No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
ChemGrab: Identification of Chemical Names Using a Combined Negative-Dictionary and Rule-Based Approach
Abstract
The growing volume of electronically available text provides the opportunity to extract potentially relevant information that may offer valuable insights. To this end, the cataloguing of documents based on named entity mentions is an essential task. Development of text mining approaches for extracting entities and relationships may enable efficient management and retrieval of relevant information within specific contexts. The system described here, ChemGrab, focused on the BioCreative V.5 CEMP Challenge that aims to identify mentions of chemical entities from within patent text. The approach used in this study to identify chemical mentions used a combination of a negativedictionary and rules based on word-level features. The system performance on the test set achieved a micro precision, recall, and F-score of 0.53, 0.67, and 0.59, respectively.
... they continue to be used in combination with other techniques, such as dictionary look-up [3,4]. • Using dictionaries to recognize known entities. ...
Background: This article describes a high-recall, high-precision approach for the extraction of biomedical entities from scientific articles.
Method: The approach uses a two-stage pipeline, combining a dictionary-based entity recognizer with a machine-learning classifier. First, the OGER entity recognizer, which has a bias towards high recall, annotates the terms that appear in selected domain ontologies. Subsequently, the Distiller framework uses this information as a feature for a machine learning algorithm to select the relevant entities only. For this step, we compare two different supervised machine-learning algorithms: Conditional Random Fields and Neural Networks.
Results: In an in-domain evaluation using the CRAFT corpus, we test the performance of the combined systems when recognizing chemicals, cell types, cellular components, biological processes, molecular functions, organisms, proteins, and biological sequences. Our best system combines dictionary-based candidate generation with Neural-Network-based filtering. It achieves an overall precision of 86% at a recall of 60% on the named entity recognition task, and a precision of 51% at a recall of 49% on the concept recognition task.
Conclusion: These results are to our knowledge the best reported so far in this particular task.
Chemical entity recognition has traditionally been performed by machine learning approaches. Here we describe an approach using grammars and dictionaries. This approach has the advantage that the entities found can be directly related to a given grammar or dictionary, which allows the type of an entity to be known and, if an entity is misannotated, indicates which resource should be corrected. As recognition is driven by what is expected, if spelling errors occur, they can be corrected. Correcting such errors is highly useful when attempting to lookup an entity in a database or, in the case of chemical names, converting them to structures.
Our system uses a mixture of expertly curated grammars and dictionaries, as well as dictionaries automatically derived from public resources. We show that the heuristics developed to filter our dictionary of trivial chemical names (from PubChem) yields a better performing dictionary than the previously published Jochem dictionary. Our final system performs post-processing steps to modify the boundaries of entities and to detect abbreviations. These steps are shown to significantly improve performance (2.6% and 4.0% F1-score respectively). Our complete system, with incremental post-BioCreative workshop improvements, achieves 89.9% precision and 85.4% recall (87.6% F1-score) on the CHEMDNER test set.
Grammar and dictionary approaches can produce results at least as good as the current state of the art in machine learning approaches. While machine learning approaches are commonly thought of as "black box" systems, our approach directly links the output entities to the input dictionaries and grammars. Our approach also allows correction of errors in detected entities, which can assist with entity resolution.
Chemical compounds and drugs are an important class of entities in biomedical research with great potential in a wide range of applications, including clinical medicine. Locating chemical named entities in the literature is a useful step in chemical text mining pipelines for identifying the chemical mentions, their properties, and their relationships as discussed in the literature.
We introduce the tmChem system, a chemical named entity recognizer created by combining two independent machine learning models in an ensemble. We use the corpus released as part of the recent CHEMDNER task to develop and evaluate tmChem, achieving a micro-averaged f-measure of 0.8739 on the CEM subtask (mention-level evaluation) and 0.8745 f-measure on the CDI subtask (abstract-level evaluation). We also report a high-recall combination (0.9212 for CEM and 0.9224 for CDI). tmChem achieved the highest f-measure reported in the CHEMDNER task for the CEM subtask, and the high recall variant achieved the highest recall on both the CEM and CDI tasks.
