About this item:

73 Views | 17 Downloads

Author Notes:

Jian Hu, jian.hu@emory.edu

Linghua Wang, lwang22@mdanderson.org

Mingyao Li, mingyao@pennmedicine.upenn.edu

This study was conceived and led by M.L. J.H. designed the model and algorithm. J.H. implemented the TESLA software and led the data analysis with input from M.L., L.W., E.B.L., H.K., K.C., and D.Z. K.C. performed cell-type deconvolution analysis. E.B.L. examined the histology images. L.W. and H.K. provided marker genes for cancer and interpreted the results. L.W. provided guidance for the tumor TME analysis. J.H., M.L., and L.W. wrote the paper with feedback from all other coauthors.

This work was supported by the following grants: National Institutes of Health grants R01GM125301 (to M.L.), P01AG066597 (to E.B.L. and M.L.), U01CA264583 (to H.K., L.W., and M.L.), and Cancer Prevention and Research Institute of Texas (CPRIT) grant RP220101 (to H.K. and L.W.). L.W. was also supported in part by the Start-up Research fund and the Institutional Research Grant (IRG) awards provided by U.T. MD Anderson Cancer Center, the Andrew Sabin Family Fellowship provided by the Andrew Sabin Family Foundation, and the RP200385 award provided by CPRIT. We thank Dr. Kim Thrane for sharing the melanoma histology image data.

M.L. received research funding from Biogen Inc. unrelated to the current manuscript.

Subject:

Keywords:

  • Science & Technology
  • Life Sciences & Biomedicine
  • Biochemistry & Molecular Biology
  • Cell Biology
  • INFILTRATING LYMPHOCYTES
  • METASTATIC MELANOMA
  • B-CELLS
  • IMMUNOTHERAPY
  • SURVIVAL
  • ARCHITECTURE
  • PROGRESSION
  • EXPRESSION

Deciphering tumor ecosystems at super resolution from spatial transcriptomics with TESLA

Tools:

Journal Title:

CELL SYSTEMS

Volume:

Volume 14, Number 5

Publisher:

, Pages 404-+

Type of Work:

Article | Post-print: After Peer Review

Abstract:

Cell populations in the tumor microenvironment (TME), including their abundance, composition, and spatial location, are critical determinants of patient response to therapy. Recent advances in spatial transcriptomics (ST) have enabled the comprehensive characterization of gene expression in the TME. However, popular ST platforms, such as Visium, only measure expression in low-resolution spots and have large tissue areas that are not covered by any spots, which limits their usefulness in studying the detailed structure of TME. Here, we present TESLA, a machine learning framework for tissue annotation with pixel-level resolution in ST. TESLA integrates histological information with gene expression to annotate heterogeneous immune and tumor cells directly on the histology image. TESLA further detects unique TME features such as tertiary lymphoid structures, which represents a promising avenue for understanding the spatial architecture of the TME. Although we mainly illustrated the applications in cancer, TESLA can also be applied to other diseases.

Copyright information:

This is an Open Access work distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (https://creativecommons.org/licenses/by-nc-nd/4.0/).
Export to EndNote