Spatial biology is a rapidly growing field that has seen tremendous progress over the last decade. We are now able to measure how the morphology, genome, transcriptome, and proteome of a tissue vary across space. Datasets generated by spatial technologies reflect the complexity of the systems they measure: They are multi-modal, high-dimensional, and layer an intricate web of dependencies between biological compartments at different length scales. To add to this complexity, measurements are often sparse and noisy, obfuscating the underlying biological signal and making the data difficult to interpret. In this thesis, we describe how data from spatial biology experiments can be analyzed with methods from deep learning and generative modeling to accelerate biological discovery. The thesis is divided into two parts. The first part provides an introduction to the fields of deep learning and spatial biology, and how the two can be combined to model spatial biology data. The second part consists of four papers describing methods that we have developed for this purpose. Paper I presents a method for inferring spatial gene expression from hematoxylin and eosin stains. The proposed method offers a data-driven approach to analyzing histopathology images without relying on expert annotations and could be a valuable tool for cancer screening and diagnosis in the clinics. Paper II introduces a method for jointly modeling spatial gene expression with histology images. We show that the method can predict super-resolved gene expression and transcriptionally characterize small-scale anatomical structures. Paper III proposes a method for learning flexible Markov kernels to model continuous and discrete data distributions. We demonstrate the method on various image synthesis tasks, including unconditional image generation and inpainting. Paper IV leverages the techniques introduced in Paper III to integrate data from different spatial biology experiments. The proposed method can be used for data imputation, super resolution, and cross-modality data transfer.

Spatial biologi är ett snabbt växande forskningsområde som har sett en hög utvecklingstakt under det senaste decenniet. Vi kan idag mäta hur en vävnads morfologi, genom, transkriptom och proteom varierar i rummet. Dataset skapade av spatiala teknologier återspeglar komplexiteten i de system de mäter: De är multimodala, högdimensionella och är uppbyggda av ett intrikat nätverk av beroenden mellan biologiska strukturer som existerar på olika längdskalor. Som om denna komplexitet inte var nog, är mätningarna ofta både glesa och brusiga, vilket försvårar tolkningen av den underliggande biologiska signalen. I denna avhandling beskriver vi hur data från experiment inom spatial biologi kan analyseras med hjälp av djupinlärning och generativ modellering för att accelerera biologiska upptäckter. Avhandlingen är uppdelad i två delar. Den första delen ger en introduktion till fälten djupinlärning och spatial biologi, och hur dessa kan kombineras för att modellera data inom spatial biologi. Den andra delen består av fyra artiklar som beskriver metoder som vi har utvecklat för detta ändamål. Artikel I presenterar en metod för att skatta spatialt genuttryck från hematoxylin-eosin-färgningar. Den föreslagna metoden erbjuder ett datadrivet tillvägagångssätt för att analysera histopatologi-bilder utan användning av expertannoteringar och kan utgöra ett värdefullt verktyg för cancerscreening och diagnos i kliniken. Artikel II introducerar en metod för sammodellering av spatialt genuttryck och histologibilder. Vi visar att metoden kan användas för att predicera superupplöst genuttryck och transkriptionellt karakterisera småskaliga anatomiska strukturer. Artikel III beskriver en metod för modellering av kontinuerliga och diskreta datafördelningar med flexibla Markovkärnor. Vi demonstrerar metoden på olika bildgenereringsuppgifter, inklusive obetingad datagenerering och inpainting. Artikel IV utnyttjar teknikerna från Artikel III för att integrera data från olika experiment inom spatial biologi. Den föreslagna metoden kan användas för imputering, superupplösning och dataöverföring mellan olika modaliteter.

Spatial landmarks are crucial in describing histological features between samples or sites, tracking regions of interest in microscopy, and registering tissue samples within a common coordinate framework. Although other studies have explored unsupervised landmark detection, existing methods are not well-suited for histological image data as they often require a large number of images to converge, are unable to handle nonlinear deformations between tissue sections and are ineffective for z-stack alignment, other modalities beyond image data or multimodal data. We address these challenges by introducing effortless landmark detection, a new unsupervised landmark detection and registration method using neural-network-guided thin-plate splines. Our proposed method is evaluated on a diverse range of datasets including histology and spatially resolved transcriptomics, demonstrating superior performance in both accuracy and stability compared to existing approaches.

Spatially resolved transcriptomics methodologies using RNA sequencing principles have and will continue to contribute to decode the molecular landscape of tissues. Linking quantitative sequencing data with tissue morphology empowers profiling of cellular morphology and transcription over time and space in health and disease. To view this SnapShot, open or download the PDF.

