Dataset Information

A Novel Coupled Reaction-Diffusion System for Explainable Gene Expression Profiling

ABSTRACT: Machine learning (ML)-based algorithms are playing an important role in cancer diagnosis and are increasingly being used to aid clinical decision-making. However, these commonly operate as ‘black boxes’ and it is unclear how decisions are derived. Recently, techniques have been applied to help us understand how specific ML models work and explain the rational for outputs. This study aims to determine why a given type of cancer has a certain phenotypic characteristic. Cancer results in cellular dysregulation and a thorough consideration of cancer regulators is required. This would increase our understanding of the nature of the disease and help discover more effective diagnostic, prognostic, and treatment methods for a variety of cancer types and stages. Our study proposes a novel explainable analysis of potential biomarkers denoting tumorigenesis in non-small cell lung cancer. A number of these biomarkers are known to appear following various treatment pathways. An enhanced analysis is enabled through a novel mathematical formulation for the regulators of mRNA, the regulators of ncRNA, and the coupled mRNA–ncRNA regulators. Temporal gene expression profiles are approximated in a two-dimensional spatial domain for the transition states before converging to the stationary state, using a system comprised of coupled-reaction partial differential equations. Simulation experiments demonstrate that the proposed mathematical gene-expression profile represents a best fit for the population abundance of these oncogenes. In future, our proposed solution can lead to the development of alternative interpretable approaches, through the application of ML models to discover unknown dynamics in gene regulatory systems.

SUBMITTER: Farouq M

PROVIDER: S-EPMC8003942 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundMicroarray hybridization studies in Sézary syndrome (SS) have compared T lymphocytes from patients with cutaneous T-cell lymphoma with those of normal controls; a major limitation of this design is that significant inherent genetic variability of lymphocyte populations between individuals may produce differences in gene expression unrelated to disease state.ObjectiveThe objective of this study was to minimize the heterogeneity of information derived from whole-genome expression analysis and to identify specific genetic differences between highly purified malignant and nonmalignant (control) T cells from the same patient with SS.MethodsPeripheral blood mononuclear cells were obtained from a patient with SS, stained with anti-T-cell receptor Vb (TCR-Vb) antibodies, and sorted by multiparameter flow cytometry. Malignant cells expressed the dominant TCR-Vb; control T cells lacked the dominant TCR-Vb but were otherwise phenotypically identical (CD3+CD4+CD45RO+). These cell populations were compared using the Illumina Inc. Sentrix Human-6 expression BeadChip system.ResultsTranscriptome analysis using the J5 test, which was selected for data analysis based on an efficiency analysis of competing statistical methods, showed differential expression of 44 genes between the malignant and nonmalignant cell subsets. Promyelocytic leukaemia zinc finger protein (ZBTB16) was the most profoundly upregulated gene in the malignant cell population, while interferon regulatory factor 3 (IRF3) and interferon-induced protein 35 (IFI35), which are important elements of the cellular response to viral infection, were significantly downregulated.ConclusionsThe results of this study suggest the feasibility of this novel comparative approach to genomic profiling in SS. Using this method, we identified several differentially expressed genes and pathways not previously described in SS. While these findings require validation in larger studies, they may be important in SS pathogenesis.

Dataset Information

A Novel Coupled Reaction-Diffusion System for Explainable Gene Expression Profiling

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets