Joint analysis of expression levels and histological images identifies genes associated with tissue morphology

Multi-Instance Multi-Task Learning for Joint Clinical Outcome and Genomic Profile Predictions From the Histopathological Images

With the remarkable success of digital histopathology and the deep learning technology, many whole-slide pathological images (WSIs) based deep learning models are designed to help pathologists diagnose human cancers. Recently, rather than predicting categorical variables as in cancer diagnosis, several deep learning studies are also proposed to estimate the continuous variables such as the patients' survival or their transcriptional profile. However, most of the existing studies focus on conducting these predicting tasks separately, which overlooks the useful intrinsic correlation among them that can boost the prediction performance of each individual task. In addition, it is sill challenge to design the WSI-based deep learning models, since a WSI is with huge size but annotated with coarse label. In this study, we propose a general multi-instance multi-task learning framework (HistMIMT) for multi-purpose prediction from WSIs. Specifically, we firstly propose a novel multi-instance learning module (TMICS) considering both common and specific task information across different tasks to generate bag representation for each individual task. Then, a soft-mask based fusion module with channel attention (SFCA) is developed to leverage useful information from the related tasks to help improve the prediction performance on target task. We evaluate our method on three cancer cohorts derived from the Cancer Genome Atlas (TCGA). For each cohort, our multi-purpose prediction tasks range from cancer diagnosis, survival prediction and estimating the transcriptional profile of gene TP53. The experimental results demonstrated that HistMIMT can yield better outcome on all clinical prediction tasks than its competitors.

Morphomics via next-generation electron microscopy

The living body is composed of innumerable fine and complex structures. Although these structures have been studied in the past, a vast amount of information pertaining to them still remains unknown. When attempting to observe these ultra-structures, the use of electron microscopy (EM) has become indispensable. However, conventional EM settings are limited to a narrow tissue area, which can bias observations. Recently, new trends in EM research have emerged, enabling coverage of far broader, nano-scale fields of view for two-dimensional wide areas and three-dimensional large volumes. Moreover, cutting-edge bioimage informatics conducted via deep learning has accelerated the quantification of complex morphological bioimages. Taken together, these technological and analytical advances have led to the comprehensive acquisition and quantification of cellular morphology, which now arises as a new omics science termed 'morphomics'.

Diagnostic Challenges during Inflammation and Cancer: Current Biomarkers and Future Perspectives in Navigating through the Minefield of Reactive versus Dysplastic and Cancerous Lesions in the Digestive System

In the setting of pronounced inflammation, changes in the epithelium may overlap with neoplasia, often rendering it impossible to establish a diagnosis with certainty in daily clinical practice. Here, we discuss the underlying molecular mechanisms driving tissue response during persistent inflammatory signaling along with the potential association with cancer in the gastrointestinal tract, pancreas, extrahepatic bile ducts, and liver. We highlight the histopathological challenges encountered in the diagnosis of chronic inflammation in routine practice and pinpoint tissue-based biomarkers that could complement morphology to differentiate reactive from dysplastic or cancerous lesions. We refer to the advantages and limitations of existing biomarkers employing immunohistochemistry and point to promising new markers, including the generation of novel antibodies targeting mutant proteins, miRNAs, and array assays. Advancements in experimental models, including mouse and 3D models, have improved our understanding of tissue response. The integration of digital pathology along with artificial intelligence may also complement routine visual inspections. Navigating through tissue responses in various chronic inflammatory contexts will help us develop novel and reliable biomarkers that will improve diagnostic decisions and ultimately patient treatment.

