A multi-encoder variational autoencoder controls multiple transformational features in single-cell image analysis

Systematic data analysis pipeline for quantitative morphological cell phenotyping

Quantitative morphological phenotyping (QMP) is an image-based method used to capture morphological features at both the cellular and population level. Its interdisciplinary nature, spanning from data collection to result analysis and interpretation, can lead to uncertainties, particularly among those new to this actively growing field. High analytical specificity for a typical QMP is achieved through sophisticated approaches that can leverage subtle cellular morphological changes. Here, we outline a systematic workflow to refine the QMP methodology. For a practical review, we describe the main steps of a typical QMP; in each step, we discuss the available methods, their applications, advantages, and disadvantages, along with the R functions and packages for easy implementation. This review does not cover theoretical backgrounds, but provides several references for interested researchers. It aims to broaden the horizons for future phenome studies and demonstrate how to exploit years of endeavors to achieve more with less.

Application of a variational autoencoder for clustering and analyzing in situ articular cartilage cellular response to mechanical stimuli

In various biological systems, analyzing how cell behaviors are coordinated over time would enable a deeper understanding of tissue-scale response to physiologic or superphysiologic stimuli. Such data is necessary for establishing both normal tissue function and the sequence of events after injury that lead to chronic disease. However, collecting and analyzing these large datasets presents a challenge-such systems are time-consuming to process, and the overwhelming scale of data makes it difficult to parse overall behaviors. This problem calls for an analysis technique that can quickly provide an overview of the groups present in the entire system and also produce meaningful categorization of cell behaviors. Here, we demonstrate the application of an unsupervised method-the Variational Autoencoder (VAE)-to learn the features of cells in cartilage tissue after impact-induced injury and identify meaningful clusters of chondrocyte behavior. This technique quickly generated new insights into the spatial distribution of specific cell behavior phenotypes and connected specific peracute calcium signaling timeseries with long term cellular outcomes, demonstrating the value of the VAE technique.

Machine learning-assisted search for novel coagulants: When machine learning can be efficient even if data availability is low

Design of new drugs is a challenging process: a candidate molecule should satisfy multiple conditions to act properly and make the least side-effect-perfect candidates selectively attach to and influence only targets, leaving off-targets intact. The amount of experimental data about various properties of molecules constantly grows, promoting data-driven approaches. However, the applicability of typical predictive machine learning techniques can be substantially limited by a lack of experimental data about a particular target. For example, there are many known Thrombin inhibitors (acting as anticoagulants), but a very limited number of known Protein C inhibitors (coagulants). In this study, we present our approach to suggest new inhibitor candidates by building an effective representation of chemical space. For this aim, we developed a deep learning model-autoencoder, trained on a large set of molecules in the SMILES format to map the chemical space. Further, we applied different sampling strategies to generate novel coagulant candidates. Symmetrically, we tested our approach on anticoagulant candidates, where we were able to predict their inhibition towards Thrombin. We also compare our approach with MegaMolBART-another deep learning generative model, but exploiting similar principles of navigation in a chemical space.

Quantitative image analysis pipeline for detecting circulating hybrid cells in immunofluorescence images with human-level accuracy

Circulating hybrid cells (CHCs) are a newly discovered, tumor-derived cell population found in the peripheral blood of cancer patients and are thought to contribute to tumor metastasis. However, identifying CHCs by immunofluorescence (IF) imaging of patient peripheral blood mononuclear cells (PBMCs) is a time-consuming and subjective process that currently relies on manual annotation by laboratory technicians. Additionally, while IF is relatively easy to apply to tissue sections, its application to PBMC smears presents challenges due to the presence of biological and technical artifacts. To address these challenges, we present a robust image analysis pipeline to automate the detection and analysis of CHCs in IF images. The pipeline incorporates quality control to optimize specimen preparation protocols and remove unwanted artifacts, leverages a β-variational autoencoder (VAE) to learn meaningful latent representations of single-cell images, and employs a support vector machine (SVM) classifier to achieve human-level CHC detection. We created a rigorously labeled IF CHC data set including nine patients and two disease sites with the assistance of 10 annotators to evaluate the pipeline. We examined annotator variation and bias in CHC detection and provided guidelines to optimize the accuracy of CHC annotation. We found that all annotators agreed on CHC identification for only 65% of the cells in the data set and had a tendency to underestimate CHC counts for regions of interest (ROIs) containing relatively large amounts of cells (>50,000) when using the conventional enumeration method. On the other hand, our proposed approach is unbiased to ROI size. The SVM classifier trained on the β-VAE embeddings achieved an F1 score of 0.80, matching the average performance of human annotators. Our pipeline enables researchers to explore the role of CHCs in cancer progression and assess their potential as a clinical biomarker for metastasis. Further, we demonstrate that the pipeline can identify discrete cellular phenotypes among PBMCs, highlighting its utility beyond CHCs.

