Zaoqu Liu

TL;DR: Li et al. as mentioned in this paper developed a machine learning-based integrative procedure for constructing a consensus immune-related lncRNA signature (IRLS), which is an independent risk factor for overall survival and displays stable and powerful performance, but only demonstrates limited predictive value for relapse-free survival.

TL;DR: Li et al. as discussed by the authors developed a machine learning-based integrative procedure for constructing a consensus immune-related lncRNA signature (IRLS), which is an independent risk factor for overall survival and displays stable and powerful performance, but only demonstrates limited predictive value for relapse-free survival.

Abstract: The tumor immunological microenvironment (TIME) has a prominent impact on prognosis and immunotherapy. However, the heterogeneous TIME and the mechanisms by which TIME affects immunotherapy have not been elucidated in hepatocellular carcinoma (HCC). A total of 2195 eligible HCC patients from TCGA and GEO database were collected. We comprehensively explored the different heterogeneous TIME phenotypes and its clinical significance. The potential immune escape mechanisms and what genomic alterations may drive the formation of different phenotypes were further investigated. We identified three phenotypes in HCC: TIME-1, the “immune-deficiency” phenotype, with immune cell depletion and proliferation; TIME-2, the “immune-suppressed” phenotype, with enrichment of immunosuppressive cells; TIME-3, the “immune-activated phenotype”, with abundant leukocytes infiltration and immune activation. The prognosis and sensitivity to both sorafenib and immunotherapy differed among the three phenotypes. We also underlined the potential immune escape mechanisms: lack of leukocytes and defective tumor antigen presentation capacity in TIME-1, increased immunosuppressive cells in TIME-2, and rich in immunoinhibitory molecules in TIME-3. The different phenotypes also demonstrated specific genomic events: TIME-1 characterized by TP53, CDKN2A, CTNNB1, AXIN1 and FOXD4 alterations; TIME-2 characterized by significant alteration patterns in the PI3K pathway; TIME-3 characterized by ARID1A mutation. Besides, the TIME index (TI) was proposed to quantify TIME infiltration pattern, and it was a superior prognostic and immunotherapy predictor. A pipeline was developed to classify single patient into one of these three subtypes and calculated the TI. We identified three TIME phenotypes with different clinical outcomes, immune escape mechanisms and genomic alterations in HCC, which could present strategies for improving the efficacy of immunotherapy. TI as a novel prognostic and immunotherapeutic signature that could guide personalized immunotherapy and clinical management of HCC.

TL;DR: Wang et al. as mentioned in this paper proposed a consensus machine learning-derived lncRNA signature (CMDLncS) that exhibited best power for predicting recurrence risk from 76 kinds of algorithm combinations.

TL;DR: Wang et al. as mentioned in this paper developed and validated a recurrenceassociated immune signature (RAIS) based on global immune genes to identify patients at high recurrence-risk for improving post-operative individual management.