Dataset Information

Of text and gene--using text mining methods to uncover hidden knowledge in toxicogenomics.

ABSTRACT:

Background

Toxicogenomics studies often profile gene expression from assays involving multiple doses and time points. The dose- and time-dependent pattern is of great importance to assess toxicity but computational approaches are lacking to effectively utilize this characteristic in toxicity assessment. Topic modeling is a text mining approach, but may be used analogously in toxicogenomics due to the similar data structures between text and gene dysregulation.

Results

Topic modeling was applied to a very large toxicogenomics dataset containing microarray gene expression data from >15,000 samples associated with 131 drugs tested in three different assay platforms (i.e., in vitro assay, in vivo repeated dose study and in vivo single dose experiment) with a design including multiple doses and time points. A set of "topics" which each consist of a set of genes was determined, by which the varying sensitivity of three assay systems was observed. We found that the drug-dependent effect was more pronounced in the two in vivo systems than the in vitro system, while the time-dependent effect was most strongly reflected in the in vitro system followed by the single dose study and lastly the repeated dose experiment. The dose-dependent effect was similar across three assay systems. Although the results indicated a challenge to extrapolate the in vitro results to the in vivo situation, we did notice that, for some drugs but not for all the drugs, the similarity in gene expression patterns was observed across all three assay systems, indicating a possibility of using in vitro systems with careful designs (such as the choice of dose and time point), to replace the in vivo testing strategy. Nonetheless, a potential to replace the repeated dose study by the single-dose short-term methodology was strongly implied.

Conclusions

The study demonstrated that text mining methodologies such as topic modeling provide an alternative method compared to traditional means for data reduction in toxicogenomics, enhancing researchers' capabilities to interpret biological information.

SUBMITTER: Lee M

PROVIDER: S-EPMC4236689 | biostudies-literature | 2014 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Of text and gene--using text mining methods to uncover hidden knowledge in toxicogenomics.

Lee Mikyung M Liu Zhichao Z Kelly Reagan R Tong Weida W

BMC systems biology 20140813

<h4>Background</h4>Toxicogenomics studies often profile gene expression from assays involving multiple doses and time points. The dose- and time-dependent pattern is of great importance to assess toxicity but computational approaches are lacking to effectively utilize this characteristic in toxicity assessment. Topic modeling is a text mining approach, but may be used analogously in toxicogenomics due to the similar data structures between text and gene dysregulation.<h4>Results</h4>Topic modeli ...[more]

PMID: 25115450

Similar Datasets

Project description:ObjectivesThis study aimed to explore, from the perspectives of nurses, how patients, the environment, and the practice of nurses interact with each other to contribute to patient falls.MethodsA retrospective review of incident reports on patient falls, registered by nurses between 2016 and 2020, was conducted. The incident reports were retrieved from the database set up for the project of the Japan Council for Quality Health Care. The text descriptions of the "background of falls" were extracted verbatim, and analyzed by using a text-mining approach.ResultsA total of 4,176 incident reports on patient falls were analyzed. Of these falls, 79.0% were unwitnessed by nurses, and 8.7% occurred during direct nursing care. Document clustering identified 16 clusters. Four clusters were related to patients, such as the decline in their physiological/cognitive function, a loss of balance, and their use of hypnotic and psychotropic agents. Three clusters were related to nurses, and these included a lack of situation awareness, reliance on patient families, and insufficient implementation of the nursing process. Six clusters were concerned with patients and nurses, including the unproductive use of a bed alarm and call bells, the use of inappropriate footwear, the problematic use of walking aids and bedrails, and insufficient understanding of patients' activities of daily living. One cluster, chair-related falls, involved both patient and environmental factors. Finally, two clusters involved patient, nurse, and environmental factors, and these falls occurred when patients were bathing/showering or using a bedside commode.ConclusionsFalls were caused by a dynamic interplay between patients, nurses, and the environment. Since many of the patient factors are difficult to modify in a short time, the focus has to be placed on nursing and environmental factors to reduce falls. In particular, improving nurses' situation awareness is of foremost importance, as it influences their decisions and actions to prevent falls.

Dataset Information

Of text and gene--using text mining methods to uncover hidden knowledge in toxicogenomics.

Background

Results

Conclusions

Publications

Of text and gene--using text mining methods to uncover hidden knowledge in toxicogenomics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets