Transcriptomic Deconvolution of Neuroendocrine Neoplasms Predicts Clinically Relevant Characteristics.

Simple Summary: Rapidly growing neuroendocrine neoplasms (NEN) often defy easy classification by the pathologist. Machine learning approaches can improve the classification's accuracy, but these generally require large amounts of training data. As tumor-based training data will remain sparse for very rare malignancies, such as NEN from the pancreas, we aimed for a machine learning-aided classification on the basis of the tumors' similarity to non-transformed pancreatic cell types. We determined the relative contribution of the different healthy cell types to the transcriptome of each NEN and used the information to train a model for predicting the overall patient survival time, neoplastic grading, and carcinoma versus tumor subclassification. This approach does not use proliferation as a feature, since healthy pancreatic epithelial cell types do not proliferate. Hence, our approach is complementary to the established proliferation rate-based classification scheme, thereby providing additional criteria for a confident classification of ambiguous cases. Pancreatic neuroendocrine neoplasms (panNENs) are a rare yet diverse type of neoplasia whose precise clinical–pathological classification is frequently challenging. Since incorrect classifications can affect treatment decisions, additional tools which support the diagnosis, such as machine learning (ML) techniques, are critically needed but generally unavailable due to the scarcity of suitable ML training data for rare panNENs. Here, we demonstrate that a multi-step ML framework predicts clinically relevant panNEN characteristics while being exclusively trained on widely available data of a healthy origin. The approach classifies panNENs by deconvolving their transcriptomes into cell type proportions based on shared gene expression profiles with healthy pancreatic cell types. The deconvolution results were found to provide a prognostic value with respect to the prediction of the overall patient survival time, neoplastic grading, and carcinoma versus tumor subclassification. The performance with which a proliferation rate agnostic deconvolution ML model could predict the clinical characteristics was found to be comparable to that of a comparative baseline model trained on the proliferation rate-informed MKI67 levels. The approach is novel in that it complements established proliferation rate-oriented classification schemes whose results can be reproduced and further refined by differentiating between identically graded subgroups. By including non-endocrine cell types, the deconvolution approach furthermore provides an in silico quantification of panNEN dedifferentiation, optimizing it for challenging clinical classification tasks in more aggressive panNEN subtypes. [ABSTRACT FROM AUTHOR]