MIM-CyCIF: masked imaging modeling for enhancing cyclic immunofluorescence (CyCIF) with panel reduction and imputation

Cyclic Immunofluorescence (CyCIF) can quantify multiple biomarkers, but panel capacity is limited by technical challenges. We propose a computational panel reduction approach that can impute the information content from 25 markers using only 9 markers, learning co-expression and morphological patterns while concurrently increasing speed and panel content and decreasing cost. We demonstrate strong correlations in predictions and generalizability across breast and colorectal cancer, illustrating applicability of our approach to diverse tissue types.

Deciphering the Lexicon of Protein Targets: A Review on Multifaceted Drug Discovery in the Era of Artificial Intelligence

Understanding protein sequence and structure is essential for understanding protein-protein interactions (PPIs), which are essential for many biological processes and diseases. Targeting protein binding hot spots, which regulate signaling and growth, with rational drug design is promising. Rational drug design uses structural data and computational tools to study protein binding sites and protein interfaces to design inhibitors that can change these interactions, thereby potentially leading to therapeutic approaches. Artificial intelligence (AI), such as machine learning (ML) and deep learning (DL), has advanced drug discovery and design by providing computational resources and methods. Quantum chemistry is essential for drug reactivity, toxicology, drug screening, and quantitative structure-activity relationship (QSAR) properties. This review discusses the methodologies and challenges of identifying and characterizing hot spots and binding sites. It also explores the strategies and applications of artificial-intelligence-based rational drug design technologies that target proteins and protein-protein interaction (PPI) binding hot spots. It provides valuable insights for drug design with therapeutic implications. We have also demonstrated the pathological conditions of heat shock protein 27 (HSP27) and matrix metallopoproteinases (MMP2 and MMP9) and designed inhibitors of these proteins using the drug discovery paradigm in a case study on the discovery of drug molecules for cancer treatment. Additionally, the implications of benzothiazole derivatives for anticancer drug design and discovery are deliberated.

Quantifying the distribution of feature values over data represented in arbitrary dimensional spaces

Identifying the structured distribution (or lack thereof) of a given feature over a point cloud is a general research question. In the neuroscience field, this problem arises while investigating representations over neural manifolds (e.g., spatial coding), in the analysis of neurophysiological signals (e.g., sensory coding) or in anatomical image segmentation. We introduce the Structure Index (SI) as a directed graph-based metric to quantify the distribution of feature values projected over data in arbitrary D-dimensional spaces (defined from neurons, time stamps, pixels, genes, etc). The SI is defined from the overlapping distribution of data points sharing similar feature values in a given neighborhood of the cloud. Using arbitrary data clouds, we show how the SI provides quantification of the degree and directionality of the local versus global organization of feature distribution. SI can be applied to both scalar and vectorial features permitting quantification of the relative contribution of related variables. When applied to experimental studies of head-direction cells, it is able to retrieve consistent feature structure from both the high- and low-dimensional representations, and to disclose the local and global structure of the angle and speed represented in different brain regions. Finally, we provide two general-purpose examples (sound and image categorization), to illustrate the potential application to arbitrary dimensional spaces. Our method provides versatile applications in the neuroscience and data science fields.

Joint shape/texture representation learning for cardiovascular disease diagnosis from magnetic resonance imaging

Aims

Cardiovascular diseases (CVDs) are the leading cause of mortality worldwide. Cardiac image and mesh are two primary modalities to present the shape and structure of the heart and have been demonstrated to be efficient in CVD prediction and diagnosis. However, previous research has been generally focussed on a single modality (image or mesh), and few of them have tried to jointly consider the image and mesh representations of heart. To obtain efficient and explainable biomarkers for CVD prediction and diagnosis, it is needed to jointly consider both representations.

Methods and results

We design a novel multi-channel variational auto-encoder, mesh-image variational auto-encoder, to learn joint representation of paired mesh and image. After training, the shape-aware image representation (SAIR) can be learned directly from the raw images and applied for further CVD prediction and diagnosis. We demonstrate our method on data from UK Biobank study and two other datasets via extensive experiments. In acute myocardial infarction prediction, SAIR achieves 81.43% accuracy, significantly higher than traditional biomarkers like metadata and clinical indices (left ventricle and right ventricle clinical indices of cardiac function like chamber volume, mass, and ejection fraction).

Conclusion

Our mesh-image variational auto-encoder provides a novel approach for 3D cardiac mesh reconstruction from images. The extraction of SAIR is fast and without need of segmentation masks, and its focussing can be visualized in the corresponding cardiac meshes. SAIR archives better performance than traditional biomarkers and can be applied as an efficient supplement to them, which is of significant potential in CVD analysis.

