Hepatocellular carcinoma (HCC) is the fifth most common tumor worldwide and has a very poor prognosis. Its occurrence has been on the increase in recent years. Surgical resection and liver transplantation are the primary methods of treatment for HCC patients, but can only be applied to 15% of patients. The median survival time of unresectable or metastasizing HCC patients is only a few months. Existing systemic treatment methods are not effective for advanced HCC patients and a new method of treatment is needed for these patients. It has been established that the HCC occurs in multiple stages, however, the pathogenesis at a molecular level is not clear and many key factors are yet to be determined. In the past 30 years, it has become evident that the Ras/Raf/MEK/extracellular signal-regulated kinase (ERK) signaling pathway plays a significant role in the occurrence and development of HCC. This review focused on the association between the Ras/Raf/MEK/ERK signaling pathway and HCC.

Multidrug resistance (MDR) accounts for poor prognosis in gastric cancer (GC). MicroRNAs (miRNAs) are critical regulators of MDR via modulation of the target genes. The present study revealed that miR-495-3p could act via a target gene, GRP78, to regulate the process of autophagy and inhibit MDR. Based on the in vitro and in vivo gain-of-function or loss-of-function experiments, overexpression of miR-495-3p was sufficient to reverse the MDR to four chemotherapeutics in vitro and inhibit the tumor growth in vivo. Moreover, GRP78 was positively associated with the occurrence of autophagy. Thus, reducing the expression of GRP78 by siRNA resulted in autophagy-suppressive activity similar to that of miR-495-3p on mammalian target of rapamycin (mTOR) and its substrates activation and autophagy inhibition, while restoring GRP78 attenuated the anti-autophagy effects caused by miR-495-3p. Clinically, either miR-495-3p downregulation or GRP78 upregulation was associated with malignant phenotypes in patients with GC. In conclusion, these findings demonstrate that miR-495-3p is an important regulator of autophagy balance and MDR by modulating the GRP78/mTOR axis. In addition, miR-495-3p and GRP78 could be used as prognostic factors for overall survival in GC, which implicates miR-495-3p as a therapeutic target in cancer.

IntroductionDespite the many benefits immunotherapy has brought to patients with different cancers, its clinical applications and improvements are still hindered by drug resistance. Fostering a reliable approach to identifying sufferers who are sensitive to certain immunotherapeutic agents is of great clinical relevance.MethodsWe propose an ELISE (Ensemble Learning for Immunotherapeutic Response Evaluation) pipeline to generate a robust and highly accurate approach to predicting individual responses to immunotherapies. ELISE employed iterative univariable logistic regression to select genetic features of patients, using Monte Carlo Tree Search (MCTS) to tune hyperparameters. In each trial, ELISE selected multiple models for integration based on add or concatenate stacking strategies, including deep neural network, automatic feature interaction learning via self-attentive neural networks, deep factorization machine, compressed interaction network, and linear neural network, then adopted the best trial to generate a final approach. SHapley Additive exPlanations (SHAP) algorithm was applied to interpret ELISE, which was then validated in an independent test set.ResultRegarding prediction of responses to atezolizumab within esophageal adenocarcinoma (EAC) patients, ELISE demonstrated a superior accuracy (Area Under Curve [AUC] = 100.00%). AC005786.3 (Mean [|SHAP value|] = 0.0097) was distinguished as the most valuable contributor to ELISE output, followed by SNORD3D (0.0092), RN7SKP72 (0.0081), EREG (0.0069), IGHV4-80 (0.0063), and MIR4526 (0.0063). Mechanistically, immunoglobulin complex, immunoglobulin production, adaptive immune response, antigen binding and others, were downregulated in ELISE-neg EAC subtypes and resulted in unfavorable responses. More encouragingly, ELISE could be extended to accurately estimate the responsiveness of various immunotherapeutic agents against other cancers, including PD1/PD-L1 suppressor against metastatic urothelial cancer (AUC = 88.86%), and MAGE−A3 immunotherapy against metastatic melanoma (AUC = 100.00%).DiscussionThis study presented deep insights into integrating ensemble deep learning with self-attention as a mechanism for predicting immunotherapy responses to human cancers, highlighting ELISE as a potential tool to generate reliable approaches to individualized treatment.