Ibrutinib and rituximab for chronic lymphocytic leukaemia

Deep learning assisted multi-omics integration for survival and drug-response prediction in breast cancer

Background

Survival and drug response are two highly emphasized clinical outcomes in cancer research that directs the prognosis of a cancer patient. Here, we have proposed a late multi omics integrative framework that robustly quantifies survival and drug response for breast cancer patients with a focus on the relative predictive ability of available omics datatypes. Neighborhood component analysis (NCA), a supervised feature selection algorithm selected relevant features from multi-omics datasets retrieved from The Cancer Genome Atlas (TCGA) and Genomics of Drug Sensitivity in Cancer (GDSC) databases. A Neural network framework, fed with NCA selected features, was used to develop survival and drug response prediction models for breast cancer patients. The drug response framework used regression and unsupervised clustering (K-means) to segregate samples into responders and non-responders based on their predicted IC50 values (Z-score).

Results

The survival prediction framework was highly effective in categorizing patients into risk subtypes with an accuracy of 94%. Compared to single-omics and early integration approaches, our drug response prediction models performed significantly better and were able to predict IC50 values (Z-score) with a mean square error (MSE) of 1.154 and an overall regression value of 0.92, showing a linear relationship between predicted and actual IC50 values.

Conclusion

The proposed omics integration strategy provides an effective way of extracting critical information from diverse omics data types enabling estimation of prognostic indicators. Such integrative models with high predictive power would have a significant impact and utility in precision oncology.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12864-021-07524-2.

Recent Advances in Allogeneic CAR-T Cells

In recent decades, great advances have been made in the field of tumor treatment. Especially, cell-based therapy targeting tumor associated antigen (TAA) has developed tremendously. T cells were engineered to have the ability to attack tumor cells by generating CAR constructs consisting of genes encoding scFv, a co-stimulatory domain (CD28 or TNFRSF9), and CD247 signaling domains for T cell proliferation and activation. Principally, CAR-T cells are activated by recognizing TAA by scFv on the T cell surface, and then signaling domains inside cells connected by scFv are subsequently activated to induce downstream signaling pathways involving T cell proliferation, activation, and production of cytokines. Many efforts have been made to increase the efficacy and persistence and also to decrease T cell exhaustion. Overall, allogeneic and universal CAR-T generation has attracted much attention because of their wide and prompt usage for patients. In this review, we summarized the current techniques for generation of allogeneic and universal CAR-T cells along with their disadvantages and limitations that still need to be overcome.