Three million images and morphological profiles of cells treated with matched chemical and genetic perturbations.

The identification of genetic and chemical perturbations with similar impacts on cell morphology can elucidate compounds' mechanisms of action or novel regulators of genetic pathways. Research on methods for identifying such similarities has lagged due to a lack of carefully designed and well-annotated image sets of cells treated with chemical and genetic perturbations. Here we create such a Resource dataset, CPJUMP1, in which each perturbed gene's product is a known target of at least two chemical compounds in the dataset. We systematically explore the directionality of correlations among perturbations that target the same protein encoded by a given gene, and we find that identifying matches between chemical and genetic perturbations is a challenging task. Our dataset and baseline analyses provide a benchmark for evaluating methods that measure perturbation similarities and impact, and more generally, learn effective representations of cellular state from microscopy images. Such advancements would accelerate the applications of image-based profiling of cellular states, such as uncovering drug mode of action or probing functional genomics.

Learning representations for image-based profiling of perturbations.

Measuring the phenotypic effect of treatments on cells through imaging assays is an efficient and powerful way of studying cell biology, and requires computational methods for transforming images into quantitative data. Here, we present an improved strategy for learning representations of treatment effects from high-throughput imaging, following a causal interpretation. We use weakly supervised learning for modeling associations between images and treatments, and show that it encodes both confounding factors and phenotypic features in the learned representation. To facilitate their separation, we constructed a large training dataset with images from five different studies to maximize experimental diversity, following insights from our causal analysis. Training a model with this dataset successfully improves downstream performance, and produces a reusable convolutional network for image-based profiling, which we call Cell Painting CNN. We evaluated our strategy on three publicly available Cell Painting datasets, and observed that the Cell Painting CNN improves performance in downstream analysis up to 30% with respect to classical features, while also being more computationally efficient.

Reproducible image-based profiling with Pycytominer.

Technological advances in high-throughput microscopy have facilitated the acquisition of cell images at a rapid pace, and data pipelines can now extract and process thousands of image-based features from microscopy images. These features represent valuable single-cell phenotypes that contain information about cell state and biological processes. The use of these features for biological discovery is known as image-based or morphological profiling. However, these raw features need processing before use and image-based profiling lacks scalable and reproducible open-source software. Inconsistent processing across studies makes it difficult to compare datasets and processing steps, further delaying the development of optimal pipelines, methods, and analyses. To address these issues, we present Pycytominer, an open-source software package with a vibrant community that establishes an image-based profiling standard. Pycytominer has a simple, user-friendly Application Programming Interface (API) that implements image-based profiling functions for processing high-dimensional morphological features extracted from microscopy images of cells. Establishing Pycytominer as a standard image-based profiling toolkit ensures consistent data processing pipelines with data provenance, therefore minimizing potential inconsistencies and enabling researchers to confidently derive accurate conclusions and discover novel insights from their data, thus driving progress in our field.

Unbiased single-cell morphology with self-supervised vision transformers.

Accurately quantifying cellular morphology at scale could substantially empower existing single-cell approaches. However, measuring cell morphology remains an active field of research, which has inspired multiple computer vision algorithms over the years. Here, we show that DINO, a vision-transformer based, self-supervised algorithm, has a remarkable ability for learning rich representations of cellular morphology without manual annotations or any other type of supervision. We evaluate DINO on a wide variety of tasks across three publicly available imaging datasets of diverse specifications and biological focus. We find that DINO encodes meaningful features of cellular morphology at multiple scales, from subcellular and single-cell resolution, to multi-cellular and aggregated experimental groups. Importantly, DINO successfully uncovers a hierarchy of biological and technical factors of variation in imaging datasets. The results show that DINO can support the study of unknown biological variation, including single-cell heterogeneity and relationships between samples, making it an excellent tool for image-based biological discovery.

Predicting compound activity from phenotypic profiles and chemical structures.