Prediction of anticancer drug resistance using a 3D microfluidic bladder cancer model combined with convolutional neural network-based image analysis

Bladder cancer is the most common urological malignancy worldwide, and its high recurrence rate leads to poor survival outcomes. The effect of anticancer drug treatment varies significantly depending on individual patients and the extent of drug resistance. In this study, we developed a validation system based on an organ-on-a-chip integrated with artificial intelligence technologies to predict resistance to anticancer drugs in bladder cancer. As a proof-of-concept, we utilized the gemcitabine-resistant bladder cancer cell line T24 with four distinct levels of drug resistance (parental, early, intermediate, and late). These cells were co-cultured with endothelial cells in a 3D microfluidic chip. A dataset comprising 2,674 cell images from the chips was analyzed using a convolutional neural network (CNN) to distinguish the extent of drug resistance among the four cell groups. The CNN achieved 95.2% accuracy upon employing data augmentation and a step decay learning rate with an initial value of 0.001. The average diagnostic sensitivity and specificity were 90.5% and 96.8%, respectively, and all area under the curve (AUC) values were over 0.988. Our proposed method demonstrated excellent performance in accurately identifying the extent of drug resistance, which can assist in the prediction of drug responses and in determining the appropriate treatment for bladder cancer patients.

Inferring super-resolution tissue architecture by integrating spatial transcriptomics with histology

Spatial transcriptomics (ST) has demonstrated enormous potential for generating intricate molecular maps of cells within tissues. Here we present iStar, a method based on hierarchical image feature extraction that integrates ST data and high-resolution histology images to predict spatial gene expression with super-resolution. Our method enhances gene expression resolution to near-single-cell levels in ST and enables gene expression prediction in tissue sections where only histology images are available.

Transformer with convolution and graph-node co-embedding: An accurate and interpretable vision backbone for predicting gene expressions from local histopathological image

Inferring gene expressions from histopathological images has long been a fascinating yet challenging task, primarily due to the substantial disparities between the two modality. Existing strategies using local or global features of histological images are suffering model complexity, GPU consumption, low interpretability, insufficient encoding of local features, and over-smooth prediction of gene expressions among neighboring sites. In this paper, we develop TCGN (Transformer with Convolution and Graph-Node co-embedding method) for gene expression estimation from H&E-stained pathological slide images. TCGN comprises a combination of convolutional layers, transformer encoders, and graph neural networks, and is the first to integrate these blocks in a general and interpretable computer vision backbone. Notably, TCGN uniquely operates with just a single spot image as input for histopathological image analysis, simplifying the process while maintaining interpretability. We validate TCGN on three publicly available spatial transcriptomic datasets. TCGN consistently exhibited the best performance (with median PCC 0.232). TCGN offers superior accuracy while keeping parameters to a minimum (just 86.241 million), and it consumes minimal memory, allowing it to run smoothly even on personal computers. Moreover, TCGN can be extended to handle bulk RNA-seq data while providing the interpretability. Enhancing the accuracy of omics information prediction from pathological images not only establishes a connection between genotype and phenotype, enabling the prediction of costly-to-measure biomarkers from affordable histopathological images, but also lays the groundwork for future multi-modal data modeling. Our results confirm that TCGN is a powerful tool for inferring gene expressions from histopathological images in precision health applications.

Graph-based multi-modality integration for prediction of cancer subtype and severity

Personalised cancer screening before therapy paves the way toward improving diagnostic accuracy and treatment outcomes. Most approaches are limited to a single data type and do not consider interactions between features, leaving aside the complementary insights that multimodality and systems biology can provide. In this project, we demonstrate the use of graph theory for data integration via individual networks where nodes and edges are individual-specific. We showcase the consequences of early, intermediate, and late graph-based fusion of RNA-Seq data and histopathology whole-slide images for predicting cancer subtypes and severity. The methodology developed is as follows: (1) we create individual networks; (2) we compute the similarity between individuals from these graphs; (3) we train our model on the similarity matrices; (4) we evaluate the performance using the macro F1 score. Pros and cons of elements of the pipeline are evaluated on publicly available real-life datasets. We find that graph-based methods can increase performance over methods that do not study interactions. Additionally, merging multiple data sources often improves classification compared to models based on single data, especially through intermediate fusion. The proposed workflow can easily be adapted to other disease contexts to accelerate and enhance personalized healthcare.

