SiGra: single-cell spatial elucidation through an image-augmented graph transformer

Unveiling fine-scale spatial structures and amplifying gene expression signals in ultra-large ST slices with HERGAST

We propose HERGAST, a system for spatial structure identification and signal amplification in ultra-large-scale and ultra-high-resolution spatial transcriptomics data. To handle ultra-large spatial transcriptomics (ST) data, we consider the divide and conquer strategy and devise a Divide-Iterate-Conquer framework especially for spatial transcriptomics data analysis, which can also be adopted by other computational methods for extending to ultra-large-scale ST data analysis. To tackle the potential over-smoothing problem arising from data splitting, we construct a heterogeneous graph network to incorporate both local and global spatial relationships. In simulations, HERGAST consistently outperforms other methods across all settings with more than a 10% increase in average adjusted rand index (ARI). In real-world datasets, HERGAST's high-precision spatial clustering identifies SPP1+ macrophages intermingled within colorectal tumors, while the enhanced gene expression signals reveal unique spatial expression patterns of key genes in breast cancer.

Spatially informed graph transformers for spatially resolved transcriptomics

Spatially resolved transcriptomics (SRT) has emerged as a powerful technique for mapping gene expression landscapes within spatial contexts. However, significant challenges persist in effectively integrating gene expression with spatial information to elucidate the heterogeneity of biological tissues. Here, we present a Spatially informed Graph Transformers framework, SpaGT, which leverages both node and edge channels to model spatially aware graph representation for denoising gene expression and identifying spatial domains. Unlike conventional graph neural networks, which rely on static, localized convolutional aggregation, SpaGT employs a structure-reinforced self-attention mechanism that iteratively evolves topological structural information and transcriptional signal representation. By replacing graph convolution with global self-attention, SpaGT enables the integration of both global and spatially localized information, thereby improving the detection of fine-grained spatial domains. We demonstrate that SpaGT achieves superior performance in identifying spatial domains and denoising gene expression data across diverse platforms and species. Furthermore, SpaGT facilitates the discovery of spatially variable genes with significant prognostic potential in cancer tissues. These findings establish SpaGT as a powerful tool for unraveling the complexities of biological tissues.

Foundation models in bioinformatics

With the adoption of foundation models (FMs), artificial intelligence (AI) has become increasingly significant in bioinformatics and has successfully addressed many historical challenges, such as pre-training frameworks, model evaluation and interpretability. FMs demonstrate notable proficiency in managing large-scale, unlabeled datasets, because experimental procedures are costly and labor intensive. In various downstream tasks, FMs have consistently achieved noteworthy results, demonstrating high levels of accuracy in representing biological entities. A new era in computational biology has been ushered in by the application of FMs, focusing on both general and specific biological issues. In this review, we introduce recent advancements in bioinformatics FMs employed in a variety of downstream tasks, including genomics, transcriptomics, proteomics, drug discovery and single-cell analysis. Our aim is to assist scientists in selecting appropriate FMs in bioinformatics, according to four model types: language FMs, vision FMs, graph FMs and multimodal FMs. In addition to understanding molecular landscapes, AI technology can establish the theoretical and practical foundation for continued innovation in molecular biology.

Graph neural networks for single-cell omics data: a review of approaches and applications

Rapid advancement of sequencing technologies now allows for the utilization of precise signals at single-cell resolution in various omics studies. However, the massive volume, ultra-high dimensionality, and high sparsity nature of single-cell data have introduced substantial difficulties to traditional computational methods. The intricate non-Euclidean networks of intracellular and intercellular signaling molecules within single-cell datasets, coupled with the complex, multimodal structures arising from multi-omics joint analysis, pose significant challenges to conventional deep learning operations reliant on Euclidean geometries. Graph neural networks (GNNs) have extended deep learning to non-Euclidean data, allowing cells and their features in single-cell datasets to be modeled as nodes within a graph structure. GNNs have been successfully applied across a broad range of tasks in single-cell data analysis. In this survey, we systematically review 107 successful applications of GNNs and their six variants in various single-cell omics tasks. We begin by outlining the fundamental principles of GNNs and their six variants, followed by a systematic review of GNN-based models applied in single-cell epigenomics, transcriptomics, spatial transcriptomics, proteomics, and multi-omics. In each section dedicated to a specific omics type, we have summarized the publicly available single-cell datasets commonly utilized in the articles reviewed in that section, totaling 77 datasets. Finally, we summarize the potential shortcomings of current research and explore directions for future studies. We anticipate that this review will serve as a guiding resource for researchers to deepen the application of GNNs in single-cell omics.

Machine learning model for menstrual cycle phase classification and ovulation day detection based on sleeping heart rate under free-living conditions

The accurate classification of menstrual cycle phases and detection of ovulation is critical for women's health management, particularly in addressing infertility, alleviating premenstrual syndrome, and preventing hormone-related disorders. However, traditional basal body temperature (BBT) measurement methods are susceptible to disruptions in sleep timing and environmental conditions, limiting practical application. This study is aimed to overcome these limitations by introducing a novel feature, heart rate at the circadian rhythm nadir (minHR), for classifying menstrual cycle phases and predicting ovulation. A machine learning model was developed using XGBoost, and data were collected under free-living conditions from 40 healthy women (18-34 years) over a maximum of three menstrual cycles. Three feature combinations- "day," "day + minHR," and "day + BBT"-were evaluated, and model performance was assessed using nested leave-one-group-out cross-validation. The feature "day" represents the number of days elapsed since the onset of menstruation. Participants were stratified into groups depending on high variability and low variability in sleep timing. Results demonstrated that adding minHR significantly improved luteal phase classification and ovulation day detection performance compared to "day" only. Furthermore, in participants with high variability in sleep timing, the minHR-based model outperformed the BBT-based model, significantly improving luteal phase recall and reducing ovulation day detection absolute errors by 2 d (p < 0.05). These findings highlight the robustness and practicality of the minHR-based model for menstrual cycle tracking, particularly in individuals with high variability in sleep timing. The proposed model holds great promise for personalized health management and large-scale epidemiological research.

Machine learning to dissect perturbations in complex cellular systems

Understanding the responses of biological systems to various perturbations, such as genetic, chemical, or environmental challenges, is essential for reconstructing causal network models. Emerging single-cell technologies have become instrumental in elucidating cell states and phenotypes and they have been used in combination with genetic screening. Recent advances in machine learning and artificial intelligence architectures have stimulated the development of computational tools for modeling perturbations and the response to compounds. This study outlined core principles underpinning perturbation analysis and discussed the methodologies and analytical frameworks used to decode drug and genetic perturbation responses, complex multicellular interactions, and network dynamics. The current tools used for various applications were overviewed. These developments hold great promise for improving drug development and personalized medicine. Foundation models and perturbation cell and tissue atlases offer immense potential for advancing our understanding of cellular behavior and disease mechanisms.

Single-cell genomics and spatial transcriptomics in islet transplantation for diabetes treatment: advancing towards personalized therapies

Diabetes mellitus (DM) is a global health crisis affecting millions, with islet transplantation emerging as a promising treatment strategy to restore insulin production. This review synthesizes the current research on single-cell and spatial transcriptomics in the context of islet transplantation, highlighting their potential to revolutionize DM management. Single-cell RNA sequencing, offers a detailed look into the diversity and functionality within islet grafts, identifying specific cell types and states that influence graft acceptance and function. Spatial transcriptomics complements this by mapping gene expression within the tissue's spatial context, crucial for understanding the microenvironment surrounding transplanted islets and their interactions with host tissues. The integration of these technologies offers a comprehensive view of cellular interactions and microenvironments, elucidating mechanisms underlying islet function, survival, and rejection. This understanding is instrumental in developing targeted therapies to enhance graft performance and patient outcomes. The review emphasizes the significance of these research avenues in informing clinical practices and improving outcomes for patients with DM through more effective islet transplantation strategies. Future research directions include the application of these technologies in personalized medicine, developmental biology, and regenerative medicine, with the potential to predict disease progression and treatment responses. Addressing ethical and technical challenges will be crucial for the successful implementation of these integrated approaches in research and clinical practice, ultimately enhancing our ability to manage DM and improve patient quality of life.

Towards the Next Generation of Data-Driven Therapeutics Using Spatially Resolved Single-Cell Technologies and Generative AI

Recent advances in multi-omics and spatially resolved single-cell technologies have revolutionised our ability to profile millions of cellular states, offering unprecedented opportunities to understand the complex molecular landscapes of human tissues in both health and disease. These developments hold immense potential for precision medicine, particularly in the rational design of novel therapeutics for treating inflammatory and autoimmune diseases. However, the vast, high-dimensional data generated by these technologies present significant analytical challenges, such as distinguishing technical variation from biological variation or defining relevant questions that leverage the added spatial dimension to improve our understanding of tissue organisation. Generative artificial intelligence (AI), specifically variational autoencoder- or transformer-based latent variable models, provides a powerful and flexible approach to addressing these challenges. These models make inferences about a cell's intrinsic state by effectively identifying complex patterns, reducing data dimensionality and modelling the biological variability in single-cell datasets. This review explores the current landscape of single-cell and spatial multi-omics technologies, the application of generative AI in data analysis and modelling and their transformative impact on our understanding of autoimmune diseases. By combining spatial and single-cell data with advanced AI methodologies, we highlight novel insights into the pathogenesis of autoimmune disorders and outline future directions for leveraging these technologies to achieve the goal of AI-powered personalised medicine.

SpaIM: Single-cell Spatial Transcriptomics Imputation via Style Transfer

Spatial transcriptomics (ST) technologies have revolutionized our understanding of cellular ecosystems. However, these technologies face challenges such as sparse gene signals and limited gene detection capacities, which hinder their ability to fully capture comprehensive spatial gene expression profiles. To address these limitations, we propose leveraging single-cell RNA sequencing (scRNA-seq), which provides comprehensive gene expression data but lacks spatial context, to enrich ST profiles. Herein, we introduce SpaIM, an innovative style transfer learning model that utilizes scRNA-seq information to predict unmeasured gene expressions in ST data, thereby improving gene coverage and expressions. SpaIM segregates scRNA-seq and ST data into data-agnostic contents and data-specific styles, with the contents capture the commonalities between the two data types, while the styles highlight their unique differences. By integrating the strengths of scRNA-seq and ST, SpaIM overcomes data sparsity and limited gene coverage issues, making significant advancements over 12 existing methods. This improvement is demonstrated across 53 diverse ST datasets, spanning sequencing- and imaging-based spatial technologies in various tissue types. Additionally, SpaIM enhances downstream analyses, including the detection of ligand-receptor interactions, spatial domain characterization, and identification of differentially expressed genes. Released as open-source software, SpaIM increases accessibility for spatial transcriptomics analysis. In summary, SpaIM represents a pioneering approach to enrich spatial transcriptomics using scRNA-seq data, enabling precise gene expression imputation and advancing the field of spatial transcriptomics research.

Deep Learning-Enabled Integration of Histology and Transcriptomics for Tissue Spatial Profile Analysis

Spatially resolved transcriptomics enable comprehensive measurement of gene expression at subcellular resolution while preserving the spatial context of the tissue microenvironment. While deep learning has shown promise in analyzing SCST datasets, most efforts have focused on sequence data and spatial localization, with limited emphasis on leveraging rich histopathological insights from staining images. We introduce GIST, a deep learning-enabled gene expression and histology integration for spatial cellular profiling. GIST employs histopathology foundation models pretrained on millions of histology images to enhance feature extraction and a hybrid graph transformer model to integrate them with transcriptome features. Validated with datasets from human lung, breast, and colorectal cancers, GIST effectively reveals spatial domains and substantially improves the accuracy of segmenting the microenvironment after denoising transcriptomics data. This enhancement enables more accurate gene expression analysis and aids in identifying prognostic marker genes, outperforming state-of-the-art deep learning methods with a total improvement of up to 49.72%. GIST provides a generalizable framework for integrating histology with spatial transcriptome analysis, revealing novel insights into spatial organization and functional dynamics.

Unveiling patterns in spatial transcriptomics data: a novel approach utilizing graph attention autoencoder and multiscale deep subspace clustering network

BACKGROUND

The accurate deciphering of spatial domains, along with the identification of differentially expressed genes and the inference of cellular trajectory based on spatial transcriptomic (ST) data, holds significant potential for enhancing our understanding of tissue organization and biological functions. However, most of spatial clustering methods can neither decipher complex structures in ST data nor entirely employ features embedded in different layers.

RESULTS

This article introduces STMSGAL, a novel framework for analyzing ST data by incorporating graph attention autoencoder and multiscale deep subspace clustering. First, STMSGAL constructs ctaSNN, a cell type-aware shared nearest neighbor graph, using Louvian clustering exclusively based on gene expression profiles. Subsequently, it integrates expression profiles and ctaSNN to generate spot latent representations using a graph attention autoencoder and multiscale deep subspace clustering. Lastly, STMSGAL implements spatial clustering, differential expression analysis, and trajectory inference, providing comprehensive capabilities for thorough data exploration and interpretation. STMSGAL was evaluated against 7 methods, including SCANPY, SEDR, CCST, DeepST, GraphST, STAGATE, and SiGra, using four 10x Genomics Visium datasets, 1 mouse visual cortex STARmap dataset, and 2 Stereo-seq mouse embryo datasets. The comparison showcased STMSGAL's remarkable performance across Davies-Bouldin, Calinski-Harabasz, S_Dbw, and ARI values. STMSGAL significantly enhanced the identification of layer structures across ST data with different spatial resolutions and accurately delineated spatial domains in 2 breast cancer tissues, adult mouse brain (FFPE), and mouse embryos.

