BACKGROUND: Breast cancer is a highly heterogeneous disease that comprises multiple biological components. Owing its diversity, patients have different prognostic outcomes; hence, early diagnosis and accurate subtype prediction are critical for treatment. Standardized breast cancer subtyping systems, mainly based on single-omics datasets, have been developed to ensure proper treatment in a systematic manner. Recently, multi-omics data integration has attracted attention to provide a comprehensive view of patients but poses a challenge due to the high dimensionality. In recent years, deep learning-based approaches have been proposed, but they still present several limitations. RESULTS: In this study, we describe moBRCA-net, an interpretable deep learning-based breast cancer subtype classification framework that uses multi-omics datasets. Three omics datasets comprising gene expression, DNA methylation and microRNA expression data were integrated while considering the biological relationships among them, and a self-attention module was applied to each omics dataset to capture the relative importance of each feature. The features were then transformed to new representations considering the respective learned importance, allowing moBRCA-net to predict the subtype. CONCLUSIONS: Experimental results confirmed that moBRCA-net has a significantly enhanced performance compared with other methods, and the effectiveness of multi-omics integration and omics-level attention were identified. moBRCA-net is publicly available at https://github.com/cbi-bioinfo/moBRCA-net .

BACKGROUND: Identification of the cancer subtype plays a crucial role to provide an accurate diagnosis and proper treatment to improve the clinical outcomes of patients. Recent studies have shown that DNA methylation is one of the key factors for tumorigenesis and tumor growth, where the DNA methylation signatures have the potential to be utilized as cancer subtype-specific markers. However, due to the high dimensionality and the low number of DNA methylome cancer samples with the subtype information, still, to date, a cancer subtype classification method utilizing DNA methylome datasets has not been proposed. RESULTS: In this paper, we present meth-SemiCancer, a semi-supervised cancer subtype classification framework based on DNA methylation profiles. The proposed model was first pre-trained based on the methylation datasets with the cancer subtype labels. After that, meth-SemiCancer generated the pseudo-subtypes for the cancer datasets without subtype information based on the model's prediction. Finally, fine-tuning was performed utilizing both the labeled and unlabeled datasets. CONCLUSIONS: From the performance comparison with the standard machine learning-based classifiers, meth-SemiCancer achieved the highest average F1-score and Matthews correlation coefficient, outperforming other methods. Fine-tuning the model with the unlabeled patient samples by providing the proper pseudo-subtypes, encouraged meth-SemiCancer to generalize better than the supervised neural network-based subtype classification method. meth-SemiCancer is publicly available at https://github.com/cbi-bioinfo/meth-SemiCancer .

Hierarchical clustering, a traditional clustering method, has been getting attention again. Among several reasons, a credit goes to a recent paper by Dasgupta in 2016 that proposed a cost function that quantitatively evaluates hierarchical clustering trees. An important question is how to combine this recent advance with existing successful clustering methods. In this paper, we propose a hierarchical clustering method to minimize the cost function of clustering tree by incorporating existing clustering techniques. First, we developed an ensemble tree-search method that finds an integrated tree with reduced cost by integrating multiple existing hierarchical clustering methods. Second, to operate on large and arbitrary shape data, we designed an efficient hierarchical clustering framework, called integrating divisive and ensemble-agglomerate (IDEA) by combining it with advanced clustering techniques such as nearest neighbor graph construction, divisive-agglomerate hybridization, and dynamic cut tree. The IDEA clustering method showed better performance in minimizing Dasgupta's cost and improving accuracy (adjusted rand index) over existing cost-minimization-based, and density-based hierarchical clustering methods in experiments using arbitrary shape datasets and complex biology-domain datasets.

