Dataset Information

DNorm: disease name normalization with pairwise learning to rank.

ABSTRACT: Despite the central role of diseases in biomedical research, there have been much fewer attempts to automatically determine which diseases are mentioned in a text-the task of disease name normalization (DNorm)-compared with other normalization tasks in biomedical text mining research.In this article we introduce the first machine learning approach for DNorm, using the NCBI disease corpus and the MEDIC vocabulary, which combines MeSH® and OMIM. Our method is a high-performing and mathematically principled framework for learning similarities between mentions and concept names directly from training data. The technique is based on pairwise learning to rank, which has not previously been applied to the normalization task but has proven successful in large optimization problems for information retrieval.We compare our method with several techniques based on lexical normalization and matching, MetaMap and Lucene. Our algorithm achieves 0.782 micro-averaged F-measure and 0.809 macro-averaged F-measure, an increase over the highest performing baseline method of 0.121 and 0.098, respectively.The source code for DNorm is available at http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/DNorm, along with a web-based demonstration and links to the NCBI disease corpus. Results on PubMed abstracts are available in PubTator: http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/PubTator .

SUBMITTER: Leaman R

PROVIDER: S-EPMC3810844 | biostudies-literature | 2013 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

DNorm: disease name normalization with pairwise learning to rank.

Leaman Robert R Islamaj Dogan Rezarta R Lu Zhiyong Z

Bioinformatics (Oxford, England) 20130821 22

<h4>Motivation</h4>Despite the central role of diseases in biomedical research, there have been much fewer attempts to automatically determine which diseases are mentioned in a text-the task of disease name normalization (DNorm)-compared with other normalization tasks in biomedical text mining research.<h4>Methods</h4>In this article we introduce the first machine learning approach for DNorm, using the NCBI disease corpus and the MEDIC vocabulary, which combines MeSH® and OMIM. Our method is a h ...[more]

PMID: 23969135

Similar Datasets

Project description:Information encoded in natural language in biomedical literature publications is only useful if efficient and reliable ways of accessing and analyzing that information are available. Natural language processing and text mining tools are therefore essential for extracting valuable information, however, the development of powerful, highly effective tools to automatically detect central biomedical concepts such as diseases is conditional on the availability of annotated corpora. This paper presents the disease name and concept annotations of the NCBI disease corpus, a collection of 793 PubMed abstracts fully annotated at the mention and concept level to serve as a research resource for the biomedical natural language processing community. Each PubMed abstract was manually annotated by two annotators with disease mentions and their corresponding concepts in Medical Subject Headings (MeSH®) or Online Mendelian Inheritance in Man (OMIM®). Manual curation was performed using PubTator, which allowed the use of pre-annotations as a pre-step to manual annotations. Fourteen annotators were randomly paired and differing annotations were discussed for reaching a consensus in two annotation phases. In this setting, a high inter-annotator agreement was observed. Finally, all results were checked against annotations of the rest of the corpus to assure corpus-wide consistency. The public release of the NCBI disease corpus contains 6892 disease mentions, which are mapped to 790 unique disease concepts. Of these, 88% link to a MeSH identifier, while the rest contain an OMIM identifier. We were able to link 91% of the mentions to a single disease concept, while the rest are described as a combination of concepts. In order to help researchers use the corpus to design and test disease identification methods, we have prepared the corpus as training, testing and development sets. To demonstrate its utility, we conducted a benchmarking experiment where we compared three different knowledge-based disease normalization methods with a best performance in F-measure of 63.7%. These results show that the NCBI disease corpus has the potential to significantly improve the state-of-the-art in disease name recognition and normalization research, by providing a high-quality gold standard thus enabling the development of machine-learning based approaches for such tasks. The NCBI disease corpus, guidelines and other associated resources are available at: http://www.ncbi.nlm.nih.gov/CBBresearch/Dogan/DISEASE/.

Project description:BackgroundMicroarray technology has become very popular for globally evaluating gene expression in biological samples. However, non-linear variation associated with the technology can make data interpretation unreliable. Therefore, methods to correct this kind of technical variation are critical. Here we consider a method to reduce this type of variation applied after three common procedures for processing microarray data: MAS 5.0, RMA, and dChip.ResultsWe commonly observe intensity-dependent technical variation between samples in a single microarray experiment. This is most common when MAS 5.0 is used to process probe level data, but we also see this type of technical variation with RMA and dChip processed data. Datasets with unbalanced numbers of up and down regulated genes seem to be particularly susceptible to this type of intensity-dependent technical variation. Unbalanced gene regulation is common when studying cancer samples or genetically manipulated animal models and preservation of this biologically relevant information, while removing technical variation has not been well addressed in the literature. We propose a method based on using rank-invariant, endogenous transcripts as reference points for normalization (GRSN). While the use of rank-invariant transcripts has been described previously, we have added to this concept by the creation of a global rank-invariant set of transcripts used to generate a robust average reference that is used to normalize all samples within a dataset. The global rank-invariant set is selected in an iterative manner so as to preserve unbalanced gene expression. Moreover, our method works well as an overlay that can be applied to data already processed with other probe set summary methods. We demonstrate that this additional normalization step at the "probe set level" effectively corrects a specific type of technical variation that often distorts samples in datasets.ConclusionWe have developed a simple post-processing tool to help detect and correct non-linear technical variation in microarray data and demonstrate how it can reduce technical variation and improve the results of downstream statistical gene selection and pathway identification methods.

Dataset Information

DNorm: disease name normalization with pairwise learning to rank.

Publications

DNorm: disease name normalization with pairwise learning to rank.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets