Dataset Information

Multi-class computational evolution: development, benchmark evaluation and application to RNA-Seq biomarker discovery.

ABSTRACT: BACKGROUND:A computational evolution system (CES) is a knowledge discovery engine that can identify subtle, synergistic relationships in large datasets. Pareto optimization allows CESs to balance accuracy with model complexity when evolving classifiers. Using Pareto optimization, a CES is able to identify a very small number of features while maintaining high classification accuracy. A CES can be designed for various types of data, and the user can exploit expert knowledge about the classification problem in order to improve discrimination between classes. These characteristics give CES an advantage over other classification and feature selection algorithms, particularly when the goal is to identify a small number of highly relevant, non-redundant biomarkers. Previously, CESs have been developed only for binary class datasets. In this study, we developed a multi-class CES. RESULTS:The multi-class CES was compared to three common feature selection and classification algorithms: support vector machine (SVM), random k-nearest neighbor (RKNN), and random forest (RF). The algorithms were evaluated on three distinct multi-class RNA sequencing datasets. The comparison criteria were run-time, classification accuracy, number of selected features, and stability of selected feature set (as measured by the Tanimoto distance). The performance of each algorithm was data-dependent. CES performed best on the dataset with the smallest sample size, indicating that CES has a unique advantage since the accuracy of most classification methods suffer when sample size is small. CONCLUSION:The multi-class extension of CES increases the appeal of its application to complex, multi-class datasets in order to identify important biomarkers and features.

SUBMITTER: Crabtree NM

PROVIDER: S-EPMC5404302 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multi-class computational evolution: development, benchmark evaluation and application to RNA-Seq biomarker discovery.

Crabtree Nathaniel M NM Moore Jason H JH Bowyer John F JF George Nysia I NI

BioData mining 20170424

<h4>Background</h4>A computational evolution system (CES) is a knowledge discovery engine that can identify subtle, synergistic relationships in large datasets. Pareto optimization allows CESs to balance accuracy with model complexity when evolving classifiers. Using Pareto optimization, a CES is able to identify a very small number of features while maintaining high classification accuracy. A CES can be designed for various types of data, and the user can exploit expert knowledge about the clas ...[more]

PMID: 28450890

Similar Datasets

Project description:BackgroundClassification is the problem of assigning each input object to one of a finite number of classes. This problem has been extensively studied in machine learning and statistics, and there are numerous applications to bioinformatics as well as many other fields. Building a multiclass classifier has been a challenge, where the direct approach of altering the binary classification algorithm to accommodate more than two classes can be computationally too expensive. Hence the indirect approach of using binary decomposition has been commonly used, in which retrieving the class posterior probabilities from the set of binary posterior probabilities given by the individual binary classifiers has been a major issue.MethodsIn this work, we present an extension of a recently introduced probabilistic kernel-based learning algorithm called the Classification Relevance Units Machine (CRUM) to the multiclass setting to increase its applicability. The extension is achieved under the error correcting output codes framework. The probabilistic outputs of the binary CRUMs are preserved using a proposed linear-time decoding algorithm, an alternative to the generalized Bradley-Terry (GBT) algorithm whose application to large-scale prediction settings is prohibited by its computational complexity. The resulting classifier is called the Multiclass Relevance Units Machine (McRUM).ResultsThe evaluation of McRUM on a variety of real small-scale benchmark datasets shows that our proposed Naïve decoding algorithm is computationally more efficient than the GBT algorithm while maintaining a similar level of predictive accuracy. Then a set of experiments on a larger scale dataset for small ncRNA classification have been conducted with Naïve McRUM and compared with the Gaussian and linear SVM. Although McRUM's predictive performance is slightly lower than the Gaussian SVM, the results show that the similar level of true positive rate can be achieved by sacrificing false positive rate slightly. Furthermore, McRUM is computationally more efficient than the SVM, which is an important factor for large-scale analysis.ConclusionsWe have proposed McRUM, a multiclass extension of binary CRUM. McRUM with Naïve decoding algorithm is computationally efficient in run-time and its predictive performance is comparable to the well-known SVM, showing its potential in solving large-scale multiclass problems in bioinformatics and other fields of study.

Project description:Replicating circular RNAs are independent plant pathogens known as viroids, or act to modulate the pathogenesis of plant and animal viruses as their satellite RNAs. The rate of discovery of these subviral pathogens was low over the past 40 years because the classical approaches are technical demanding and time-consuming. We previously described an approach for homology-independent discovery of replicating circular RNAs by analysing the total small RNA populations from samples of diseased tissues with a computational program known as progressive filtering of overlapping small RNAs (PFOR). However, PFOR written in PERL language is extremely slow and is unable to discover those subviral pathogens that do not trigger in vivo accumulation of extensively overlapping small RNAs. Moreover, PFOR is yet to identify a new viroid capable of initiating independent infection. Here we report the development of PFOR2 that adopted parallel programming in the C++ language and was 3 to 8 times faster than PFOR. A new computational program was further developed and incorporated into PFOR2 to allow the identification of circular RNAs by deep sequencing of long RNAs instead of small RNAs. PFOR2 analysis of the small RNA libraries from grapevine and apple plants led to the discovery of Grapevine latent viroid (GLVd) and Apple hammerhead viroid-like RNA (AHVd-like RNA), respectively. GLVd was proposed as a new species in the genus Apscaviroid, because it contained the typical structural elements found in this group of viroids and initiated independent infection in grapevine seedlings. AHVd-like RNA encoded a biologically active hammerhead ribozyme in both polarities, and was not specifically associated with any of the viruses found in apple plants. We propose that these computational algorithms have the potential to discover novel circular RNAs in plants, invertebrates and vertebrates regardless of whether they replicate and/or induce the in vivo accumulation of small RNAs.

Dataset Information

Multi-class computational evolution: development, benchmark evaluation and application to RNA-Seq biomarker discovery.

Publications

Multi-class computational evolution: development, benchmark evaluation and application to RNA-Seq biomarker discovery.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets