Application of automatic mutation-gene pair extraction to diseases

To have a better understanding of the mechanisms of disease development, knowledge of mutations and the genes on which the mutations occur is of crucial importance. Information on disease-related mutations can be accessed through public databases or biomedical literature sources. However, information retrieval from such resources can be problematic because of two reasons: manually created databases are usually incomplete and not up to date, and reading through a vast amount of publicly available biomedical documents is very time-consuming. In this paper, we describe an automated system, MuGeX (Mutation Gene eXtractor), that automatically extracts mutation-gene pairs from Medline abstracts for a disease query. Our system is tested on a corpus that consists of 231 Medline abstracts. While recall for mutation detection alone is 85.9%, precision is 95.9%. For extraction of mutation-gene pairs, we focus on Alzheimer's disease. The recall for mutation-gene pair identification is estimated at 91.3%, and precision is estimated at 88.9%. With automatic extraction techniques, MuGeX overcomes the problems of information retrieval from public resources and reduces the time required to access relevant information, while preserving the accuracy of retrieved information.     

Finding relevant references to genes and proteins in Medline using a Bayesian approach

MOTIVATION: Mining the biomedical literature for references to genes and proteins always involves a tradeoff between high precision with false negatives, and high recall with false positives. Having a reliable method for assessing the relevance of literature mining results is crucial to finding ways to balance precision and recall, and for subsequently building automated systems to analyze these results. We hypothesize that abstracts and titles that discuss the same gene or protein use similar words. To validate this hypothesis, we built a dictionary- and rule-based system to mine Medline for references to genes and proteins, and used a Bayesian metric for scoring the relevance of each reference assignment. RESULTS: We analyzed the entire set of Medline records from 1966 to late 2001, and scored each gene and protein reference using a Bayesian estimated probability (EP) based on word frequency in a training set of 137837 known assignments from 30594 articles to 36197 gene and protein symbols. Two test sets of 148 and 150 randomly chosen assignments, respectively, were hand-validated and categorized as either good or bad. The distributions of EP values, when plotted on a log-scale histogram, are shown to markedly differ between good and bad assignments. Using EP values, recall was 100% at 61% precision (EP=2 x 10(-5)), 63% at 88% precision (EP=0.008), and 10% at 100% precision (EP=0.1). These results show that Medline entries discussing the same gene or protein have similar word usage, and that our method of assessing this similarity using EP values is valid, and enables an EP cutoff value to be determined that accurately and reproducibly balances precision and recall, allowing automated analysis of literature mining results. .     

Markov model recognition and classification of DNA/protein sequences within large text databases

MOTIVATION: Short sequence patterns frequently define regions of biological interest (binding sites, immune epitopes, primers, etc.), yet a large fraction of this information exists only within the scientific literature and is thus difficult to locate via conventional means (e.g. keyword queries or manual searches). We describe herein a system to accurately identify and classify sequence patterns from within large corpora using an n-gram Markov model (MM). RESULTS: As expected, on test sets we found that identification of sequences with limited alphabets and/or regular structures such as nucleic acids (non-ambiguous) and peptide abbreviations (3-letter) was highly accurate, whereas classification of symbolic (1-letter) peptide strings with more complex alphabets was more problematic. The MM was used to analyze two very large, sequence-containing corpora: over 7.75 million Medline abstracts and 9000 full-text articles from Journal of Virology. Performance was benchmarked by comparing the results with Journal of Virology entries in two existing manually curated databases: VirOligo and the HLA Ligand Database. Performance estimates were 98 +/- 2% precision/84% recall for primer identification and classification and 67 +/- 6% precision/85% recall for peptide epitopes. We also find a dramatic difference between the amounts of sequence-related data reported in abstracts versus full text. Our results suggest that automated extraction and classification of sequence elements is a promising, low-cost means of sequence database curation and annotation. AVAILABILITY: MM routine and datasets are available upon request.     

Text processing through Web services: calling Whatizit

MOTIVATION: Text-mining (TM) solutions are developing into efficient services to researchers in the biomedical research community. Such solutions have to scale with the growing number and size of resources (e.g. available controlled vocabularies), with the amount of literature to be processed (e.g. about 17 million documents in PubMed) and with the demands of the user community (e.g. different methods for fact extraction). These demands motivated the development of a server-based solution for literature analysis. Whatizit is a suite of modules that analyse text for contained information, e.g. any scientific publication or Medline abstracts. Special modules identify terms and then link them to the corresponding entries in bioinformatics databases such as UniProtKb/Swiss-Prot data entries and gene ontology concepts. Other modules identify a set of selected annotation types like the set produced by the EBIMed analysis pipeline for proteins. In the case of Medline abstracts, Whatizit offers access to EBI's in-house installation via PMID or term query. For large quantities of the user's own text, the server can be operated in a streaming mode (http://www.ebi.ac.uk/webservices/whatizit).     

EBIMed--text crunching to gather facts for proteins from Medline

To allow efficient and systematic retrieval of statements from Medline we have developed EBIMed, a service that combines document retrieval with co-occurrence-based analysis of Medline abstracts. Upon keyword query, EBIMed retrieves the abstracts from EMBL-EBI's installation of Medline and filters for sentences that contain biomedical terminology maintained in public bioinformatics resources. The extracted sentences and terminology are used to generate an overview table on proteins, Gene Ontology (GO) annotations, drugs and species used in the same biological context. All terms in retrieved abstracts and extracted sentences are linked to their entries in biomedical databases. We assessed the quality of the identification of terms and relations in the retrieved sentences. More than 90% of the protein names found indeed represented a protein. According to the analysis of four protein-protein pairs from the Wnt pathway we estimated that 37% of the statements containing such a pair mentioned a meaningful interaction and clarified the interaction of Dkk with LRP. We conclude that EBIMed improves access to information where proteins and drugs are involved in the same biological process, e.g. statements with GO annotations of proteins, protein-protein interactions and effects of drugs on proteins. AVAILABILITY: Available at http://www.ebi.ac.uk/Rebholz-srv/ebimed     

Mining literature for protein-protein interactions

MOTIVATION: A central problem in bioinformatics is how to capture information from the vast current scientific literature in a form suitable for analysis by computer. We address the special case of information on protein-protein interactions, and show that the frequencies of words in Medline abstracts can be used to determine whether or not a given paper discusses protein-protein interactions. For those papers determined to discuss this topic, the relevant information can be captured for the Database of Interacting PROTEINS: Furthermore, suitable gene annotations can also be captured. RESULTS: Our Bayesian approach scores Medline abstracts for probability of discussing the topic of interest according to the frequencies of discriminating words found in the abstract. More than 80 discriminating words (e.g. complex, interaction, two-hybrid) were determined from a training set of 260 Medline abstracts corresponding to previously validated entries in the Database of Interacting Proteins. Using these words and a log likelihood scoring function, approximately 2000 Medline abstracts were identified as describing interactions between yeast proteins. This approach now forms the basis for the rapid expansion of the Database of Interacting Proteins.     

CGMIM: Automated text-mining of Online Mendelian Inheritance in Man (OMIM) to identify genetically-associated cancers and candidate genes

Background  

Online Mendelian Inheritance in Man (OMIM) is a computerized database of information about genes and heritable traits in human populations, based on information reported in the scientific literature. Our objective was to establish an automated text-mining system for OMIM that will identify genetically-related cancers and cancer-related genes. We developed the computer program CGMIM to search for entries in OMIM that are related to one or more cancer types. We performed manual searches of OMIM to verify the program results.     

PNAD-CSS: a workbench for constructing a protein name abbreviation dictionary

MOTIVATION: Since their initial development, integration and construction of databases for molecular-level data have progressed. Though biological molecules are related to each other and form a complex system, the information is stored in the vast archives of the literature or in diverse databases. There is no unified naming convention for biological object, and biological terms may be ambiguous or polysemic. This makes the integration and interaction of databases difficult. In order to eliminate these problems, machine-readable natural language resources appear to be quite promising. We have developed a workbench for protein name abbreviation dictionary (PNAD) building. RESULTS: We have developed PNAD Construction Support System (PNAD-CSS), which offers various convenient facilities to decrease the construction costs of a protein name abbreviation dictionary of which entries are collected from abstracts in biomedical papers. The system allows the users to concentrate on higher level interpretation by removing some troublesome tasks, e.g. management of abstracts, extracting protein names and their abbreviations, and so on. To extract a pair of protein names and abbreviations, we have developed a hybrid system composed of the PROPER System and the PNAD System. The PNAD System can extract the pairs from parenthetical-paraphrases involved in protein names, the PROPER System identified these paris, with 98.95% precision, 95.56% recall and 97.58% complete precision. AVAILABILITY: PROPER System is freely available from http://www.hgc.inc.u-tokyo.ac.jp/service/tooldoc /KeX/intro.html. The other software are also available on request. Contact the authors. CONTACT: mikio@ims.u-tokyo.ac.jp     

The human gene mutation database.

The Human Gene Mutation Database (HGMD) represents a comprehensive core collection of data on published germline mutations in nuclear genes underlying human inherited disease. By September 1997, the database contained nearly 12 000 different lesions in a total of 636 different genes, with new entries currently accumulating at a rate of over 2000 per annum. Although originally established for the scientific study of mutational mechanisms in human genes, HGMD has acquired a much broader utility to researchers, physicians and genetic counsellors so that it was made publicly available at http://uwcm.ac.uk/uwcm/mg/hgmd0.html in April 1996. Mutation data in HGMD are accessible on the basis of every gene being allocated one web page per mutation type, if data of that type are present. Meaningful integration with phenotypic, structural and mapping information has been accomplished through bi-directional links between HGMD and both the Genome Database (GDB) and Online Mendelian Inheritance in Man (OMIM), Baltimore, USA. Hypertext links have also been established to Medline abstracts through Entrez , and to a collection of 458 reference cDNA sequences also used for data checking. Being both comprehensive and fully integrated into the existing bioinformatics structures relevant to human genetics, HGMD has established itself as the central core database of inherited human gene mutations.     

Can Bibliographic Pointers for Known Biological Data Be Found Automatically? Protein Interactions as a Case Study

The Dictionary of Interacting Proteins (DIP) (Xenarios et al., 2000) is a large repository of protein interactions: its March 2000 release included 2379 protein pairs whose interactions have been detected by experimental methods. Even if many of these correspond to poorly characterized proteins, the result of massive yeast two-hybrid screenings, as many as 851 correspond to interactions detected using direct biochemical methods.We used information retrieval technology to search automatically for sentences in Medline abstracts that support these 851 DIP interactions. Surprisingly, we found correspondence between DIP protein pairs and Medline sentences describing their interactions in only 30% of the cases. This low coverage has interesting consequences regarding the quality of annotations (references) introduced in the database and the limitations of the application of information extraction (IE) technology to Molecular Biology. It is clear that the limitation of analyzing abstracts rather than full papers and the lack of standard protein names are difficulties of considerably more importance than the limitations of the IE methodology employed. A positive finding is the capacity of the IE system to identify new relations between proteins, even in a set of proteins previously characterized by human experts. These identifications are made with a considerable degree of precision.THIS IS, TO OUR KNOWLEDGE, THE FIRST LARGE SCALE ASSESSMENT OF IE CAPACITY TO DETECT PREVIOUSLY KNOWN INTERACTIONS: we thus propose the use of the DIP data set as a biological reference to benchmark IE systems.     

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.     

Towards classifying species in systems biology papers using text mining

Background

In recent years high throughput methods have led to a massive expansion in the free text literature on molecular biology. Automated text mining has developed as an application technology for formalizing this wealth of published results into structured database entries. However, database curation as a task is still largely done by hand, and although there have been many studies on automated approaches, problems remain in how to classify documents into top-level categories based on the type of organism being investigated. Here we present a comparative analysis of state of the art supervised models that are used to classify both abstracts and full text articles for three model organisms.

Results

Ablation experiments were conducted on a large gold standard corpus of 10,000 abstracts and full papers containing data on three model organisms (fly, mouse and yeast). Among the eight learner models tested, the best model achieved an F-score of 97.1% for fly, 88.6% for mouse and 85.5% for yeast using a variety of features that included gene name, organism frequency, MeSH headings and term-species associations. We noted that term-species associations were particularly effective in improving classification performance. The benefit of using full text articles over abstracts was consistently observed across all three organisms.

Conclusions

By comparing various learner algorithms and features we presented an optimized system that automatically detects the major focus organism in full text articles for fly, mouse and yeast. We believe the method will be extensible to other organism types.

     

miRTex: A Text Mining System for miRNA-Gene Relation Extraction

MicroRNAs (miRNAs) regulate a wide range of cellular and developmental processes through gene expression suppression or mRNA degradation. Experimentally validated miRNA gene targets are often reported in the literature. In this paper, we describe miRTex, a text mining system that extracts miRNA-target relations, as well as miRNA-gene and gene-miRNA regulation relations. The system achieves good precision and recall when evaluated on a literature corpus of 150 abstracts with F-scores close to 0.90 on the three different types of relations. We conducted full-scale text mining using miRTex to process all the Medline abstracts and all the full-length articles in the PubMed Central Open Access Subset. The results for all the Medline abstracts are stored in a database for interactive query and file download via the website at http://proteininformationresource.org/mirtex. Using miRTex, we identified genes potentially regulated by miRNAs in Triple Negative Breast Cancer, as well as miRNA-gene relations that, in conjunction with kinase-substrate relations, regulate the response to abiotic stress in Arabidopsis thaliana. These two use cases demonstrate the usefulness of miRTex text mining in the analysis of miRNA-regulated biological processes.     

Literature mining and database annotation of protein phosphorylation using a rule-based system

MOTIVATION: A large volume of experimental data on protein phosphorylation is buried in the fast-growing PubMed literature. While of great value, such information is limited in databases owing to the laborious process of literature-based curation. Computational literature mining holds promise to facilitate database curation. RESULTS: A rule-based system, RLIMS-P (Rule-based LIterature Mining System for Protein Phosphorylation), was used to extract protein phosphorylation information from MEDLINE abstracts. An annotation-tagged literature corpus developed at PIR was used to evaluate the system for finding phosphorylation papers and extracting phosphorylation objects (kinases, substrates and sites) from abstracts. RLIMS-P achieved a precision and recall of 91.4 and 96.4% for paper retrieval, and of 97.9 and 88.0% for extraction of substrates and sites. Coupling the high recall for paper retrieval and high precision for information extraction, RLIMS-P facilitates literature mining and database annotation of protein phosphorylation.     

Automated extraction of information in molecular biology

We review data mining techniques in molecular biology, specifically those that extract information from the scientific literature itself. As more of the biological literature is published electronically, there is an opportunity, and even a need, to automatically summarize the literature in a customized way, for example by associating keywords to a topic. These keywords can be extracted from relevant publications. The process of keyword extraction can be automated and optimized to keep literature pointers automatically up-to-date or to filter relevant information from the literature. To illustrate these points, OMIM (Online Mendelian Inheritance in Man), a database of human inherited diseases, was linked to the literature and keywords were derived that covered distinct aspects such as genetic information on the one hand and disease-specific protein and phenotypic information on the other. They were used to extract information that is helpful for keeping entries about disease up-to-date.     

Identifying relevant studies for systematic reviews.

OBJECTIVE--To examine the sensitivity and precision of Medline searching for randomised clinical trials. DESIGN--Comparison of results of Medline searches to a "gold standard" of known randomised clinical trials in ophthalmology published in 1988; systematic review (meta-analysis) of results of similar, but separate, studies from many fields of medicine. POPULATIONS--Randomised clinical trials published in 1988 in journals indexed in Medline, and those not indexed in Medline and identified by hand search, comprised the gold standard. Gold standards for the other studies combined in the meta-analysis were based on: randomised clinical trials published in any journal, whether indexed in Medline or not; those published in any journal indexed in Medline; or those published in a selected group of journals indexed in Medline. MAIN OUTCOME MEASURE--Sensitivity (proportion of the total number of known randomised clinical trials identified by the search) and precision (proportion of publications retrieved by Medline that were actually randomised clinical trials) were calculated for each study and combined to obtain weighted means. Searches producing the "best" sensitivity were used for sensitivity and precision estimates when multiple searches were performed. RESULTS--The sensitivity of searching for ophthalmology randomised clinical trials published in 1988 was 82%, when the gold standard was for any journal, 87% for any journal indexed in Medline, and 88% for selected journals indexed in Medline. Weighted means for sensitivity across all studies were 51%, 77%, and 63%, respectively. The weighted mean for precision was 8% (median 32.5%). Most searchers seemed not to use freetext subject terms and truncation of those terms. CONCLUSION--Although the indexing terms available for searching Medline for randomised clinical trials have improved, sensitivity still remains unsatisfactory. A mechanism is needed to "''register" known trials, preferably by retrospective tagging of Medline entries, and incorporating trials published before 1966 and in journals not indexed by Medline into the system.     

Text-analysis reveals taxonomic and geographic disparities in animal pollination literature

Ecological systematic reviews and meta-analyses have significantly increased our understanding of global biodiversity decline. However, for some ecological groups, incomplete and biased datasets have hindered our ability to construct robust, predictive models. One such group consists of the animal pollinators. Approximately 88% of wild plant species are thought to be pollinated by animals, with an estimated annual value of $230–410 billion dollars. Here we apply text-analysis to quantify the taxonomic and geographical distribution of the animal pollinator literature, both temporally and spatially. We show that the publication of pollinator literature increased rapidly in the 1980s and 1990s. Taxonomically, we show that the distribution of pollinator literature is concentrated in the honey bees (Apis) and bumble bees (Bombus), and geographically in North America and Europe. At least 25% of pollination-related abstracts mention a species of honey bee and at least 20% a species of bumble bee, and approximately 46% of abstracts are focussed on either North America (32%) or Europe (14%). Although these results indicate strong taxonomic and geographic biases in the pollinator literature, a large number of studies outside North America and Europe do exist. We then discuss how text-analysis could be used to shorten the literature search for ecological systematic reviews and meta-analyses, and to address more applied questions related to pollinator biodiversity, such as the identification of likely interacting plant–pollinator pairs and the number of pollinating species.