SUMMARY Embryonal rhabdomyosarcoma (eRMS) shows the most myodifferentiation amongst sarcomas, yet the precise cell of origin remains undefined. Using Ptch1, p53 and/or Rb1 conditional mouse models and controlling prenatal or postnatal myogenic cell of origin, we demonstrate that eRMS and undifferentiated pleomorphic sarcoma (UPS) lie in a continuum, with satellite cells predisposed to giving rise to UPS. Conversely, p53 loss in maturing myoblasts gives rise to eRMS, which have the highest myodifferentiation potential. Irrespective of origin, Rb1 loss modifies tumor phenotype to mimic UPS. In human sarcomas that lack pathognomic chromosomal translocations, p53 loss of function is prevalent whereas Shh or Rb1 alterations likely act primarily as modifiers. Thus, sarcoma phenotype is strongly influenced by cell of origin and mutational profile.

Supplementary data are available at Bioinformatics online.

BackgroundThe study of high-throughput genomic profiles from a pharmacogenomics viewpoint has provided unprecedented insights into the oncogenic features modulating drug response. A recent study screened for the response of a thousand human cancer cell lines to a wide collection of anti-cancer drugs and illuminated the link between cellular genotypes and vulnerability. However, due to essential differences between cell lines and tumors, to date the translation into predicting drug response in tumors remains challenging. Recently, advances in deep learning have revolutionized bioinformatics and introduced new techniques to the integration of genomic data. Its application on pharmacogenomics may fill the gap between genomics and drug response and improve the prediction of drug response in tumors.ResultsWe proposed a deep learning model to predict drug response (DeepDR) based on mutation and expression profiles of a cancer cell or a tumor. The model contains three deep neural networks (DNNs), i) a mutation encoder pre-trained using a large pan-cancer dataset (The Cancer Genome Atlas; TCGA) to abstract core representations of high-dimension mutation data, ii) a pre-trained expression encoder, and iii) a drug response predictor network integrating the first two subnetworks. Given a pair of mutation and expression profiles, the model predicts IC50 values of 265 drugs. We trained and tested the model on a dataset of 622 cancer cell lines and achieved an overall prediction performance of mean squared error at 1.96 (log-scale IC50 values). The performance was superior in prediction error or stability than two classical methods (linear regression and support vector machine) and four analog DNN models of DeepDR, including DNNs built without TCGA pre-training, partly replaced by principal components, and built on individual types of input data. We then applied the model to predict drug response of 9059 tumors of 33 cancer types. Using per-cancer and pan-cancer settings, the model predicted both known, including EGFR inhibitors in non-small cell lung cancer and tamoxifen in ER+ breast cancer, and novel drug targets, such as vinorelbine for TTN-mutated tumors. The comprehensive analysis further revealed the molecular mechanisms underlying the resistance to a chemotherapeutic drug docetaxel in a pan-cancer setting and the anti-cancer potential of a novel agent, CX-5461, in treating gliomas and hematopoietic malignancies.ConclusionsHere we present, as far as we know, the first DNN model to translate pharmacogenomics features identified from in vitro drug screening to predict the response of tumors. The results covered both well-studied and novel mechanisms of drug resistance and drug targets. Our model and findings improve the prediction of drug response and the identification of novel therapeutic options.