Document Detail

FACTA: a text search engine for finding associated biomedical concepts.
Jump to Full Text
MedLine Citation:
PMID:  18772154     Owner:  NLM     Status:  MEDLINE    
AVAILABILITY: The system is available at
Yoshimasa Tsuruoka; Jun'ichi Tsujii; Sophia Ananiadou
Related Documents :
10724864 - Human aspects of medical computer application.
18710224 - Most efficient cocaine hydrolase designed by virtual screening of transition states.
10339164 - Developing a reliable medical informatics network.
7719804 - Toward a medical-concept representation language. the canon group.
22321914 - Thrombo-prophylaxis (tp) in colo-rectal surgery: a national questionnaire survey (nqs) ...
22644214 - Cost of healthcare for patients with migraine in five european countries: results from ...
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't     Date:  2008-09-04
Journal Detail:
Title:  Bioinformatics (Oxford, England)     Volume:  24     ISSN:  1367-4811     ISO Abbreviation:  Bioinformatics     Publication Date:  2008 Nov 
Date Detail:
Created Date:  2008-10-21     Completed Date:  2008-11-18     Revised Date:  2013-06-05    
Medline Journal Info:
Nlm Unique ID:  9808944     Medline TA:  Bioinformatics     Country:  England    
Other Details:
Languages:  eng     Pagination:  2559-60     Citation Subset:  IM    
School of Computer Science, The University of Manchester, Manchester, UK.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Abstracting and Indexing as Topic / methods*
Database Management Systems
Grant Support
BB/E004431/1//Biotechnology and Biological Sciences Research Council

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Full Text
Journal Information
Journal ID (nlm-ta): Bioinformatics
Journal ID (publisher-id): bioinformatics
Journal ID (hwp): bioinfo
ISSN: 1367-4803
ISSN: 1460-2059
Publisher: Oxford University Press
Article Information
? 2008 The Author(s)
creative-commons: This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Received Day: 13 Month: 6 Year: 2008
Revision Received Day: 9 Month: 8 Year: 2008
Accepted Day: 29 Month: 8 Year: 2008
Print publication date: Day: 1 Month: 11 Year: 2008
Electronic publication date: Day: 4 Month: 9 Year: 2008
pmc-release publication date: Day: 4 Month: 9 Year: 2008
Volume: 24 Issue: 21
First Page: 2559 Last Page: 2560
ID: 2572701
DOI: 10.1093/bioinformatics/btn469
Publisher Id: btn469
PubMed Id: 18772154

FACTA: a text search engine for finding associated biomedical concepts
Yoshimasa Tsuruoka12*
Jun'ichi Tsujii123
Sophia Ananiadou12
1School of Computer Science, The University of Manchester, 2National Centre for Text Mining (NaCTeM), Manchester, UK and 3Department of Computer Science, The University of Tokyo, Japan
Correspondence: *To whom correspondence should be addressed.
Associate Editor: Jonathan Wren


Information about pairwise association between biomedical concepts, such as genes, proteins, diseases and chemical compounds constitutes an important part of biomedical knowledge.1 It is common for a researcher to need answers to questions like ?What diseases are relevant to a particular gene?? or ?What chemical compounds are relevant to a particular disease?? Text mining complements biomedical databases by providing researchers with a convenient way to find such information from the literature.

There are a number of web-based text mining applications which can be used for this purpose. EBIMed (Rebholz-Schuhmann et al., 2007) receives a PubMed-style query from the user and analyzes the matched documents to recognize protein/gene names, GO annotations, drugs and species mentioned. Frequently occurring concepts are shown in a table, and the user can view the sentences corresponding to the associations. PolySearch (Cheng et al., 2008) can produce a list of concepts which are relevant to the user's query by analyzing multiple information sources including PubMed, OMIM, DrugBank and Swiss-Prot. It covers many types of biomedical concepts including diseases, genes/proteins, drugs, metabolites, SNPs, pathways and tissues. Systems that provide similar functionality include XplorMed (Perez-Iratxeta et al., 2003), MedlineR (Lin et al., 2004), LitMiner (Maier et al., 2005) and Anii (Jelier et al., 2008).

Although these applications are useful in exploring such information in the literature, not many of them provide real-time responses?the users often have to wait for several minutes (or even hours) before they receive the results. Some of the systems provide reasonably quick responses by limiting the number of documents to be analyzed to a very small number (e.g. 500 abstracts), but such limitation leads to a significant deterioration of the coverage. LitMiner and Anii are exceptions in that they can return the result immediately, presumably thanks to pre-computed association statistics between the concepts. However, they do not accept a flexible query (e.g. free keywords or Boolean combinations of keywords/concepts), hence the concepts that can be specified by the user's query are limited to predefined ones.

To complement existing applications, we have developed FACTA, which is a text search engine for browsing biomedical concepts that are potentially relevant to a query. The distinct advantage of FACTA is that it delivers real-time responses while being able to accept flexible queries. This is achieved by online computation of association statistics?FACTA analyzes the documents retrieved by the query dynamically, using pre-indexed words and concepts.


