Abstract 202P
Background
Spatial imaging of single cells and their protein markers in multiple tumor tissues offers detailed insights into the mechanisms of tumor-microenvironment interactions. The identification and characterization of cellular neighborhoods are vital to elucidating these mechanisms. However, existing approaches for cellular neighborhood analyses resort to predefined cell types or coarse, neighborhood-wide cell marker aggregations, failing to preserve the marker information at the single-cell level resolution.
Methods
We developed Cellohood - the first permutation-invariant, transformer-based autoencoder designed to model cellular neighborhoods explicitly. Cellohood compresses information about each cell and its marker expression for a given neighborhood, providing representations of the cellular neighborhoods. Based on these representations, we derived novel cellular neighborhood prototypes. Cell types, protein markers, and spatial arrangement patterns describe each identified prototype. Consequently, patients can be described by the abundance of cellular neighborhood prototypes and their mutual arrangements.
Results
We showcased the performance of Cellohood by applying it to the Imaging Mass Cytometry data from a non-small cell lung cancer (NSCLC) patient cohort (N=192) from the IMMUcan (Integrated iMMUnoprofiling of large adaptive CANcer patient cohorts) consortium. Prototypes discovered by Cellohood, including tumor neighborhoods characterized by i) low B2M expression, ii) IDO1+ tumor cells, iii) plasma cell enrichment, and iv) T-reg infiltration, defined patient clustering that surpassed the TNM cancer staging in terms of survival prediction. Analysis of macrophage-enriched neighborhoods indicated that CD206+ macrophages are a key differentiating factor between cancer histologies.
Conclusions
Thanks to transformer-based generative modeling, Cellohood is the first model to utilize complete cell marker information during training without resorting to coarse, neighborhood-wide approximation. Results on the NSCLC cohort from the IMMUcan consortium demonstrated that Cellohood enables marker-driven discovery of tumor-microenvironment interactions and their clinical implications.
Legal entity responsible for the study
IMMUcan (Integrated iMMUnoprofiling of large adaptive CANcer patient cohorts).
Funding
IMI2 JU grant agreement 821558, supported by EU’s Horizon 2020 and EFPIA.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
14P - Integrated modelling of T cell repertoires to identify clonotype signatures of ICI response
Presenter: Juan Luis Melero
Session: Poster Display
16P - Exosomal PD-L1 and lactate predict clinical outcomes of PD-1 blockade combined with chemotherapy in advanced-stage gastric and gastroesophageal junction adenocarcinoma
Presenter: Yongshun Chen
Session: Poster Display
17P - Spatial Characteristics Associated with the Chemo and Immuno-treatment Response of Gastric Cancer Revealed by Multi-omics Analysis
Presenter: Gang Che
Session: Poster Display
18P - Association of DNA methylation profiles with pathologic complete response in early triple negative breast cancer patients receiving neoadjuvant chemoimmunotherapy
Presenter: Angelika Starzer
Session: Poster Display
19P - The prognostic value of soluble CD73 in advanced triple-negative breast cancer: an exploratory analysis of the SYNERGY trial
Presenter: Denis Zoë
Session: Poster Display
21P - Mass cytometry reveals a population of exhausted CD8+ T cells associated with durvalumab/tremelimumab/vinorelbine efficacy in advanced cervical cancer (iMOVIE).
Presenter: Alexandre Bertucci
Session: Poster Display
22P - Predictive value of Tertiary Lymphoid Structure in patients with mismatch repair deficient advanced/ recurrent endometrial cancer treated with Dostarlimab.
Presenter: Maria Kfoury
Session: Poster Display
23P - Circulating immune cells and activity of immune checkpoint inhibitors in metastatic renal cell carcinoma
Presenter: Ronan Flippot
Session: Poster Display
24P - Chromosome 3p-related gene alterations (GA) as biomarkers for immunocombinations in metastatic renal cell carcinoma (mRCC): a hypothesis-generating analysis
Presenter: Matteo Rosellini
Session: Poster Display