 This paper presents a large integrated SCRNA sec dataset containing 224,611 cells from human primary non-small cell lung cancer, NSCLC, tumors. The authors used publicly available resources to pre-process and integrate seven independent SCRNA sec datasets using an anchor-based approach. They then created two levels of annotation based on cell-type specific markers conserved across the datasets. Furthermore, they conducted a trajectory analysis on subsets of T cells and lung cancer cells. This integrated data can be used to study NSCLC transcriptome at the single cell level. This article was authored by Carolina Hanna-Prazynowska and Sue Binlim.