A fast non-parametric test of association for multiple traits

The increasing availability of multidimensional phenotypic data in large cohorts of genotyped individuals requires efficient methods to identify genetic effects on multiple traits. Permutational multivariate analysis of variance (PERMANOVA) offers a powerful non-parametric approach. However, it relies on permutations to assess significance, which hinders the analysis of large datasets. Here, we derive the limiting null distribution of the PERMANOVA test statistic, providing a framework for the fast computation of asymptotic p values. Our asymptotic test presents controlled type I error and high power, often outperforming parametric approaches. We illustrate its applicability in the context of QTL mapping and GWAS.

Deep learning integrates histopathology and proteogenomics at a pan-cancer level

We introduce a pioneering approach that integrates pathology imaging with transcriptomics and proteomics to identify predictive histology features associated with critical clinical outcomes in cancer. We utilize 2,755 H&E-stained histopathological slides from 657 patients across 6 cancer types from CPTAC. Our models effectively recapitulate distinctions readily made by human pathologists: tumor vs. normal (AUROC = 0.995) and tissue-of-origin (AUROC = 0.979). We further investigate predictive power on tasks not normally performed from H&E alone, including TP53 prediction and pathologic stage. Importantly, we describe predictive morphologies not previously utilized in a clinical setting. The incorporation of transcriptomics and proteomics identifies pathway-level signatures and cellular processes driving predictive histology features. Model generalizability and interpretability is confirmed using TCGA. We propose a classification system for these tasks, and suggest potential clinical applications for this integrated human and machine learning approach. A publicly available web-based platform implements these models.

Identification and Analysis of Imaging-Genomic Signatures to Study Recurrence in Breast Cancers

One of the main causes of breast cancer related death is its recurrence. In this study, we investigate the association of gene expression and pathological image features to understand breast cancer recurrence. A total of 172 breast cancer patient data was downloaded from the TCGA-BRCA database. The dataset contained diagnostic whole slide images and RNA-seq data of 80 recurrent and 92 disease-free breast cancer patients. We performed genomic analysis on RNA-seq data to obtain the hub genes related to recurrent breast cancer. We extracted relevant pathomic features from histopathology images. The discriminative ability of the hub genes and pathomic features were evaluated using machine learning classifiers. We used Spearman rank correlation analysis to find statistically significant association between gene expression and pathomic features. We identified that, genes which are related to breast cancer progression is significantly associated (adjusted p-value<0.05) with several pathomic features.Clinical Relevance- Histopathology is the gold standard for cancer detection. It provides us with cellular level information. A strong association between a pathomic feature and a gene expression will help clinicians understand the cellular and molecular mechanism of cancer for better prognosis.

SynapseCLR: Uncovering features of synapses in primary visual cortex through contrastive representation learning

3D electron microscopy (EM) connectomics image volumes are surpassing 1 mm³, providing information-dense, multi-scale visualizations of brain circuitry and necessitating scalable analysis techniques. We present SynapseCLR, a self-supervised contrastive learning method for 3D EM data, and use it to extract features of synapses from mouse visual cortex. SynapseCLR feature representations separate synapses by appearance and functionally important structural annotations. We demonstrate SynapseCLR's utility for valuable downstream tasks, including one-shot identification of defective synapse segmentations, dataset-wide similarity-based querying, and accurate imputation of annotations for unlabeled synapses, using manual annotation of only 0.2% of the dataset's synapses. In particular, excitatory versus inhibitory neuronal types can be assigned with >99.8% accuracy to individual synapses and highly truncated neurites, enabling neurite-enhanced connectomics analysis. Finally, we present a data-driven, unsupervised study of synaptic structural variation on the representation manifold, revealing its intrinsic axes of variation and showing that representations contain inhibitory subtype information.