Evolution and impact of high content imaging

The field of high content imaging has steadily evolved and expanded substantially across many industry and academic research institutions since it was first described in the early 1990's. High content imaging refers to the automated acquisition and analysis of microscopic images from a variety of biological sample types. Integration of high content imaging microscopes with multiwell plate handling robotics enables high content imaging to be performed at scale and support medium- to high-throughput screening of pharmacological, genetic and diverse environmental perturbations upon complex biological systems ranging from 2D cell cultures to 3D tissue organoids to small model organisms. In this perspective article the authors provide a collective view on the following key discussion points relevant to the evolution of high content imaging: • Evolution and impact of high content imaging: An academic perspective • Evolution and impact of high content imaging: An industry perspective • Evolution of high content image analysis • Evolution of high content data analysis pipelines towards multiparametric and phenotypic profiling applications • The role of data integration and multiomics • The role and evolution of image data repositories and sharing standards • Future perspective of high content imaging hardware and software.

MIM-CyCIF: Masked Imaging Modeling for Enhancing Cyclic Immunofluorescence (CyCIF) with Panel Reduction and Imputation

CyCIF can quantify multiple biomarkers, but panel capacity is limited by technical challenges. We propose a computational panel reduction approach that can impute the information content from 25 markers using only 9 markers, learning co-expression and morphological patterns while concurrently increasing speed and panel content and decreasing cost. We demonstrate strong correlations in predictions and generalizability across breast and colorectal cancer, illustrating applicability of our approach to diverse tissue types.

Quantitative image analysis pipeline for detecting circulating hybrid cells in immunofluorescence images with human-level accuracy

Circulating hybrid cells (CHCs) are a newly discovered, tumor-derived cell population identified in the peripheral blood of cancer patients and are thought to contribute to tumor metastasis. However, identifying CHCs by immunofluorescence (IF) imaging of patient peripheral blood mononuclear cells (PBMCs) is a time-consuming and subjective process that currently relies on manual annotation by laboratory technicians. Additionally, while IF is relatively easy to apply to tissue sections, its application on PBMC smears presents challenges due to the presence of biological and technical artifacts. To address these challenges, we present a robust image analysis pipeline to automate the detection and analyses of CHCs in IF images. The pipeline incorporates quality control to optimize specimen preparation protocols and remove unwanted artifacts, leverages a β-variational autoencoder (VAE) to learn meaningful latent representations of single-cell images and employs a support vector machine (SVM) classifier to achieve human-level CHC detection. We created a rigorously labeled IF CHC dataset including 9 patients and 2 disease sites with the assistance of 10 annotators to evaluate the pipeline. We examined annotator variation and bias in CHC detection and then provided guidelines to optimize the accuracy of CHC annotation. We found that all annotators agreed on CHC identification for only 65% of the cells in the dataset and had a tendency to underestimate CHC counts for regions of interest (ROI) containing relatively large amounts of cells (>50,000) when using conventional enumeration methods. On the other hand, our proposed approach is unbiased to ROI size. The SVM classifier trained on the β-VAE encodings achieved an F1 score of 0.80, matching the average performance of annotators. Our pipeline enables researchers to explore the role of CHCs in cancer progression and assess their potential as a clinical biomarker for metastasis. Further, we demonstrate that the pipeline can identify discrete cellular phenotypes among PBMCs, highlighting its utility beyond CHCs.

MIM-CyCIF: Masked Imaging Modeling for Enhancing Cyclic Immunofluorescence (CyCIF) with Panel Reduction and Imputation

CyCIF quantifies multiple biomarkers, but panel capacity is compromised by technical challenges including tissue loss. We propose a computational panel reduction, inferring surrogate CyCIF data from a subset of biomarkers. Our model reconstructs the information content from 25 markers using only 9 markers, learning co-expression and morphological patterns. We demonstrate strong correlations in predictions and generalizability across breast and colorectal cancer tissue microarrays, illustrating broader applicability to diverse tissue types.

Addressing persistent challenges in digital image analysis of cancerous tissues

The National Cancer Institute (NCI) supports many research programs and consortia, many of which use imaging as a major modality for characterizing cancerous tissue. A trans-consortia Image Analysis Working Group (IAWG) was established in 2019 with a mission to disseminate imaging-related work and foster collaborations. In 2022, the IAWG held a virtual hackathon focused on addressing challenges of analyzing high dimensional datasets from fixed cancerous tissues. Standard image processing techniques have automated feature extraction, but the next generation of imaging data requires more advanced methods to fully utilize the available information. In this perspective, we discuss current limitations of the automated analysis of multiplexed tissue images, the first steps toward deeper understanding of these limitations, what possible solutions have been developed, any new or refined approaches that were developed during the Image Analysis Hackathon 2022, and where further effort is required. The outstanding problems addressed in the hackathon fell into three main themes: 1) challenges to cell type classification and assessment, 2) translation and visual representation of spatial aspects of high dimensional data, and 3) scaling digital image analyses to large (multi-TB) datasets. We describe the rationale for each specific challenge and the progress made toward addressing it during the hackathon. We also suggest areas that would benefit from more focus and offer insight into broader challenges that the community will need to address as new technologies are developed and integrated into the broad range of image-based modalities and analytical resources already in use within the cancer research community.