CONCLUSIONS

STMSGAL can serve as an essential tool for bridging the analysis of cellular spatial organization and disease pathology, offering valuable insights for researchers in the field.

Spatially Informed Graph Structure Learning Extracts Insights from Spatial Transcriptomics

Embeddings derived from cell graphs hold significant potential for exploring spatial transcriptomics (ST) datasets. Nevertheless, existing methodologies rely on a graph structure defined by spatial proximity, which inadequately represents the diversity inherent in cell-cell interactions (CCIs). This study introduces STAGUE, an innovative framework that concurrently learns a cell graph structure and a low-dimensional embedding from ST data. STAGUE employs graph structure learning to parameterize and refine a cell graph adjacency matrix, enabling the generation of learnable graph views for effective contrastive learning. The derived embeddings and cell graph improve spatial clustering accuracy and facilitate the discovery of novel CCIs. Experimental benchmarks across 86 real and simulated ST datasets show that STAGUE outperforms 15 comparison methods in clustering performance. Additionally, STAGUE delineates the heterogeneity in human breast cancer tissues, revealing the activation of epithelial-to-mesenchymal transition and PI3K/AKT signaling in specific sub-regions. Furthermore, STAGUE identifies CCIs with greater alignment to established biological knowledge than those ascertained by existing graph autoencoder-based methods. STAGUE also reveals the regulatory genes that participate in these CCIs, including those enriched in neuropeptide signaling and receptor tyrosine kinase signaling pathways, thereby providing insights into the underlying biological processes.

Deciphering cell to cell spatial relationship for pathology images using SpatialQPFs

Understanding spatial dynamics within tissue microenvironments is crucial for deciphering cellular interactions and molecular signaling in living systems. These spatial characteristics govern cell distribution, extracellular matrix components, and signaling molecules, influencing local biochemical and biophysical conditions. Despite significant progress in analyzing digital pathology images, current methods for capturing spatial relationships are limited. They often rely on specific spatial features that only partially describe the complex spatial distributions of cells and are frequently tied to particular outcomes within predefined model frameworks. Furthermore, these methods are typically limited to field of view analysis, which restricts their capacity to capture spatial patterns across whole-slide images, thereby limiting their ability to fully address the complexities of tissue architecture. To address these limitations, we present SpatialQPFs (Spatial Quantitative Pathology Features), an R package designed to extract interpretable spatial features from cell imaging data using spatial statistical methodologies. Leveraging segmented cell information, our package offers a comprehensive toolkit for applying a range of spatial statistical methods within a stochastic process framework, including analyses of point process data, areal data, and geostatistical data. By decoupling feature extraction from specific outcome models, SpatialQPFs enables thorough large-scale spatial analyses applicable across diverse clinical and biological contexts. This approach enhances the depth and accuracy of spatial insights derived from tissue data, empowering researchers to conduct comprehensive spatial analyses efficiently and reproducibly. By providing a flexible and robust framework for spatial feature extraction, SpatialQPFs facilitates advanced spatial analyses, paving the way for new discoveries in tissue biology and pathology. SpatialQPFs code and documentation are publicly available at https://github.com/Genentech/SpatialQPFs .

Enhancing spatial domain detection in spatial transcriptomics with EnSDD

Advancements in spatial transcriptomics have transformed our understanding of organ function and tissue microenvironment. However, accurately identifying spatial domains to depict genome heterogeneity and cellular interactions remains a challenge. In this study, we propose EnSDD (Ensemble-learning for Spatial Domain Detection), a method that ingeniously integrates eight state-of-the-art spatial domain detection methods to automatically identify spatial domains. A key innovation of EnSDD is its dynamic weighting mechanism within the ensemble learning process, which optimizes the contribution of each base model and provides a performance evaluation metric without the need for ground truth data. By leveraging the spatial domains identified through EnSDD, we incorporate the detection of domain-specific spatially variable genes and the spatial distribution of cell types, thereby providing deeper insights into tissue heterogeneity. We validate EnSDD across diverse spatial transcriptomics datasets from various tissue organizational structures. Our results demonstrate that EnSDD significantly enhances spatial domain identification accuracy, identifies genes with spatial expression patterns, and reveals domain-specific cell type enrichment patterns, offering invaluable insights into tissue spatial heterogeneity and regionalization.