A Comprehensive Landscape of Imaging Feature-Associated RNA Expression Profiles in Human Breast Tissue

The expression abundance of transcripts in nondiseased breast tissue varies among individuals. The association study of genotypes and imaging phenotypes may help us to understand this individual variation. Since existing reports mainly focus on tumors or lesion areas, the heterogeneity of pathological image features and their correlations with RNA expression profiles for nondiseased tissue are not clear. The aim of this study is to discover the association between the nucleus features and the transcriptome-wide RNAs. We analyzed both microscopic histology images and RNA-sequencing data of 456 breast tissues from the Genotype-Tissue Expression (GTEx) project and constructed an automatic computational framework. We classified all samples into four clusters based on their nucleus morphological features and discovered feature-specific gene sets. The biological pathway analysis was performed on each gene set. The proposed framework evaluates the morphological characteristics of the cell nucleus quantitatively and identifies the associated genes. We found image features that capture population variation in breast tissue associated with RNA expressions, suggesting that the variation in expression pattern affects population variation in the morphological traits of breast tissue. This study provides a comprehensive transcriptome-wide view of imaging-feature-specific RNA expression for healthy breast tissue. Such a framework could also be used for understanding the connection between RNA expression and morphology in other tissues and organs. Pathway analysis indicated that the gene sets we identified were involved in specific biological processes, such as immune processes.

The landscape of expression and alternative splicing variation across human traits

Understanding the consequences of individual transcriptome variation is fundamental to deciphering human biology and disease. We implement a statistical framework to quantify the contributions of 21 individual traits as drivers of gene expression and alternative splicing variation across 46 human tissues and 781 individuals from the Genotype-Tissue Expression project. We demonstrate that ancestry, sex, age, and BMI make additive and tissue-specific contributions to expression variability, whereas interactions are rare. Variation in splicing is dominated by ancestry and is under genetic control in most tissues, with ribosomal proteins showing a strong enrichment of tissue-shared splicing events. Our analyses reveal a systemic contribution of types 1 and 2 diabetes to tissue transcriptome variation with the strongest signal in the nerve, where histopathology image analysis identifies novel genes related to diabetic neuropathy. Our multi-tissue and multi-trait approach provides an extensive characterization of the main drivers of human transcriptome variation in health and disease.

Unsupervised discovery of tissue architecture in multiplexed imaging

Multiplexed imaging and spatial transcriptomics enable highly resolved spatial characterization of cellular phenotypes, but still largely depend on laborious manual annotation to understand higher-order patterns of tissue organization. As a result, higher-order patterns of tissue organization are poorly understood and not systematically connected to disease pathology or clinical outcomes. To address this gap, we developed an approach called UTAG to identify and quantify microanatomical tissue structures in multiplexed images without human intervention. Our method combines information on cellular phenotypes with the physical proximity of cells to accurately identify organ-specific microanatomical domains in healthy and diseased tissue. We apply our method to various types of images across healthy and disease states to show that it can consistently detect higher-level architectures in human tissues, quantify structural differences between healthy and diseased tissue, and reveal tissue organization patterns at the organ scale.

Direct Gene Expression Profile Prediction for Uveal Melanoma from Digital Cytopathology Images via Deep Learning and Salient Image Region Identification

Objective

To demonstrate that deep learning (DL) methods can produce robust prediction of gene expression profile (GEP) in uveal melanoma (UM) based on digital cytopathology images.

Design

Evaluation of a diagnostic test or technology.

Subjects Participants and Controls

Deidentified smeared cytology slides stained with hematoxylin and eosin obtained from a fine needle aspirated from UM.

Methods

Digital whole-slide images were generated by fine-needle aspiration biopsies of UM tumors that underwent GEP testing. A multistage DL system was developed with automatic region-of-interest (ROI) extraction from digital cytopathology images, an attention-based neural network, ROI feature aggregation, and slide-level data augmentation.

Main Outcome Measures

The ability of our DL system in predicting GEP on a slide (patient) level. Data were partitioned at the patient level (73% training; 27% testing).

Results

In total, our study included 89 whole-slide images from 82 patients and 121 388 unique ROIs. The testing set included 24 slides from 24 patients (12 class 1 tumors; 12 class 2 tumors; 1 slide per patient). Our DL system for GEP prediction achieved an area under the receiver operating characteristic curve of 0.944, an accuracy of 91.7%, a sensitivity of 91.7%, and a specificity of 91.7% on a slide-level analysis. The incorporation of slide-level feature aggregation and data augmentation produced a more predictive DL model (P = 0.0031).

Conclusions

Our current work established a complete pipeline for GEP prediction in UM tumors: from automatic ROI extraction from digital cytopathology whole-slide images to slide-level predictions. Our DL system demonstrated robust performance and, if validated prospectively, could serve as an image-based alternative to GEP testing.

Spatial Transcriptomic Analysis Reveals Associations between Genes and Cellular Topology in Breast and Prostate Cancers

BACKGROUND

Cancer is the leading cause of death worldwide with breast and prostate cancer the most common among women and men, respectively. Gene expression and image features are independently prognostic of patient survival; but until the advent of spatial transcriptomics (ST), it was not possible to determine how gene expression of cells was tied to their spatial relationships (i.e., topology).

METHODS

We identify topology-associated genes (TAGs) that correlate with 700 image topological features (ITFs) in breast and prostate cancer ST samples. Genes and image topological features are independently clustered and correlated with each other. Themes among genes correlated with ITFs are investigated by functional enrichment analysis.

RESULTS

Overall, topology-associated genes (TAG) corresponding to extracellular matrix (ECM) and Collagen Type I Trimer gene ontology terms are common to both prostate and breast cancer. In breast cancer specifically, we identify the ZAG-PIP Complex as a TAG. In prostate cancer, we identify distinct TAGs that are enriched for GI dysmotility and the IgA immunoglobulin complex. We identified TAGs in every ST slide regardless of cancer type.

CONCLUSIONS

These TAGs are enriched for ontology terms, illustrating the biological relevance to our image topology features and their potential utility in diagnostic and prognostic models.

Telescoping bimodal latent Dirichlet allocation to identify expression QTLs across tissues

Expression quantitative trait loci (eQTLs), or single-nucleotide polymorphisms that affect average gene expression levels, provide important insights into context-specific gene regulation. Classic eQTL analyses use one-to-one association tests, which test gene-variant pairs individually and ignore correlations induced by gene regulatory networks and linkage disequilibrium. Probabilistic topic models, such as latent Dirichlet allocation, estimate latent topics for a collection of count observations. Prior multimodal frameworks that bridge genotype and expression data assume matched sample numbers between modalities. However, many data sets have a nested structure where one individual has several associated gene expression samples and a single germline genotype vector. Here, we build a telescoping bimodal latent Dirichlet allocation (TBLDA) framework to learn shared topics across gene expression and genotype data that allows multiple RNA sequencing samples to correspond to a single individual's genotype. By using raw count data, our model avoids possible adulteration via normalization procedures. Ancestral structure is captured in a genotype-specific latent space, effectively removing it from shared components. Using GTEx v8 expression data across 10 tissues and genotype data, we show that the estimated topics capture meaningful and robust biological signal in both modalities and identify associations within and across tissue types. We identify 4,645 cis-eQTLs and 995 trans-eQTLs by conducting eQTL mapping between the most informative features in each topic. Our TBLDA model is able to identify associations using raw sequencing count data when the samples in two separate data modalities are matched one-to-many, as is often the case in biological data. Our code is freely available at https://github.com/gewirtz/TBLDA.

Unraveling the Complexity of Liver Disease One Cell at a Time

The human liver is a complex organ made up of multiple specialized cell types that carry out key physiological functions. An incomplete understanding of liver biology limits our ability to develop therapeutics to prevent chronic liver diseases, liver cancers, and death as a result of organ failure. Recently, single-cell modalities have expanded our understanding of the cellular phenotypic heterogeneity and intercellular cross-talk in liver health and disease. This review summarizes these findings and looks forward to highlighting new avenues for the application of single-cell genomics to unravel unknown pathogenic pathways and disease mechanisms for the development of new therapeutics targeting liver pathology. As these technologies mature, their integration into clinical data analysis will aid in patient stratification and in developing treatment plans for patients suffering from liver disease.

