Extraction of regulatory gene/protein networks from Medline

MOTIVATION: We have previously developed a rule-based approach for extracting information on the regulation of gene expression in yeast. The biomedical literature, however, contains information on several other equally important regulatory mechanisms, in particular phosphorylation, which we now expanded for our rule-based system also to extract. RESULTS: This paper presents new results for extraction of relational information from biomedical text. We have improved our system, STRING-IE, to capture both new types of linguistic constructs as well as new types of biological information [i.e. (de-)phosphorylation]. The precision remains stable with a slight increase in recall. From almost one million PubMed abstracts related to four model organisms, we manage to extract regulatory networks and binary phosphorylations comprising 3,319 relation chunks. The accuracy is 83-90% and 86-95% for gene expression and (de-)phosphorylation relations, respectively. To achieve this, we made use of an organism-specific resource of gene/protein names considerably larger than those used in most other biology related information extraction approaches. These names were included in the lexicon when retraining the part-of-speech (POS) tagger on the GENIA corpus. For the domain in question, an accuracy of 96.4% was attained on POS tags. It should be noted that the rules were developed for yeast and successfully applied to both abstracts and full-text articles related to other organisms with comparable accuracy. AVAILABILITY: The revised GENIA corpus, the POS tagger, the extraction rules and the full sets of extracted relations are available from http://www.bork.embl.de/Docu/STRING-IE     

NetiNeti: discovery of scientific names from text using machine learning methods

ABSTRACT: BACKGROUND: A scientific name for an organism can be associated with almost all biological data. Name identification is an important step in many text mining tasks aiming to extract useful information from biological, biomedical and biodiversity text sources. A scientific name acts as an important metadata element to link biological information. RESULTS: We present NetiNeti (Name Extraction from Textual Information-Name Extraction for Taxonomic Indexing), a machine learning based approach for recognition of scientific names including the discovery of new species names from text that will also handle misspellings, OCR errors and other variations in names. The system generates candidate names using rules for scientific names and applies probabilistic machine learning methods to classify names based on structural features of candidate names and features derived from their contexts. NetiNeti can also disambiguate scientific names from other names using the contextual information. We evaluated NetiNeti on legacy biodiversity texts and biomedical literature (MEDLINE). NetiNeti performs better (precision = 98.9 % and recall = 70.5 %) compared to a popular dictionary based approach (precision = 97.5 % and recall = 54.3 %) on a 600-page biodiversity book that was manually marked by an annotator. On a small set of PubMed Central's full text articles annotated with scientific names, the precision and recall values are 98.5 % and 96.2 % respectively. NetiNeti found more than 190,000 unique binomial and trinomial names in more than 1,880,000 PubMed records when used on the full MEDLINE database. NetiNeti also successfully identifies almost all of the new species names mentioned within web pages. Additionally, we present the comparison results of various machine learning algorithms on our annotated corpus. Naive Bayes and Maximum Entropy with Generalized Iterative Scaling (GIS) parameter estimation are the top two performing algorithms. CONCLUSIONS: We present NetiNeti, a machine learning based approach for identification and discovery of scientific names. The system implementing the approach can be accessed at http://namefinding.ubio.org.     

Combination of text-mining algorithms increases the performance

MOTIVATION: Recently, several information extraction systems have been developed to retrieve relevant information out of biomedical text. However, these methods represent individual efforts. In this paper, we show that by combining different algorithms and their outcome, the results improve significantly. For this reason, CONAN has been created, a system which combines different programs and their outcome. Its methods include tagging of gene/protein names, finding interaction and mutation data, tagging of biological concepts and linking to MeSH and Gene Ontology terms. RESULTS: In this paper, we will present data that show that combining different text-mining algorithms significantly improves the results. Not only is CONAN a full-scale approach that will ultimately cover all of PubMed/MEDLINE, we also show that this universality has no effect on quality: our system performs as well as or better than existing systems. AVAILABILITY: The LDD corpus presented is available by request to the author. The system will be available shortly. For information and updates on CONAN please visit http://www.cs.uu.nl/people/rainer/conan.html.     

Integrating Various Resources for Gene Name Normalization

The recognition and normalization of gene mentions in biomedical literature are crucial steps in biomedical text mining. We present a system for extracting gene names from biomedical literature and normalizing them to gene identifiers in databases. The system consists of four major components: gene name recognition, entity mapping, disambiguation and filtering. The first component is a gene name recognizer based on dictionary matching and semi-supervised learning, which utilizes the co-occurrence information of a large amount of unlabeled MEDLINE abstracts to enhance feature representation of gene named entities. In the stage of entity mapping, we combine the strategies of exact match and approximate match to establish linkage between gene names in the context and the EntrezGene database. For the gene names that map to more than one database identifiers, we develop a disambiguation method based on semantic similarity derived from the Gene Ontology and MEDLINE abstracts. To remove the noise produced in the previous steps, we design a filtering method based on the confidence scores in the dictionary used for NER. The system is able to adjust the trade-off between precision and recall based on the result of filtering. It achieves an F-measure of 83% (precision: 82.5% recall: 83.5%) on BioCreative II Gene Normalization (GN) dataset, which is comparable to the current state-of-the-art.     

Distribution of information in biomedical abstracts and full-text publications

MOTIVATION: Full-text documents potentially hold more information than their abstracts, but require more resources for processing. We investigated the added value of full text over abstracts in terms of information content and occurrences of gene symbol--gene name combinations that can resolve gene-symbol ambiguity. RESULTS: We analyzed a set of 3902 biomedical full-text articles. Different keyword measures indicate that information density is highest in abstracts, but that the information coverage in full texts is much greater than in abstracts. Analysis of five different standard sections of articles shows that the highest information coverage is located in the results section. Still, 30-40% of the information mentioned in each section is unique to that section. Only 30% of the gene symbols in the abstract are accompanied by their corresponding names, and a further 8% of the gene names are found in the full text. In the full text, only 18% of the gene symbols are accompanied by their gene names.     

Protein name tagging guidelines: lessons learned

Interest in information extraction from the biomedical literature is motivated by the need to speed up the creation of structured databases representing the latest scientific knowledge about specific objects, such as proteins and genes. This paper addresses the issue of a lack of standard definition of the problem of protein name tagging. We describe the lessons learned in developing a set of guidelines and present the first set of inter-coder results, viewed as an upper bound on system performance. Problems coders face include: (a) the ambiguity of names that can refer to either genes or proteins; (b) the difficulty of getting the exact extents of long protein names; and (c) the complexity of the guidelines. These problems have been addressed in two ways: (a) defining the tagging targets as protein named entities used in the literature to describe proteins or protein-associated or -related objects, such as domains, pathways, expression or genes, and (b) using two types of tags, protein tags and long-form tags, with the latter being used to optionally extend the boundaries of the protein tag when the name boundary is difficult to determine. Inter-coder consistency across three annotators on protein tags on 300 MEDLINE abstracts is 0.868 F-measure. The guidelines and annotated datasets, along with automatic tools, are available for research use.     

BioContrasts: extracting and exploiting protein-protein contrastive relations from biomedical literature

MOTIVATION: Contrasts are useful conceptual vehicles for learning processes and exploratory research of the unknown. For example, contrastive information between proteins can reveal what similarities, divergences and relations there are of the two proteins, leading to invaluable insights for better understanding about the proteins. Such contrastive information are found to be reported in the biomedical literature. However, there have been no reported attempts in current biomedical text mining work that systematically extract and present such useful contrastive information from the literature for exploitation. RESULTS: Our BioContrasts system extracts protein-protein contrastive information from MEDLINE abstracts and presents the information to biologists in a web-application for exploitation. Contrastive information are identified in the text abstracts with contrastive negation patterns such as 'A but not B'. A total of 799 169 pairs of contrastive expressions were successfully extracted from 2.5 million MEDLINE abstracts. Using grounding of contrastive protein names to Swiss-Prot entries, we were able to produce 41 471 pieces of contrasts between Swiss-Prot protein entries. These contrastive pieces of information are then presented via a user-friendly interactive web portal that can be exploited for applications such as the refinement of biological pathways. AVAILABILITY: BioContrasts can be accessed at http://biocontrasts.i2r.a-star.edu.sg. It is also mirrored at http://biocontrasts.biopathway.org. SUPPLEMENTARY INFORMATION: Supplementary materials are available at Bioinformatics online.     

Gene symbol disambiguation using knowledge-based profiles

MOTIVATION: The ambiguity of biomedical entities, particularly of gene symbols, is a big challenge for text-mining systems in the biomedical domain. Existing knowledge sources, such as Entrez Gene and the MEDLINE database, contain information concerning the characteristics of a particular gene that could be used to disambiguate gene symbols. RESULTS: For each gene, we create a profile with different types of information automatically extracted from related MEDLINE abstracts and readily available annotated knowledge sources. We apply the gene profiles to the disambiguation task via an information retrieval method, which ranks the similarity scores between the context where the ambiguous gene is mentioned, and candidate gene profiles. The gene profile with the highest similarity score is then chosen as the correct sense. We evaluated the method on three automatically generated testing sets of mouse, fly and yeast organisms, respectively. The method achieved the highest precision of 93.9% for the mouse, 77.8% for the fly and 89.5% for the yeast. AVAILABILITY: The testing data sets and disambiguation programs are available at http://www.dbmi.columbia.edu/~hux7002/gsd2006     

Automatic extraction of gene/protein biological functions from biomedical text

MOTIVATION: With the rapid advancement of biomedical science and the development of high-throughput analysis methods, the extraction of various types of information from biomedical text has become critical. Since automatic functional annotations of genes are quite useful for interpreting large amounts of high-throughput data efficiently, the demand for automatic extraction of information related to gene functions from text has been increasing. RESULTS: We have developed a method for automatically extracting the biological process functions of genes/protein/families based on Gene Ontology (GO) from text using a shallow parser and sentence structure analysis techniques. When the gene/protein/family names and their functions are described in ACTOR (doer of action) and OBJECT (receiver of action) relationships, the corresponding GO-IDs are assigned to the genes/proteins/families. The gene/protein/family names are recognized using the gene/protein/family name dictionaries developed by our group. To achieve wide recognition of the gene/protein/family functions, we semi-automatically gather functional terms based on GO using co-occurrence, collocation similarities and rule-based techniques. A preliminary experiment demonstrated that our method has an estimated recall of 54-64% with a precision of 91-94% for actually described functions in abstracts. When applied to the PUBMED, it extracted over 190 000 gene-GO relationships and 150 000 family-GO relationships for major eukaryotes.     

Large-scale extraction of gene regulation for model organisms in an ontological context

This paper presents an approach using syntactosemantic rules for the extraction of relational information from biomedical abstracts. The results show that by overcoming the hurdle of technical terminology, high precision results can be achieved. From abstracts related to baker's yeast, we manage to extract a regulatory network comprised of 441 pairwise relations from 58,664 abstracts with an accuracy of 83 - 90%. To achieve this, we made use of a resource of gene/protein names considerably larger than those used in most other biology related information extraction approaches. This list of names was included in the lexicon of our retrained partof- speech tagger for use on molecular biology abstracts. For the domain in question an accuracy of 93.6 - 97.7% was attained on Part-of-speech-tags. The method can be easily adapted to other organisms than yeast, allowing us to extract many more biologically relevant relations. The main reason for the comparable precision rates is the ontological model that was built beforehand and served as a guiding force for the manual coding of the syntactosemantic rules.     

Building an abbreviation dictionary using a term recognition approach

MOTIVATION: Acronyms result from a highly productive type of term variation and trigger the need for an acronym dictionary to establish associations between acronyms and their expanded forms. RESULTS: We propose a novel method for recognizing acronym definitions in a text collection. Assuming a word sequence co-occurring frequently with a parenthetical expression to be a potential expanded form, our method identifies acronym definitions in a similar manner to the statistical term recognition task. Applied to the whole MEDLINE (7 811 582 abstracts), the implemented system extracted 886 755 acronym candidates and recognized 300 954 expanded forms in reasonable time. Our method outperformed base-line systems, achieving 99% precision and 82-95% recall on our evaluation corpus that roughly emulates the whole MEDLINE. AVAILABILITY AND SUPPLEMENTARY INFORMATION: The implementations and supplementary information are available at our web site: http://www.chokkan.org/research/acromine/     

Gene name ambiguity of eukaryotic nomenclatures

MOTIVATION: With more and more scientific literature published online, the effective management and reuse of this knowledge has become problematic. Natural language processing (NLP) may be a potential solution by extracting, structuring and organizing biomedical information in online literature in a timely manner. One essential task is to recognize and identify genomic entities in text. 'Recognition' can be accomplished using pattern matching and machine learning. But for 'identification' these techniques are not adequate. In order to identify genomic entities, NLP needs a comprehensive resource that specifies and classifies genomic entities as they occur in text and that associates them with normalized terms and also unique identifiers so that the extracted entities are well defined. Online organism databases are an excellent resource to create such a lexical resource. However, gene name ambiguity is a serious problem because it affects the appropriate identification of gene entities. In this paper, we explore the extent of the problem and suggest ways to address it. RESULTS: We obtained gene information from 21 organisms and quantified naming ambiguities within species, across species, with English words and with medical terms. When the case (of letters) was retained, official symbols displayed negligible intra-species ambiguity (0.02%) and modest ambiguities with general English words (0.57%) and medical terms (1.01%). In contrast, the across-species ambiguity was high (14.20%). The inclusion of gene synonyms increased intra-species ambiguity substantially and full names contributed greatly to gene-medical-term ambiguity. A comprehensive lexical resource that covers gene information for the 21 organisms was then created and used to identify gene names by using a straightforward string matching program to process 45,000 abstracts associated with the mouse model organism while ignoring case and gene names that were also English words. We found that 85.1% of correctly retrieved mouse genes were ambiguous with other gene names. When gene names that were also English words were included, 233% additional 'gene' instances were retrieved, most of which were false positives. We also found that authors prefer to use synonyms (74.7%) to official symbols (17.7%) or full names (7.6%) in their publications. CONTACT: lifeng.chen@dbmi.columbia.edu     

RelEx--relation extraction using dependency parse trees

MOTIVATION: The discovery of regulatory pathways, signal cascades, metabolic processes or disease models requires knowledge on individual relations like e.g. physical or regulatory interactions between genes and proteins. Most interactions mentioned in the free text of biomedical publications are not yet contained in structured databases. RESULTS: We developed RelEx, an approach for relation extraction from free text. It is based on natural language preprocessing producing dependency parse trees and applying a small number of simple rules to these trees. We applied RelEx on a comprehensive set of one million MEDLINE abstracts dealing with gene and protein relations and extracted approximately 150,000 relations with an estimated performance of both 80% precision and 80% recall. AVAILABILITY: The used natural language preprocessing tools are free for use for academic research. Test sets and relation term lists are available from our website (http://www.bio.ifi.lmu.de/publications/RelEx/).     

Which species is it? Species-driven gene name disambiguation using random walks over a mixture of adjacency matrices

MOTIVATION: The scientific literature contains a wealth of information about biological systems. Manual curation lacks the scalability to extract this information due to the ever-increasing numbers of papers being published. The development and application of text mining technologies has been proposed as a way of dealing with this problem. However, the inter-species ambiguity of the genomic nomenclature makes mapping of gene mentions identified in text to their corresponding Entrez gene identifiers an extremely difficult task. We propose a novel method, which transforms a MEDLINE record into a mixture of adjacency matrices; by performing a random walkover the resulting graph, we can perform multi-class supervised classification allowing the assignment of taxonomy identifiers to individual gene mentions. The ability to achieve good performance at this task has a direct impact on the performance of normalizing gene mentions to Entrez gene identifiers. Such graph mixtures add flexibility and allow us to generate probabilistic classification schemes that naturally reflect the uncertainties inherent, even in literature-derived data. RESULTS: Our method performs well in terms of both micro- and macro-averaged performance, achieving micro-F(1) of 0.76 and macro-F(1) of 0.36 on the publicly available DECA corpus. Re-curation of the DECA corpus was performed, with our method achieving 0.88 micro-F(1) and 0.51 macro-F(1). Our method improves over standard classification techniques [such as support vector machines (SVMs)] in a number of ways: flexibility, interpretability and its resistance to the effects of class bias in the training data. Good performance is achieved without the need for computationally expensive parse tree generation or 'bag of words classification'.     