BayeSMART: Bayesian clustering of multi-sample spatially resolved transcriptomics data

The field of spatially resolved transcriptomics (SRT) has greatly advanced our understanding of cellular microenvironments by integrating spatial information with molecular data collected from multiple tissue sections or individuals. However, methods for multi-sample spatial clustering are lacking, and existing methods primarily rely on molecular information alone. This paper introduces BayeSMART, a Bayesian statistical method designed to identify spatial domains across multiple samples. BayeSMART leverages artificial intelligence (AI)-reconstructed single-cell level information from the paired histology images of multi-sample SRT datasets while simultaneously considering the spatial context of gene expression. The AI integration enables BayeSMART to effectively interpret the spatial domains. We conducted case studies using four datasets from various tissue types and SRT platforms, and compared BayeSMART with alternative multi-sample spatial clustering approaches and a number of state-of-the-art methods for single-sample SRT analysis, demonstrating that it surpasses existing methods in terms of clustering accuracy, interpretability, and computational efficiency. BayeSMART offers new insights into the spatial organization of cells in multi-sample SRT data.

MorphLink: Bridging Cell Morphological Behaviors and Molecular Dynamics in Multi-modal Spatial Omics

Multi-modal spatial omics data are invaluable for exploring complex cellular behaviors in diseases from both morphological and molecular perspectives. Current analytical methods primarily focus on clustering and classification, and do not adequately examine the relationship between cell morphology and molecular dynamics. Here, we present MorphLink, a framework designed to systematically identify disease-related morphological-molecular interplays. MorphLink has been evaluated across a wide array of datasets, showcasing its effectiveness in extracting and linking interpretable morphological features with various molecular measurements in multi-modal spatial omics analyses. These linkages provide a transparent depiction of cellular behaviors that drive transcriptomic heterogeneity and immune diversity across different regions within diseased tissues, such as cancer. Additionally, MorphLink is scalable and robust against cross-sample batch effects, making it an efficient method for integrative spatial omics data analysis across samples, cohorts, and modalities, and enhancing the interpretation of results for large-scale studies.

Fragment-Fusion Transformer: Deep Learning-Based Discretization Method for Continuous Single-Cell Raman Spectral Analysis

Raman spectroscopy has become an important single-cell analysis tool for monitoring biochemical changes at the cellular level. However, Raman spectral data, typically presented as continuous data with high-dimensional characteristics, is distinct from discrete sequences, which limits the application of deep learning-based algorithms in data analysis due to the lack of discretization. Herein, a model called fragment-fusion transformer is proposed, which integrates the discrete fragmentation of continuous spectra based on their intrinsic characteristics with the extraction of intrafragment features and the fusion of interfragment features. The model integrates the intrinsic feature-based fragmentation of spectra with transformer, constructing the fragment transformer block for feature extraction within fragments. Interfragment information is combined through the pyramid design structure to improve the model's receptive field and fully exploit the spectral properties. During the pyramidal fusion process, the information gain of the final extracted features in the spectrum has been enhanced by a factor of 9.24 compared to the feature extraction stage within the fragment, and the information entropy has been enhanced by a factor of 13. The fragment-fusion transformer achieved a spectral recognition accuracy of 94.5%, which is 4% higher compared to the method without fragmentation and fusion processes on the test set of cell Raman spectroscopy identification experiments. In comparison to common spectral classification models such as KNN, SVM, logistic regression, and CNN, fragment-fusion transformer has achieved 4.4% higher accuracy than the best-performing CNN model. Fragment-fusion transformer method has the potential to serve as a general framework for discretization in the field of continuous spectral data analysis and as a research tool for analyzing the intrinsic information within spectra.

xSiGra: explainable model for single-cell spatial data elucidation

Recent advancements in spatial imaging technologies have revolutionized the acquisition of high-resolution multichannel images, gene expressions, and spatial locations at the single-cell level. Our study introduces xSiGra, an interpretable graph-based AI model, designed to elucidate interpretable features of identified spatial cell types, by harnessing multimodal features from spatial imaging technologies. By constructing a spatial cellular graph with immunohistology images and gene expression as node attributes, xSiGra employs hybrid graph transformer models to delineate spatial cell types. Additionally, xSiGra integrates a novel variant of gradient-weighted class activation mapping component to uncover interpretable features, including pivotal genes and cells for various cell types, thereby facilitating deeper biological insights from spatial data. Through rigorous benchmarking against existing methods, xSiGra demonstrates superior performance across diverse spatial imaging datasets. Application of xSiGra on a lung tumor slice unveils the importance score of cells, illustrating that cellular activity is not solely determined by itself but also impacted by neighboring cells. Moreover, leveraging the identified interpretable genes, xSiGra reveals endothelial cell subset interacting with tumor cells, indicating its heterogeneous underlying mechanisms within complex cellular interactions.

