What question did this study set out to answer?

This research aims to develop a deep learning framework that predicts multiplex protein markers from standard H&E slides for various cancers.

April 5, 2026

Abstract 85: Path2Marker: Cell-level prediction of multiplex protein expression from routine H&E slides.

Key Points

This research aims to develop a deep learning framework that predicts multiplex protein markers from standard H&E slides for various cancers.
Analyzed three cancer-specific cohorts with paired H&E and multiplex immunofluorescence.
Developed cancer-specific models to predict protein marker intensities from H&E slides.
Evaluated model performance using Pearson correlation on held-out samples.
Robustly predicted 23, 26, and 44 markers in breast, lung, and colorectal cancers, respectively.
Outperformed existing tools like ROSIE, which achieved fewer markers in comparison.
Top markers included EpCAM with r=0.79 and PanCK with r=0.73, enabling detailed cell-type annotation.

Abstract

Abstract Background: High-plex spatial proteomics platforms (e.g., PhenoCycler) have transformed our ability to map the tumor microenvironment (TME) at single-cell resolution, but their cost constrains cohort sizes for biomarker discovery and validation. Recently, ROSIE (Wu et al., Nat Commun 2025) aimed to tackle this problem by predicting protein markers directly from H 396,995 cells), using Pearson correlation between the measured and predicted marker intensities. Results: We robustly predict (Pearson r 0.4 for measured vs. predicted intensity) 23, 26, and 44 markers in the breast, lung and colorectal cohorts, respectively, markedly outperforming the published state of the art. When benchmarked on the same samples, ROSIE achieved fewer robustly predicted markers, with only 3 markers in colon, 2 in lung and 0 in breast. The ensemble model significantly improved mean marker-level correlation in lung and was comparable to the indication-specific models in breast and colorectal cancer. Top-performing markers included EpCAM in colon (r=0.79), PanCK in lung (r=0.73), and PanCK in breast (r=0.64). Notably, they include not only lineage markers (e.g., PanCK, CD3e) but also functional markers (e.g., PD-L1, Ki-67), enabling downstream cell-state and cell-type annotation, laying the basis for robust annotation of 25, 16, and 17 different cell-types in colon, lung, and breast, respectively. Conclusion: Path2Marker enables robust prediction of more than 20 multiplex protein markers at single-cell, spatial resolution directly from standard H Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 85.

اسأل الذكاء الاصطناعي

Bookmark