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.

Thyroid transcription factor-1 (TTF-1) is a transcription factor that plays a role in the development and physiology of the thyroid and lungs. Expression of TTF-1 is used as a marker of lung and thyroid clinically. Commercially available clones of TTF-1 monoclonal antibodies, 8G7G3/1 and SPT24, have been reported to have different sensitivities for the detection of neoplasms of different origins. Although they are used extensively in daily practice, a comprehensive comparative study of these antibodies in a wide variety of neoplasms is lacking. We examined TTF-1 expression in primary tumors of the lung, prostrate, pancreas, stomach, salivary glands, breast, bladder, colon and squamous cell carcinoma of the head and neck and compared the results obtained with both TTF-1 clones. The SPT24 clone detected more primary lung tumors of all histologic subtypes. Importantly, the SPT24 clone detected a significantly higher number of squamous cell carcinomas and carcinoid tumors of the lung. Among non-pulmonary primary tumors, a significant number of invasive urothelial carcinoma of the bladder (5.1%) was TTF-1 positive. Additionally, a small proportion of prostate (1.2%), stomach (0.9%), salivary gland (1.8%), and colon (2.5%) carcinomas were positive with both clones. Notably, both clones stained the same non-pulmonary tumors with similar intensity and distribution. Carcinomas of the pancreas, breast and squamous cell carcinomas of the head and neck were negative with both clones. In summary, the SPT24 clone detected a higher number of pulmonary non-small cell tumors of all histologic subtypes while both clones stained a similar proportion of non-pulmonary tumors.

No abstract