AntiFormer: graph enhanced large language model for binding affinity prediction

Antibodies play a pivotal role in immune defense and serve as key therapeutic agents. The process of affinity maturation, wherein antibodies evolve through somatic mutations to achieve heightened specificity and affinity to target antigens, is crucial for effective immune response. Despite their significance, assessing antibody-antigen binding affinity remains challenging due to limitations in conventional wet lab techniques. To address this, we introduce AntiFormer, a graph-based large language model designed to predict antibody binding affinity. AntiFormer incorporates sequence information into a graph-based framework, allowing for precise prediction of binding affinity. Through extensive evaluations, AntiFormer demonstrates superior performance compared with existing methods, offering accurate predictions with reduced computational time. Application of AntiFormer to severe acute respiratory syndrome coronavirus 2 patient samples reveals antibodies with strong neutralizing capabilities, providing insights for therapeutic development and vaccination strategies. Furthermore, analysis of individual samples following influenza vaccination elucidates differences in antibody response between young and older adults. AntiFormer identifies specific clonotypes with enhanced binding affinity post-vaccination, particularly in young individuals, suggesting age-related variations in immune response dynamics. Moreover, our findings underscore the importance of large clonotype category in driving affinity maturation and immune modulation. Overall, AntiFormer is a promising approach to accelerate antibody-based diagnostics and therapeutics, bridging the gap between traditional methods and complex antibody maturation processes.

Data enhancement in the age of spatial biology

Unveiling the intricate interplay of cells in their native environment lies at the heart of understanding fundamental biological processes and unraveling disease mechanisms, particularly in complex diseases like cancer. Spatial transcriptomics (ST) offers a revolutionary lens into the spatial organization of gene expression within tissues, empowering researchers to study both cell heterogeneity and microenvironments in health and disease. However, current ST technologies often face limitations in either resolution or the number of genes profiled simultaneously. Integrating ST data with complementary sources, such as single-cell transcriptomics and detailed tissue staining images, presents a powerful solution to overcome these limitations. This review delves into the computational approaches driving the integration of spatial transcriptomics with other data types. By illuminating the key challenges and outlining the current algorithmic solutions, we aim to highlight the immense potential of these methods to revolutionize our understanding of cancer biology.

Foundation models in molecular biology

Determining correlations between molecules at various levels is an important topic in molecular biology. Large language models have demonstrated a remarkable ability to capture correlations from large amounts of data in the field of natural language processing as well as image generation, and correlations captured from data using large language models can also be applicable to solving a wide range of specific tasks, hence large language models are also referred to as foundation models. The massive amount of data that exists in the field of molecular biology provides an excellent basis for the development of foundation models, and the recent emergence of foundation models in the field of molecular biology has really pushed the entire field forward. We summarize the foundation models developed based on RNA sequence data, DNA sequence data, protein sequence data, single-cell transcriptome data, and spatial transcriptome data respectively, and further discuss the research directions for the development of foundation models in molecular biology.

Advances in spatial transcriptomics and its applications in cancer research

Malignant tumors have increasing morbidity and high mortality, and their occurrence and development is a complicate process. The development of sequencing technologies enabled us to gain a better understanding of the underlying genetic and molecular mechanisms in tumors. In recent years, the spatial transcriptomics sequencing technologies have been developed rapidly and allow the quantification and illustration of gene expression in the spatial context of tissues. Compared with the traditional transcriptomics technologies, spatial transcriptomics technologies not only detect gene expression levels in cells, but also inform the spatial location of genes within tissues, cell composition of biological tissues, and interaction between cells. Here we summarize the development of spatial transcriptomics technologies, spatial transcriptomics tools and its application in cancer research. We also discuss the limitations and challenges of current spatial transcriptomics approaches, as well as future development and prospects.

Complete spatially resolved gene expression is not necessary for identifying spatial domains

Spatially resolved transcriptomics (SRT) technologies have revolutionized the study of tissue organization. We introduce a graph convolutional network with an attention and positive emphasis mechanism, termed BINARY, relying exclusively on binarized SRT data to accurately delineate spatial domains. BINARY outperforms existing methods across various SRT data types while using significantly less input information. Our study suggests that precise gene expression quantification may not always be essential, inspiring further exploration of the broader applications of spatially resolved binarized gene expression data.

iIMPACT: integrating image and molecular profiles for spatial transcriptomics analysis

Current clustering analysis of spatial transcriptomics data primarily relies on molecular information and fails to fully exploit the morphological features present in histology images, leading to compromised accuracy and interpretability. To overcome these limitations, we have developed a multi-stage statistical method called iIMPACT. It identifies and defines histology-based spatial domains based on AI-reconstructed histology images and spatial context of gene expression measurements, and detects domain-specific differentially expressed genes. Through multiple case studies, we demonstrate iIMPACT outperforms existing methods in accuracy and interpretability and provides insights into the cellular spatial organization and landscape of functional genes within spatial transcriptomics data.

