An automated procedure to identify biomedical articles that contain cancer-associated gene variants

Abstract

The proliferation of biomedical literature makes it increasingly difficult for researchers to find and manage relevant information. However, identifying research articles containing mutation data, a requisite first step in integrating large and complex mutation data sets, is currently tedious, time-consuming and imprecise. More effective mechanisms for identifying articles containing mutation information would be beneficial both for the curation of mutation databases and for individual researchers. We developed an automated method that uses information extraction, classifier, and relevance ranking techniques to determine the likelihood of MEDLINE abstracts containing information regarding genomic variation data suitable for inclusion in mutation databases. We targeted the CDKN2A (p16) gene and the procedure for document identification currently used by CDKN2A Database curators as a measure of feasibility. A set of abstracts was manually identified from a MEDLINE search as potentially containing specific CDKN2A mutation events. A subset of these abstracts was used as a training set for a maximum entropy classifier to identify text features distinguishing "relevant" from "not relevant" abstracts. Each document was represented as a set of indicative word, word pair, and entity tagger-derived genomic variation features. When applied to a test set of 200 candidate abstracts, the classifier predicted 88 articles as being relevant; of these, 29 of 32 manuscripts in which manual curation found CDKN2A sequence variants were positively predicted. Thus, the set of potentially useful articles that a manual curator would have to review was reduced by 56%, maintaining 91% recall (sensitivity) and more than doubling precision (positive predictive value). Subsequent expansion of the training set to 494 articles yielded similar precision and recall rates, and comparison of the original and expanded trials demonstrated that the average precision improved with the larger data set. Our results show that automated systems can effectively identify article subsets relevant to a given task and may prove to be powerful tools for the broader research community. This procedure can be readily adapted to any or all genes, organisms, or sets of documents. Classifying text for cancer mutations AbstractThe proliferation of biomedical literature makes it increasingly difficult for researchers to find and manage relevant information. However, identifying research articles containing mutation data, a requisite first step in integrating large and complex mutation data sets, is currently tedious, time-consuming and imprecise. More effective mechanisms for identifying articles containing mutation information would be beneficial both for the curation of mutation databases and for individual researchers. We developed an automated method that uses information extraction, classifier, and relevance ranking techniques to determine the likelihood of MEDLINE abstracts containing mentions of genomic variation data suitable for inclusion in mutation d...

A learning-based approach for performing an in-depth literature search using MEDLINE

“…‘McDonald et al. (17) explored an automated method for effective identification of appropriate research articles. This study developed an automated method using information extraction, classifiers and relevance ranking techniques to determine the likelihood of MEDLINE abstracts containing the relevant information.…”

“…This was achieved by training the algorithm on a subset of articles, based on identification of relevant keywords. The results of the study showed that the proposed automated system could effectively identify articles relevant to the immediate question and may prove to be a powerful tool for the broader research community (17). The principle difference between the previous automated searches (16, 17) lies in the intuitive learning nature of the algorithm proposed here, where in each iteration, an adaptive feedback step is employed to increase the search coverage.…”

Identifying Gene-Specific Variations in Biomedical Text

“…In a first naive step, we checked the complete set of Medline abstracts (version as of April 26, 2007) to see if a regular expression finding mentions of [rR] [sS][ ]*[0-9][0-9]* in articles published after the year 2000 would be sufficient for the task. With this approach, we could guarantee a recall of 100% and checked the precision by subsampling of 300 mentions from the number of all mentions matching the regular expression (3,030). The ambiguity of rs number mentions was surprisingly high, which resulted in a precision of only 74%.…”

“…3 This kind of information will allow semantic searches like, "Give me all articles mentioning a variation and diabetes." It is obvious that this will be of great help in the design of genetic studies.…”

Immunoinformatics: Current trends and future directions

“…Attempts are being made for the extraction of interesting and complex patterns from non-structured text documents in the immunological domain. Examples include categorization of allergen cross-reactivity information [22], identification of cancer-associated gene variants [23], and the classification of immune epitopes [24].…”