Deep learning in spatial transcriptomics: Learning from the next next-generation sequencing

Computational Strategies and Algorithms for Inferring Cellular Composition of Spatial Transcriptomics Data

Spatial transcriptomics technology has been an essential and powerful method for delineating tissue architecture at the molecular level. However, due to the limitations of the current spatial techniques, the cellular information cannot be directly measured but instead spatial spots typically varying from a diameter of 0.2 to 100 µm are characterized. Therefore, it is vital to apply computational strategies for inferring the cellular composition within each spatial spot. The main objective of this review is to summarize the most recent progresses in estimating the exact cellular proportions for each spatial spot, and to prospect the future directions of this field.

ST-SCSR: identifying spatial domains in spatial transcriptomics data via structure correlation and self-representation

Recent advances in spatial transcriptomics (ST) enable measurements of transcriptome within intact biological tissues by preserving spatial information, offering biologists unprecedented opportunities to comprehensively understand tissue micro-environment, where spatial domains are basic units of tissues. Although great efforts are devoted to this issue, they still have many shortcomings, such as ignoring local information and relations of spatial domains, requiring alternatives to solve these problems. Here, a novel algorithm for spatial domain identification in Spatial Transcriptomics data with Structure Correlation and Self-Representation (ST-SCSR), which integrates local information, global information, and similarity of spatial domains. Specifically, ST-SCSR utilzes matrix tri-factorization to simultaneously decompose expression profiles and spatial network of spots, where expressional and spatial features of spots are fused via the shared factor matrix that interpreted as similarity of spatial domains. Furthermore, ST-SCSR learns affinity graph of spots by manipulating expressional and spatial features, where local preservation and sparse constraints are employed, thereby enhancing the quality of graph. The experimental results demonstrate that ST-SCSR not only outperforms state-of-the-art algorithms in terms of accuracy, but also identifies many potential interesting patterns.

Deep learning in spatially resolved transcriptfomics: a comprehensive technical view

Spatially resolved transcriptomics (SRT) is a pioneering method for simultaneously studying morphological contexts and gene expression at single-cell precision. Data emerging from SRT are multifaceted, presenting researchers with intricate gene expression matrices, precise spatial details and comprehensive histology visuals. Such rich and intricate datasets, unfortunately, render many conventional methods like traditional machine learning and statistical models ineffective. The unique challenges posed by the specialized nature of SRT data have led the scientific community to explore more sophisticated analytical avenues. Recent trends indicate an increasing reliance on deep learning algorithms, especially in areas such as spatial clustering, identification of spatially variable genes and data alignment tasks. In this manuscript, we provide a rigorous critique of these advanced deep learning methodologies, probing into their merits, limitations and avenues for further refinement. Our in-depth analysis underscores that while the recent innovations in deep learning tailored for SRT have been promising, there remains a substantial potential for enhancement. A crucial area that demands attention is the development of models that can incorporate intricate biological nuances, such as phylogeny-aware processing or in-depth analysis of minuscule histology image segments. Furthermore, addressing challenges like the elimination of batch effects, perfecting data normalization techniques and countering the overdispersion and zero inflation patterns seen in gene expression is pivotal. To support the broader scientific community in their SRT endeavors, we have meticulously assembled a comprehensive directory of readily accessible SRT databases, hoping to serve as a foundation for future research initiatives.

Spatial transcriptomic analysis of the mouse brain following chronic social defeat stress

Depression is a highly prevalent and disabling mental disorder, involving numerous genetic changes that are associated with abnormal functions in multiple regions of the brain. However, there is little transcriptomic-wide characterization of chronic social defeat stress (CSDS) to comprehensively compare the transcriptional changes in multiple brain regions. Spatial transcriptomics (ST) was used to reveal the spatial difference of gene expression in the control, resilient (RES) and susceptible (SUS) mouse brains, and annotated eight anatomical brain regions and six cell types. The gene expression profiles uncovered that CSDS leads to gene synchrony changes in different brain regions. Then it was identified that inhibitory neurons and synaptic functions in multiple regions were primarily affected by CSDS. The brain regions Hippocampus (HIP), Isocortex, and Amygdala (AMY) present more pronounced transcriptional changes in genes associated with depressive psychiatric disorders than other regions. Signalling communication between these three brain regions may play a critical role in susceptibility to CSDS. Taken together, this study provides important new insights into CSDS susceptibility at the ST level, which offers a new approach for understanding and treating depression.