A Spatial Transcriptomics Browser for Discovering Gene Expression Landscapes across Microscopic Tissue Sections

A crucial feature of life is its spatial organization and compartmentalization on the molecular, cellular, and tissue levels. Spatial transcriptomics (ST) technology has opened a new chapter of the sequencing revolution, emerging rapidly with transformative effects across biology. This technique produces extensive and complex sequencing data, raising the need for computational methods for their comprehensive analysis and interpretation. We developed the ST browser web tool for the interactive discovery of ST images, focusing on different functional aspects such as single gene expression, the expression of functional gene sets, as well as the inspection of the spatial patterns of cell-cell interactions. As a unique feature, our tool applies self-organizing map (SOM) machine learning to the ST data. Our SOM data portrayal method generates individual gene expression landscapes for each spot in the ST image, enabling its downstream analysis with high resolution. The performance of the spatial browser is demonstrated by disentangling the intra-tumoral heterogeneity of melanoma and the microarchitecture of the mouse brain. The integration of machine-learning-based SOM portrayal into an interactive ST analysis environment opens novel perspectives for the comprehensive knowledge mining of the organization and interactions of cellular ecosystems.

xSiGra: Explainable model for single-cell spatial data elucidation

Recent advancements in spatial imaging technologies have revolutionized the acquisition of high-resolution multi-channel images, gene expressions, and spatial locations at the single-cell level. Our study introduces xSiGra, an interpretable graph-based AI model, designed to elucidate interpretable features of identified spatial cell types, by harnessing multi-modal features from spatial imaging technologies. By constructing a spatial cellular graph with immunohistology images and gene expression as node attributes, xSiGra employs hybrid graph transformer models to delineate spatial cell types. Additionally, xSiGra integrates a novel variant of Grad-CAM component to uncover interpretable features, including pivotal genes and cells for various cell types, thereby facilitating deeper biological insights from spatial data. Through rigorous benchmarking against existing methods, xSiGra demonstrates superior performance across diverse spatial imaging datasets. Application of xSiGra on a lung tumor slice unveils the importance score of cells, illustrating that cellular activity is not solely determined by itself but also impacted by neighboring cells. Moreover, leveraging the identified interpretable genes, xSiGra reveals endothelial cell subset interacting with tumor cells, indicating its heterogeneous underlying mechanisms within the complex cellular communications.

In situ characterization of the tumor microenvironment

The development of new therapies for cancer is underpinned by an increasing need to comprehensively characterize the tumor microenvironment (TME). While traditional approaches have relied on bulk or single-cell approaches, these are limited in their ability to provide cellular context. Deconvolution of the complex TME is fundamental to understanding tumor dynamics and treatment resistance. Spatially resolved characterization of the TME is likely to provide greater insights into the cellular architecture, tumor-immune cell interactions, receptor-ligand interactions, and cell niches. In turn, these aid in dictating the optimal way in which to target each patient's individual cancer. In this review, we discuss a number of cutting-edge in situ spatial profiling methods giving us new insights into tumor biology.

Artificial Intelligence for Precision Oncology of Triple-Negative Breast Cancer: Learning from Melanoma

Thanks to new technologies using artificial intelligence (AI) and machine learning, it is possible to use large amounts of data to try to extract information that can be used for personalized medicine. The great challenge of the future is, on the one hand, to acquire masses of biological data that nowadays are still limited and, on the other hand, to develop innovative strategies to extract information that can then be used for the development of predictive models. From this perspective, we discuss these aspects in the context of triple-negative breast cancer, a tumor where a specific treatment is still lacking and new therapies, such as immunotherapy, are under investigation. Since immunotherapy is already in use for other tumors such as melanoma, we discuss the strengths and weaknesses identified in the use of immunotherapy with melanoma to try to find more successful strategies. It is precisely in this context that AI and predictive tools can be extremely valuable. Therefore, the discoveries and advancements in immunotherapy for melanoma provide a foundation for developing effective immunotherapies for triple-negative breast cancer. Shared principles, such as immune system activation, checkpoint inhibitors, and personalized treatment, can be applied to TNBC to improve patient outcomes and offer new hope for those with aggressive, hard-to-treat breast cancer.