We report that tmChem is a state-of-the-art tool for chemical named entity recognition and that performance for chemical named entity recognition has now tied (or exceeded) the performance previously reported for genes and diseases. Future research should focus on tighter integration between the named entity recognition and normalization steps for improved performance.
The source code and a trained model for both models of tmChem is available at: http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/tmChem. The results of running tmChem (Model 2) on PubMed are available in PubTator: http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/PubTator
The language of patent claims differs from ordinary language to a great extent, which results in the fact that tools especially adapted to patent lan-guage are needed in patent processing. In order to evaluate these tools, manually annotated patent corpora are necessary. Thus, we constructed a corpus of English language pharmaceutical patents belonging to the class A61K, on which several layers of manual annotation (such as named entities, keys, NucleusNPs, quanti-tative expressions, heads and complements, perdurants) were carried out and on which tools for patent processing can be evaluated.
Exploring the chemical and biological space covered by patent applications is crucial in early-stage medicinal chemistry activities. Patent analysis can provide understanding of compound prior art, novelty checking, validation of biological assays, and identification of new starting points for chemical exploration. Extracting chemical and biological entities from patents through manual extraction by expert curators can take substantial amount of time and resources. Text mining methods can help to ease this process. To validate the performance of such methods, a manually annotated patent corpus is essential. In this study we have produced a large gold standard chemical patent corpus. We developed annotation guidelines and selected 200 full patents from the World Intellectual Property Organization, United States Patent and Trademark Office, and European Patent Office. The patents were pre-annotated automatically and made available to four independent annotator groups each consisting of two to ten annotators. The annotators marked chemicals in different subclasses, diseases, targets, and modes of action. Spelling mistakes and spurious line break due to optical character recognition errors were also annotated. A subset of 47 patents was annotated by at least three annotator groups, from which harmonized annotations and inter-annotator agreement scores were derived. One group annotated the full set. The patent corpus includes 400,125 annotations for the full set and 36,537 annotations for the harmonized set. All patents and annotated entities are publicly available at www.biosemantics.org.
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.
There is an increasing need to facilitate automated access to information relevant for chemical compounds and drugs described in text, including scientific articles, patents or health agency reports. A number of recent efforts have implemented natural language processing (NLP) and text mining technologies for the chemical domain (ChemNLP or chemical text mining). Due to the lack of manually labeled Gold Standard datasets together with comprehensive annotation guidelines, both the implementation as well as the comparative assessment of ChemNLP technologies is opaque. Two key components for most chemical text mining technologies are the indexing of documents with chemicals (chemical document indexing - CDI) and finding the mentions of chemicals in text (chemical entity mention recognition - CEM). These two tasks formed part of the chemical compound and drug named entity recognition (CHEMDNER) task introduced at the fourth BioCreative challenge, a community effort to evaluate biomedical text mining applications. For this task, the CHEMDNER text corpus was constructed, consisting of 10,000 abstracts containing a total of 84,355 mentions of chemical compounds and drugs that have been manually labeled by domain experts following specific annotation guidelines. This corpus covers representative abstracts from major chemistry-related sub-disciplines such as medicinal chemistry, biochemistry, organic chemistry and toxicology.
A total of 27 teams -- 23 academic and 4 commercial ones, comprised of 87 researchers -- submitted results for this task. 26 of these teams provided submissions for the CEM subtask and 23 for the CDI subtask. Teams were provided with the manual annotations of 7,000 abstracts to implement and train their systems and then had to return predictions for the 3,000 test set abstracts during a short period of time. When comparing exact matches of the automated results against the manually labeled Gold Standard annotations, the best teams reached an F-score of 87.39% for the CEM task and of 88.20% for the CDI task. This can be regarded as a very competitive result when compared to the expected upper boundary, the agreement between to human annotators, at 91%. In general, the technologies used to detect chemicals and drugs by the teams included machine learning methods (particularly CRFs using a considerable range of different features), interaction of chemistry-related lexical resources and manual rules (e.g., to cover abbreviations, chemical formula or chemical identifiers). By promoting the availability of the software of the participating systems as well as through the release of the CHEMDNER corpus to enable implementation of new tools, this work fosters the development of text mining applications like the automatic extraction of biochemical reactions, toxicological properties of compounds, or the detection of associations between genes or mutations to drugs in the context pharmacogenomics.
