TIGER:A Web Portal of Tumor Immunotherapy Gene Expression Resource

Immunotherapy is a promising cancer treatment method;however,only a few patients benefit from it.The development of new immunotherapy strategies and effective biomarkers of response and resistance is urgently needed.Recently,high-throughput bulk and single-cell gene expression profling technologies have generated valuable resources.However,these resources are not well organized and systematic analysis is difficult.Here,we present TIGER,a tumor immunotherapy gene expression resource,which contains bulk transcriptome data of 1508 tumor samples with clinical immunotherapy outcomes and 11,057 tumor/normal samples without clinical immunotherapy outcomes,as well as single-cell transcriptome data of 2,116,945 immune cells from 655 samples.TIGER provides many useful modules for analyzing collected and user-provided data.Using the resource in TIGER,we identified a tumor-enriched subset of CD4^(+)T cells.Patients with melanoma with a higher signature score of this subset have a significantly better response and survival under immunotherapy.We believe that TIGER will be helpful in understanding anti-tumor immunity mechanisms and discovering effective biomarkers.

A generic and extensible model for the martensite start temperature incorporating thermodynamic data mining and deep learning framework

The martensite start temperature is a critical parameter for steels with metastable austenite.Although numerous models have been developed to predict the martensite start(Ms)temperature,the complexity of the martensitic transformation greatly limits their performance and extensibility.In this work,we apply deep data mining of thermodynamic calculations and deep learning to develop a generic model for Msprediction.Deep data mining was used to establish a hierarchical database with three levels of information.Then,a convolutional neural network model,which can accurately treat the hierarchical data structure,was used to obtain the final model.By integrating thermodynamic calculations,traditional machine learning and deep learning modeling,the final predictor model shows excellent generalizability and extensibility,i.e.model performance both within and beyond the composition range of the original database.The effects of 15 alloying elements were considered successfully using the proposed methodology.The work suggests that,with the help of deep data mining considering the physical mechanisms,deep learning methods can partially mitigate the challenge with limited data in materials science and provide a means for solving complex problems with small databases.