The Development of Plant Genome Sequencing Technology and Its Conservation and Application in Endangered Gymnosperms

Genome sequencing is widely recognized as a fundamental pillar in genetic research and legal studies of biological phenomena, providing essential insights for genetic investigations and legal analyses of biological events. The field of genome sequencing has experienced significant progress due to rapid improvements in scientific and technological developments. These advancements encompass not only significant improvements in the speed and quality of sequencing but also provide an unparalleled opportunity to explore the subtle complexities of genomes, particularly in the context of rare species. Such a wide range of possibilities has successfully supported the validation of plant gene functions and the refinement of precision breeding methodologies. This expanded scope now includes a comprehensive exploration of the current state and conservation efforts of gymnosperm gene sequencing, offering invaluable insights into their genomic landscapes. This comprehensive review elucidates the trajectory of development and the diverse applications of genome sequencing. It encompasses various domains, including crop breeding, responses to abiotic stress, species evolutionary dynamics, biodiversity, and the unique challenges faced in the conservation and utilization of gymnosperms. It highlights both ongoing challenges and the unveiling of forthcoming developmental trajectories.

Inferring Cell-Cell Communications from Spatially Resolved Transcriptomics Data Using a Bayesian Tweedie Model

Cellular communication through biochemical signaling is fundamental to every biological activity. Investigating cell signaling diffusions across cell types can further help understand biological mechanisms. In recent years, this has become an important research topic as single-cell sequencing technologies have matured. However, cell signaling activities are spatially constrained, and single-cell data cannot provide spatial information for each cell. This issue may cause a high false discovery rate, and using spatially resolved transcriptomics data is necessary. On the other hand, as far as we know, most existing methods focus on providing an ad hoc measurement to estimate intercellular communication instead of relying on a statistical model. It is undeniable that descriptive statistics are straightforward and accessible, but a suitable statistical model can provide more accurate and reliable inference. In this way, we propose a generalized linear regression model to infer cellular communications from spatially resolved transcriptomics data, especially spot-based data. Our BAyesian Tweedie modeling of COMmunications (BATCOM) method estimates the communication scores between cell types with the consideration of their corresponding distances. Due to the properties of the regression model, BATCOM naturally provides the direction of the communication between cell types and the interaction of ligands and receptors that other approaches cannot offer. We conduct simulation studies to assess the performance under different scenarios. We also employ BATCOM in a real-data application and compare it with other existing algorithms. In summary, our innovative model can fill gaps in the inference of cell-cell communication and provide a robust and straightforward result.

Boosting Single-Cell RNA Sequencing Analysis with Simple Neural Attention

A limitation of current deep learning (DL) approaches for single-cell RNA sequencing (scRNAseq) analysis is the lack of interpretability. Moreover, existing pipelines are designed and trained for specific tasks used disjointly for different stages of analysis. We present scANNA, a novel interpretable DL model for scRNAseq studies that leverages neural attention to learn gene associations. After training, the learned gene importance (interpretability) is used to perform downstream analyses (e.g., global marker selection and cell-type classification) without retraining. ScANNA's performance is comparable to or better than state-of-the-art methods designed and trained for specific standard scRNAseq analyses even though scANNA was not trained for these tasks explicitly. ScANNA enables researchers to discover meaningful results without extensive prior knowledge or training separate task-specific models, saving time and enhancing scRNAseq analyses.

Microsystem Advances through Integration with Artificial Intelligence

Microfluidics is a rapidly growing discipline that involves studying and manipulating fluids at reduced length scale and volume, typically on the scale of micro- or nanoliters. Under the reduced length scale and larger surface-to-volume ratio, advantages of low reagent consumption, faster reaction kinetics, and more compact systems are evident in microfluidics. However, miniaturization of microfluidic chips and systems introduces challenges of stricter tolerances in designing and controlling them for interdisciplinary applications. Recent advances in artificial intelligence (AI) have brought innovation to microfluidics from design, simulation, automation, and optimization to bioanalysis and data analytics. In microfluidics, the Navier-Stokes equations, which are partial differential equations describing viscous fluid motion that in complete form are known to not have a general analytical solution, can be simplified and have fair performance through numerical approximation due to low inertia and laminar flow. Approximation using neural networks trained by rules of physical knowledge introduces a new possibility to predict the physicochemical nature. The combination of microfluidics and automation can produce large amounts of data, where features and patterns that are difficult to discern by a human can be extracted by machine learning. Therefore, integration with AI introduces the potential to revolutionize the microfluidic workflow by enabling the precision control and automation of data analysis. Deployment of smart microfluidics may be tremendously beneficial in various applications in the future, including high-throughput drug discovery, rapid point-of-care-testing (POCT), and personalized medicine. In this review, we summarize key microfluidic advances integrated with AI and discuss the outlook and possibilities of combining AI and microfluidics.