Artificial intelligence-based analysis of tumor-infiltrating lymphocyte spatial distribution for colorectal cancer prognosis

Background:Artificial intelligence(AI)technology represented by deep learning has made remarkable achievements in digital pathology,enhancing the accuracy and reliability of diagnosis and prognosis evaluation.The spatial distribution of CD3^(+)and CD8^(+)T cells within the tumor microenvironment has been demonstrated to have a significant impact on the prognosis of colorectal cancer(CRC).This study aimed to investigate CD3_(CT)(CD3^(+)T cells density in the core of the tumor[CT])prognostic ability in patients with CRC by using AI technology.Methods:The study involved the enrollment of 492 patients from two distinct medical centers,with 358 patients assigned to the training cohort and an additional 134 patients allocated to the validation cohort.To facilitate tissue segmentation and T-cells quantification in whole-slide images(WSIs),a fully automated workflow based on deep learning was devised.Upon the completion of tissue segmentation and subsequent cell segmentation,a comprehensive analysis was conducted.Results:The evaluation of various positive T cell densities revealed comparable discriminatory ability between CD3_(CT) and CD3-CD8(the combination of CD3^(+)and CD8^(+)T cells density within the CT and invasive margin)in predicting mortality(C-index in training cohort:0.65 vs.0.64;validation cohort:0.69 vs.0.69).The CD3_(CT) was confirmed as an independent prognostic factor,with high CD3_(CT) density associated with increased overall survival(OS)in the training cohort(hazard ratio[HR]=0.22,95%confidence interval[CI]:0.12–0.38,P<0.001)and validation cohort(HR=0.21,95%CI:0.05–0.92,P=0.037).Conclusions:We quantify the spatial distribution of CD3^(+)and CD8^(+)T cells within tissue regions in WSIs using AI technology.The CD3_(CT) confirmed as a stage-independent predictor for OS in CRC patients.Moreover,CD3_(CT) shows promise in simplifying the CD3-CD8 system and facilitating its practical application in clinical settings.

CircRNA.0007127 triggers apoptosis through the miR-513a-5p/CASP8 axis in K-562 cells

Background:Circular RNAs(circR NAs)are covalently closed single-stranded RNAs with multiple biological functions.CircRNA.0007127 is derived from the carbon catabolite repression 4-negative on TATA-less(CCR4-NOT)complex subunit2(CNOT2),which was found to regulate tumor cell apoptosis through caspase pathway.Methods:Potential circR NA.0007127 target microRNAs(miRNAs)were analyzed by miRanda,TargetScan,and RNAhybrid software,and the miRNAs with binding sites for apoptosis-related genes were screened.The roles of circR NA.0007127 and its downstream target,microR NA(miR)-513a-5p,were validated by quantitative real-time polymerase chain reaction(qPCR),flow cytometry,mitochondrial membrane potential,immunofluorescence,western blot,and caspase-8(CASP8)protein activity in vitro in HO-induced K-562 cells.The circRNA.0007127-miR-513a-5p and CASP8-miR-513a-5p interactions were verified by luciferase reporter assays.Results:Silencing circRNA.0007127 decreased cell apoptosis by inhibiting CASP8 pathway activation in K-562 cells.Compared with the control group,the expression of CASP8 was reduced by 50%and the 43-kD fragment of CASP8 protein was significantly reduced(P≤0.05).The luciferase reporting assay showed that circRNA.0007127 combined with miR-513a-5p or CASP8,with extremely significant differences(P≤0.001).The overexpression of miR-513a-5p inhibited the gene expression level of CASP8in a human myeloid leukemia cell model(75%change)and the level of a 43-kD fragment of CASP8 protein(P small-interfering RNA(siRNA)and the miR-≤0.01).The rescue experiment showed that cotransfection with circRNA.0007127513a-5p inhibitor increased CASP8 gene expression and the apoptosis rate,suggesting that the miR-513a-5p inhibitor is a circRNA.0007127siRNA antagonist.Conclusions:CircRNA.0007127 regulates K-562 cell apoptosis through the miR-513a-5p/CASP8 axis,which can serve as a novel powerful molecular target for K-562 cells.