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

Abstract

Histomorphology and immunohistochemistry are the most common ways of cancer classification in routine cancer diagnostics, but often reach their limits in determining the organ origin in metastasis. These cancers of unknown primary, which are mostly adenocarcinomas or squamous cell carcinomas, therefore require more sophisticated methodologies of classification. Here, we report a multiplex protein profiling-based approach for the classification of fresh frozen and formalin-fixed paraffin-embedded (FFPE) cancer tissue samples using the digital western blot technique DigiWest. A DigiWest-compatible FFPE extraction protocol was developed, and a total of 634 antibodies were tested in an initial set of 16 FFPE samples covering tumors from different origins. Of the 303 detected antibodies, 102 yielded significant correlation of signals in 25 pairs of fresh frozen and FFPE primary tumor samples, including head and neck squamous cell carcinomas (HNSC), lung squamous cell carcinomas (LUSC), lung adenocarcinomas (LUAD), colorectal adenocarcinomas (COAD), and pancreatic adenocarcinomas (PAAD). For this signature of 102 analytes (covering 88 total proteins and 14 phosphoproteins), a support vector machine (SVM) algorithm was developed. This allowed for the classification of the tissue of origin for all five tumor types studied here with high overall accuracies in both fresh frozen (90.4%) and FFPE (77.6%) samples. In addition, the SVM classifier reached an overall accuracy of 88% in an independent validation cohort of 25 FFPE tumor samples. Our results indicate that DigiWest-based protein profiling represents a valuable method for cancer classification, yielding conclusive and decisive data not only from fresh frozen specimens but also FFPE samples, thus making this approach attractive for routine clinical applications.

Machine learning models predict the primary sites of head and neck squamous cell carcinoma metastases based on DNA methylation

“…Gene expression [36][37][38] and protein profiling [39][40][41] have been successfully applied to the classification of other tumor entities by tissue of origin. A recent study [17] showed the superiority of a DNA methylation-based classifier over both of these approaches in distinguishing HNSC metastases from primary lung carcinoma, suggesting that this method is more promising for the goal of the present study.…”

“…In recent years, machine learning (ML) techniques have contributed to diagnosis in pathology [8–13]. Models based on DNA methylation profiles have been used to classify CNS tumors [14] and to predict the origin of neuroendocrine tumors [15] as well as CUPs [16].…”

Title: Discriminating between p16-negative oropharyngeal and non-oropharyngeal origins by their metastatic lymph nodes using machine learning approach based on MRI radiomics

“…Recent studies have shown the potential of radiomics and ML-based classi ers for distinguishing metastases from primary lesions [27,28], suggesting that this method is promising for the goal of the present study. Although gene expression [22,29] and protein pro ling [30] have been successfully applied to the classi cation of other tumor entities by tissue of origin, they are preferably performed on freshfrozen samples as they are negatively affected by RNA and protein deterioration in formalin-xed, para n-embedded tissue [21]. Radiomics and ML-based methods can be applied more practically as MRI data are more readily available in routine diagnostic work.…”

Research paper classification model based on deep learning network and text fine-grained features

“…One of the most accurate techniques is the support vector machine (SVM) [5,6,7], which uses kernel functions to find a separating hyperplane in high-dimensional space. Other kernel methods include string kernels [8,9], which are widely used for DNA and RNA sequence data. However, SVM and related methods can be difficult to interpret.…”