RECON infers regions of interest from H&E images and reconstructs whole-slide molecular profiles at single-cell resolution
- 1The University of Chicago
Abstract
Spatial omics technologies resolve molecular expression and spatial architecture at single-cell resolution, but profiling whole slides remains costly. In practice, only a few regions of interest (ROIs) are profiled, leaving the rest of the tissue unmeasured. S2-omics was the first framework to unify ROI selection with out-of-ROI prediction, but it operates on superpixels rather than individual cells and predicts discrete cell types rather than continuous molecular profiles. Superpixel-based representations do not explicitly preserve cell boundaries, while categorical cell-type labels cannot quantify molecular expression within cells. Here we present RECON, a two-stage framework that performs ROI inference and whole-slide molecular reconstruction at single-cell resolution, predicting both continuous molecular profiles and discrete cell-type labels. In the first stage, RECON extracts morphological and microenvironmental features from individual cells to identify a representative ROI for spatially resolved single-cell molecular profiling. In the second stage, RECON trains deep learning models on molecular measurements acquired within the selected ROI and reconstructs transcriptomic or proteomic profiles for all remaining cells on the slide. Benchmarked against pathologist annotations, RECONs ROI selection outperforms the superpixel-based S2-omics approaches (IoU: 0.75 versus 0.64). For transcriptomics, refining the modeling unit from superpixels to single cells improves per-gene Pearson correlation by 22%. For proteomics, RECON surpasses the current state-of-the-art method, ROSIE, across all 16 markers, with a median per-cell Pearson correlation of 0.91 versus 0.84. Moreover, RECON delineates tumour boundaries and regions with distinct immune-cell densities, and highlights candidate tertiary lymphoid structures. Together, these results demonstrate that RECON enables informative ROI selection and whole-slide molecular reconstruction at single-cell resolution for both spatial transcriptomics and spatial proteomics.
Related
- Refining RNA-Seq Transcriptome Profiles with Transcript-Specific Minimal-Shared Regions
- High-Resolution Melting (HRM) Assay for Molecular Detection of Calonectria ilicicola in Soybean
- Joint recording of past and present transcriptomes reconstructs single-cell trajectories
- scMTG reconstructs single-cell temporal dynamics with Markov transition generators
- LOTUS: lineage-aware optimal transport reconstructs continuous clonal fate dynamics
BibTeX
@misc{yang2026recon,
title = {{RECON infers regions of interest from H&E images and reconstructs whole-slide molecular profiles at single-cell resolution}},
author = {X. Yang and N. Hao and R. Zhao and S. Angel and Y. Tan and C. G. Lian and L. Zhou and D. Olson and K.-H. Yu and A. Ruiz de Luzuriaga and G. Wan},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.25.747122},
url = {https://www.biorxiv.org/content/10.64898/2026.08.25.747122v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - RECON infers regions of interest from H&E images and reconstructs whole-slide molecular profiles at single-cell resolution
AU - X. Yang
AU - N. Hao
AU - R. Zhao
AU - S. Angel
AU - Y. Tan
AU - C. G. Lian
AU - L. Zhou
AU - D. Olson
AU - K.-H. Yu
AU - A. Ruiz de Luzuriaga
AU - G. Wan
PY - 2026
DA - 2026/08/25
PB - bioRxiv
DO - 10.64898/2026.08.25.747122
UR - https://www.biorxiv.org/content/10.64898/2026.08.25.747122v1
AB - Spatial omics technologies resolve molecular expression and spatial architecture at single-cell resolution, but profiling whole slides remains costly. In practice, only a few regions of interest (ROIs) are profiled, leaving the rest of the tissue unmeasured. S2-omics was the first framework to unify ROI selection with out-of-ROI prediction, but it operates on superpixels rather than individual cells and predicts discrete cell types rather than continuous molecular profiles. Superpixel-based representations do not explicitly preserve cell boundaries, while categorical cell-type labels cannot quantify molecular expression within cells. Here we present RECON, a two-stage framework that performs ROI inference and whole-slide molecular reconstruction at single-cell resolution, predicting both continuous molecular profiles and discrete cell-type labels. In the first stage, RECON extracts morphological and microenvironmental features from individual cells to identify a representative ROI for spatially resolved single-cell molecular profiling. In the second stage, RECON trains deep learning models on molecular measurements acquired within the selected ROI and reconstructs transcriptomic or proteomic profiles for all remaining cells on the slide. Benchmarked against pathologist annotations, RECONs ROI selection outperforms the superpixel-based S2-omics approaches (IoU: 0.75 versus 0.64). For transcriptomics, refining the modeling unit from superpixels to single cells improves per-gene Pearson correlation by 22%. For proteomics, RECON surpasses the current state-of-the-art method, ROSIE, across all 16 markers, with a median per-cell Pearson correlation of 0.91 versus 0.84. Moreover, RECON delineates tumour boundaries and regions with distinct immune-cell densities, and highlights candidate tertiary lymphoid structures. Together, these results demonstrate that RECON enables informative ROI selection and whole-slide molecular reconstruction at single-cell resolution for both spatial transcriptomics and spatial proteomics.
ER -