Contrastive learning-based computational histopathology predict differential expression of cancer driver genes

MOTIVATION

Digital pathological analysis is run as the main examination used for cancer diagnosis. Recently, deep learning-driven feature extraction from pathology images is able to detect genetic variations and tumor environment, but few studies focus on differential gene expression in tumor cells.

RESULTS

In this paper, we propose a self-supervised contrastive learning framework, HistCode, to infer differential gene expression from whole slide images (WSIs). We leveraged contrastive learning on large-scale unannotated WSIs to derive slide-level histopathological features in latent space, and then transfer it to tumor diagnosis and prediction of differentially expressed cancer driver genes. Our experiments showed that our method outperformed other state-of-the-art models in tumor diagnosis tasks, and also effectively predicted differential gene expression. Interestingly, we found the genes with higher fold change can be more precisely predicted. To intuitively illustrate the ability to extract informative features from pathological images, we spatially visualized the WSIs colored by the attention scores of image tiles. We found that the tumor and necrosis areas were highly consistent with the annotations of experienced pathologists. Moreover, the spatial heatmap generated by lymphocyte-specific gene expression patterns was also consistent with the manually labeled WSIs.

transferGWAS: GWAS of images using deep transfer learning

MOTIVATION

Medical images can provide rich information about diseases and their biology. However, investigating their association with genetic variation requires non-standard methods. We propose transferGWAS, a novel approach to perform genome-wide association studies directly on full medical images. First, we learn semantically meaningful representations of the images based on a transfer learning task, during which a deep neural network is trained on independent but similar data. Then, we perform genetic association tests with these representations.

RESULTS

We validate the type I error rates and power of transferGWAS in simulation studies of synthetic images. Then we apply transferGWAS in a genome-wide association study of retinal fundus images from the UK Biobank. This first-of-a-kind GWAS of full imaging data yielded 60 genomic regions associated with retinal fundus images, of which 7 are novel candidate loci for eye-related traits and diseases.

AVAILABILITY AND IMPLEMENTATION

Our method is implemented in Python and available at https://github.com/mkirchler/transferGWAS/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Self-supervised learning of cell type specificity from immunohistochemical images

Motivation

Advances in bioimaging now permit in situ proteomic characterization of cell–cell interactions in complex tissues, with important applications across a spectrum of biological problems from development to disease. These methods depend on selection of antibodies targeting proteins that are expressed specifically in particular cell types. Candidate marker proteins are often identified from single-cell transcriptomic data, with variable rates of success, in part due to divergence between expression levels of proteins and the genes that encode them. In principle, marker identification could be improved by using existing databases of immunohistochemistry for thousands of antibodies in human tissue, such as the Human Protein Atlas. However, these data lack detailed annotations of the types of cells in each image.

Results

We develop a method to predict cell type specificity of protein markers from unlabeled images. We train a convolutional neural network with a self-supervised objective to generate embeddings of the images. Using non-linear dimensionality reduction, we observe that the model clusters images according to cell types and anatomical regions for which the stained proteins are specific. We then use estimates of cell type specificity derived from an independent single-cell transcriptomics dataset to train an image classifier, without requiring any human labelling of images. Our scheme demonstrates superior classification of known proteomic markers in kidney compared to selection via single-cell transcriptomics.

Availability and implementation

Code and trained model are available at www.github.com/murphy17/HPA-SimCLR.

Supplementary information

Supplementary data are available at Bioinformatics online.

