Three-dimensional spatial transcriptomics (3D ST) enables the analysis of gene-expression patterns across tissue depths. However, 3D ST measurements are acquired from discrete 2D tissue sections, which are often sparsely sampled due to high acquisition costs. To address this limitation, we propose a histology-informed multi-task implicit neural representation (HIM-INR) for continuous 3D gene-expression reconstruction from sparse ST observations. HIM-INR jointly reconstructs gene-expression profiles and histological representations using an INR with a shared backbone, leveraging densely sampled histological images as auxiliary spatial supervision. Once trained, HIM-INR predicts gene expression at arbitrary 3D coordinates without requiring histological images. Experiments on two 3D ST datasets demonstrate improved reconstruction over existing methods, particularly as the number of missing ST sections increases.
Figures & tables
Figure 1: Overview of the proposed histology-informed multi-task INR (HIM-INR). Gene-expression profiles and histology image features are compressed into modality-specific latent spaces. A shared INR backbone with modality-specific heads and decoders reconstructs both modalities from 3D coordinates, enabling dense image-only sections to provide auxiliary spatial supervision between sparse ST observations.
Method
3DST-RA [ 15 ]
HemiBrainA [ 16 ]
HemiBrainB [ 16 ]
HVGs50
HVGs250
HVGs50
HVGs250
HVGs50
HVGs250
NN
0.1779
0.1385
0.0966
0.1240
0.0958
0.0741
KNN
0.2609
0.2148
0.1449
0.1921
0.1288
0.1114
STAGE [ 6 ]
0.2743
0.2041
0.2344
0.3095
0.1398
0.1525
3D-STINR [ 13 ]
0.2202
0.2425
0.1395
0.2113
0.1703
0.1453
3D-SUICA [ 14 ]
0.3409
0.3044
0.1883
0.2664
0.1518
0.1513
Table 1: Quantitative comparison of gene-expression reconstruction at withheld sections. PCC is computed on the top 50 and 250 HVGs and averaged over three random seeds. Best and second-best results are shown in bold and underlined, respectively.
Method
HIM
3DST-RA [ 15 ]
HemiBrainA [ 16 ]
HemiBrainB [ 16 ]
HVGs50
HVGs250
HVGs50
HVGs250
HVGs50
HVGs250
Ours w/o HIM
✗
0.3593
0.3054
0.2259
0.3052
0.1742
0.1645
Ours
✓
0.3711
0.3145
0.2253
0.3101
0.1824
0.1685
Table 2: Ablation study on histological supervision (HIM). PCC is evaluated on image-unavailable locations using the top 50 and 250 HVGs.
Figure 2: Effect of ST sparsity on HemiBrainA (top 50 HVGs). The number of missing ST sections between observed sections is varied from 3 to 7. Values above the bars indicate the PCC differences between Ours and Ours w/o HIM (Ours − Ours w/o HIM).
Method
3DST-RA [ 15 ]
HemiBrainA [ 16 ]
HemiBrainB [ 16 ]
UNI2-h+LP
0.2726
0.2744
0.1646
Ours
0.3145
0.3101
0.1685
Table 3: Comparison with oracle image-based prediction (UNI2-h+LP), which uses true histological images at the evaluation sections. PCC is evaluated on the top 250 HVGs.
Spatial transcriptomics (ST) provides spatially resolved gene expression measurements, but most 3D ST datasets are acquired as independently processed 2D sections. Computational approaches span slice registration and integration, explicit or generative interpolation, and coordinate-field modeling. Within the last family, implicit neural representations (INRs) offer a continuous, coordinate-queryable parameterization, but standard isotropic coordinate encodings do not explicitly reflect that serial-section measurements are dense in-plane and sparse along the axial direction. We present HoloGene, an anisotropic conditional INR framework for estimating continuous 3D gene-expression fields from pre-registered ST sections. Its central contribution is an acquisition-aware factorization that couples dense in-plane synthesis with sparse axial evolution using established GAE, FiLM, pseudo-label supervision, and CORAL components. HoloGene compresses high-dimensional expression profiles into a graph-autoencoder latent manifold, uses pseudo-label-derived signature conditioning to provide coarse intra-section context, and applies depth-dependent FiLM modulation to model axial variation. A signature-stratified correlation-alignment regularizer encourages cross-slice covariance alignment in latent features. Using held-out measured sections as cross-sectional references, HoloGene improves reconstruction accuracy and biological preservation metrics compared with general-purpose INRs and adapted spatial-transcriptomics baselines. These results support anisotropic conditional modeling as a practical strategy for estimating 3D expression fields from discontinuous ST sections. Code is available at https://github.com/Szym29/HoloGene.
Yumin Zheng, Qingtian Zhu, Ziyan Zhu +3
McGill University · MUHC Research Institute · The University of Tokyo +2
A 3D transcriptomic profile of a tissue can give a holistic view of its organization in health and disease, but spatial transcriptomics (ST) is costly, so usually only some serial sections are profiled, while H&E is available for all. Most methods that infer ST from histology treat each section independently and ignore 3D structure, while existing 3D-aware approaches are not generative and do not scale well. We present Holographic Tissue Expression Inpainting and Analysis (HoloTea), a 3D-aware flow-matching framework that imputes spot-level gene expression on an unprofiled section from its H&E and the measured expression of adjacent profiled sections. Our key idea is to take the measured expression at the same registered position on neighboring sections and feed this cross-section context to the flow model through a lightweight ControlNet, so that predictions follow anatomical continuity along z. To capture the discrete, zero-inflated nature of counts, the flow starts from a learned zero-inflated negative binomial (ZINB) prior that, on an unprofiled section, is predicted from the measured expression of the nearest profiled section. A global attention block with a small set of inducing tokens adds whole-slide context at a cost linear in the number of spots, so training and inference scale to large 3D ST datasets. Across three ST datasets spanning different tissue types and resolutions, HoloTea consistently improves 3D expression accuracy and generalization compared to 2D and 3D baselines. We envision HoloTea advancing the creation of accurate 3D virtual tissues, ultimately accelerating biomarker discovery and deepening our understanding of disease. Code is available at https://github.com/Lotfollahi-lab/HoloTea.
Mohammad Vali Sanian, Arshia Hemmat, Amirhossein Vahidi +10
Computer Science Department, University of Helsinki · Institute for Molecular Medicine Finland, University of Helsinki · Wellcome Sanger Institute +4
Spatial transcriptomics (ST) enables joint characterization of tissue morphology and gene expression. However, 3D volumetric ST acquisition remains expensive. AI-driven methods offer a low-cost alternative but remain limited in accuracy, while recent 2D section-wise ST acquisition still rely on dense grid sampling, resulting in redundant measurements and undersampling of biologically informative regions. To bridge the gap, we propose STRATA, a reinforcement-driven active sampling framework with tri-paradigm adaptation for reconstructing dense 3D transcriptomic maps from sparse voxel-wise ST acquisition. STRATA constructs a 3D graph integrating H&E morphology with single-cell priors and employs a reinforcement learning agent to estimate morphological sparsity and transcriptomic informativeness, enabling budget-aware selection of informative spots. Given these sparse measurements, an adaptive tri-paradigm predictor combines retrieval, regression, and cross-layer imputation through lightweight fusion, dynamically weighting their contributions. Experiments across datasets demonstrate improved sampling efficiency and accuracy, particularly under low-budget settings. Code is available at https://github.com/Junchao-Zhu/STRATA.
Junchao Zhu, Ruining Deng, Chongyu Qu +7
Vanderbilt University, Tennessee, USA · Weill Cornell Medicine, New York, USA · Vanderbilt University Medical Center, Tennessee, USA