In silico prediction of novel miRNAs from genomic sequences remains a challenging problem. This study presents a genome-wide miRNA discovery software package called GenoScan and evaluates two hairpin classification methods. These methods, one ensemble-based and one using logistic regression were benchmarked along with 15 published methods. In addition, the sequence-folding step is addressed by investigating the impact of secondary structure prediction methods and the choice of input sequence length on prediction performance. Both the accuracy of secondary structure predictions and the miRNA prediction are evaluated. In the benchmark of hairpin classification methods, the regression model achieved highest classification accuracy. Of the structure prediction methods evaluated, ContextFold achieved the highest agreement between predicted and experimentally determined structures. However, both the choice of secondary structure prediction method and input sequence length had limited impact on hairpin classification performance.

We present a novel machine learning approach for the classification of cancer samples using expression data. We refer to the method as "decision trunks," since it is loosely based on decision trees, but contains several modifications designed to achieve an algorithm that: (1) produces smaller and more easily interpretable classifiers than decision trees; (2) is more robust in varying application scenarios; and (3) achieves higher classification accuracy. The decision trunk algorithm has been implemented and tested on 26 classification tasks, covering a wide range of cancer forms, experimental methods, and classification scenarios. This comprehensive evaluation indicates that the proposed algorithm performs at least as well as the current state of the art algorithms in terms of accuracy, while producing classifiers that include on average only 2-3 markers. We suggest that the resulting decision trunks have clear advantages over other classifiers due to their transparency, interpretability, and their correspondence with human decision-making and clinical testing practices. © the author(s), publisher and licensee Libertas Academica Ltd.

Background

Endometrial cancer (EC) is the most frequently diagnosed gynecological malignancy and the fourth most common cancer diagnosis overall among women. As with many other forms of cancer, it has been shown that certain miRNAs are differentially expressed in EC and these miRNAs are believed to play important roles as regulators of processes involved in the development of the disease. With the rapidly growing number of studies of miRNA expression in EC, there is a need to organize the data, combine the findings from experimental studies of EC with information from various miRNA databases, and make the integrated information easily accessible for the EC research community.

Findings

The miREC database is an organized collection of data and information about miRNAs shown to be differentially expressed in EC. The database can be used to map connections between miRNAs and their target genes in order to identify specific miRNAs that are potentially important for the development of EC. The aim of the miREC database is to integrate all available information about miRNAs and target genes involved in the development of endometrial cancer, and to provide a comprehensive, up-to-date, and easily accessible source of knowledge regarding the role of miRNAs in the development of EC. Database URL: http://www.mirecdb.orgwebcite.

Conclusions

Several databases have been published that store information about all miRNA targets that have been predicted or experimentally verified to date. It would be a time-consuming task to navigate between these different data sources and literature to gather information about a specific disease, such as endometrial cancer. The miREC database is a specialized data repository that, in addition to miRNA target information, keeps track of the differential expression of genes and miRNAs potentially involved in endometrial cancer development. By providing flexible search functions it becomes easy to search for EC-associated genes and miRNAs from different starting points, such as differential expression and genomic loci (based on genomic aberrations).