Predicting assay results for compounds virtually using chemical structures and phenotypic profiles has the potential to reduce the time and resources of screens for drug discovery. Here, we evaluate the relative strength of three high-throughput data sources-chemical structures, imaging (Cell Painting), and gene-expression profiles (L1000)-to predict compound bioactivity using a historical collection of 16,170 compounds tested in 270 assays for a total of 585,439 readouts. All three data modalities can predict compound activity for 6-10% of assays, and in combination they predict 21% of assays with high accuracy, which is a 2 to 3 times higher success rate than using a single modality alone. In practice, the accuracy of predictors could be lower and still be useful, increasing the assays that can be predicted from 37% with chemical structures alone up to 64% when combined with phenotypic data. Our study shows that unbiased phenotypic profiling can be leveraged to enhance compound bioactivity prediction to accelerate the early stages of the drug-discovery process.

Personality Traits in Patients With Cirrhosis Are Different From Those of the General Population and Impact Likelihood of Liver Transplantation.

BACKGROUND: Personality traits influence clinical outcomes in chronic diseases, but their impact in cirrhosis is unknown. We studied the personality of patients with cirrhosis undergoing liver transplant (LT) evaluation and determined their correlation to clinical outcomes. METHODS: A multicenter' prospective study of adult patients undergoing LT evaluation was performed from January 2018 to October 2019. The "Big Five" personality traits of conscientiousness, extraversion, openness, neuroticism, and agreeableness plus agency were assessed with the Midlife Development Inventory Personality Scale and compared with the general population. Frailty was assessed with the Liver Frailty Index. RESULTS: Two hundred sixty-three LT candidates were enrolled. Twenty-four percent had hepatitis C virus, 25% nonalcoholic steatohepatitis, and 25% ethyl alcohol (mean model for end-stage liver disease = 15.7). Compared with the general population, LT candidates had higher openness (3.1 versus 2.9; P < 0.001), extraversion (3.2 versus 3.1; P < 0.001), agreeableness (3.5 versus 3.4; P = 0.04), agency (2.9 versus 2.6; P < 0.001), neuroticism (2.2 versus 2.1; P = 0.001), and lower conscientiousness (3.3 versus 3.4; P = 0.007). Patients with higher conscientiousness were more likely to receive an LT (HR = 2.76; P = 0.003). CONCLUSIONS: Personality traits in LT candidates differ significantly from the general population, with higher conscientiousness associated with a higher likelihood of receiving a transplant.

High-dimensional gene expression and morphology profiles of cells across 28,000 genetic and chemical perturbations.

Cells can be perturbed by various chemical and genetic treatments and the impact on gene expression and morphology can be measured via transcriptomic profiling and image-based assays, respectively. The patterns observed in these high-dimensional profile data can power a dozen applications in drug discovery and basic biology research, but both types of profiles are rarely available for large-scale experiments. Here, we provide a collection of four datasets with both gene expression and morphological profile data useful for developing and testing multimodal methodologies. Roughly a thousand features are measured for each of the two data types, across more than 28,000 chemical and genetic perturbations. We define biological problems that use the shared and complementary information in these two data modalities, provide baseline analysis and evaluation metrics for multi-omic applications, and make the data resource publicly available ( https://broad.io/rosetta/ ).

Morphology and gene expression profiling provide complementary information for mapping cell state.

Morphological and gene expression profiling can cost-effectively capture thousands of features in thousands of samples across perturbations by disease, mutation, or drug treatments, but it is unclear to what extent the two modalities capture overlapping versus complementary information. Here, using both the L1000 and Cell Painting assays to profile gene expression and cell morphology, respectively, we perturb human A549 lung cancer cells with 1,327 small molecules from the Drug Repurposing Hub across six doses, providing a data resource including dose-response data from both assays. The two assays capture both shared and complementary information for mapping cell state. Cell Painting profiles from compound perturbations are more reproducible and show more diversity but measure fewer distinct groups of features. Applying unsupervised and supervised methods to predict compound mechanisms of action (MOAs) and gene targets, we find that the two assays not only provide a partially shared but also a complementary view of drug mechanisms. Given the numerous applications of profiling in biology, our analyses provide guidance for planning experiments that profile cells for detecting distinct cell types, disease phenotypes, and response to chemical or genetic perturbations.

Cell Painting predicts impact of lung cancer variants.

Most variants in most genes across most organisms have an unknown impact on the function of the corresponding gene. This gap in knowledge is especially acute in cancer, where clinical sequencing of tumors now routinely reveals patient-specific variants whose functional impact on the corresponding genes is unknown, impeding clinical utility. Transcriptional profiling was able to systematically distinguish these variants of unknown significance as impactful vs. neutral in an approach called expression-based variant-impact phenotyping. We profiled a set of lung adenocarcinoma-associated somatic variants using Cell Painting, a morphological profiling assay that captures features of cells based on microscopy using six stains of cell and organelle components. Using deep-learning-extracted features from each cell's image, we found that cell morphological profiling (cmVIP) can predict variants' functional impact and, particularly at the single-cell level, reveals biological insights into variants that can be explored at our public online portal. Given its low cost, convenient implementation, and single-cell resolution, cmVIP profiling therefore seems promising as an avenue for using non-gene specific assays to systematically assess the impact of variants, including disease-associated alleles, on gene function.

Which recipient pretransplant factors, such as MELD, renal function, sarcopenia, and recent sepsis influence suitability for and outcome after living donor liver transplantation? A systematic review of the literature and expert panel recommendations.

BACKGROUND: Varied access to deceased donors across the globe has resulted in differential living donor liver transplant (LDLT) practices and lack of consensus over the influence of models for end stage liver disease (MELD), renal function, sarcopenia, or recent infection on short-term outcomes. OBJECTIVES: Consider these risk factors in relation to patient selection and provide recommendations. DATA SOURCES: Ovid MEDLINE, Embase, Scopus, Google Scholar, Cochrane Central. METHODS: PRIMSA systematic review and GRADE. PROSPERO ID: RD42021260809 RESULTS: MELD >25-30 alone is not a contraindication to LDLT, and multiple studies found no increase in short term mortality in high MELD patients. Contributing factors such as muscle mass, acute physiologic assessment and chronic health evaluation score, donor age, graft weight/recipient weight ratio, and inclusion of the middle hepatic vein in a right lobe graft influence morbidity and mortality in high MELD patients. Higher mortality is observed with pretransplant renal dysfunction, but short-term mortality is rare. Sarcopenia and recent infection are not contraindications to LDLT. Morbidity and prolonged LOS are common, and more frequent in patients with renal dysfunction, nutritional deficiency or recent infection. CONCLUSIONS: When individual risk factors are studied mortality is low and graft loss is infrequent, but morbidity is common. MELD, especially with concomitant risk factors, had the greatest influence on short term outcome, and recent infection had the least. A multidisciplinary team of experts should carefully assess patients with multiple risk factors, and an optimal graft is recommended.

Black Patients With Cirrhosis Have Higher Mortality and Lower Transplant Rates: Results From a Metropolitan Cohort Study.

BACKGROUND AND AIMS: Estimates of racial disparity in cirrhosis have been limited by lack of large-scale, longitudinal data, which track patients from diagnosis to death and/or transplant. APPROACH AND RESULTS: We analyzed a large, metropolitan, population-based electronic health record data set from seven large health systems linked to the state death registry and the national transplant database. Multivariate competing risk analyses, adjusted for sex, age, insurance status, Elixhauser score, etiology of cirrhosis, HCC, portal hypertensive complication, and Model for End-Stage Liver Disease-Sodium (MELD-Na), examined the relationship between race, transplant, and cause of death as defined by blinded death certificate review. During the study period, 11,277 patients met inclusion criteria, of whom 2,498 (22.2%) identified as Black. Compared to White patients, Black patients had similar age, sex, MELD-Na, and proportion of alcohol-associated liver disease, but higher comorbidity burden, lower rates of private insurance, and lower rates of portal hypertensive complications. Compared to White patients, Black patients had the highest rate all-cause mortality and non-liver-related death and were less likely to be listed or transplanted (P < 0.001 for all). In multivariate competing risk analysis, Black patients had a 26% increased hazard of liver-related death (subdistribution HR, 1.26; 95% CI, [1.15-1.38]; P < 0.001). CONCLUSIONS: Black patients with cirrhosis have discordant outcomes. Further research is needed to determine how to address these real disparities in the field of hepatology.

Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry.

Deep learning offers the potential to extract more than meets the eye from images captured by imaging flow cytometry. This protocol describes the application of deep learning to single-cell images to perform supervised cell classification and weakly supervised learning, using example data from an experiment exploring red blood cell morphology. We describe how to acquire and transform suitable input data as well as the steps required for deep learning training and inference using an open-source web-based application. All steps of the protocol are provided as open-source Python as well as MATLAB runtime scripts, through both command-line and graphic user interfaces. The protocol enables a flexible and friendly environment for morphological phenotyping using supervised and weakly supervised learning and the subsequent exploration of the deep learning features using multi-dimensional visualization tools. The protocol requires 40 h when training from scratch and 1 h when using a pre-trained model.

