Efficient prediction of a spatial transcriptomics profile better characterizes breast cancer tissue sections without costly experimentation

Abstract

Spatial transcriptomics is an emerging technology requiring costly reagents and considerable skills, limiting the identification of transcriptional markers related to histology. Here, we show that predicted spatial gene-expression in unmeasured regions and tissues can enhance biologists’ histological interpretations. We developed the Deep learning model for Spatial gene Clusters and Expression, DeepSpaCE, and confirmed its performance using the spatial-transcriptome profiles and immunohistochemistry images of consecutive human breast cancer tissue sections. For example, the predicted expression patterns of SPARC, an invasion marker, highlighted a small tumor-invasion region difficult to identify using raw spatial transcriptome data alone because of a lack of measurements. We further developed semi-supervised DeepSpaCE using unlabeled histology images and increased the imputation accuracy of consecutive sections, enhancing applicability for a small sample size. Our method enables users to derive hidden histological characters via spatial transcriptome and gene annotations, leading to accelerated biological discoveries without additional experiments.

Detection of abnormal extraocular muscles in small datasets of computed tomography images using a three-dimensional variational autoencoder

“…To our knowledge, no previous study has applied unsupervised DL to a small dataset of CT images. Most DL studies involving small numbers of medical images used supervised [22][23][24] , or semi-supervised DL [25][26][27] . These approaches may be used because supervised DL algorithms are expected to identify features that distinguish among data in small datasets; they require definite answers to focus on during the model training.…”

Deep spatial-omics to aid personalization of precision medicine in metastatic recurrent Head & Neck Cancers

“…We envision that spatial RNA/protein analysis can be adopted in the clinical settings, as whole genome sequencing is now a routine test requested by clinicians. Importantly, the cost of these technologies and high technical requirements can already be drastically reduced by the implementation of artificial intelligence (AI) models capable to predict in situ gene expression inferred from fast/low-cost H&E images using curated disease Spatial-omics training data sets 36,37 Thus, after an initial investment dedicated to create standardized disease-specific AI training material, the spatial data of each patient’s tumor biopsy can be obtained (experimentally or AI-inferred) and contrasted against spatial databases of the disease to help with different steps along each patient’s journey: (i) aid in the annotation of the tumor, (ii) stratify patients based on disease risk progression to personalize surveillance plans; and (iii) to generate a list based on a patient’s own disease features which informs oncologists of targets with quantifiable likelihood to have an impact on the disease. This information can be used to implement combinatorial therapeutic programs to prevent drug resistance minimizing off-target effects ( Figure 3M ).…”

Spatial RNA sequencing methods show high resolution of single cell in cancer metastasis and the formation of tumor microenvironment

“…We have summarized some research methods used to improve ST imaging during the past 2 years, basically involving deconvolution software designed to evaluate the localization of transcriptome expression in ST data through calculations, including SpaGCN [65], MULTILAYER [66], STARCH [67], SPARK-X [68], DeepSpaCE [69], spatialGE [70], MISTy [71], and SpotClean [72]. These methods are mainly aimed at rare cell types existing in complex and multi-level tissue regions that may not be detected by ST, which is equivalent to deep in situ sequencing of some key areas in the whole tissue section.…”