Integration of RNA-Seq data with heterogeneous microarray data for breast cancer profiling

Abstract

BackgroundNowadays, many public repositories containing large microarray gene expression datasets are available. However, the problem lies in the fact that microarray technology are less powerful and accurate than more recent Next Generation Sequencing technologies, such as RNA-Seq. In any case, information from microarrays is truthful and robust, thus it can be exploited through the integration of microarray data with RNA-Seq data. Additionally, information extraction and acquisition of large number of samples in RNA-Seq still entails very high costs in terms of time and computational resources.This paper proposes a new model to find the gene signature of breast cancer cell lines through the integration of heterogeneous data from different breast cancer datasets, obtained from microarray and RNA-Seq technologies. Consequently, data integration is expected to provide a more robust statistical significance to the results obtained. Finally, a classification method is proposed in order to test the robustness of the Differentially Expressed Genes when unseen data is presented for diagnosis.ResultsThe proposed data integration allows analyzing gene expression samples coming from different technologies. The most significant genes of the whole integrated data were obtained through the intersection of the three gene sets, corresponding to the identified expressed genes within the microarray data itself, within the RNA-Seq data itself, and within the integrated data from both technologies. This intersection reveals 98 possible technology-independent biomarkers. Two different heterogeneous datasets were distinguished for the classification tasks: a training dataset for gene expression identification and classifier validation, and a test dataset with unseen data for testing the classifier. Both of them achieved great classification accuracies, therefore confirming the validity of the obtained set of genes as possible biomarkers for breast cancer. Through a feature selection process, a final small subset made up by six genes was considered for breast cancer diagnosis.ConclusionsThis work proposes a novel data integration stage in the traditional gene expression analysis pipeline through the combination of heterogeneous data from microarrays and RNA-Seq technologies. Available samples have been successfully classified using a subset of six genes obtained by a feature selection method. Consequently, a new classification and diagnosis tool was built and its performance was validated using previously unseen samples.

Likelihood contrasts: a machine learning algorithm for binary classification of longitudinal data

“…For example, Pirooznia et al 36 used eight machine learning algorithms in eight microarray gene expression data sets, and they found SVM to have the best performance. In line with this, Castillo et al 37 analysed RNA-sequencing and microarray data sets, finding SVM to be more accurate than RF or nearest-neighbour classification. However, Bienkowska et al 38 used SVM and RF in combination with iterated feature selection in gene expression data.…”

Integration of Mouse and Human Single-cell RNA Sequencing Infers Spatial Cell-type Composition in Human Brains

“…Computational deconvolution to differentiate cell types is an important topic of transcriptomic data analysis, which can facilitate the elucidation of cell-type specific transcriptomic profiles in future studies [10, 19, 21, 23-31]. These approaches are generally limited to a single platform and usually for a single species, however, even though RNA-Seq/microarray data integration has already been applied in comparison studies [35, 36], tool development [37], and cancer research [38]. Due to the limitations of prior techniques, the vast accumulation of gene expression microarray and RNA-Seq data usually contains a tissue mixture with multiple cell types.…”

Transcriptome analysis shows ambiguous phenotypes of murine primitive endoderm‐related stem cell lines

“…They were then mapped de novo to mm10 genome and annotated depending on Gencode vM15 by STAR 2.5.3a (Dobin et al, 2013). The integration of microarray and RNA-seq data followed Castillo's strategy (Castillo et al, 2017). Specifically, the RNA-seq count matrix was normalized by Limma-voom (Law, Chen, Shi, & Smyth, 2014), then combined with the downloaded microarray matrix and (after removing the genes that were absent from both platforms) further normalized by Limma-normalizeBetweenArrays.…”