FACTA receives a query from the user as the input. A query can be a word (e.g. ?p53?), a concept ID (e.g. ?UNIPROT:P04637?), or a combination of these [e.g. ?(UNIPROT:P04637 AND (lung OR gastric))?]. The system then retrieves all the documents that match the query from MEDLINE using word/concept indexes. The concepts contained in the documents are then counted and ranked according to their relevance to the query. The results are presented to the user in a tabular format.

Figure 1 shows an example of the search result. For the input query ?apoptosis AND blood?, the system retrieved 7734 documents from MEDLINE in 0.04 s. The relevant concepts of six categories are displayed in a table and ranked by their frequencies. The document icon next to each concept name in the table allows the user to view snippets from MEDLINE and see textual evidence of the association. The user can also invoke another search by clicking a concept name in the table. This allows the user to explore associations between many different concepts in a highly interactive manner.

2.1 Indexing

FACTA's real-time responses to the queries are made possible by the use of its own indexing scheme and implementation of the analysis engines in C++. It uses two indexes built offline?one for the words and the other for the concepts. Both indexes are stored in memory to achieve quick responses, while the actual sentences of MEDLINE abstracts are stored on external storage. The system runs on a generic Linux server with 2.2 GHz AMD Opteron processors and 16 GB memory.

Currently, FACTA covers six categories of biomedical concepts: human genes/proteins, diseases, symptoms, drugs, enzymes and chemical compounds. The concepts appearing in the documents are recognized by dictionary matching. In total, 80 260 unique concepts are indexed. We used UniProt accession numbers as the concept IDs for genes/proteins and collected their names and synonyms from BioThesaurus (Liu et al., 2006). We used UMLS (Humphreys and Lindberg, 1989) for diseases and symptoms. The concept IDs and names for drugs, enzymes and chemical compounds were collected from several databases including HMDB, KEGG and DrugBank.

Ambiguity causes problems in indexing. For example, the term ?collapse? is not necessarily used as a symptom name in the documents that produced the results shown in Figure 1, so ideally such occurrences should be disambiguated using the context and excluded from the counting for the category. There is also intra-category ambiguity, e.g. some protein synonyms can be mapped to multiple gene/protein IDs. These problems are currently not addressed in FACTA.

2.2 Ranking

Since the number of the concepts contained in the documents is usually very large, it is important that the concepts are properly ranked when presented to the user. Although frequencies are normally a good indicator of the relevance of a concept, they tend to overestimate the importance of common concepts. FACTA can also rank the concepts by using pointwise mutual information, which is defined as log p(x, y)/(p(x)p(y)), where p(x) is the proportion of the documents that match the query, p(y) is the proportion of the documents that contain the concept, and p(x, y) is the proportion of the documents that match the query and contain the concept. Pointwise mutual information gives an indication of how much more the query and concept co-occur than we expect by chance. For example, if their occurrences are completely independent (i.e. p(x, y)=p(x)p(y)), the measure gives a value of zero.


FN11In this article, a biomedical concept refers to a conceptual entity which is normally grounded to a record in a biomedical database. In text, the same concept (e.g. UniProt:O00203) may be represented by different terms (e.g. ?AP-3 complex subunit beta-1? or ?Beta3A-adaptin?). Note also that the same term may represent different concepts depending on the context, although this problem is currently not resolved in FACTA.


The research team is hosted by the JISC/BBSRC/EPSRC sponsored National Centre for Text Mining.

Funding: Biotechnology and Biological Sciences Research Council (grant code BB/E004431/1).

Conflict of Interest: none declared.

Cheng D,et al. PolySearch: a web-based text mining system for extracting relationships between human diseases, genes, mutations, drugs and metabolitesNucleic Acids Res 2008;36:W399–W405. [pmid: 18487273]
Humphreys BL,Lindberg DAB. Building the unified medical language systemProceedings of the 13th SCAMC 1989:475–480.
Jelier R,et al. Anni 2.0: a multipurpose text-mining tool for the life sciencesGenome Biol 2008;9
Lin SM,et al. MedlineR: an open source library in R for Medline literature data miningBioinformatics 2004;20:3659–3661. [pmid: 15284107]
Liu H,et al. BioThesaurus: a web-based thesaurus of protein and gene namesBioinformatics 2006;22:103–105. [pmid: 16267085]
Maier H,et al. LitMiner and WikiGene: identifying problem-related key players of gene regulation using publication abstractsNucleic Acids Res 2005;33:W779–W782. [pmid: 15980584]
Perez-Iratxeta C,et al. Update on XplorMed: a web server for exploring scientific literatureNucleic Acids Res 2003;31:3866–3868. [pmid: 12824439]
Rebholz-Schuhmann D,et al. EBIMed?text crunching to gather facts for proteins from MEDLINEBioinformatics 2007;23:e237–e244. [pmid: 17237098]


[Figure ID: F1]
Fig. 1. 

A screenshot of FACTA search results.

Article Categories:
  • Applications Note
    • Data and Text Mining

Previous Document:  System estimation from metabolic time-series data.
Next Document:  Identification of the idiosyncratic bacterial protein tyrosine kinase (BY-kinase) family signature.