Defining the transition from benign to malignant tissue is fundamental to improving early diagnosis of cancer(1). Here we use a systematic approach to study spatial genome integrity in situ and describe previously unidentified clonal relationships. We used spatially resolved transcriptomics(2) to infer spatial copy number variations in >120,000 regions across multiple organs, in benign and malignant tissues. We demonstrate that genome-wide copy number variation reveals distinct clonal patterns within tumours and in nearby benign tissue using an organ-wide approach focused on the prostate. Our results suggest a model for how genomic instability arises in histologically benign tissue that may represent early events in cancer evolution. We highlight the power of capturing the molecular and spatial continuums in a tissue context and challenge the rationale for treatment paradigms, including focal therapy.

The molecular mechanisms underlying lethal castration-resistant prostate cancer remain poorly understood, with intratumoral heterogeneity a likely contributing factor. To examine the temporal aspects of resistance, we analyze tumor heterogeneity in needle biopsies collected before and after treatment with androgen deprivation therapy. By doing so, we are able to couple clinical responsiveness and morphological information such as Gleason score to transcriptome-wide data. Our data-driven analysis of transcriptomes identifies several distinct intratumoral cell populations, characterized by their unique gene expression profiles. Certain cell populations present before treatment exhibit gene expression profiles that match those of resistant tumor cell clusters, present after treatment. We confirm that these clusters are resistant by the localization of active androgen receptors to the nuclei in cancer cells post-treatment. Our data also demonstrates that most stromal cells adjacent to resistant clusters do not express the androgen receptor, and we identify differentially expressed genes for these cells. Altogether, this study shows the potential to increase the power in predicting resistant tumors. Spatial heterogeneity in prostate cancer can contribute to its resistance to androgen deprivation therapy (ADT). Here, the authors analyse prostate cancer samples before and after ADT using Spatial Transcriptomics, and find heterogeneous pre-treatment tumour cell populations and stromal cells that are associated with resistance.

Current methods for spatial transcriptomics are limited by low spatial resolution. Here we introduce a method that integrates spatial gene expression data with histological image data from the same tissue section to infer higher-resolution expression maps. Using a deep generative model, our method characterizes the transcriptome of micrometer-scale anatomical features and can predict spatial gene expression from histology images alone. 

Angiotensin-converting enzyme 2 (ACE2) and accessory proteases (TMPRSS2 and CTSL) are needed for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) cellular entry, and their expression may shed light on viral tropism and impact across the body. We assessed the cell-type-specific expression of ACE2, TMPRSS2 and CTSL across 107 single-cell RNA-sequencing studies from different tissues. ACE2, TMPRSS2 and CTSL are coexpressed in specific subsets of respiratory epithelial cells in the nasal passages, airways and alveoli, and in cells from other organs associated with coronavirus disease 2019 (COVID-19) transmission or pathology. We performed a meta-analysis of 31 lung single-cell RNA-sequencing studies with 1,320,896 cells from 377 nasal, airway and lung parenchyma samples from 228 individuals. This revealed cell-type-specific associations of age, sex and smoking with expression levels of ACE2, TMPRSS2 and CTSL. Expression of entry factors increased with age and in males, including in airway secretory cells and alveolar type 2 cells. Expression programs shared by ACE2(+)TMPRSS2(+) cells in nasal, lung and gut tissues included genes that may mediate viral entry, key immune functions and epithelial-macrophage cross-talk, such as genes involved in the interleukin-6, interleukin-1, tumor necrosis factor and complement pathways. Cell-type-specific expression patterns may contribute to the pathogenesis of COVID-19, and our work highlights putative molecular pathways for therapeutic intervention.

An integrated analysis of over 100 single-cell and single-nucleus transcriptomics studies illustrates severe acute respiratory syndrome coronavirus 2 viral entry gene coexpression patterns across different human tissues, and shows association of age, smoking status and sex with viral entry gene expression in respiratory cell populations.

Background: Interest in studying the spatial distribution of gene expression in tissues is rapidly increasing. Spatial Transcriptomics is a novel sequencing-based technology that generates high-throughput information on the distribution, heterogeneity and co-expression of cells in tissues. Unfortunately, manual preparation of high-quality sequencing libraries is time-consuming and subject to technical variability due to human error during manual pipetting, which results in sample swapping and the accidental introduction of batch effects. All these factors complicate the production and interpretation of biological datasets.

Results: We have integrated an Agilent Bravo Automated Liquid Handling Platform into the Spatial Transcriptomics workflow. Compared to the previously reported Magnatrix 8000+ automated protocol, this approach increases the number of samples processed per run, reduces sample preparation time by 35%, and minimizes batch effects between samples. The new approach is also shown to be highly accurate and almost completely free from technical variability between prepared samples.

Conclusions: The new automated Spatial Transcriptomics protocol using the Agilent Bravo Automated Liquid Handling Platform rapidly generates high-quality Spatial Transcriptomics libraries. Given the wide use of the Agilent Bravo Automated Liquid Handling Platform in research laboratories and facilities, this will allow many researchers to quickly create robust Spatial Transcriptomics libraries.