Morphodynamical cell state description via live-cell imaging trajectory embedding

Time-lapse imaging is a powerful approach to gain insight into the dynamic responses of cells, but the quantitative analysis of morphological changes over time remains challenging. Here, we exploit the concept of "trajectory embedding" to analyze cellular behavior using morphological feature trajectory histories-that is, multiple time points simultaneously, rather than the more common practice of examining morphological feature time courses in single timepoint (snapshot) morphological features. We apply this approach to analyze live-cell images of MCF10A mammary epithelial cells after treatment with a panel of microenvironmental perturbagens that strongly modulate cell motility, morphology, and cell cycle behavior. Our morphodynamical trajectory embedding analysis constructs a shared cell state landscape revealing ligand-specific regulation of cell state transitions and enables quantitative and descriptive models of single-cell trajectories. Additionally, we show that incorporation of trajectories into single-cell morphological analysis enables (i) systematic characterization of cell state trajectories, (ii) better separation of phenotypes, and (iii) more descriptive models of ligand-induced differences as compared to snapshot-based analysis. This morphodynamical trajectory embedding is broadly applicable to the quantitative analysis of cell responses via live-cell imaging across many biological and biomedical applications.

Computational multiplex panel reduction to maximize information retention in breast cancer tissue microarrays

Recent state-of-the-art multiplex imaging techniques have expanded the depth of information that can be captured within a single tissue sample by allowing for panels with dozens of markers. Despite this increase in capacity, space on the panel is still limited due to technical artifacts, tissue loss, and long imaging acquisition time. As such, selecting which markers to include on a panel is important, since removing important markers will result in a loss of biologically relevant information, but identifying redundant markers will provide a room for other markers. To address this, we propose computational approaches to determine the amount of shared information between markers and select an optimally reduced panel that captures maximum amount of information with the fewest markers. Here we examine several panel selection approaches and evaluate them based on their ability to reconstruct the full panel images and information within breast cancer tissue microarray datasets using cyclic immunofluorescence as a proof of concept. We show that all methods perform adequately and can re-capture cell types using only 18 of 25 markers (72% of the original panel size). The correlation-based selection methods achieved the best single-cell marker mean intensity predictions with a Spearman correlation of 0.90 with the reduced panel. Using the proposed methods shown here, it is possible for researchers to design more efficient multiplex imaging panels that maximize the amount of information retained with the limited number of markers with respect to certain evaluation metrics and architecture biases.

Deciphering the Immune Complexity in Esophageal Adenocarcinoma and Pre-Cancerous Lesions With Sequential Multiplex Immunohistochemistry and Sparse Subspace Clustering Approach

Esophageal adenocarcinoma (EAC) develops from a chronic inflammatory environment across four stages: intestinal metaplasia, known as Barrett's esophagus, low- and high-grade dysplasia, and adenocarcinoma. Although the genomic characteristics of this progression have been well defined via large-scale DNA sequencing, the dynamics of various immune cell subsets and their spatial interactions in their tumor microenvironment remain unclear. Here, we applied a sequential multiplex immunohistochemistry (mIHC) platform with computational image analysis pipelines that allow for the detection of 10 biomarkers in one formalin-fixed paraffin-embedded (FFPE) tissue section. Using this platform and quantitative image analytics, we studied changes in the immune landscape during disease progression based on 40 normal and diseased areas from endoscopic mucosal resection specimens of chemotherapy treatment- naïve patients, including normal esophagus, metaplasia, low- and high-grade dysplasia, and adenocarcinoma. The results revealed a steady increase of FOXP3+ T regulatory cells and a CD163+ myelomonocytic cell subset. In parallel to the manual gating strategy applied for cell phenotyping, we also adopted a sparse subspace clustering (SSC) algorithm allowing the automated cell phenotyping of mIHC-based single-cell data. The algorithm successfully identified comparable cell types, along with significantly enriched FOXP3 T regulatory cells and CD163+ myelomonocytic cells as found in manual gating. In addition, SCC identified a new CSF1R+CD1C+ myeloid lineage, which not only was previously unknown in this disease but also increases with advancing disease stages. This study revealed immune dynamics in EAC progression and highlighted the potential application of a new multiplex imaging platform, combined with computational image analysis on routine clinical FFPE sections, to investigate complex immune populations in tumor ecosystems.