Image-based cell phenotyping with deep learning.

A cell's phenotype is the culmination of several cellular processes through a complex network of molecular interactions that ultimately result in a unique morphological signature. Visual cell phenotyping is the characterization and quantification of these observable cellular traits in images. Recently, cellular phenotyping has undergone a massive overhaul in terms of scale, resolution, and throughput, which is attributable to advances across electronic, optical, and chemical technologies for imaging cells. Coupled with the rapid acceleration of deep learning-based computational tools, these advances have opened up new avenues for innovation across a wide variety of high-throughput cell biology applications. Here, we review applications wherein deep learning is powering the recognition, profiling, and prediction of visual phenotypes to answer important biological questions. As the complexity and scale of imaging assays increase, deep learning offers computational solutions to elucidate the details of previously unexplored cellular phenotypes.

Pregnancy Outcomes After Living Liver Donation: A Multi-Institutional Study.

Nearly half of living liver donors in North America are women of child-bearing age. Fetal and maternal outcomes after donation are unknown. We conducted a retrospective cohort study of female living liver donors (aged 18-50 years at donation) from 6 transplant centers. Participants were surveyed about their pregnancies and fertility. Outcomes were compared between predonation and postdonation pregnancies. Generalized estimating equations were clustered on donor and adjusted for age at pregnancy, parity, and pregnancy year. Among the 276 donors surveyed, 151 donors responded (54.7% response rate) and reported 313 pregnancies; 168/199 (68.8%) of the predonation pregnancies and 82/114 (71.9%) of the postdonation pregnancies resulted in live births, whereas 16.6% and 24.6% resulted in miscarriage, respectively. Women with postdonation pregnancies were older (32.0 versus 26.7 years; P < 0.001) and more frequently reported abnormal liver enzymes during pregnancy (3.5% versus 0.0%; P = 0.02) and delivery via cesarean delivery (35.4% versus 19.7%; P = 0.01). On adjusted analysis, there was no difference in cesarean delivery (odds ratio [OR], 2.44; 95% confidence interval [95% CI], 0.98-6.08), miscarriage (OR, 1.59; 95% CI, 0.78-3.24), combined endpoints of pregnancy-induced hypertension and preeclampsia (OR, 1.27; 95% CI, 0.36-4.49), or intrauterine growth restriction and preterm birth (OR, 0.91; 95% CI, 0.19-4.3). Of the 49 women who attempted pregnancy after donation, 11 (22.5%) self-reported infertility; however, 8/11 (72.7%) eventually had live births. Aside from increased reporting of abnormal liver enzymes and cesarean deliveries, there was no significant difference in pregnancy outcomes before and after living liver donation. One-fifth of women who attempt pregnancy after liver donation reported infertility, and although the majority went on to successful live births, further exploration is needed to understand the contributing factors. Future research should continue to monitor this patient-centered outcome across a large cohort of donors.

Objective assessment of stored blood quality by deep learning.

Stored red blood cells (RBCs) are needed for life-saving blood transfusions, but they undergo continuous degradation. RBC storage lesions are often assessed by microscopic examination or biochemical and biophysical assays, which are complex, time-consuming, and destructive to fragile cells. Here we demonstrate the use of label-free imaging flow cytometry and deep learning to characterize RBC lesions. Using brightfield images, a trained neural network achieved 76.7% agreement with experts in classifying seven clinically relevant RBC morphologies associated with storage lesions, comparable to 82.5% agreement between different experts. Given that human observation and classification may not optimally discern RBC quality, we went further and eliminated subjective human annotation in the training step by training a weakly supervised neural network using only storage duration times. The feature space extracted by this network revealed a chronological progression of morphological changes that better predicted blood quality, as measured by physiological hemolytic assay readouts, than the conventional expert-assessed morphology classification system. With further training and clinical testing across multiple sites, protocols, and instruments, deep learning and label-free imaging flow cytometry might be used to routinely and objectively assess RBC storage lesions. This would automate a complex protocol, minimize laboratory sample handling and preparation, and reduce the impact of procedural errors and discrepancies between facilities and blood donors. The chronology-based machine-learning approach may also improve upon humans' assessment of morphological changes in other biomedically important progressions, such as differentiation and metastasis.

