SC2Spa: a deep learning based approach to map transcriptome to spatial origins at cellular resolution

Abstract Background Understanding cellular heterogeneity within tissues hinges on knowledge of their spatial context. However, it is still challenging to accurately map cells to their spatial coordinates. Results We present SC2Spa, a deep learning-based approach that learns intricate spatial relatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Linbu Liao, Esha Madan, António M. Palma, Hyobin Kim, Amit Kumar, Praveen Bhoopathi, Robert Winn, Jose Trevino, Paul Fisher, Cord Herbert Brakebusch, Gahyun Kim, Junil Kim, Rajan Gogna, Kyoung Jae Won
Format: Article
Language:English
Published: BMC 2025-06-01
Series:BMC Bioinformatics
Subjects:
Online Access:https://doi.org/10.1186/s12859-025-06173-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849469911334649856
author Linbu Liao
Esha Madan
António M. Palma
Hyobin Kim
Amit Kumar
Praveen Bhoopathi
Robert Winn
Jose Trevino
Paul Fisher
Cord Herbert Brakebusch
Gahyun Kim
Junil Kim
Rajan Gogna
Kyoung Jae Won
author_facet Linbu Liao
Esha Madan
António M. Palma
Hyobin Kim
Amit Kumar
Praveen Bhoopathi
Robert Winn
Jose Trevino
Paul Fisher
Cord Herbert Brakebusch
Gahyun Kim
Junil Kim
Rajan Gogna
Kyoung Jae Won
author_sort Linbu Liao
collection DOAJ
description Abstract Background Understanding cellular heterogeneity within tissues hinges on knowledge of their spatial context. However, it is still challenging to accurately map cells to their spatial coordinates. Results We present SC2Spa, a deep learning-based approach that learns intricate spatial relationships from spatial transcriptomics (ST) data. Benchmarking tests show that SC2Spa outperformed other predictors and accurately detected tissue architecture from transcriptome. SC2Spa successfully mapped single cell RNA sequencing (scRNA-seq) to Visium assay, providing an approach to enhance the resolution for low resolution ST data. Our test showed that SC2Spa performs well for various ST technologies and robust to spatial resolution. In addition, SC2Spa can suggest spatially variable genes that cannot be identified from previous approaches. Conclusions SC2Spa is a robust and accurate approach to provide single cells with their spatial location and identify spatially meaningful genes.
format Article
id doaj-art-06952bec3ebf48d1bb2009f49b7ec212
institution Kabale University
issn 1471-2105
language English
publishDate 2025-06-01
publisher BMC
record_format Article
series BMC Bioinformatics
spelling doaj-art-06952bec3ebf48d1bb2009f49b7ec2122025-08-20T03:25:19ZengBMCBMC Bioinformatics1471-21052025-06-0126111910.1186/s12859-025-06173-6SC2Spa: a deep learning based approach to map transcriptome to spatial origins at cellular resolutionLinbu Liao0Esha Madan1António M. Palma2Hyobin Kim3Amit Kumar4Praveen Bhoopathi5Robert Winn6Jose Trevino7Paul Fisher8Cord Herbert Brakebusch9Gahyun Kim10Junil Kim11Rajan Gogna12Kyoung Jae Won13Biotech Research and Innovation Centre (BRIC), University of CopenhagenDepartment of Surgery, School of Medicine, Virginia Commonwealth UniversityDepartment of Surgery, School of Medicine, Virginia Commonwealth UniversityDepartment of Bioinformatics, Soongsil UniversityMassey Cancer Center, Virginia Commonwealth UniversityMassey Cancer Center, Virginia Commonwealth UniversityDepartment of Surgery, School of Medicine, Virginia Commonwealth UniversityDepartment of Surgery, School of Medicine, Virginia Commonwealth UniversityMassey Cancer Center, Virginia Commonwealth UniversityBiotech Research and Innovation Centre (BRIC), University of CopenhagenDepartment of Bioinformatics, Soongsil UniversityDepartment of Bioinformatics, Soongsil UniversityDepartment of Surgery, School of Medicine, Virginia Commonwealth UniversityDepartment of Computational Biomedicine, Cedars-Sinai Medical CenterAbstract Background Understanding cellular heterogeneity within tissues hinges on knowledge of their spatial context. However, it is still challenging to accurately map cells to their spatial coordinates. Results We present SC2Spa, a deep learning-based approach that learns intricate spatial relationships from spatial transcriptomics (ST) data. Benchmarking tests show that SC2Spa outperformed other predictors and accurately detected tissue architecture from transcriptome. SC2Spa successfully mapped single cell RNA sequencing (scRNA-seq) to Visium assay, providing an approach to enhance the resolution for low resolution ST data. Our test showed that SC2Spa performs well for various ST technologies and robust to spatial resolution. In addition, SC2Spa can suggest spatially variable genes that cannot be identified from previous approaches. Conclusions SC2Spa is a robust and accurate approach to provide single cells with their spatial location and identify spatially meaningful genes.https://doi.org/10.1186/s12859-025-06173-6Spatial transcriptomicsSpatial inferenceSpatial mappingDeep learningSpatially variable genes
spellingShingle Linbu Liao
Esha Madan
António M. Palma
Hyobin Kim
Amit Kumar
Praveen Bhoopathi
Robert Winn
Jose Trevino
Paul Fisher
Cord Herbert Brakebusch
Gahyun Kim
Junil Kim
Rajan Gogna
Kyoung Jae Won
SC2Spa: a deep learning based approach to map transcriptome to spatial origins at cellular resolution
BMC Bioinformatics
Spatial transcriptomics
Spatial inference
Spatial mapping
Deep learning
Spatially variable genes
title SC2Spa: a deep learning based approach to map transcriptome to spatial origins at cellular resolution
title_full SC2Spa: a deep learning based approach to map transcriptome to spatial origins at cellular resolution
title_fullStr SC2Spa: a deep learning based approach to map transcriptome to spatial origins at cellular resolution
title_full_unstemmed SC2Spa: a deep learning based approach to map transcriptome to spatial origins at cellular resolution
title_short SC2Spa: a deep learning based approach to map transcriptome to spatial origins at cellular resolution
title_sort sc2spa a deep learning based approach to map transcriptome to spatial origins at cellular resolution
topic Spatial transcriptomics
Spatial inference
Spatial mapping
Deep learning
Spatially variable genes
url https://doi.org/10.1186/s12859-025-06173-6
work_keys_str_mv AT linbuliao sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT eshamadan sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT antoniompalma sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT hyobinkim sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT amitkumar sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT praveenbhoopathi sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT robertwinn sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT josetrevino sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT paulfisher sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT cordherbertbrakebusch sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT gahyunkim sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT junilkim sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT rajangogna sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution
AT kyoungjaewon sc2spaadeeplearningbasedapproachtomaptranscriptometospatialoriginsatcellularresolution