Addressing the heterogeneity in liver diseases using biological networks

Abstract

The abnormalities in human metabolism have been implicated in the progression of several complex human diseases, including certain cancers. Hence, deciphering the underlying molecular mechanisms associated with metabolic reprogramming in a disease state can greatly assist in elucidating the disease aetiology. An invaluable tool for establishing connections between global metabolic reprogramming and disease development is the genome-scale metabolic model (GEM). Here, we review recent work on the reconstruction of cell/tissue-type and cancer-specific GEMs and their use in identifying metabolic changes occurring in response to liver disease development, stratification of the heterogeneous disease population and discovery of novel drug targets and biomarkers. We also discuss how GEMs can be integrated with other biological networks for generating more comprehensive cell/tissue models. In addition, we review the various biological network analyses that have been employed for the development of efficient treatment strategies. Finally, we present three case studies in which independent studies converged on conclusions underlying liver disease.

Keywords: Computational biology; Genome-scale metabolic model; Integrated network; Liver metabolism; Omics integration; Systems biology.

Figure 1

Iterative computational biology workflow. Data are gathered by experimentation, from the literature or from publicly accessible databases. Computational models describing biological knowledge are generated and refined. Models are used for in silico simulation, re-refinement of the model and hypothesis generation. Findings are validated experimentally, feeding into new data for the next iteration of the cycle.

Figure 2

IN construction. The formation of INs and their overlap with CNs can reveal metabolic pathways that are regulated specifically in a tissue of interest. A, Formation of an IN through the integration of GEMs with other biological networks, including regulatory networks, PPINs and signalling networks. INs are necessary in order to cover the entire biological functions of cells and tissues in a holistic manner and should enable a better prediction of the cell phenotype. Arrows with barbed heads, activatory relationships; arrows with bars, inhibitory relationships; dotted lines, physical interactions; and arrows with filled heads, integration of data. B, Overlap of an IN with a CN can reveal tissue-specific functional and physical interactions, which can then be used to determine BPs that are uniquely regulated in a tissue of interest.

Figure 3

Independent studies highlight convergent conclusions in acetate utilisation in HCC heterogeneity. Separate investigations associated increased expression of ACSS1 with poor survival outcome. A, Stratification of tumours based on ACSS1 and ACSS2 expression led to the identification of poor prognosis markers in tumours expressing ACSS1 at a high level [6]. B, Clustering of tumours on the basis of fGGN and transcriptomic data resulted in the characterisation of three HCC subtypes, of which the subtype conferring the least favourable survival was found to preferentially express ACSS1 for acetate utilisation [56].

Figure 4

Alternative splice isoforms of PKM. Homology modelling and structure alignment can reveal functionally important sites and identify functionally significant deletions that occur in different PKM isoforms [62]. A, The template structure for PKM consists of four domains. The A-domain participates in the formation of dimers and the C-domain mediates the interactions between dimers that allow them to form tetramers. The active site (K270) and FBP binding site (K433) are shown. B, The alternatively spliced forms of PKM reveal large deletions corresponding to the ADP binding site in isoforms ENST00000389093 and ENST00000568883, which may impede dimerisation. In TGCA KIRC datasets, these transcripts are associated with unfavourable survival.

Figure 5

Independent studies reveal redox metabolism as a commonly dysregulated cellular function in heterogeneous HCC. Three separate investigations identified common redox metabolism genes (shown in red) as being associated with poor favourable survival of HCC. A, Stratification by antagonistic clusters of co-expressing redox metabolism genes reveals that the cluster associated with the least favourable survival is enriched for genes associated with inflammation, morphogenesis and hypoxia [70]. B, Differential expression between iHCC3 and iHCC1/iHCC2 tumours also identified elevated G6PD and PKM expression [56]. C, Differential expression of high ACSS1 HCC versus low ACSS1 HCC also revealed increased PKM and HIF1A [6].