A CD8+ T cell-associated immune gene panel for prediction of the prognosis and immunotherapeutic effect of melanoma

High-accuracy prediction of colorectal cancer chemotherapy efficacy using machine learning applied to gene expression data

Introduction: FOLFOX and FOLFIRI chemotherapy are considered standard first-line treatment options for colorectal cancer (CRC). However, the criteria for selecting the appropriate treatments have not been thoroughly analyzed. Methods: A newly developed machine learning model was applied on several gene expression data from the public repository GEO database to identify molecular signatures predictive of efficacy of 5-FU based combination chemotherapy (FOLFOX and FOLFIRI) in patients with CRC. The model was trained using 5-fold cross validation and multiple feature selection methods including LASSO and VarSelRF methods. Random Forest and support vector machine classifiers were applied to evaluate the performance of the models. Results and Discussion: For the CRC GEO dataset samples from patients who received either FOLFOX or FOLFIRI, validation and test sets were >90% correctly classified (accuracy), with specificity and sensitivity ranging between 85%-95%. In the datasets used from the GEO database, 28.6% of patients who failed the treatment therapy they received are predicted to benefit from the alternative treatment. Analysis of the gene signature suggests the mechanistic difference between colorectal cancers that respond and those that do not respond to FOLFOX and FOLFIRI. Application of this machine learning approach could lead to improvements in treatment outcomes for patients with CRC and other cancers after additional appropriate clinical validation.

Interferon-gamma is quintessential for NOS2 and COX2 expression in ER- breast tumors that lead to poor outcome

A strong correlation between NOS2 and COX2 tumor expression and poor clinical outcomes in ER breast cancer has been established. However, the mechanisms of tumor induction of these enzymes are unclear. Analysis of The Cancer Genome Atlas (TCGA) revealed correlations between NOS2 and COX2 expression and Th1 cytokines. Herein, single-cell RNAseq analysis of TNBC cells shows potent NOS2 and COX2 induction by IFNγ combined with IL1β or TNFα. Given that IFNγ is secreted by cytolytic lymphocytes, which improve clinical outcomes, this role of IFNγ presents a dichotomy. To explore this conundrum, tumor NOS2, COX2, and CD8⁺ T cells were spatially analyzed in aggressive ER-, TNBC, and HER2 + breast tumors. High expression and clustering of NOS2-expressing tumor cells occurred at the tumor/stroma interface in the presence of stroma-restricted CD8⁺ T cells. High expression and clustering of COX2-expressing tumor cells extended into immune desert regions in the tumor core where CD8⁺ T cell penetration was limited or absent. Moreover, high NOS2-expressing tumor cells were proximal to areas with increased satellitosis, suggestive of cell clusters with a higher metastatic potential. Further in vitro experiments revealed that IFNγ + IL1β/TNFα increased the elongation and migration of treated tumor cells. This spatial analysis of the tumor microenvironment provides important insight into distinct neighborhoods where stroma-restricted CD8⁺ T cells exist proximal to NOS2-expressing tumor niches that could have increased metastatic potential.

Interferon-gamma is Quintessential for NOS2 and COX2 Expression in ER - Breast Tumors that Lead to Poor Outcome

A strong correlation between NOS2 and COX2 tumor expression and poor clinical outcomes in ER-breast cancer has been established. However, mechanisms of tumor induction of these enzymes are unclear. Analysis of The Cancer Genome Atlas (TCGA) revealed correlations between NOS2 and COX2 expression and Th1 cytokines. Herein, single cell RNAseq analysis of TNBC cells shows potent NOS2 and COX2 induction by IFNγ combined with IL1β or TNFα. Given that IFNγ is secreted by cytolytic lymphocytes, which improve clinical outcomes, this role of IFNγpresents a dichotomy. To explore this conundrum, tumor NOS2, COX2, and CD8 ⁺ T cells were spatially analyzed in aggressive ER-, TNBC, and HER2+ breast tumors. High expression and clustering of NOS2-expressing tumor cells occurred at the tumor/stroma interface in the presence of stroma-restricted CD8 ⁺ T cells. High expression and clustering of COX2-expressing tumor cells extended into immune desert regions in the tumor core where CD8 ⁺ T cell penetration was limited or absent. Moreover, high NOS2-expressing tumor cells were proximal to areas with increased satellitosis suggestive of cell clusters with a higher metastatic potential. Further in vitro experiments revealed that IFNγ+IL1β/TNFα increased elongation and migration of treated tumor cells. This spatial analysis of the tumor microenvironment provides important insight of distinct neighborhoods where stroma-restricted CD8 ⁺ T cells exist proximal to NOS2-expressing tumor niches that could have increased metastatic potential.