Deep Learning-Based Survival Analysis Identified Associations Between Molecular Subtype and Optimal Adjuvant Treatment of Patients With Gastric Cancer.

PURPOSE: Gastric cancer (GC) is the third-leading cause of cancer-related deaths. Several pivotal clinical trials of adjuvant treatments were performed during the previous decade; however, the optimal regimen for adjuvant treatment of GC remains controversial. PATIENTS AND METHODS: We developed a novel deep learning-based survival model (survival recurrent network [SRN]) in patients with GC by including all available clinical and pathologic data and treatment regimens. This model uses time-sequential data only in the training step, and upon being trained, it receives the initial data from the first visit and then sequentially predicts the outcome at each time point until it reaches 5 years. In total, 1,190 patients from three cohorts (the Asian Cancer Research Group cohort, n = 300; the fluorouracil, leucovorin, and radiotherapy cohort, n = 432; and the Adjuvant Chemoradiation Therapy in Stomach Cancer cohort, n = 458) were included in the analysis. In addition, we added Asian Cancer Research Group molecular classifications into the prediction model. SRN simulated the sequential learning process of clinicians in the outpatient clinic using a recurrent neural network and time-sequential outcome data. RESULTS: The mean area under the receiver operating characteristics curve was 0.92 ± 0.049 at the fifth year. The SRN demonstrated that GC with a mesenchymal subtype should elicit a more risk-adapted postoperative treatment strategy as a result of its high recurrence rate. In addition, the SRN found that GCs with microsatellite instability and GCs of the papillary type exhibited significantly more favorable survival outcomes after capecitabine plus cisplatin chemotherapy alone. CONCLUSION: Our SRN predicted survival at a high rate, reaching 92% at postoperative year 5. Our findings suggest that SRN-based clinical trials or risk-adapted adjuvant trials could be considered for patients with GC to investigate more individualized adjuvant treatments after curative gastrectomy.

TP53 alteration determines the combinational cytotoxic effect of doxorubicin and an antioxidant NAC.

The anticancer effect of doxorubicin is closely related to the generation of reactive oxygen species. On the contrary, doxorubicin-induced reactive oxygen species induces heart failure, a critical side effect of doxorubicin. Antioxidant supplementation has been proposed to reduce the side effects. However, the use of antioxidants may hamper the anticancer effect of doxorubicin. In this study, doxorubicin-induced reactive oxygen species was shown to differentially affect cancer cells based on their TP53 genetic status; doxorubicin-induced apoptosis was attenuated by an antioxidant, N-acetylcysteine, in TP53 wild cells; however, N-acetylcysteine caused a synergistic increase in the apoptosis rate in TP53-altered cells. N-acetylcysteine prevented phosphorylation of P53 protein that had been induced by doxorubicin. However, N-acetylcysteine increased the cleavage of poly (ADP-ribose) polymerase in the presence of doxorubicin. Synergy score of 26 patient-derived cells were evaluated after the combination treatment of doxorubicin and N-acetylcysteine. The synergy score was significantly higher in TP53-altered group compared with those in TP53 wild group. In conclusion, TP53 genetic alteration is a critical factor that determines the use of antioxidant supplements during doxorubicin treatment.

Biomineralized matrix-assisted osteogenic differentiation of human embryonic stem cells.

The physical and chemical properties of a matrix play an important role in determining various cellular behaviors, including lineage specificity. We demonstrate that the differentiation commitment of human embryonic stem cells (hESCs), both in vitro and in vivo, can be solely achieved through synthetic biomaterials. hESCs were cultured using mineralized synthetic matrices mimicking a calcium phosphate (CaP)-rich bone environment differentiated into osteoblasts in the absence of any osteogenic inducing supplements. When implanted in vivo, these hESC-laden mineralized matrices contributed to ectopic bone tissue formation. In contrast, cells within the corresponding non-mineralized matrices underwent either osteogenic or adipogenic fate depending upon the local cues present in the microenvironment. To our knowledge, this is the first demonstration where synthetic matrices are shown to induce terminal cell fate specification of hESCs exclusively by biomaterial-based cues both in vitro and in vivo. Technologies that utilize tissue specific cell-matrix interactions to control stem cell fate could be a powerful tool in regenerative medicine. Such approaches can be used as a tool to advance our basic understanding and assess the translational potential of stem cells.