Background No study has evaluated the predictive and prognostic role of CD8 and PD-L1 coexpression in non–small-cell lung cancer (NSCLC). Methods We analyzed RNA sequencing and/or immunohistochemistry staining in NSCLC patients from The Cancer Genome Atlas ( n = 1016), and 34 metastatic NSCLC samples not treated by immunotherapy as prognostic cohorts. As predictive aspect of CD8 and PD-L1, we used 85 NSCLC patients treated with anti-PD-1. Two validation cohorts were used including 44 NSCLC patients treated with anti-PD-1 and an external cohort with different tumor types. Results In prognostic cohorts, high CD8A expression was associated with longer OS ( p = 0.02), while high CD274 mRNA was associated with poor prognosis ( p = 0.05). In predictive cohort, high CD8 expression and CD8A mRNA were associated with longer progression-free survival (PFS) ( p = 0.0002). There was no significant association between PD-L1 expression and PFS while high CD274 mRNA was associated with longer PFS ( p = 0.009). A combination of CD8A and CD274 was highly predictive of outcome. These results were confirmed in the validation cohorts. This two-genes signature demonstrated similar results compared to gold standard signatures. Conclusion CD8 represents both a prognostic and predictive factor of outcomes, while PD-L1 share different prognostic and predictive roles.
ObjectiveDiagnostic tests, such as Immunoscore, predict prognosis in patients with colon cancer. However, additional prognostic markers could be detected on pathological slides using artificial intelligence tools.DesignWe have developed a software to detect colon tumour, healthy mucosa, stroma and immune cells on CD3 and CD8 stained slides. The lymphocyte density and surface area were quantified automatically in the tumour core (TC) and invasive margin (IM). Using a LASSO algorithm, DGMate (DiGital tuMor pArameTErs), we detected digital parameters within the tumour cells related to patient outcomes.ResultsWithin the dataset of 1018 patients, we observed that a poorer relapse-free survival (RFS) was associated with high IM stromal area (HR 5.65; 95% CI 2.34 to 13.67; p<0.0001) and high DGMate (HR 2.72; 95% CI 1.92 to 3.85; p<0.001). Higher CD3+ TC, CD3+ IM and CD8+ TC densities were significantly associated with a longer RFS. Analysis of variance showed that CD3+ TC yielded a similar prognostic value to the classical CD3/CD8 Immunoscore (p=0.44). A combination of the IM stromal area, DGMate and CD3, designated ‘DGMuneS’, outperformed Immunoscore when used in estimating patients’ prognosis (C-index=0.601 vs 0.578, p=0.04) and was independently associated with patient outcomes following Cox multivariate analysis. A predictive nomogram based on DGMuneS and clinical variables identified a group of patients with less than 10% relapse risk and another group with a 50% relapse risk.ConclusionThese findings suggest that artificial intelligence can potentially improve patient care by assisting pathologists in better defining stage III colon cancer patients’ prognosis.
BackgroundT lymphocytes and HLA expression on tumor cell both influence prognostic of localized colorectal cancer, but their role following chemotherapy in patients with liver metastatic colorectal cancer (mCRC) was not addressed.MethodsOne hundred fourteen patients treated in curative intend of liver mCRC were included in this retrospective study. Patients were either untreated or treated with neoadjuvant therapy containing an anti-EGFR, bevacizumab or oxaliplatin. Immune densities were quantified in the tumor core and in invasive margin of metastases, using Qupath software or a pathologist’s quantification. CD8, NKp46, Foxp3, CD163, HLA, PD-L1 were analyzed and were correlated with progression free survival (PFS) and overall survival (OS) using multivariable Cox proportional hazards models.ResultsIn the whole cohort only a high CD8+ cells infiltrate, a high HLA-I expression and wild-type RAS/RAF status were associated with a better overall survival in both univariate and multivariate model. Moreover, CD8+ cells immune infiltrate at invasive margin combined to HLA expression in cancer cell could increase patient’s outcome prediction. RAS status but not immune cell infiltrate was associated with HLA expression on tumor cells. In comparison to untreated patients, neoadjuvant chemotherapy induced CD8+ cells recruitment and increased PD-L1 staining in immune infiltrates only for WT RAS patients. In this context, anti-EGFR and oxaliplatin based chemotherapy are the most powerful to induce CD8+ cells mobilization within the metastatic site.ConclusionsWhile CD8 infiltrate and HLA expression appear to be prognostic for mCRC, CD8 and PD-L1 infiltrate are enhanced by neoadjuvant chemotherapy in mCRC under RAS status dependence.Electronic supplementary materialThe online version of this article (10.1186/s40425-018-0438-3) contains supplementary material, which is available to authorized users.
Background Prognostic markers for glioblastoma are lacking. Both intrinsic tumour characteristics and microenvironment could influence cancer prognostic. The aim of our study was to generate a pure glioblastoma cell lines and immune classification in order to decipher the respective role of glioblastoma cell and microenvironment on prognosis. Methods We worked on two large cohorts of patients suffering from glioblastoma (TCGA, n = 481 and Rembrandt, n = 180) for which clinical data, transcriptomic profiles and outcome were recorded. Transcriptomic profiles of 129 pure glioblastoma cell lines were clustered to generate a glioblastoma cell lines classification. Presence of subtypes of glioblastoma cell lines and immune cells was determined using deconvolution. Results Glioblastoma cell lines classification defined three new molecular groups called oncogenic, metabolic and neuronal communication enriched. Neuronal communication-enriched tumours were associated with poor prognosis in both cohorts. Immune cell infiltrate was more frequent in mesenchymal classical classification subgroup and metabolic-enriched tumours. A combination of age, glioblastoma cell lines classification and immune classification could be used to determine patient’s outcome in both cohorts. Conclusions Our study shows that glioblastoma-bearing patients can be classified based on their age, glioblastoma cell lines classification and immune classification. The combination of these information improves the capacity to address prognosis.
Finding the optimal hyperparameters of a model can be cast as a bilevel optimization problem, typically solved using zero-order techniques. In this work we study first-order methods when the inner optimization problem is convex but non-smooth. We show that the forward-mode differentiation of proximal gradient descent and proximal coordinate descent yield sequences of Jacobians converging toward the exact Jacobian. Using implicit differentiation, we show it is possible to leverage the non-smoothness of the inner problem to speed up the computation. Finally, we provide a bound on the error made on the hypergradient when the inner optimization problem is solved approximately. Results on regression and classification problems reveal computational benefits for hyperparameter optimization, especially when multiple hyperparameters are required.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.