An AI-assisted integrated, scalable, single-cell phenomic-transcriptomic platform to elucidate intratumor heterogeneity against immune response.

"the single cell rna-seq data sets are available in the gene expression omnibus (geo) repository under the accession number gse117872.; data availability statement data that support the findings of this study are openly available in the gene expression omnibus (geo) repository under the accession number gse117872. single cell libraries were first filtered (number of genes by total counts <10000 percent mitochondrial genes <20%) normalized and logarithmized and highly variable genes were selected prior to performing principal component analysis (pca) (supplementary data s1 ).; data s1. table s3. raw data data availability statement data that support the findings of this study are openly available in the gene expression omnibus (geo) repository under the accession number gse117872"

"CONFLICT OF INTEREST STATEMENT The authors declare no competing interests."

"This study was funded by the Agency for Science Technology and Research Singapore (A*STAR) under a GAP Fund Grant (ACCL/19‐GAP074‐R20H) and AME YIRG Grant (A1884c0019). The authors would like to thank Professor Joel Voldman from Massachusetts Institute of Technology for providing the microfluidic cell trapping device used in this study. The authors would also like to thank Dr Fiona Lee for her assistance and guidance with HNSCC cell lines. Part of the graphical abstract as well as parts of Figures 1 and 5 were created with BioRender.com."