech. The ANTLR grammar is used to structure this into tree-based phrases. Using a metric that allows for overlapping annotations, we achieved machine-annotator agreements of 88.9% for phrase recognition and 91.9% for phrase-type identification (Action names).

Conclusions

It is possible parse to chemical experimental text using rule-based techniques in conjunction with a formal grammar parser. ChemicalTagger has been deployed for over 10,000 patents and has identified solvents from their linguistic context with >99.5% precision.

Identifying, Indexing, and Ranking Chemical Formulae and Chemical Names in Digital Documents

End-users utilize chemical search engines to search for chemical formulae and chemical names. Chemical search engines identify and index chemical formulae and chemical names appearing in text documents to support efficient search and retrieval in the future. Identifying chemical formulae and chemical names in text automatically has been a hard problem that has met with varying degrees of success in the past. We propose algorithms for chemical formula and chemical name tagging using Conditional Random Fields (CRFs) and Support Vector Machines (SVMs) that achieve higher accuracy than existing (published) methods. After chemical entities have been identified in text documents, they must be indexed. In order to support user-provided search queries that require a partial match between the chemical name segment used as a keyword or a partial chemical formula, all possible (or a significant number of) subformulae of formulae that appear in any document and all possible subterms (e.g., “methyl”) of chemical names (e.g., “methylethyl ketone”) must be indexed. Indexing all possible subformulae and subterms results in an exponential increase in the storage and memory requirements as well as the time taken to process the indices. We propose techniques to prune the indices significantly without reducing the quality of the returned results significantly. Finally, we propose multiple query semantics to allow users to pose different types of partial search queries for chemical entities. We demonstrate empirically that our search engines improve the relevance of the returned results for search queries involving chemical entities.

A systematic review of named entity recognition in biomedical texts

Biomedical Named Entities (NEs) are phrases or combinations of phrases that denote specific objects or groups of objects in the biomedical literature. Research on Named Entity Recognition (NER) is one of the most disseminated activities in the automatic processing of biomedical scientific articles. We analyzed articles relevant to NER in biomedical texts, in the period from 2007 to 2009, through a systematic review. The results identify the main methods in the recognition of Biomedical NEs, features and methodologies for a NER system implementation. Aside from the tendencies identified, some gaps are detected that may constitute opportunities for new studies in the area.

Mining metabolites: extracting the yeast metabolome from the literature

Text mining methods have added considerably to our capacity to extract biological knowledge from the literature. Recently the field of systems biology has begun to model and simulate metabolic networks, requiring knowledge of the set of molecules involved. While genomics and proteomics technologies are able to supply the macromolecular parts list, the metabolites are less easily assembled. Most metabolites are known and reported through the scientific literature, rather than through large-scale experimental surveys. Thus it is important to recover them from the literature. Here we present a novel tool to automatically identify metabolite names in the literature, and associate structures where possible, to define the reported yeast metabolome. With ten-fold cross validation on a manually annotated corpus, our recognition tool generates an f-score of 78.49 (precision of 83.02) and demonstrates greater suitability in identifying metabolite names than other existing recognition tools for general chemical molecules. The metabolite recognition tool has been applied to the literature covering an important model organism, the yeast Saccharomyces cerevisiae, to define its reported metabolome. By coupling to ChemSpider, a major chemical database, we have identified structures for much of the reported metabolome and, where structure identification fails, been able to suggest extensions to ChemSpider. Our manually annotated gold-standard data on 296 abstracts are available as supplementary materials. Metabolite names and, where appropriate, structures are also available as supplementary materials. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (doi:10.1007/s11306-010-0251-6) contains supplementary material, which is available to authorized users.

Automatic vs. manual curation of a multi-source chemical dictionary: the impact on text mining

BACKGROUND

Previously, we developed a combined dictionary dubbed Chemlist for the identification of small molecules and drugs in text based on a number of publicly available databases and tested it on an annotated corpus. To achieve an acceptable recall and precision we used a number of automatic and semi-automatic processing steps together with disambiguation rules. However, it remained to be investigated which impact an extensive manual curation of a multi-source chemical dictionary would have on chemical term identification in text. ChemSpider is a chemical database that has undergone extensive manual curation aimed at establishing valid chemical name-to-structure relationships.

RESULTS

We acquired the component of ChemSpider containing only manually curated names and synonyms. Rule-based term filtering, semi-automatic manual curation, and disambiguation rules were applied. We tested the dictionary from ChemSpider on an annotated corpus and compared the results with those for the Chemlist dictionary. The ChemSpider dictionary of ca. 80 k names was only a 1/3 to a 1/4 the size of Chemlist at around 300 k. The ChemSpider dictionary had a precision of 0.43 and a recall of 0.19 before the application of filtering and disambiguation and a precision of 0.87 and a recall of 0.19 after filtering and disambiguation. The Chemlist dictionary had a precision of 0.20 and a recall of 0.47 before the application of filtering and disambiguation and a precision of 0.67 and a recall of 0.40 after filtering and disambiguation.

CONCLUSIONS

We conclude the following: (1) The ChemSpider dictionary achieved the best precision but the Chemlist dictionary had a higher recall and the best F-score; (2) Rule-based filtering and disambiguation is necessary to achieve a high precision for both the automatically generated and the manually curated dictionary. ChemSpider is available as a web service at http://www.chemspider.com/ and the Chemlist dictionary is freely available as an XML file in Simple Knowledge Organization System format on the web at http://www.biosemantics.org/chemlist.

Text mining and manual curation of chemical-gene-disease networks for the comparative toxicogenomics database (CTD)

BACKGROUND

The Comparative Toxicogenomics Database (CTD) is a publicly available resource that promotes understanding about the etiology of environmental diseases. It provides manually curated chemical-gene/protein interactions and chemical- and gene-disease relationships from the peer-reviewed, published literature. The goals of the research reported here were to establish a baseline analysis of current CTD curation, develop a text-mining prototype from readily available open source components, and evaluate its potential value in augmenting curation efficiency and increasing data coverage.

RESULTS

Prototype text-mining applications were developed and evaluated using a CTD data set consisting of manually curated molecular interactions and relationships from 1,600 documents. Preliminary results indicated that the prototype found 80% of the gene, chemical, and disease terms appearing in curated interactions. These terms were used to re-rank documents for curation, resulting in increases in mean average precision (63% for the baseline vs. 73% for a rule-based re-ranking), and in the correlation coefficient of rank vs. number of curatable interactions per document (baseline 0.14 vs. 0.38 for the rule-based re-ranking).

CONCLUSION

This text-mining project is unique in its integration of existing tools into a single workflow with direct application to CTD. We performed a baseline assessment of the inter-curator consistency and coverage in CTD, which allowed us to measure the potential of these integrated tools to improve prioritization of journal articles for manual curation. Our study presents a feasible and cost-effective approach for developing a text mining solution to enhance manual curation throughput and efficiency.