Gene expressions are subtly regulated by quantifiable measures of genetic molecules such as interaction with other genes, methylation, mutations, transcription factor and histone modifications. Integrative analysis of multi-omics data can help scientists understand the condition or patient-specific gene regulation mechanisms. However, analysis of multi-omics data is challenging since it requires not only the analysis of multiple omics data sets but also mining complex relations among different genetic molecules by using state-of-the-art machine learning methods. In addition, analysis of multi-omics data needs quite large computing infrastructure. Moreover, interpretation of the analysis results requires collaboration among many scientists, often requiring reperforming analysis from different perspectives. Many of the aforementioned technical issues can be nicely handled when machine learning tools are deployed on the cloud. In this survey article, we first survey machine learning methods that can be used for gene regulation study, and we categorize them according to five different goals: gene regulatory subnetwork discovery, disease subtype analysis, survival analysis, clinical prediction and visualization. We also summarize the methods in terms of multi-omics input types. Then, we explain why the cloud is potentially a good solution for the analysis of multi-omics data, followed by a survey of two state-of-the-art cloud systems, Galaxy and BioVLAB. Finally, we discuss important issues when the cloud is used for the analysis of multi-omics data for the gene regulation study.

The first version of this article neglected to identify Minsik Oh and Sungjoon Park as joint first authors. This has now been corrected.

MOTIVATION: Multi-omics data in molecular biology has accumulated rapidly over the years. Such data contains valuable information for research in medicine and drug discovery. Unfortunately, data-driven research in medicine and drug discovery is challenging for a majority of small research labs due to the large volume of data and the complexity of analysis pipeline. RESULTS: We present BioVLAB-Cancer-Pharmacogenomics, a bioinformatics system that facilitates analysis of multi-omics data from breast cancer to analyze and investigate intratumor heterogeneity and pharmacogenomics on Amazon Web Services. Our system takes multi-omics data as input to perform tumor heterogeneity analysis in terms of TCGA data and deconvolve-and-match the tumor gene expression to cell line data in CCLE using DNA methylation profiles. We believe that our system can help small research labs perform analysis of tumor multi-omics without worrying about computational infrastructure and maintenance of databases and tools. AVAILABILITY AND IMPLEMENTATION: http://biohealth.snu.ac.kr/software/biovlab_cancer_pharmacogenomics. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Recently, DNA methylation has drawn great attention due to its strong correlation with abnormal gene activities and informative representation of the cancer status. As a number of studies focus on DNA methylation signatures in cancer, demand for utilizing publicly available methylome dataset has been increased. To satisfy this, large-scale projects were launched to discover biological insights into cancer, providing a collection of the dataset. However, public cancer data, especially for certain cancer types, is still limited to be used in research. Several simulation tools for producing epigenetic dataset have been introduced in order to alleviate the issue, still, to date, generation for user-specified cancer type dataset has not been proposed. RESULTS: In this paper, we present methCancer-gen, a tool for generating DNA methylome dataset considering type for cancer. Employing conditional variational autoencoder, a neural network-based generative model, it estimates the conditional distribution with latent variables and data, and generates samples for specified cancer type. CONCLUSIONS: To evaluate the simulation performance of methCancer-gen for the user-specified cancer type, our proposed model was compared to a benchmark method and it could successfully reproduce cancer type-wise data with high accuracy helping to alleviate the lack of condition-specific data issue. methCancer-gen is publicly available at https://github.com/cbi-bioinfo/methCancer-gen.

BACKGROUND: Integrated analysis that uses multiple sample gene expression data measured under the same stress can detect stress response genes more accurately than analysis of individual sample data. However, the integrated analysis is challenging since experimental conditions (strength of stress and the number of time points) are heterogeneous across multiple samples. RESULTS: HTRgene is a computational method to perform the integrated analysis of multiple heterogeneous time-series data measured under the same stress condition. The goal of HTRgene is to identify "response order preserving DEGs" that are defined as genes not only which are differentially expressed but also whose response order is preserved across multiple samples. The utility of HTRgene was demonstrated using 28 and 24 time-series sample gene expression data measured under cold and heat stress in Arabidopsis. HTRgene analysis successfully reproduced known biological mechanisms of cold and heat stress in Arabidopsis. Also, HTRgene showed higher accuracy in detecting the documented stress response genes than existing tools. CONCLUSIONS: HTRgene, a method to find the ordering of response time of genes that are commonly observed among multiple time-series samples, successfully integrated multiple heterogeneous time-series gene expression datasets. It can be applied to many research problems related to the integration of time series data analysis.

