Prediction and Explanation in Biomedicine using Network-Based Approaches

Chemotherapy is a mainstream cancer treatment, but has a constant challenge of drug resistance, which consequently leads to poor prognosis in cancer treatment. For better understanding and effective treatment of drug-resistant cancer cells, omics approaches have been widely conducted in various forms. A notable use of omics data beyond routine data mining is to use them for computational modeling that allows generating useful predictions, such as drug responses and prognostic biomarkers. In particular, an increasing volume of omics data has facilitated the development of machine learning models. In this mini review, we highlight recent studies on the use of multi-omics data for studying drug-resistant cancer cells. We put a particular focus on studies that use computational models to characterize drug-resistant cancer cells, and to predict biomarkers and/or drug responses. Computational models covered in this mini review include network-based models, machine learning models and genome-scale metabolic models. We also provide perspectives on future research opportunities for combating drug-resistant cancer cells.

Objective: Acute lymphoblastic leukemia (ALL) is a malignant disease most commonly diagnosed in adolescents and young adults. This study aimed to explore potential signatures and their functions for ALL.

Methods: Differentially expressed mRNAs (DEmRNAs) and differentially expressed long non-coding RNAs (DElncRNAs) were identified for ALL from The Cancer Genome Atlas (TCGA) and normal control from Genotype-Tissue Expression (GTEx). DElncRNA–microRNA (miRNA) and miRNA–DEmRNA pairs were predicted using online databases. Then, a competing endogenous RNA (ceRNA) network was constructed. Functional enrichment analysis of DEmRNAs in the ceRNA network was performed. Protein–protein interaction (PPI) network was then constructed. Hub genes were identified. DElncRNAs in the ceRNA network were validated using Real-time qPCR.

Results: A total of 2,903 up- and 3,228 downregulated mRNAs and 469 up- and 286 downregulated lncRNAs were identified for ALL. A ceRNA network was constructed for ALL, consisting of 845 lncRNA-miRNA and 395 miRNA–mRNA pairs. These DEmRNAs in the ceRNA network were mainly enriched in ALL-related biological processes and pathways. Ten hub genes were identified, including SMAD3, SMAD7, SMAD5, ZFYVE9, FKBP1A, FZD6, FZD7, LRP6, WNT1, and SFRP1. According to Real-time qPCR, eight lncRNAs including ATP11A-AS1, ITPK1-AS1, ANO1-AS2, CRNDE, MALAT1, CACNA1C-IT3, PWRN1, and WT1-AS were significantly upregulated in ALL bone marrow samples compared to normal samples.

Conclusion: Our results showed the lncRNA expression profiles and constructed ceRNA network in ALL. Furthermore, eight lncRNAs including ATP11A-AS1, ITPK1-AS1, ANO1-AS2, CRNDE, MALAT1, CACNA1C-IT3, PWRN1, and WT1-AS were identified. These results could provide a novel insight into the study of ALL.

The multi-level organization of nature is self-evident: proteins do interact among them to give rise to an organized metabolism, while in the same time each protein (a single node of such interaction network) is itself a network of interacting amino-acid residues allowing coordinated motion of the macromolecule and systemic effect as allosteric behavior. Similar pictures can be drawn for structure and function of cells, organs, tissues, and ecological systems. The majority of biologists are used to think that causally relevant events originate from the lower level (the molecular one) in the form of perturbations, that “climb up” the hierarchy reaching the ultimate layer of macroscopic behavior (e.g., causing a specific disease). Such causative model, stemming from the usual genotype-phenotype distinction, is not the only one. As a matter of fact, one can observe top-down, bottom-up, as well as middle-out perturbation/control trajectories. The recent complex network studies allow to go further the pure qualitative observation of the existence of both non-linear and non-bottom-up processes and to uncover the deep nature of multi-level organization. Here, taking as paradigm protein structural and interaction networks, we review some of the most relevant results dealing with between networks communication shedding light on the basic principles of complex system control and dynamics and offering a more realistic frame of causation in biology.

We propose a method for generating an electrocardiogram (ECG) signal for one cardiac cycle using a variational autoencoder. Our goal was to encode the original ECG signal using as few features as possible. Using this method we extracted a vector of new 25 features, which in many cases can be interpreted. The generated ECG has quite natural appearance. The low value of the Maximum Mean Discrepancy metric, 3.83 × 10⁻³, indicates good quality of ECG generation too. The extracted new features will help to improve the quality of automatic diagnostics of cardiovascular diseases. Generating new synthetic ECGs will allow us to solve the issue of the lack of labeled ECG for using them in supervised learning.