Dataset Information

Predicting biomedical metadata in CEDAR: A study of Gene Expression Omnibus (GEO).

ABSTRACT: A crucial and limiting factor in data reuse is the lack of accurate, structured, and complete descriptions of data, known as metadata. Towards improving the quantity and quality of metadata, we propose a novel metadata prediction framework to learn associations from existing metadata that can be used to predict metadata values. We evaluate our framework in the context of experimental metadata from the Gene Expression Omnibus (GEO). We applied four rule mining algorithms to the most common structured metadata elements (sample type, molecular type, platform, label type and organism) from over 1.3million GEO records. We examined the quality of well supported rules from each algorithm and visualized the dependencies among metadata elements. Finally, we evaluated the performance of the algorithms in terms of accuracy, precision, recall, and F-measure. We found that PART is the best algorithm outperforming Apriori, Predictive Apriori, and Decision Table. All algorithms perform significantly better in predicting class values than the majority vote classifier. We found that the performance of the algorithms is related to the dimensionality of the GEO elements. The average performance of all algorithm increases due of the decreasing of dimensionality of the unique values of these elements (2697 platforms, 537 organisms, 454 labels, 9 molecules, and 5 types). Our work suggests that experimental metadata such as present in GEO can be accurately predicted using rule mining algorithms. Our work has implications for both prospective and retrospective augmentation of metadata quality, which are geared towards making data easier to find and reuse.

SUBMITTER: Panahiazar M

PROVIDER: S-EPMC5643580 | biostudies-literature | 2017 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting biomedical metadata in CEDAR: A study of Gene Expression Omnibus (GEO).

Panahiazar Maryam M Dumontier Michel M Gevaert Olivier O

Journal of biomedical informatics 20170616

A crucial and limiting factor in data reuse is the lack of accurate, structured, and complete descriptions of data, known as metadata. Towards improving the quantity and quality of metadata, we propose a novel metadata prediction framework to learn associations from existing metadata that can be used to predict metadata values. We evaluate our framework in the context of experimental metadata from the Gene Expression Omnibus (GEO). We applied four rule mining algorithms to the most common struct ...[more]

PMID: 28625880

Similar Datasets

Project description:Background The purpose of this study is to explore the relationship between the ferroptosis-related gene zinc finger protein 36 (ZFP36) and the prognosis of osteosarcoma patients after surgery. Methods Differential expression genes (DEGs) between osteosarcoma and normal tissues were screened using osteosarcoma chip data in GEO database. Based on the median expression quantity, ferroptosis DEGs were divided into high and low expression groups. Combined with its corresponding clinical survival data, the survival analysis of ferroptosis DEGs was carried out using the Survival package, and ferroptosis-related genes related to prognosis were identified. Next, the clinical data of 60 osteosarcoma patients treated in Jiangyin Hospital Affiliated to Nanjing University of Chinese Medicine, Zhongda Hospital and Nanjing Drum Tower Hospital from January 2011 to January 2016 were retrospectively analyzed. Immunohistochemistry and reverse transcription quantitative polymerase chain reaction (qRT-PCR) were used to detect gene expression in osteosarcoma. The Kaplan-Meier method and log rank test were used for univariate survival analysis, the Cox regression method was used for multivariate analysis, and the nomogram was constructed for internal verification on this basis. Results Immunohistochemical and reverse transcription quantitative PCR results showed that the expression of ZFP36 was mainly higher in cancer-adjacent tissues than in tumor tissues. There were significant differences in age, tumor location, Enneking stage, and tumor specific growth factor (TSGF) between the high and low expression groups of ZFP36 (P<0.05). The final study included 60 patients, of whom 23 patients died (mortality rate: 38.33%), and 37 patients survived (survival rate: 61.67%), with a median progression-free survival (PFS) of 32.5 months and a median overall survival (OS) of 77 months. The Cox multivariate analysis showed that distant metastasis and ZFP36 were independent risk factors affecting tumor progression (P=0.021 and P=0.006, respectively). Elevated ZFP36 can significantly prolong the OS and PFS of osteosarcoma patients. In internal verification, the Concordance index (C-index) of the nomogram was 0.7211 [95% confidence interval (CI): 0.6308–0.8115], and the prediction model had certain accuracy. Conclusions Elevated ZFP36 can significantly prolong the OS and PFS in osteosarcoma patients. At the same time, ZFP36 could be used as a new predictive biomarker and novel therapeutic target for osteosarcoma patients.

Dataset Information

Predicting biomedical metadata in CEDAR: A study of Gene Expression Omnibus (GEO).

Publications

Predicting biomedical metadata in CEDAR: A study of Gene Expression Omnibus (GEO).

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets