Search

Understanding the complex biology of the tumor microenvironment (TME) is necessary to understand the mechanisms of action of immuno-oncology therapies and to match the right therapies to the right patients. Multiplex immunofluorescence (mIF) is a useful technology that has tremendous potential to further our understanding of cancer patho-biology; however, tools that fully leverage the high dimensionality of this data are still in their infancy. We describe here a novel deep learning pipeline aimed to allow Graph-based Inspection of Tissues via Embeddings, GraphITE. GraphITE transforms mIF data into a graph representation, where unsupervised learning algorithms can be utilised to generate embeddings representing cellular ‘neighbourhoods’. The embeddings can be downprojected and explored for clustering analysis, and patterns can be mapped back to the image as well as interrogated for phenotypical, morphological, or structural distinctiveness. GraphITE supports the extraction of information not only on the phenotypes of individual cells or the relationships between specific cell types, but is able to characterize cell neighborhoods to look for more complex interactions, thereby allowing pathologists and data scientists to explore mIF data sets, uncovering patterns that are otherwise obscured by the high-dimensionality of the data. In this work, we showcase the current setup of the system, going from raw input data all the way to a user friendly exploration tool. Using this tool, we show how the data can be navigated in a way previously not possible.

ObjectivesThe interaction between the immune system and tumor cells is an important feature for the prognosis and treatment of cancer. Multiplex immunohistochemistry (mIHC) and multiplex immunofluorescence (mIF) analyses are emerging technologies that can be used to help quantify immune cell subsets, their functional state, and their spatial arrangement within the tumor microenvironment.MethodsThe Society for Immunotherapy of Cancer (SITC) convened a task force of pathologists and laboratory leaders from academic centers as well as experts from pharmaceutical and diagnostic companies to develop best practice guidelines for the optimization and validation of mIHC/mIF assays across platforms.ResultsRepresentative outputs and the advantages and disadvantages of mIHC/mIF approaches, such as multiplexed chromogenic IHC, multiplexed immunohistochemical consecutive staining on single slide, mIF (including multispectral approaches), tissue-based mass spectrometry, and digital spatial profiling are discussed.ConclusionsmIHC/mIF technologies are becoming standard tools for biomarker studies and are likely to enter routine clinical practice in the near future. Careful assay optimization and validation will help ensure outputs are robust and comparable across laboratories as well as potentially across mIHC/mIF platforms. Quantitative image analysis of mIHC/mIF output and data management considerations will be addressed in a complementary manuscript from this task force.

Continued developments in immuno-oncology require an increased understanding of the mechanisms of cancer immunology. The immunoprofiling analysis of tissue samples from formalin-fixed, paraffin-embedded (FFPE) biopsies has become a key tool for understanding the complexity of tumor immunology and discovering novel predictive biomarkers for cancer immunotherapy. Immunoprofiling analysis of tissues requires the evaluation of combined markers, including inflammatory cell subpopulations and immune checkpoints, in the tumor microenvironment. The advent of novel multiplex immunohistochemical methods allows for a more efficient multiparametric analysis of single tissue sections than does standard monoplex immunohistochemistry (IHC). One commercially available multiplex immunofluorescence (IF) method is based on tyramide-signal amplification and, combined with multispectral microscopic analysis, allows for a better signal separation of diverse markers in tissue. This methodology is compatible with the use of unconjugated primary antibodies that have been optimized for standard IHC on FFPE tissue samples. Herein we describe in detail an automated protocol that allows multiplex IF labeling of carcinoma tissue samples with a six-marker multiplex antibody panel comprising PD-L1, PD-1, CD68, CD8, Ki-67, and AE1/AE3 cytokeratins with 4',6-diamidino-2-phenylindole as a nuclear cell counterstain. The multiplex panel protocol is optimized in an automated IHC stainer for a staining time that is shorter than that of the manual protocol and can be directly applied and adapted by any laboratory investigator for immuno-oncology studies on human FFPE tissue samples. Also described are several controls and tools, including a drop-control method for fine quality control of a new multiplex IF panel, that are useful for the optimization and validation of the technique.

Background The tumor immune microenvironment (TIME) may hold critical information for developing and optimizing immuno-therapeutic approaches, identifying predictive signatures, and selecting the most adequate treatment option for a given patient. Tissue phenomics facilitates the use of the TIME to derive predictive conclusions. The visual information content in histological sections is systematically converted into numerical readouts using artificial intelligence (AI). Resulting quantitative descriptors, phenes, of detected structures are mined to yield local expression profiles; this spatial data aggregation detects categories of local environments, which are correlated to clinical, genomic or other -omics data to identify relevant cohort subpopulations. Methods Exploration of this technology is illustrated by various examples on different cohorts of NSCLC patients: A categorization of n = 45 non-IO-treated patients with respect to local immune profiles learned via AI in a hypothesis-free scenario was examined. A deep learning based PD-L1 scoring was compared to 3 pathologist’s scoring on n = 40 durvalumab-treated patients using the cutoff 25% of tumor cells staining positive for PD-L1 at any intensity. The predictive value of a digital signature combining cell densities of PD-L1 and CD8+ was tested on n = 163 durvalumab-treated and n = 199 non-IO-treated samples. Results A categorization into biologically interpretable classes learned by AI illustrates the exploratory benefits of tissue phenomics. The scoring algorithm could reproduce survival prediction when compared to pathologist’s visual scoring.The digital signature suggests a predictive value for patient stratification into responders and non-responders for durvalumab, while no prognostic value could be found on the non-IO-treated patients. Kaplan-Meier plots for the 2 latter examples will be presented in the poster. Conclusions Tissue phenomics facilitates the quantitative assessment of the tumor geography and may lead to improved tools for biomarker analysis and diagnosis. Analysis on larger and prospective datasets are to be conducted in the future to strengthen the findings. Clinical trial identification All of these results have been generated retrospectively from samples unrelated to a trial or related to the durvalumab-trial NCT01693562. Legal entity responsible for the study The authors. Funding Boehringer Ingelheim, MedImmune, Definiens AG. Disclosure M. Groher: Full / Part-time employment: Definiens AG. J. Zimmermann: Shareholder / Stockholder / Stock options: AstraZeneca; Full / Part-time employment: Definiens AG. H. Musa: Full / Part-time employment: Boehringer Ingelheim. A. Ackermann: Full / Part-time employment: Boehringer Ingelheim. M. Surace: Shareholder / Stockholder / Stock options, Full / Part-time employment: AstraZeneca. J. Rodriguez-Canales: Shareholder / Stockholder / Stock options, Full / Part-time employment: AstraZeneca. M. Rebelatto: Shareholder / Stackeholder / Stock options: AstraZenec LLC; Full / Part-time employment: AstraZeneca LLC. K. Steele: Shareholder / Stockholder / Stock options, Full / Part-time employment: AstraZeneca; Spouse / Financial dependant: Arcellx LLC. A. Kapil: Full / Part-time employment: Definiens AG. N. Brieu: Shareholder / Stockholder / Stock options, Full / Part-time employment: Definiens AG. L. Rognoni: Full / Part-time employment: Definiens AG. F. Segerer: Full / Part-time employment: Definiens AG. A. Spitzmuller: Full / Part-time employment: Definiens AG. T. Tan: Full / Part-time employment: Definiens AG. A. Schape: Full / Part-time employment: Definiens AG. G. Schmidt: Full / Part-time employment: Definiens AG; Shareholder / Stockholder / Stock options: AstraZeneca.