Identification of shared and disease-specific host gene-microbiome associations across human diseases using multi-omic integration

While gut microbiome and host gene regulation independently contribute to gastrointestinal disorders, it is unclear how the two may interact to influence host pathophysiology. Here we developed a machine learning-based framework to jointly analyse paired host transcriptomic (n = 208) and gut microbiome (n = 208) profiles from colonic mucosal samples of patients with colorectal cancer, inflammatory bowel disease and irritable bowel syndrome. We identified associations between gut microbes and host genes that depict shared as well as disease-specific patterns. We found that a common set of host genes and pathways implicated in gastrointestinal inflammation, gut barrier protection and energy metabolism are associated with disease-specific gut microbes. Additionally, we also found that mucosal gut microbes that have been implicated in all three diseases, such as Streptococcus, are associated with different host pathways in each disease, suggesting that similar microbes can affect host pathophysiology in a disease-specific manner through regulation of different host genes. Our framework can be applied to other diseases for the identification of host gene-microbiome associations that may influence disease outcomes.

Multi-modal Learning with Missing Data for Cancer Diagnosis Using Histopathological and Genomic Data

Multi-modal learning (e.g., integrating pathological images with genomic features) tends to improve the accuracy of cancer diagnosis and prognosis as compared to learning with a single modality. However, missing data is a common problem in clinical practice, i.e., not every patient has all modalities available. Most of the previous works directly discarded samples with missing modalities, which might lose information in these data and increase the likelihood of overfitting. In this work, we generalize the multi-modal learning in cancer diagnosis with the capacity of dealing with missing data using histological images and genomic data. Our integrated model can utilize all available data from patients with both complete and partial modalities. The experiments on the public TCGA-GBM and TCGA-LGG datasets show that the data with missing modalities can contribute to multi-modal learning, which improves the model performance in grade classification of glioma cancer.

JOINT AND INDIVIDUAL ANALYSIS OF BREAST CANCER HISTOLOGIC IMAGES AND GENOMIC COVARIATES

The two main approaches in the study of breast cancer are histopathology (analyzing visual characteristics of tumors) and genomics. While both histopathology and genomics are fundamental to cancer research, the connections between these fields have been relatively superficial. We bridge this gap by investigating the Carolina Breast Cancer Study through the development of an integrative, exploratory analysis framework. Our analysis gives insights - some known, some novel - that are engaging to both pathologists and geneticists. Our analysis framework is based on Angle-based Joint and Individual Variation Explained (AJIVE) for statistical data integration and exploits Convolutional Neural Networks (CNNs) as a powerful, automatic method for image feature extraction. CNNs raise interpretability issues that we address by developing novel methods to explore visual modes of variation captured by statistical algorithms (e.g. PCA or AJIVE) applied to CNN features.

Integrating pathomics with radiomics and genomics for cancer prognosis: A brief review

In the last decade, the focus of computational pathology research community has shifted from replicating the pathological examination for diagnosis done by pathologists to unlocking and discovering "sub-visual" prognostic image cues from the histopathological image. While we are getting more knowledge and experience in digital pathology, the emerging goal is to integrate other-omics or modalities that will contribute for building a better prognostic assay. In this paper, we provide a brief review of representative works that focus on integrating pathomics with radiomics and genomics for cancer prognosis. It includes: correlation of pathomics and genomics; fusion of pathomics and genomics; fusion of pathomics and radiomics. We also present challenges, potential opportunities, and avenues for future work.

Deep learning for bioimage analysis in developmental biology

Deep learning has transformed the way large and complex image datasets can be processed, reshaping what is possible in bioimage analysis. As the complexity and size of bioimage data continues to grow, this new analysis paradigm is becoming increasingly ubiquitous. In this Review, we begin by introducing the concepts needed for beginners to understand deep learning. We then review how deep learning has impacted bioimage analysis and explore the open-source resources available to integrate it into a research project. Finally, we discuss the future of deep learning applied to cell and developmental biology. We analyze how state-of-the-art methodologies have the potential to transform our understanding of biological systems through new image-based analysis and modelling that integrate multimodal inputs in space and time.