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.
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.
ChemSpot is freely available at: http://www.informatik.hu-berlin.de/wbi/resources.
The task of recognizing and identifying species names in biomedical literature has recently been regarded as critical for a number of applications in text and data mining, including gene name recognition, species-specific document retrieval, and semantic enrichment of biomedical articles.
In this paper we describe an open-source species name recognition and normalization software system, LINNAEUS, and evaluate its performance relative to several automatically generated biomedical corpora, as well as a novel corpus of full-text documents manually annotated for species mentions. LINNAEUS uses a dictionary-based approach (implemented as an efficient deterministic finite-state automaton) to identify species names and a set of heuristics to resolve ambiguous mentions. When compared against our manually annotated corpus, LINNAEUS performs with 94% recall and 97% precision at the mention level, and 98% recall and 90% precision at the document level. Our system successfully solves the problem of disambiguating uncertain species mentions, with 97% of all mentions in PubMed Central full-text documents resolved to unambiguous NCBI taxonomy identifiers.
LINNAEUS is an open source, stand-alone software system capable of recognizing and normalizing species name mentions with speed and accuracy, and can therefore be integrated into a range of bioinformatics and text-mining applications. The software and manually annotated corpus can be downloaded freely at http://linnaeus.sourceforge.net/.
From the scientific community, a lot of effort has been spent on the correct identification of gene and protein names in text, while less effort has been spent on the correct identification of chemical names. Dictionary-based term identification has the power to recognize the diverse representation of chemical information in the literature and map the chemicals to their database identifiers.
We developed a dictionary for the identification of small molecules and drugs in text, combining information from UMLS, MeSH, ChEBI, DrugBank, KEGG, HMDB and ChemIDplus. Rule-based term filtering, manual check of highly frequent terms and disambiguation rules were applied. We tested the combined dictionary and the dictionaries derived from the individual resources on an annotated corpus, and conclude the following: (i) each of the different processing steps increase precision with a minor loss of recall; (ii) the overall performance of the combined dictionary is acceptable (precision 0.67, recall 0.40 (0.80 for trivial names); (iii) the combined dictionary performed better than the dictionary in the chemical recognizer OSCAR3; (iv) the performance of a dictionary based on ChemIDplus alone is comparable to the performance of the combined dictionary.
The combined dictionary is freely available as an XML file in Simple Knowledge Organization System format on the web site http://www.biosemantics.org/chemlist.
Motivation:
Natural language processing (NLP) methods are regarded as being useful to raise the potential of text mining from biological literature. The lack of an extensively annotated corpus of this literature, however, causes a major bottleneck for applying NLP techniques. GENIA corpus is being developed to provide reference materials to let NLP techniques work for bio-textmining.
Results:
GENIA corpus version 3.0 consisting of 2000 MEDLINE abstracts has been released with more than 400,000 words and almost 100,000 annotations for biological terms.
Patent specifications are one of many information sources needed to progress drug discovery projects. Understanding compound prior art and novelty checking, validation of biological assays, and identification of new starting points for chemical explorations are a few areas where patent analysis is an important component. Cheminformatics methods can be used to facilitate the identification of so-called key compounds in patent specifications. Such methods, relying on structural information extracted from documents by expert curation or text mining, can complement or in some cases replace the traditional manual approach of searching for clues in the text. This paper describes and compares three different methods for the automatic prediction of key compounds in patent specifications using structural information alone. For this data set, the cluster seed analysis described by Hattori et al. (Hattori, K.; Wakabayashi, H.; Tamaki, K. Predicting key example compounds in competitors' patent applications using structural information alone. J. Chem. Inf. Model.2008, 48, 135-142) is superior in terms of prediction accuracy with 26 out of 48 drugs (54%) correctly predicted from their corresponding patents. Nevertheless, the two new methods, based on frequency of R-groups (FOG) and maximum common substructure (MCS) similarity measures, show significant advantages due to their inherent ability to visualize relevant structural features. The results of the FOG method can be enhanced by manual selection of the scaffolds used in the analysis. Finally, a successful example of applying FOG analysis for designing potent ATP-competitive AXL kinase inhibitors with improved properties is described.
