Winnow-KAN: single-cell RNA-seq location recovery with small-gene-set spatial transcriptomics

Abstract Keywords: Cell mapping, Deep Learning, Kolmogorov-Arnold network, Single-cell RNA-seq, Spatial transcriptomics. Single-cell RNA sequencing (scRNA-seq) has revolutionized our understanding of cellular heterogeneity. However, its collection process prevents the investigation of tissue organiz...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuyang Zhang, Qihuang Zhang
Format: Article
Language:English
Published: BMC 2025-08-01
Series:BMC Bioinformatics
Subjects:
Online Access:https://doi.org/10.1186/s12859-025-06243-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235686826180608
author Yuyang Zhang
Qihuang Zhang
author_facet Yuyang Zhang
Qihuang Zhang
author_sort Yuyang Zhang
collection DOAJ
description Abstract Keywords: Cell mapping, Deep Learning, Kolmogorov-Arnold network, Single-cell RNA-seq, Spatial transcriptomics. Single-cell RNA sequencing (scRNA-seq) has revolutionized our understanding of cellular heterogeneity. However, its collection process prevents the investigation of tissue organization due to the lack of spatial origins for the cells. Recent advances in computational methods have addressed this gap by leveraging spatial transcriptomics, which simultaneously profiles gene expression and spatial coordinates. While these state-of-the-art methods demonstrate excellent performance in cell location recovery, their effectiveness is often specific to the particular pair of scRNA-seq and spatial transcriptomics datasets used, limiting their scalability to larger datasets and generalizability to external query scRNA-seq data. In this study, we demonstrate the feasibility of leveraging a novel model architecture to address the redundancy in scRNA-seq datasets and facilitate prediction with a much smaller set of genes. We present Winnow-KAN, a method designed to reduce the number of required gene variables in cell-mapping tasks. Built on a modified structure of the Kolmogorov-Arnold Network, Winnow-KAN leverages the Kolmogorov-Arnold Representation Theorem to facilitate location predictions using fewer features than those required by multi-layer perceptron-based methods. Winnow-KAN includes a selector layer that reduces the size of the gene set used for prediction, enabling the model to recover query scRNA-seq data with performance comparable to MLP-based approaches that rely on the full gene set. We benchmarked Winnow-KAN using multiple datasets generated from brain and cancer tissues, derived from platforms such as Visium and MERFISH.
format Article
id doaj-art-8c83fc39ca17453695ce9ea296aee2ea
institution Kabale University
issn 1471-2105
language English
publishDate 2025-08-01
publisher BMC
record_format Article
series BMC Bioinformatics
spelling doaj-art-8c83fc39ca17453695ce9ea296aee2ea2025-08-20T04:02:42ZengBMCBMC Bioinformatics1471-21052025-08-0126111710.1186/s12859-025-06243-9Winnow-KAN: single-cell RNA-seq location recovery with small-gene-set spatial transcriptomicsYuyang Zhang0Qihuang Zhang1Department of Epidemiology, Biostatistics and Occupational Health, McGill UniversityDepartment of Epidemiology, Biostatistics and Occupational Health, McGill UniversityAbstract Keywords: Cell mapping, Deep Learning, Kolmogorov-Arnold network, Single-cell RNA-seq, Spatial transcriptomics. Single-cell RNA sequencing (scRNA-seq) has revolutionized our understanding of cellular heterogeneity. However, its collection process prevents the investigation of tissue organization due to the lack of spatial origins for the cells. Recent advances in computational methods have addressed this gap by leveraging spatial transcriptomics, which simultaneously profiles gene expression and spatial coordinates. While these state-of-the-art methods demonstrate excellent performance in cell location recovery, their effectiveness is often specific to the particular pair of scRNA-seq and spatial transcriptomics datasets used, limiting their scalability to larger datasets and generalizability to external query scRNA-seq data. In this study, we demonstrate the feasibility of leveraging a novel model architecture to address the redundancy in scRNA-seq datasets and facilitate prediction with a much smaller set of genes. We present Winnow-KAN, a method designed to reduce the number of required gene variables in cell-mapping tasks. Built on a modified structure of the Kolmogorov-Arnold Network, Winnow-KAN leverages the Kolmogorov-Arnold Representation Theorem to facilitate location predictions using fewer features than those required by multi-layer perceptron-based methods. Winnow-KAN includes a selector layer that reduces the size of the gene set used for prediction, enabling the model to recover query scRNA-seq data with performance comparable to MLP-based approaches that rely on the full gene set. We benchmarked Winnow-KAN using multiple datasets generated from brain and cancer tissues, derived from platforms such as Visium and MERFISH.https://doi.org/10.1186/s12859-025-06243-9Cell mappingDeep learningKolmogorov-Arnold networkSingle-cell RNA-seqSpatial transcriptomics
spellingShingle Yuyang Zhang
Qihuang Zhang
Winnow-KAN: single-cell RNA-seq location recovery with small-gene-set spatial transcriptomics
BMC Bioinformatics
Cell mapping
Deep learning
Kolmogorov-Arnold network
Single-cell RNA-seq
Spatial transcriptomics
title Winnow-KAN: single-cell RNA-seq location recovery with small-gene-set spatial transcriptomics
title_full Winnow-KAN: single-cell RNA-seq location recovery with small-gene-set spatial transcriptomics
title_fullStr Winnow-KAN: single-cell RNA-seq location recovery with small-gene-set spatial transcriptomics
title_full_unstemmed Winnow-KAN: single-cell RNA-seq location recovery with small-gene-set spatial transcriptomics
title_short Winnow-KAN: single-cell RNA-seq location recovery with small-gene-set spatial transcriptomics
title_sort winnow kan single cell rna seq location recovery with small gene set spatial transcriptomics
topic Cell mapping
Deep learning
Kolmogorov-Arnold network
Single-cell RNA-seq
Spatial transcriptomics
url https://doi.org/10.1186/s12859-025-06243-9
work_keys_str_mv AT yuyangzhang winnowkansinglecellrnaseqlocationrecoverywithsmallgenesetspatialtranscriptomics
AT qihuangzhang winnowkansinglecellrnaseqlocationrecoverywithsmallgenesetspatialtranscriptomics