Successful Resection of a Retrohepatic Inferior Vena Cava Primary Leiomyosarcoma with Atrial Thrombus Extension in a 30-Week Pregnant Woman.

Leiomyosarcomas are an uncommon malignant subset of tumors accounting for approximately 20% of soft tissue sarcomas. Primary vascular leiomyosarcomas (PVLs) are a rare subset of leiomyosarcomas that may originate in the arterial or venous circulation but most commonly affect the inferior vena cava (IVC). PVLs more commonly affect women to men in a 2:1 ratio and most frequently occur in the fourth to sixth decades of life. Few reports have described this infrequent pathologic state in the setting of advanced pregnancy. Presented is a case of a 44-year-old 30-week pregnant woman who presented with a PVL of the retrohepatic IVC, which was complicated by occlusion of the IVC and tumor thrombus extension into the hepatic veins and right atrium. Herein, we describe our multidisciplinary management of this rare problem with successful surgical resection of her tumor and IVC reconstruction.

Publisher Correction: Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl.

Segmenting the nuclei of cells in microscopy images is often the first step in the quantitative analysis of imaging data for biological and biomedical applications. Many bioimage analysis tools can segment nuclei in images but need to be selected and configured for every experiment. The 2018 Data Science Bowl attracted 3,891 teams worldwide to make the first attempt to build a segmentation method that could be applied to any two-dimensional light microscopy image of stained nuclei across experiments, with no human interaction. Top participants in the challenge succeeded in this task, developing deep-learning-based models that identified cell nuclei across many image types and experimental conditions without the need to manually adjust segmentation parameters. This represents an important step toward configuration-free bioimage analysis software tools.

Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images.

Identifying nuclei is often a critical first step in analyzing microscopy images of cells and classical image processing algorithms are most commonly used for this task. Recent developments in deep learning can yield superior accuracy, but typical evaluation metrics for nucleus segmentation do not satisfactorily capture error modes that are relevant in cellular images. We present an evaluation framework to measure accuracy, types of errors, and computational efficiency; and use it to compare deep learning strategies and classical approaches. We publicly release a set of 23,165 manually annotated nuclei and source code to reproduce experiments and run the proposed evaluation methodology. Our evaluation framework shows that deep learning improves accuracy and can reduce the number of biologically relevant errors by half. © 2019 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

The Hispanic Paradox in Patients With Liver Cirrhosis: Current Evidence From a Large Regional Retrospective Cohort Study.

BACKGROUND: Despite lower socioeconomic status, Hispanics in the United States paradoxically maintain equal or higher average survival rates compared to non-Hispanic Whites (NHW). METHODS: We used multivariable Cox regression to assess whether this "Hispanic paradox" applies to patients with liver cirrhosis using a retrospective cohort of twenty 121 patients in a Chicago-wide electronic health record database. RESULTS: Our study population included 3279 (16%) Hispanics, 9150 (45%) NHW, 4432 (22%) African Americans, 529 (3%) Asians, and 2731 (14%) of other races/ethnic groups. Compared to Hispanics, NHW (hazard ratio [HR] 1.26; 95% confidence interval [CI], 1.16-1.37), African American (HR 1.26; 95% CI, 1.15-1.39), and other races/ethnic groups (HR 1.55; 95% CI, 1.40-1.71) had an increased risk of death despite adjustment for age, sex, insurance status, etiology of cirrhosis, and comorbidities. On stratified analyses, a mortality advantage for Hispanics compared to NHW was seen for alcohol cirrhosis (HR for NHW 1.35; 95% CI, 1.19-1.52), hepatitis B (HR for NHW 1.35; 95% CI, 0.98-1.87), hepatitis C (HR for NHW 1.21; 95% CI, 1.06-1.38), and nonalcoholic steatohepatitis (HR for NHW 1.14; 95% CI, 0.94-1.39). There was no advantage associated with Hispanic race over NHW in cases of hepatocellular carcinoma or cholestatic liver disease. CONCLUSIONS: Hispanic patients with cirrhosis experience a survival advantage over many other racial groups despite adjustment for multiple covariates.