Adaptively capturing the heterogeneity of expression for cancer biomarker identification

Abstract

BackgroundIdentifying cancer biomarkers from transcriptomics data is of importance to cancer research. However, transcriptomics data are often complex and heterogeneous, which complicates the identification of cancer biomarkers in practice. Currently, the heterogeneity still remains a challenge for detecting subtle but consistent changes of gene expression in cancer cells.ResultsIn this paper, we propose to adaptively capture the heterogeneity of expression across samples in a gene regulation space instead of in a gene expression space. Specifically, we transform gene expression profiles into gene regulation profiles and mathematically formulate gene regulation probabilities (GRPs)-based statistics for characterizing differential expression of genes between tumor and normal tissues. Finally, an unbiased estimator (aGRP) of GRPs is devised that can interrogate and adaptively capture the heterogeneity of gene expression. We also derived an asymptotical significance analysis procedure for the new statistic. Since no parameter needs to be preset, aGRP is easy and friendly to use for researchers without computer programming background. We evaluated the proposed method on both simulated data and real-world data and compared with previous methods. Experimental results demonstrated the superior performance of the proposed method in exploring the heterogeneity of expression for capturing subtle but consistent alterations of gene expression in cancer.ConclusionsExpression heterogeneity largely influences the performance of cancer biomarker identification from transcriptomics data. Models are needed that efficiently deal with the expression heterogeneity. The proposed method can be a standalone tool due to its capacity of adaptively capturing the sample heterogeneity and the simplicity in use.Software availabilityThe source code of aGRP can be downloaded from https://github.com/hqwang126/aGRP.Electronic supplementary materialThe online version of this article (10.1186/s12859-018-2437-2) contains supplementary material, which is available to authorized users.

A Biomedical Knowledge Graph for Biomarker Discovery in Cancer

“…Yet, the adoption of data-driven approaches has been hampered in many clinical settings by the lack of scalable computational methods (e.g., ML models) that can deal with large-scale data (being often heterogeneous, high dimensional, unstructured, and having high levels of uncertainty) to perform in a reliable and safe manner [3]. The development of solutions for precision medicine requires the integration of multi-omics data (genomics, transcriptomics, proteomics, or metabolomics data), into clinical decision-making process [4]. Furthermore, harmonization and seamless integration of diverse datasets from heterogeneous and distributed systems across different platforms is challenging [4] as the quantity and diversity of biomedical data, and the spread of clinically relevant knowledge across multiple biomedical databases and publications, pose a challenge to data integration.…”

“…The development of solutions for precision medicine requires the integration of multi-omics data (genomics, transcriptomics, proteomics, or metabolomics data), into clinical decision-making process [4]. Furthermore, harmonization and seamless integration of diverse datasets from heterogeneous and distributed systems across different platforms is challenging [4] as the quantity and diversity of biomedical data, and the spread of clinically relevant knowledge across multiple biomedical databases and publications, pose a challenge to data integration.…”

“…The so-called marker genes including oncogenes and tumor suppressor genes are often responsible for cancer growth. When a gene is over-or under-expressed as a differentially expressed gene, it becomes uncontrollable proliferation or immorality of cancer cells [2], [4]. Although the difference in the average of expression values between two sample classes is frequently employed in transcriptomics analyses, such difference is not the only way a gene can be expressed differentially [4].…”

“…When a gene is over-or under-expressed as a differentially expressed gene, it becomes uncontrollable proliferation or immorality of cancer cells [2], [4]. Although the difference in the average of expression values between two sample classes is frequently employed in transcriptomics analyses, such difference is not the only way a gene can be expressed differentially [4]. With more than 200 different types identified to date, cancer has become the second leading cause of death worldwide [10].…”

Adversary-Aware Multimodal Neural Networks for Cancer Susceptibility Prediction From Multiomics Data

“…When a gene is over-or under-VOLUME XXXX, 2020 expressed as a differentially expressed gene, the gene becomes uncontrollable proliferation or immortality of cancer cells [1,2]. Although the difference in the average of expression values between two sample classes is frequently employed in transcriptomics analyses, such difference is not the only way a gene can be expressed differentially [3]. With more than 200 different types identified to date, cancer has become the second leading cause of death worldwide [4].…”