TEMINET: A Co-Informative and Trustworthy Multi-Omics Integration Network for Diagnostic Prediction

Advancing the domain of biomedical investigation, integrated multi-omics data have shown exceptional performance in elucidating complex human diseases. However, as the variety of omics information expands, precisely perceiving the informativeness of intra- and inter-omics becomes challenging due to the intricate interrelations, thus presenting significant challenges in the integration of multi-omics data. To address this, we introduce a novel multi-omics integration approach, referred to as TEMINET. This approach enhances diagnostic prediction by leveraging an intra-omics co-informative representation module and a trustworthy learning strategy used to address inter-omics fusion. Considering the multifactorial nature of complex diseases, TEMINET utilizes intra-omics features to construct disease-specific networks; then, it applies graph attention networks and a multi-level framework to capture more collective informativeness than pairwise relations. To perceive the contribution of co-informative representations within intra-omics, we designed a trustworthy learning strategy to identify the reliability of each omics in integration. To integrate inter-omics information, a combined-beliefs fusion approach is deployed to harmonize the trustworthy representations of different omics types effectively. Our experiments across four different diseases using mRNA, methylation, and miRNA data demonstrate that TEMINET achieves advanced performance and robustness in classification tasks.

TrialView: An AI-powered Visual Analytics System for Temporal Event Data in Clinical Trials

Randomized controlled trials (RCT) are the gold standards for evaluating the efficacy and safety of therapeutic interventions in human subjects. In addition to the pre-specified endpoints, trial participants' experience reveals the time course of the intervention. Few analytical tools exist to summarize and visualize the individual experience of trial participants. Visual analytics allows integrative examination of temporal event patterns of patient experience, thus generating insights for better care decisions. Towards this end, we introduce TrialView, an information system that combines graph artificial intelligence (AI) and visual analytics to enhance the dissemination of trial data. TrialView offers four distinct yet interconnected views: Individual, Cohort, Progression, and Statistics, enabling an interactive exploration of individual and group-level data. The TrialView system is a general-purpose analytical tool for a broad class of clinical trials. The system is powered by graph AI, knowledge-guided clustering, explanatory modeling, and graph-based agglomeration algorithms. We demonstrate the system's effectiveness in analyzing temporal event data through a case study.

Novel research and future prospects of artificial intelligence in cancer diagnosis and treatment

Research into the potential benefits of artificial intelligence for comprehending the intricate biology of cancer has grown as a result of the widespread use of deep learning and machine learning in the healthcare sector and the availability of highly specialized cancer datasets. Here, we review new artificial intelligence approaches and how they are being used in oncology. We describe how artificial intelligence might be used in the detection, prognosis, and administration of cancer treatments and introduce the use of the latest large language models such as ChatGPT in oncology clinics. We highlight artificial intelligence applications for omics data types, and we offer perspectives on how the various data types might be combined to create decision-support tools. We also evaluate the present constraints and challenges to applying artificial intelligence in precision oncology. Finally, we discuss how current challenges may be surmounted to make artificial intelligence useful in clinical settings in the future.

Advanced Omics Techniques for Understanding Cochlear Genome, Epigenome, and Transcriptome in Health and Disease

Advanced genomics, transcriptomics, and epigenomics techniques are providing unprecedented insights into the understanding of the molecular underpinnings of the central nervous system, including the neuro-sensory cochlea of the inner ear. Here, we report for the first time a comprehensive and updated overview of the most advanced omics techniques for the study of nucleic acids and their applications in cochlear research. We describe the available in vitro and in vivo models for hearing research and the principles of genomics, transcriptomics, and epigenomics, alongside their most advanced technologies (like single-cell omics and spatial omics), which allow for the investigation of the molecular events that occur at a single-cell resolution while retaining the spatial information.

Feature Selection for Unsupervised Machine Learning

Compared to supervised machine learning (ML), the development of feature selection for unsupervised ML is far behind. To address this issue, the current research proposes a stepwise feature selection approach for clustering methods with a specification to the Gaussian mixture model (GMM) and the k -means. Rather than the existing GMM and k -means which are carried out based on all the features, the proposed method selects a subset of features to implement the two methods, respectively. The research finds that a better result can be obtained if the existing GMM and k -means methods are modified by nice initializations. Experiments based on Monte Carlo simulations show that the proposed method is more computationally efficient and the result is more accurate than the existing GMM and k -means methods based on all the features. The experiment based on a real-world dataset confirms this finding.