In The Journal of molecular diagnostics : JMD
Cancers of unknown primary (CUP) are metastatic cancers for which the primary tumor is not found despite thorough diagnostic investigations. Multiple molecular assays have been proposed to identify the tissue of origin (TOO) and inform clinical care, however none has been able to combine accuracy, interpretability and easy access for routine use. We developed a classifier tool based on the training of a variational autoencoder (VAE) to predict tissue of origin based on RNA-seq data. We used as training data 20,918 samples corresponding to 94 different categories, including 39 cancer types and 55 normal tissues. The TransCUPtomics classifier was applied to a retrospective cohort of 37 CUP patients, and to 11 prospective patients. TransCUPtomics showed an overall accuracy of 96% on reference data for TOO prediction. The TOO could be identified in 38/48 CUP patients (79%). 8/11 prospective CUP patients (73%) could receive first-line therapy guided by TransCUPtomics prediction with responses observed in most patients. The VAE added further utility by enabling prediction interpretability, and diagnostic predictions could be matched to detection of gene fusions and expressed variants. TransCUPtomics confidently predicted TOO for CUP and enabled tailored treatments leading to significant clinical responses. The interpretability of our approach is a powerful addition to improve the management of CUP patients.
Vibert Julien, Pierron Gaëlle, Benoist Camille, Gruel Nadège, Guillemot Delphine, Vincent-Salomon Anne, Le Tourneau Christophe, Livartowski Alain, Mariani Odette, Baulande Sylvain, Bidard François-Clément, Delattre Olivier, Waterfall Joshua J, Watson Sarah