Deep Learning in Spatial Transcriptomics: Learning From the Next Next-Generation Sequencing

Abstract

Spatial transcriptomics (ST) technologies are rapidly becoming the extension of single-cell RNA sequencing (scRNAseq), holding the potential of profiling gene expression at a single-cell resolution while maintaining cellular compositions within a tissue. Having both expression profiles and tissue organization enables researchers to better understand cellular interactions and heterogeneity, providing insight into complex biological processes that would not be possible with traditional sequencing technologies. The data generated by ST technologies are inherently noisy, high-dimensional, sparse, and multi-modal (including histological images, count matrices, etc.), thus requiring specialized computational tools for accurate and robust analysis. However, many ST studies currently utilize traditional scRNAseq tools, which are inadequate for analyzing complex ST datasets. On the other hand, many of the existing ST-specific methods are built upon traditional statistical or machine learning frameworks, which have shown to be sub-optimal in many applications due to the scale, multi-modality, and limitations of spatially-resolved data (such as spatial resolution, sensitivity and gene coverage). Given these intricacies, researchers have developed deep learning (DL)-based models to alleviate ST-specific challenges. These methods include new state-of-the-art models in alignment, spatial reconstruction, and spatial clustering among others. However, deep-learning models for ST analysis are nascent and remain largely underexplored. In this review, we provide an overview of existing state-of-the-art tools for analyzing spatially-resolved transcriptomics, while delving deeper into the DL-based approaches. We discuss the new frontiers and the open questions in this field and highlight the domains in which we anticipate transformational DL applications.

N-ACT: An Interpretable Deep Learning Model for Automatic Cell Type and Salient Gene Identification

“…Given that the cell types are not known a priori , labels must be generated before training the DL core. To do so, we choose to perform unsupervised clustering using the Leiden algorithm (Traag et al, 2019), a standard scRNAseq clustering technique in many pipelines (Heydari & Sindi, 2022), allowing label generation without supervision. All results shown in this section follow this approach.…”

“…We included a mouse dataset to demonstrate our model can be effectively used on non-human and non-immune datasets. All datasets were generated using the 10x Genomics platform (see (Goodwin et al, 2016; Heydari & Sindi, 2022) for a review of next-generation scRNAseq). A summary for each dataset is provided in subsequent subsections (see Fig.…”

Deep Learning in Diverse Intelligent Sensor Based Systems

“…For example, a RAN-based solution for detecting long ncRNAs achieved a remarkable 99% accuracy [ 300 ]. For comprehensive introductions and discussions we refer to various survey papers [ 301 , 302 ].…”

TissUUmaps 3: Improvements in interactive visualization, exploration, and quality assessment of large-scale spatial omics data

“…During the past years, several new methods for analyzing 2 ST data have emerged. For example, tools for cell segmentation, identification of spatially variable genes, cell typing, data imputation, and analyses of cellcell interactions, as summarized in [19,23]. A deeper biological understanding of the results produced by these methods can be done with the help of visual inspection.…”