Next-generation cancer and oncology research needs to take full advantage of the multimodal structured, or graph, information, with the graph data types ranging from molecular structures to spatially resolved imaging and digital pathology, biological networks, and knowledge graphs. Graph Neural Networks (GNNs) efficiently combine the graph structure representations with the high predictive performance of deep learning, especially on large multimodal datasets. In this review article, we survey the landscape of recent (2020–present) GNN applications in the context of cancer and oncology research, and delineate six currently predominant research areas. We then identify the most promising directions for future research. We compare GNNs with graphical models and “non-structured” deep learning, and devise guidelines for cancer and oncology researchers or physician-scientists, asking the question of whether they should adopt the GNN methodology in their research pipelines.

Data on biological mechanisms of aging are mostly obtained from cross-sectional study designs. An inherent disadvantage of this design is that inter-individual differences can mask small but biologically significant age-dependent changes. A serially sampled design (same individual at different time points) would overcome this problem but is often limited by the relatively small numbers of available paired samples and the statistics being used. To overcome these limitations, we have developed a new vector-based approach, termed three-component analysis, which incorporates temporal distance, signal intensity and variance into one single score for gene ranking and is combined with gene set enrichment analysis. We tested our method on a unique age-based sample set of human skin fibroblasts and combined genome-wide transcription, DNA methylation and histone methylation (H3K4me3 and H3K27me3) data. Importantly, our method can now for the first time demonstrate a clear age-dependent decrease in expression of genes coding for proteins involved in translation and ribosome function. Using analogies with data from lower organisms, we propose a model where age-dependent down-regulation of protein translation-related components contributes to extend human lifespan.

Bayesian network (BN) reconstruction is a prototypical systems biology data analysis approach that has been successfully used to reverse engineer and model networks reflecting different layers of biological organization (ranging from genetic to epigenetic to cellular pathway to metabolomic). It is especially relevant in the context of modern (ongoing and prospective) studies that generate heterogeneous high-throughput omics datasets. However, there are both theoretical and practical obstacles to the seamless application of BN modeling to such big data, including computational inefficiency of optimal BN structure search algorithms, ambiguity in data discretization, mixing data types, imputation and validation, and, in general, limited scalability in both reconstruction and visualization of BNs. To overcome these and other obstacles, we present BNOmics, an improved algorithm and software toolkit for inferring and analyzing BNs from omics datasets. BNOmics aims at comprehensive systems biology—type data exploration, including both generating new biological hypothesis and testing and validating the existing ones. Novel aspects of the algorithm center around increasing scalability and applicability to varying data types (with different explicit and implicit distributional assumptions) within the same analysis framework. An output and visualization interface to widely available graph-rendering software is also included. Three diverse applications are detailed. BNOmics was originally developed in the context of genetic epidemiology data and is being continuously optimized to keep pace with the ever-increasing inflow of available large-scale omics datasets. As such, the software scalability and usability on the less than exotic computer hardware are a priority, as well as the applicability of the algorithm and software to the heterogeneous datasets containing many data types—single-nucleotide polymorphisms and other genetic/epigenetic/transcriptome variables, metabolite levels, epidemiological variables, endpoints, and phenotypes, etc.

Recent successes of immune-modulating therapies for cancer have stimulated research on information flow within the immune system and, in turn, clinical applications of concepts from information theory. Through information theory, one can describe and formalize, in a mathematically rigorous fashion, the function of interconnected components of the immune system in health and disease. Specifically, using concepts including entropy, mutual information, and channel capacity, one can quantify the storage, transmission, encoding, and flow of information within and between cellular components of the immune system on multiple temporal and spatial scales. To understand, at the quantitative level, immune signaling function and dysfunction in cancer, we present a methodology-oriented review of information-theoretic treatment of biochemical signal transduction and transmission coupled with mathematical modeling.

Bayesian Network (BN) modeling is a prominent and increasingly popular computational systems biology method. It aims to construct network graphs from the large heterogeneous biological datasets that reflect the underlying biological relationships. Currently, a variety of strategies exist for evaluating BN methodology performance, ranging from utilizing artificial benchmark datasets and models, to specialized biological benchmark datasets, to simulation studies that generate synthetic data from predefined network models. The last is arguably the most comprehensive approach; however, existing implementations often rely on explicit and implicit assumptions that may be unrealistic in a typical biological data analysis scenario, or are poorly equipped for automated arbitrary model generation. In this study, we develop a purely probabilistic simulation framework that addresses the demands of statistically sound simulations studies in an unbiased fashion. Additionally, we expand on our current understanding of the theoretical notions of causality and dependence / conditional independence in BNs and the Markov Blankets within.

Evolution by gene duplication is generally accepted as one of the crucial driving forces for the gain of new complexity and functions, but the formation of pseudogenes remains a problem for this mechanism. Here we expand on earlier ideas that epigenetic modifications can drive neo- and subfunctionalization in evolution by gene duplication. We explore the effects of stochastic epigenetic modifications on the evolution (and thus development) of complex organisms in a constant environment. Modeling is done both using a modified genetic drift analytical treatment and computer simulations, which were found to agree. A transposon silencing model is also explored. Some key assumptions made include (i) stochastic, incomplete removal (or addition) of repressive epigenetic marks takes place during a window(s) of opportunity in the zygote and early embryo; (ii) there is no statistical variation of the marks after the window closes; and (iii) the genes affected are sensitive to dosage. Our genetic drift treatment takes into account that after gene duplication the prevailing case upon which selection operates is a duplicate/singlet heterozygote; to the best of our knowledge, this has not been considered in previous treatments. We conclude from our modeling that stochastic epigenetic modifications, with rates consistent with experimental observation, can both increase the rate of gene fixation and decrease pseudogenization, thus dramatically improving the efficacy of evolution by gene duplication. We also find that a transposon silencing model is advantageous for fixation of recessive genes in diploid organisms, especially with large effective population sizes. Significance In this paper we investigate by quantitative modeling the effect on evolution of epigenetic variation during a window of opportunity in the early embryo. It is generally accepted that generation of new functions is primarily driven by gene duplication. However, pseudogenization (degradation of a new gene copy) is statistically much more likely than gaining a new function, and thus this remains a serious conceptual problem. We find that epigenetic variation, even in a constant environment, can essentially eliminate the pseudogenization problem and dramatically improve the efficacy of evolution by gene duplication.