Machine learning analysis of DNA methylation profiles distinguishes primary lung squamous cell carcinomas from head and neck metastases

Abstract

Head and neck squamous cell carcinoma (HNSC) patients are at risk of suffering from both pulmonary metastases or a second squamous cell carcinoma of the lung (LUSC). Differentiating pulmonary metastases from primary lung cancers is of high clinical importance, but not possible in most cases with current diagnostics. To address this, we performed DNA methylation profiling of primary tumors and trained three different machine learning methods to distinguish metastatic HNSC from primary LUSC. We developed an artificial neural network that correctly classified 96.4% of the cases in a validation cohort of 279 patients with HNSC and LUSC as well as normal lung controls, outperforming support vector machines (95.7%) and random forests (87.8%). Prediction accuracies of more than 99% were achieved for 92.1% (neural network), 90% (support vector machine), and 43% (random forest) of these cases by applying thresholds to the resulting probability scores and excluding samples with low confidence. As independent clinical validation of the approach, we analyzed a series of 51 patients with a history of HNSC and a second lung tumor, demonstrating the correct classifications based on clinicopathological properties. In summary, our approach may facilitate the reliable diagnostic differentiation of pulmonary metastases of HNSC from primary LUSC to guide therapeutic decisions.

Invited Review: DNA methylation‐based classification of paediatric brain tumours

“…Still, such analyses may well overlook more subtle or focal changes of the methylome and at least for adult glioblastoma some degree of temporal evolution has been reported . Nonetheless there seems to be a relative persistence of the tumoral methylation pattern which provides the foundation for the utility of DNA methylation‐based analyses for cell lineage tracing and by extension, the identification of the origin of metastases of unknown primaries and the rapidly developing field of DNA methylation‐based tumour classification . A graphical summary of the evolution of the field within the context of brain tumours is displayed in Figure .…”

“…Potentially less reproducible methods like clustering or t‐distributed stochastic neighbour embedding are also implemented to allocate samples according to reference groups but the interpretation of the results still has to be defined and may be quite unclear with these methods. In the brain tumour field, so called Random Forest machine learning algorithms are widely applied but other types of machine learning algorithms also hold promise and for other classificatory questions the inferiority of Random Forest to other machine or deep learning techniques has been suggested . Tumour sub‐classification : A second level of information that is closely related to the above is the possibility to sub‐classify certain classes into subclasses. This also relies on DNA methylation levels at specific CpG sites.…”

Potential of Genomic Selection and Integrating “Omics” Data for Disease Evaluation in Wheat

“…In addition, ML allows algorithms to interpret data by learning patterns through experience [105]. Success stories of ML cover various research fields, including robotics [106], bioinformatics [107], biochemistry [108], medical diagnosis [109,110], meteorology [111] and climatology [112]. In agricultural research, ML techniques have been used for predicting regulatory and non-regulatory regions in the maize genome [113], predicting mRNA expression levels in maize [114], polyadenylation site prediction in Arabidopsis thaliana [115] and predicting macronutrient deficiencies in tomato [116].…”

Multiclass cancer classification in fresh frozen and formalin-fixed paraffin-embedded tissue by DigiWest multiplex protein analysis

“…Through the advances in molecular techniques, sophisticated diagnostic approaches have been developed and applied to cancer classification. Several studies describe the classification of tumors according to their tissue of origin using gene expression [5][6][7], microRNA [8,9], and, more recently, DNA methylation [10,11] profiling. Tissue-based protein profiling constitutes a further promising approach for cancer classification, as tumor types are characterized by specific protein profiles [12].…”