Microbiomes of Various Maternal Body Systems Are Predictive of Calf Digestive Bacterial Ecology

Body systems once thought sterile at birth instead have complex and sometimes abundant microbial ecosystems. However, relationships between dam and calf microbial ecosystems are still unclear. The objectives of this study were to (1) characterize the various maternal and calf microbiomes during peri-partum and post-partum periods and (2) examine the influence of the maternal microbiome on calf fecal microbiome composition during the pre-weaning phase. Multiparous Holstein cows were placed in individual, freshly bedded box stalls 14 d before expected calving. Caudal vaginal fluid samples were collected approximately 24 h before calving and dam fecal, oral, colostrum, and placenta samples were collected immediately after calving. Calf fecal samples were collected at birth (meconium) and 24 h, 7 d, 42 d, and 60 d of age. Amplicons covering V4 16S rDNA regions were generated using DNA extracted from all samples and were sequenced using 300 bp paired end Illumina MiSeq sequencing. Spearman rank correlations were performed between genera in maternal and calf fecal microbiomes. Negative binomial regression models were created for genera in calf fecal samples at each time point using genera in maternal microbiomes. We determined that Bacteroidetes dominated the calf fecal microbiome at all time points (relative abundance ≥42.55%) except for 24 h post-calving, whereas Proteobacteria were the dominant phylum (relative abundance = 85.10%). Maternal fecal, oral, placental, vaginal, and colostrum microbiomes were significant predictors of calf fecal microbiome throughout pre-weaning. Results indicate that calf fecal microbiome inoculation and development may be derived from various maternal sources. Maternal microbiomes could be used to predict calf microbiome development, but further research on the environmental and genetic influences is needed.

Interpretable deep learning uncovers cellular properties in label-free live cell images that are predictive of highly metastatic melanoma

Deep learning has emerged as the technique of choice for identifying hidden patterns in cell imaging data but is often criticized as "black box." Here, we employ a generative neural network in combination with supervised machine learning to classify patient-derived melanoma xenografts as "efficient" or "inefficient" metastatic, validate predictions regarding melanoma cell lines with unknown metastatic efficiency in mouse xenografts, and use the network to generate in silico cell images that amplify the critical predictive cell properties. These exaggerated images unveiled pseudopodial extensions and increased light scattering as hallmark properties of metastatic cells. We validated this interpretation using live cells spontaneously transitioning between states indicative of low and high metastatic efficiency. This study illustrates how the application of artificial intelligence can support the identification of cellular properties that are predictive of complex phenotypes and integrated cell functions but are too subtle to be identified in the raw imagery by a human expert. A record of this paper's transparent peer review process is included in the supplemental information. VIDEO ABSTRACT.

Automated AI labeling of optic nerve head enables insights into cross-ancestry glaucoma risk and genetic discovery in >280,000 images from UKB and CLSA

Cupping of the optic nerve head, a highly heritable trait, is a hallmark of glaucomatous optic neuropathy. Two key parameters are vertical cup-to-disc ratio (VCDR) and vertical disc diameter (VDD). However, manual assessment often suffers from poor accuracy and is time intensive. Here, we show convolutional neural network models can accurately estimate VCDR and VDD for 282,100 images from both UK Biobank and an independent study (Canadian Longitudinal Study on Aging), enabling cross-ancestry epidemiological studies and new genetic discovery for these optic nerve head parameters. Using the AI approach, we perform a systematic comparison of the distribution of VCDR and VDD and compare these with intraocular pressure and glaucoma diagnoses across various genetically determined ancestries, which provides an explanation for the high rates of normal tension glaucoma in East Asia. We then used the large number of AI gradings to conduct a more powerful genome-wide association study (GWAS) of optic nerve head parameters. Using the AI-based gradings increased estimates of heritability by ∼50% for VCDR and VDD. Our GWAS identified more than 200 loci associated with both VCDR and VDD (double the number of loci from previous studies) and uncovered dozens of biological pathways; many of the loci we discovered also confer risk for glaucoma.