Software and data will be available on request.

There have been many attempts in cancer clinical-type classification by using a dataset from a number of molecular layers of biological system. Despite these efforts, however, it still remains difficult to elucidate the cancer phenotypes because the cancer genome is neither simple nor independent but rather complicated and dysregulated by multiple molecular mechanisms. Recently, heterogeneous types of data, generated from all molecular levels of 'omic' dimensions from genome to phenome, for instance, copy number variants at the genome level, DNA methylation at the epigenome level, and gene expression and microRNA at the transcriptome level, have become available. In this paper, we propose an integrated framework that uses multi-level genomic data for prediction of clinical outcomes in brain cancer (glioblastoma multiforme, GBM) and ovarian cancer (serous cystadenocarcinoma, OV). From empirical comparison results on individual genomic data, we provide some preliminary insights about which level of data is more informative to a given clinical-type classification problem and justify these perceptions with the corresponding biological implications for each type of cancer. For GBM, all clinical outcomes had a better the area under the curve (AUC) of receiver operating characteristic when integrating multi-layers of genomic data, 0.876 for survival to 0.832 for recurrence. Moreover, the better AUCs were achieved from the integration approach for all clinical outcomes in OV as well, ranging from 0.787 to 0.893. We found that the opportunity for success in prediction of clinical outcomes in cancer was increased when the prediction was based on the integration of multi-layers of genomic data. This study is expecting to improve comprehension of the molecular pathogenesis and underlying biology of both cancer types.

No abstract

Objective Cancer can involve gene dysregulation via multiple mechanisms, so no single level of genomic data fully elucidates tumor behavior due to the presence of numerous genomic variations within or between levels in a biological system. We have previously proposed a graph-based integration approach that combines multi-omics data including copy number alteration, methylation, miRNA, and gene expression data for predicting clinical outcome in cancer. However, genomic features likely interact with other genomic features in complex signaling or regulatory networks, since cancer is caused by alterations in pathways or complete processes.Methods Here we propose a new graph-based framework for integrating multi-omics data and genomic knowledge to improve power in predicting clinical outcomes and elucidate interplay between different levels. To highlight the validity of our proposed framework, we used an ovarian cancer dataset from The Cancer Genome Atlas for predicting stage, grade, and survival outcomes.Results Integrating multi-omics data with genomic knowledge to construct pre-defined features resulted in higher performance in clinical outcome prediction and higher stability. For the grade outcome, the model with gene expression data produced an area under the receiver operating characteristic curve (AUC) of 0.7866. However, models of the integration with pathway, Gene Ontology, chromosomal gene set, and motif gene set consistently outperformed the model with genomic data only, attaining AUCs of 0.7873, 0.8433, 0.8254, and 0.8179, respectively.Conclusions Integrating multi-omics data and genomic knowledge to improve understanding of molecular pathogenesis and underlying biology in cancer should improve diagnostic and prognostic indicators and the effectiveness of therapies.

No abstract