BACKGROUND: Bisulfite sequencing is one of the major high-resolution DNA methylation measurement method. Due to the selective nucleotide conversion on unmethylated cytosines after treatment with sodium bisulfite, processing bisulfite-treated sequencing reads requires additional steps which need high computational demands. However, a dearth of efficient aligner that is designed for bisulfite-treated sequencing becomes a bottleneck of large-scale DNA methylome analyses. RESULTS: In this study, we present a highly scalable, efficient, and load-balanced bisulfite aligner, BiSpark, which is designed for processing large volumes of bisulfite sequencing data. We implemented the BiSpark algorithm over the Apache Spark, a memory optimized distributed data processing framework, to achieve the maximum data parallel efficiency. The BiSpark algorithm is designed to support redistribution of imbalanced data to minimize delays on large-scale distributed environment. CONCLUSIONS: Experimental results on methylome datasets show that BiSpark significantly outperforms other state-of-the-art bisulfite sequencing aligners in terms of alignment speed and scalability with respect to dataset size and a number of computing nodes while providing highly consistent and comparable mapping results. AVAILABILITY: The implementation of BiSpark software package and source code is available at https://github.com/bhi-kimlab/BiSpark/ .

MOTIVATION: It is now well established that microRNAs (miRNAs) play a critical role in regulating gene expression in a sequence-specific manner, and genome-wide efforts are underway to predict known and novel miRNA targets. However, the integrated miRNA-mRNA analysis remains a major computational challenge, requiring powerful informatics systems and bioinformatics expertise. RESULTS: The objective of this study was to modify our widely recognized Web server for the integrated mRNA-miRNA analysis (MMIA) and its subsequent deployment on the Amazon cloud (BioVLAB-MMIA) to be compatible with high-throughput platforms, including next-generation sequencing (NGS) data (e.g. RNA-seq). We developed a new version called the BioVLAB-MMIA-NGS, deployed on both Amazon cloud and on a high-performance publicly available server called MAHA. By using NGS data and integrating various bioinformatics tools and databases, BioVLAB-MMIA-NGS offers several advantages. First, sequencing data is more accurate than array-based methods for determining miRNA expression levels. Second, potential novel miRNAs can be detected by using various computational methods for characterizing miRNAs. Third, because miRNA-mediated gene regulation is due to hybridization of an miRNA to its target mRNA, sequencing data can be used to identify many-to-many relationship between miRNAs and target genes with high accuracy. AVAILABILITY AND IMPLEMENTATION: http://epigenomics.snu.ac.kr/biovlab_mmia_ngs/.

Micro RNAs, by regulating the expression of hundreds of target genes, play critical roles in developmental biology and the etiology of numerous diseases, including cancer. As vast amounts of micro RNA expression profile data are now publicly available, the integration of those data sets with gene expression profiles represents an extremely active area of life science research. However, the ability to conduct genome-wide micro RNA-mRNA (gene) integration currently requires sophisticated, high-end informatics tools, significant expertise in bioinformatics and computer science to carry out the complex integration analysis. In addition, increased computing infrastructure capabilities are essential in order to accommodate large data sets. In this study, we have extending BioVLAB cloud workbench to develop an environment for the integrated analysis of micro RNA and mRNA expression data, named BioVLAB-MMIA. The workbench facilitates computations on the Amazon EC2 and S3 resources orchestrated by XBaya Workflow Suite. The advantages of BioVLAB-MMIA over the web-based MMIA system include: 1) readily expanded as new computational tools become available, 2) easily modifiable by re-configuring graphic icons in the workflow, 3) on-demand cloud computing resources can be used on an "as needed" basis, 4) distributed orchestration supports complex and long running workflows asynchronously.