Explainable multi-task learning for multi-modality biological data analysis

Abstract

Current biotechnologies can simultaneously measure multiple high-dimensional modalities (e.g., RNA, DNA accessibility, and protein) from the same cells. A combination of different analytical tasks (e.g., multi-modal integration and cross-modal analysis) is required to comprehensively understand such data, inferring how gene regulation drives biological diversity and functions. However, current analytical methods are designed to perform a single task, only providing a partial picture of the multi-modal data. Here, we present UnitedNet, an explainable multi-task deep neural network capable of integrating different tasks to analyze single-cell multi-modality data. Applied to various multi-modality datasets (e.g., Patch-seq, multiome ATAC + gene expression, and spatial transcriptomics), UnitedNet demonstrates similar or better accuracy in multi-modal integration and cross-modal prediction compared with state-of-the-art methods. Moreover, by dissecting the trained UnitedNet with the explainable machine learning algorithm, we can directly quantify the relationship between gene expression and other modalities with cell-type specificity. UnitedNet is a comprehensive end-to-end framework that could be broadly applicable to single-cell multi-modality biology. This framework has the potential to facilitate the discovery of cell-type-specific regulation kinetics across transcriptomics and other modalities.

A deep generative model integrating single-cell time-frequency characteristics transformed from electrophysiological data with transcriptomic features

“…This suggests that some groups of cells exhibited consistent e-features among the cell types. The heterogeneity of the e-features can be associated with the finer subtypes of each cell type 8 . Moreover, we discovered that both excitatory and inhibitory cell types were included in the same cluster, consistent with the findings from a previous study 11 ; for these cell types, we observed continuous changes in the e-features of glutamatergic and GABAergic neurons in the primary motor cortex of mice.…”

IOBR2: Multidimensional Decoding Tumor Microenvironment for Immuno-Oncology Research

“…By integrating and analyzing multi-omic data, including transcriptomics, single-cell, and genomics, we can dissect the underlying gene regulatory mechanisms and unveil the landscape of the tumor microenvironment. This deepens our understanding of the interactions and biological mechanisms between immune and tumor cells [31,32]. However, the complexity and growing volume of multi-omics data introduce new opportunities and challenges in analyzing the tumor microenvironment.…”

A mini-review on perturbation modelling across single-cell omic modalities

“…Contextualising affinities among latent representation learning with other pivotal tasks in single-cell analysis like GRN inference, cell clustering, multi-modal inference could be a viable way to allow DL architectures to capture better the systemic changes that a perturbation can confer across diverse cell populations. Recent tools like UnitedNet [83] , adopted in a perturbational landscape, could be highly informative for better future inferences of multi-modal Perturb-seq models.…”