Experimental and bioinformatics comparison of gene expression between T cells from TIL of liver cancer and T cells from UniGene

Background. The major difficulty of mapping parallel gene expression obtained from solid tumors is mainly due to contaminating cells. In this study, by applying a strategy of parallel gene expression at a cell-cluster or colony level, we have identified the gene expression pattern of T cells within tumor-infiltrating lymphocytes (TILs) obtained from two liver cancer patients. Methods. Here a new method was utilized to analyze the parallel gene expression. By using bioinformatics analysis, the data were also compared with T-cell gene expression present in UniGene. Results. Our results demonstrated that 18 genes in specimen A and 13 genes in specimen B were highly expressed after the removal of a nonspecific TIL cDNA library, by pairing gene hybridization; the genes were expressed in CD3+ cells from peripheral blood mononuclear cells (PBMC). By using BlastN search, 17 of the 18, and 12 of the 13 sequences were exhibited, respectively, in Homo Sapiens, with a range of BlastN E values of 0 to 4 x 10(-13). The LocusLink distribution in chromosomes obtained from both specimens was not significantly different; 17 of 19 putative genes (both specimen A and specimen B) were observed in the UniGene cluster in Homo sapiens, except for dihydropyrimidinase-related protein-3 and diacyglycerol kinase alpha. Interestingly, only 4 of 19 (21%) putative genes were displayed in the T-cell UniGene database (i.e., LD-78 in Hs. 73817, IL-8 in Hs. 624, TRAIL in Hs. 83429, and Fas ligand in Hs. 2007). Conclusions. By comparison with the reported data and UniGene, the parallel gene expression of T cells obtained from TIL can provide essential new insights into T-cell activity, T-cell extravasation into tumor tissues, and T-cell cytotoxicity against tumor cells.