Because meaningful sentences are composed of meaningful words, any system that hopes to process natural languages as people do must have information about words and their meanings. This information is traditionally provided through dictionaries, and machine-readable dictionaries are now widely available. But dictionary entries evolved for the convenience of human readers, not for machines. WordNet ¹ provides a more effective combination of traditional lexicographic information and modern computing. WordNet is an online lexical database designed for use under program control. English nouns, verbs, adjectives, and adverbs are organized into sets of synonyms, each representing a lexicalized concept. Semantic relations link the synonym sets [4].
Global access to advanced vaccine technologies is challenged by the interrelated components of intellectual property (IP) management strategies, technology transfer (legal and technical) capabilities and the capacity necessary for accelerating R&D, commercialization and delivery of vaccines. Due to a negative association with the management of IP, patents are often overlooked as a vast resource of freely available, information akin to scientific journals as well as business and technological information and trends fundamental for formulating policies and IP management strategies. Therefore, a fundamental step towards facilitating global vaccine access will be the assembly, organization and analysis of patent landscapes, to identify the amount of patenting, ownership (assignees) and fields of technology covered. This is critical for making informed decisions (e.g., identifying licensees, building research and product development collaborations, and ascertaining freedom to operate). Such information is of particular interest to the HIV vaccine community where the HIV Vaccine Enterprise, have voiced concern that IP rights (particularly patents and trade secrets) may prevent data and materials sharing, delaying progress in research and development of a HIV vaccine. We have compiled and analyzed a representative HIV vaccine patent landscape for a prime-boost, DNA/adenoviral vaccine platform, as an example for identifying obstacles, maximizing opportunities and making informed IP management strategy decisions towards the development and deployment of an efficacious HIV vaccine.
Scientific progress is increasingly based on knowledge and information. Knowledge is now recognized as the driver of productivity and economic growth, leading to a new focus on the role of information in the decision-making process. Most scientific knowledge is registered in publications and other unstructured representations that make it difficult to use and to integrate the information with other sources (e.g. biological databases). Making a computer understand human language has proven to be a complex achievement, but there are techniques capable of detecting, distinguishing and extracting a limited number of different classes of facts. In the biomedical field, extracting information has specific problems: complex and ever-changing nomenclature (especially genes and proteins) and the limited representation of domain knowledge.
Overview of the CHEMDNER patents task
- M Krallinger
- O Rabal
- A Lourenço
- M P Perez
- G P Rodriguez
- M Vazquez
- F Leitner
- J Oyarzabal
- A Valencia
Krallinger, M., Rabal, O., Lourenço, A., Perez, M.P., Rodriguez, G.P., Vazquez, M., Leitner,
F., Oyarzabal, J., Valencia, A.: Overview of the CHEMDNER patents task. In: Proceedings
of the fifth BioCreative challenge evaluation workshop. pp. 63-75 (2015).
Chemical names: terminological resources and corpora annotation
- C Kolárik
- R Klinger
- C M Friedrich
- M Hofmann-Apitius
- J Fluck
Kolárik, C., Klinger, R., Friedrich, C.M., Hofmann-Apitius, M., Fluck, J.: Chemical names:
terminological resources and corpora annotation. In: Workshop on Building and evaluating
resources for biomedical text mining (6th edition of the Language Resources and Evaluation
Conference) (2008).
Peregrine: Lightweight gene name normalization by dictionary lookup
- M J Schuemie
- R Jelier
- J A Kors
Schuemie, M.J., Jelier, R., Kors, J.A.: Peregrine: Lightweight gene name normalization by
dictionary lookup. In: Proceedings of the Biocreative 2 workshop (2007).
- D Koning
- I N Sarkar
- T Moritz
Koning, D., Sarkar, I.N., Moritz, T.: Taxongrab: Extracting Taxonomic Names from Text.
(2008).
The specialist lexicon. National Library of Medicine Technical Reports
- A C Browne
- A T Mccray
- S Srinivasan
Browne, A.C., McCray, A.T., Srinivasan, S.: The specialist lexicon. National Library of
Medicine Technical Reports. 18-21 (2000).