Identifying gene-specific variations in biomedical text

The influence of genetic variations on diseases or cellular processes is the main focus of many investigations, and results of biomedical studies are often only accessible through scientific publications. Automatic extraction of this information requires recognition of the gene names and the accompanying allelic variant information. In a previous work, the OSIRIS system for the detection of allelic variation in text based on a query expansion approach was communicated. Challenges associated with this system are the relatively low recall for variation mentions and gene name recognition. To tackle this challenge, we integrate the ProMiner system developed for the recognition and normalization of gene and protein names with a conditional random field (CRF)-based recognition of variation terms in biomedical text. Following the newly developed normalization of variation entities, we can link textual entities to Single Nucleotide Polymorphism database (dbSNP) entries. The performance of this novel approach is evaluated, and improved results in comparison to state-of-the-art systems are reported.     

The SPECIES and ORGANISMS Resources for Fast and Accurate Identification of Taxonomic Names in Text

The exponential growth of the biomedical literature is making the need for efficient, accurate text-mining tools increasingly clear. The identification of named biological entities in text is a central and difficult task. We have developed an efficient algorithm and implementation of a dictionary-based approach to named entity recognition, which we here use to identify names of species and other taxa in text. The tool, SPECIES, is more than an order of magnitude faster and as accurate as existing tools. The precision and recall was assessed both on an existing gold-standard corpus and on a new corpus of 800 abstracts, which were manually annotated after the development of the tool. The corpus comprises abstracts from journals selected to represent many taxonomic groups, which gives insights into which types of organism names are hard to detect and which are easy. Finally, we have tagged organism names in the entire Medline database and developed a web resource, ORGANISMS, that makes the results accessible to the broad community of biologists. The SPECIES software is open source and can be downloaded from http://species.jensenlab.org along with dictionary files and the manually annotated gold-standard corpus. The ORGANISMS web resource can be found at http://organisms.jensenlab.org.     

BioIE: extracting informative sentences from the biomedical literature

SUMMARY: BioIE is a rule-based system that extracts informative sentences relating to protein families, their structures, functions and diseases from the biomedical literaturE. Based on manual definition of templates and rules, it aims at precise sentence extraction rather than wide recall. After uploading source text or retrieving abstracts from MEDLINE, users can extract sentences based on predefined or user-defined template categories. BioIE also provides a brief insight into the syntactic and semantic context of the source-text by looking at word, N-gram and MeSH-term distributions. Important Applications of BioIE are in, for example, annotation of microarray data and of protein databases. AVAILABILITY: http://umber.sbs.man.ac.uk/dbbrowser/bioie/     

A cascaded approach to normalising gene mentions in biomedical literature

Linking gene and protein names mentioned in the literature to unique identifiers in referent genomic databases is an essential step in accessing and integrating knowledge in the biomedical domain. However, it remains a challenging task due to lexical and terminological variation, and ambiguity of gene name mentions in documents. We present a generic and effective rule-based approach to link gene mentions in the literature to referent genomic databases, where pre-processing of both gene synonyms in the databases and gene mentions in text are first applied. The mapping method employs a cascaded approach, which combines exact, exact-like and token-based approximate matching by using flexible representations of a gene synonym dictionary and gene mentions generated during the pre-processing phase. We also consider multi-gene name mentions and permutation of components in gene names. A systematic evaluation of the suggested methods has identified steps that are beneficial for improving either precision or recall in gene name identification. The results of the experiments on the BioCreAtIvE2 data sets (identification of human gene names) demonstrated that our methods achieved highly encouraging results with F-measure of up to 81.20%.     

A scalable machine-learning approach to recognize chemical names within large text databases

MOTIVATION: The use or study of chemical compounds permeates almost every scientific field and in each of them, the amount of textual information is growing rapidly. There is a need to accurately identify chemical names within text for a number of informatics efforts such as database curation, report summarization, tagging of named entities and keywords, or the development/curation of reference databases. RESULTS: A first-order Markov Model (MM) was evaluated for its ability to distinguish chemical names from words, yielding approximately 93% recall in recognizing chemical terms and approximately 99% precision in rejecting non-chemical terms on smaller test sets. However, because total false-positive events increase with the number of words analyzed, the scalability of name recognition was measured by processing 13.1 million MEDLINE records. The method yielded precision ranges from 54.7% to 100%, depending upon the cutoff score used, averaging 82.7% for approximately 1.05 million putative chemical terms extracted. Extracted chemical terms were analyzed to estimate the number of spelling variants per term, which correlated with the total number of times the chemical name appeared in MEDLINE. This variability in term construction was found to affect both information retrieval and term mapping when using PubMed and Ovid.