Precision Oncology: Artificial Intelligence and DNA Methylation Analysis of Circulating Cell-Free DNA for Lung Cancer Detection

Abstract

BackgroundLung cancer (LC) is a leading cause of cancer-deaths globally. Its lethality is due in large part to the paucity of accurate screening markers. Precision Medicine includes the use of omics technology and novel analytic approaches for biomarker development. We combined Artificial Intelligence (AI) and DNA methylation analysis of circulating cell-free tumor DNA (ctDNA), to identify putative biomarkers for and to elucidate the pathogenesis of LC.MethodsIllumina Infinium MethylationEPIC BeadChip array analysis was used to measure cytosine (CpG) methylation changes across the genome in LC. Six different AI platforms including support vector machine (SVM) and Deep Learning (DL) were used to identify CpG biomarkers and for LC detection. Training set and validation sets were generated, and 10-fold cross validation performed. Gene enrichment analysis using g:profiler and GREAT enrichment was used to elucidate the LC pathogenesis.ResultsUsing a stringent GWAS significance threshold, p-value <5x10-8, we identified 4389 CpGs (cytosine methylation loci) in coding genes and 1812 CpGs in non-protein coding DNA regions that were differentially methylated in LC. SVM and three other AI platforms achieved an AUC=1.00; 95% CI (0.90-1.00) for LC detection. DL achieved an AUC=1.00; 95% CI (0.95-1.00) and 100% sensitivity and specificity. High diagnostic accuracies were achieved with only intragenic or only intergenic CpG loci. Gene enrichment analysis found dysregulation of molecular pathways involved in the development of small cell and non-small cell LC.ConclusionUsing AI and DNA methylation analysis of ctDNA, high LC detection rates were achieved. Further, many of the genes that were epigenetically altered are known to be involved in the biology of neoplasms in general and lung cancer in particular.

A Systematic Review of Progress toward Unlocking the Power of Epigenetics in NSCLC: Latest Updates and Perspectives

“…Fifthly, high-throughput technologies and artificial intelligence (AI) have been identified as powerful tools for the analysis of large-scale epigenomic datasets in non-small-cell lung cancer (NSCLC). These technologies enable comprehensive screening of various epigenetic alterations such as histone modification, DNA methylation, chromatin organization, and miRNA and lncRNA expression, which can be used to identify signatures associated with disease progression, therapeutic response, and drug sensitivity [ 167 , 168 ]. AI provides rapid and efficient assessments of the effects of environmental and genetic factors on NSCLC progression and can generate predictive models.…”

Precision gynecologic oncology: circulating cell free DNA epigenomic analysis, artificial intelligence and the accurate detection of ovarian cancer

“…All samples were bisulfite converted using EZ DNA Methylation Kit (Zymo, USA) per the manufacturer's standardized method. Illumina Infinium MethylationEPIC BeadChip arrays (~ 850,000 CpG loci genome-wide) was used for methylation analysis based on manufacturer's standardized protocol 20 .…”

“…Its extraordinary capacity for handling high dimensional or big data makes AI attractive for use in omics studies. The authors have focused on combining AI and epigenomics for minimal invasive disease detection 14,15 . Given the enormous currently untapped potential of Artificial Intelligence in the medical sciences, the current enthusiasm for the use of AI in cancer research 16 appears warranted.…”

Liquid biopsies for cancer: From bench to clinic

“…208 Currently, the traditional machine learning models such as support vector machine (SVM), linear models, and random forest (RF) still account for a major position in early cancer detection due to their training speed and robustness on small dataset. 209 One of the nice examples was carried out by Bahado-Singh et al 210 on LC. When using plasma CpG biomarkers combined with multiple machine learning algorithms including SVM, RF, generalized linear model, prediction analysis for microarrays, linear discriminant analysis, and deep learning, they achieved highly accurate detection of LC (AUC = 0.90-1.0) with high sensitivity and specificity values.…”

“…When using plasma CpG biomarkers combined with multiple machine learning algorithms including SVM, RF, generalized linear model, prediction analysis for microarrays, linear discriminant analysis, and deep learning, they achieved highly accurate detection of LC (AUC = 0.90-1.0) with high sensitivity and specificity values. 210 Meanwhile, algorithms are under updating with leaps and bounds to fill in the information gaps over current methods and further improve the performance. For example, the most-used DNA methylation analysis focuses on the methylation rate (β value) of an individual CpG site in a cell population.…”