MultiCapsNet: a interpretable deep learning classifier integrate data from multiple sources

Wang, L.; Miao, X.; Zhang, J.; Cai, J.

doi:10.1101/570507

Home/Archive/bioRxiv

bioRxiv · 10.1101/570507

MultiCapsNet: a interpretable deep learning classifier integrate data from multiple sources

Wang, L.·Miao, X.·Zhang, J.·Cai, J.

View original source ↗Export metadata ↓

Abstract

Recent advances in experimental biology have generated huge amount of data. Due to differences present in detection targets and detection mechanisms, the produced data comes with different formats and lengths. There is an urgent call for computational methods to integrate these diverse data. Deep learning model is an ideal tool to cope with complex datasets, but its inherent black box nature needs more interpretability. Here, we present MultiCapsNet, a deep learning model built on CapsNet and scCapsNet. The MultiCapsNet model possesses the merits of both easier data integration and higher model interpretability. In the first example, we use the labeled variant call dataset, which is originally used to test the models for automating somatic variant refinement. We divide the 71 features listed in the dataset into eight groups according to data source and data property. Then, the data from those eight groups with different formats and lengths are integrated by our MultiCapsNet to predict the labels associated with each variant call. The performance of our MultiCapsNet matches the previous deep learning model well, given much less parameters than those needed by the previous model. After training, the MultiCapsNet model provides importance scores for each data source directly, while the previous deep learning model needs an extra importance determination step to do so. Despite that our MultiCapsNet model is substantially different from the previous deep learning model and the source importance measuring methods are also different, the importance score correlation between these two models is very high. In the second example, the prior knowledge, including information for protein-protein interactions and protein-DNA interactions, is used to determine the structure of MultiCapsNet model. The single cell RNA sequence data are decoupled into multiple parts according to the structure of MultiCapsNet model that has been integrated with prior knowledge, with each part represents genes influenced by a transcription factor or involved in a protein-protein interaction network and then could be viewed as a data source. The MultiCapsNet model could classify cells with high accuracy as well as reveal the contribution of each data source for cell type recognition. The high ranked contributors are often relevant to the contributed cell type.

Explore related subjects

bioinformatics Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Wang, L., Miao, X., Zhang, J., Cai, J.. 2019-03-07. MultiCapsNet: a interpretable deep learning classifier integrate data from multiple sources. https://doi.org/10.1101/570507

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

spatialMET: an open and scalable framework for spatial metabolomics analysis

Mass spectrometry imaging (MSI) enables spatially resolved metabolomics in intact tissue sections, but analysis remains challenging at scale. Existing MSI workflows often require users to combine multiple software tools, while others rely on proprietary vendor software that limits interoperability and reproducibility. To address these challenges, we developed spatialMET, an open-source framework that provides an end-to-end workflow for MSI analysis. spatialMET provides a unified platform for preprocessing, spatial domain detection, and visualization. Downstream analyses include differential abundance testing, spatial autocorrelation and gradient analysis, dimensionality reduction, and correlation network analysis. Spatial domain detection uses hcdist, a C-based hierarchical clustering implementation that substantially reduces runtime and memory use relative to existing R-based approaches. spatialMET can be run through an interactive R Shiny application or as a standalone command-line workflow for larger datasets or high-performance computing environments. Applied to mouse small cell lung cancer MALDI-MSI data containing 284,673 pixels, spatialMET identified tumor-associated, stromal, and adjacent lung spatial domains that aligned with matched histology. Differential abundance analysis identified 117 m/z features that differed between tumor and stromal regions, while spatial autocorrelation analyses revealed spatially structured abundance patterns. Applying spatialMET to mouse lung adenocarcinoma data from an entire lung lobe containing 338,477 pixels further demonstrated scalability and captured spatial heterogeneity across tumor and surrounding lung tissue. In summary, spatialMET provides a scalable, open-source framework for end-to-end spatial metabolomics analysis, and it is distributed as a Docker container for reproducible deployment. Source code and installation instructions are available at https://github.com/biodatalab/spatialMET.

bioinformatics↗

bioRxiv2026

Probing the transcriptome response to shivering in skeletal muscle using a multilayered bioinformatics approach

Cold acclimation holds therapeutic potential for improving metabolic health. We previously demonstrated that repeated cold-induced shivering enhances insulin sensitivity in humans. However, the molecular pathways that underlie the skeletal muscle shivering response, and how these relate to beneficial physiological effects, remain poorly understood. In this study, we combined complementary bioinformatics approaches to allow in-depth analysis of the transcriptomic response of human skeletal muscle to repeated shivering. We identified a robust transcriptional signature and show a sex-specific component in the shivering skeletal muscle response, which seemed to diminish following cold adaptation. Our findings provide mechanistic insights into cold-induced muscle adaptations, shed light on potential interesting molecular targets for further investigation, and emphasize the importance of including both sexes in future cold acclimation studies.

bioinformatics↗

bioRxiv2026

An Information Geometry approach to model topological trajectories and Gene Expression Radius from UMAP geometry.

Understanding the relationship between gene expression dynamics and cellular identity remains a central challenge in single cell biology. Here, we introduce a novel computational and mathematical framework that integrates information geometry, fuzzy topology, and UMAP analysis to model gene expression landscapes derived from single cell RNA sequencing data. We formalize gene expression data as a fuzzy topological space, where interactions between expression points are governed by probabilistic distributions inspired by manifold learning approaches such as UMAP. Within this framework, we define an information geometric structure through a Fisher metric induced by these distributions, enabling the computation of geodesic trajectories that capture cellular differentiation processes. A key contribution of this work is the derivation of analytical conditions, expressed as expression radius formulas, that characterize local neighborhoods in gene expression space. These conditions allow for the identification of genes associated with stem cell states and predictions in transitional cell types in future work. Application of the proposed framework to single cell datasets reveals biologically meaningful gene sets enriched in key regulatory pathways and transcription factors, demonstrating the capacity of our approach to uncover latent structure in complex gene expression data. Our results suggest that integrating differential geometry with statistical learning theory offers a powerful paradigm for modeling genotype and phenotype relationships and cellular state transitions, with potential implications for precision medicine and systems biology.

bioinformatics↗