RESUMEN
Image-based cell profiling is a powerful tool that compares perturbed cell populations by measuring thousands of single-cell features and summarizing them into profiles. Typically a sample is represented by averaging across cells, but this fails to capture the heterogeneity within cell populations. We introduce CytoSummaryNet: a Deep Sets-based approach that improves mechanism of action prediction by 30-68% in mean average precision compared to average profiling on a public dataset. CytoSummaryNet uses self-supervised contrastive learning in a multiple-instance learning framework, providing an easier-to-apply method for aggregating single-cell feature data than previously published strategies. Interpretability analysis suggests that the model achieves this improvement by downweighting small mitotic cells or those with debris and prioritizing large uncrowded cells. The approach requires only perturbation labels for training, which are readily available in all cell profiling datasets. CytoSummaryNet offers a straightforward post-processing step for single-cell profiles that can significantly boost retrieval performance on image-based profiling datasets.
RESUMEN
High-throughput image-based profiling platforms are powerful technologies capable of collecting data from billions of cells exposed to thousands of perturbations in a time- and cost-effective manner. Therefore, image-based profiling data has been increasingly used for diverse biological applications, such as predicting drug mechanism of action or gene function. However, batch effects severely limit community-wide efforts to integrate and interpret image-based profiling data collected across different laboratories and equipment. To address this problem, we benchmark ten high-performing single-cell RNA sequencing (scRNA-seq) batch correction techniques, representing diverse approaches, using a newly released Cell Painting dataset, JUMP. We focus on five scenarios with varying complexity, ranging from batches prepared in a single lab over time to batches imaged using different microscopes in multiple labs. We find that Harmony and Seurat RPCA are noteworthy, consistently ranking among the top three methods for all tested scenarios while maintaining computational efficiency. Our proposed framework, benchmark, and metrics can be used to assess new batch correction methods in the future. This work paves the way for improvements that enable the community to make the best use of public Cell Painting data for scientific discovery.
Asunto(s)
Análisis de la Célula Individual , Análisis de la Célula Individual/métodos , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Análisis de Secuencia de ARN/métodos , BenchmarkingRESUMEN
Predicting drug efficacy and safety in vivo requires information on biological responses (e.g., cell morphology and gene expression) to small molecule perturbations. However, current molecular representation learning methods do not provide a comprehensive view of cell states under these perturbations and struggle to remove noise, hindering model generalization. We introduce the Information Alignment (InfoAlign) approach to learn molecular representations through the information bottleneck method in cells. We integrate molecules and cellular response data as nodes into a context graph, connecting them with weighted edges based on chemical, biological, and computational criteria. For each molecule in a training batch, InfoAlign optimizes the encoder's latent representation with a minimality objective to discard redundant structural information. A sufficiency objective decodes the representation to align with different feature spaces from the molecule's neighborhood in the context graph. We demonstrate that the proposed sufficiency objective for alignment is tighter than existing encoder-based contrastive methods. Empirically, we validate representations from InfoAlign in two downstream tasks: molecular property prediction against up to 19 baseline methods across four datasets, plus zero-shot molecule-morphology matching.
RESUMEN
In profiling assays, thousands of biological properties are measured in a single test, yielding biological discoveries by capturing the state of a cell population, often at the single-cell level. However, for profiling datasets, it has been challenging to evaluate the phenotypic activity of a sample and the phenotypic consistency among samples, due to profiles' high dimensionality, heterogeneous nature, and non-linear properties. Existing methods leave researchers uncertain where to draw boundaries between meaningful biological response and technical noise. Here, we developed a statistical framework that uses the well-established mean average precision (mAP) as a single, data-driven metric to bridge this gap. We validated the mAP framework against established metrics through simulations and real-world data applications, revealing its ability to capture subtle and meaningful biological differences in cell state. Specifically, we used mAP to assess both phenotypic activity for a given perturbation (or a sample) as well as consistency within groups of perturbations (or samples) across diverse high-dimensional datasets. We evaluated the framework on different profile types (image, protein, and mRNA profiles), perturbation types (CRISPR gene editing, gene overexpression, and small molecules), and profile resolutions (single-cell and bulk). Our open-source software allows this framework to be applied to identify interesting biological phenomena and promising therapeutics from large-scale profiling data.
RESUMEN
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.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Microscopía/métodosRESUMEN
High-throughput image-based profiling platforms are powerful technologies capable of collecting data from billions of cells exposed to thousands of perturbations in a time- and cost-effective manner. Therefore, image-based profiling data has been increasingly used for diverse biological applications, such as predicting drug mechanism of action or gene function. However, batch effects pose severe limitations to community-wide efforts to integrate and interpret image-based profiling data collected across different laboratories and equipment. To address this problem, we benchmarked seven high-performing scRNA-seq batch correction techniques, representing diverse approaches, using a newly released Cell Painting dataset, the largest publicly accessible image-based dataset. We focused on five different scenarios with varying complexity, and we found that Harmony, a mixture-model based method, consistently outperformed the other tested methods. Our proposed framework, benchmark, and metrics can additionally be used to assess new batch correction methods in the future. Overall, this work paves the way for improvements that allow the community to make best use of public Cell Painting data for scientific discovery.
RESUMEN
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.
RESUMEN
Objective.Multi-parametric magnetic resonance imaging (MP-MRI) has played an important role in prostate cancer diagnosis. Nevertheless, in the clinical routine, these sequences are principally analyzed from expert observations, which introduces an intrinsic variability in the diagnosis. Even worse, the isolated study of these MRI sequences trends to false positive detection due to other diseases that share similar radiological findings. Hence, the main objective of this study was to design, propose and validate a deep multimodal learning framework to support MRI-based prostate cancer diagnosis using cross-correlation modules that fuse MRI regions, coded from independent MRI parameter branches.Approach.This work introduces a multimodal scheme that integrates MP-MRI sequences and allows to characterize prostate lesions related to cancer disease. For doing so, potential 3D regions were extracted around expert annotations over different prostate zones. Then, a convolutional representation was obtained from each evaluated sequence, allowing a rich and hierarchical deep representation. Each convolutional branch representation was integrated following a special inception-like module. This module allows a redundant non-linear integration that preserves textural spatial lesion features and could obtain higher levels of representation.Main results.This strategy enhances micro-circulation, morphological, and cellular density features, which thereafter are integrated according to an inception late fusion strategy, leading to a better differentiation of prostate cancer lesions. The proposed strategy achieved a ROC-AUC of 0.82 over the PROSTATEx dataset by fusing regions ofKtransand apparent diffusion coefficient (ADC) maps coded from DWI-MRI.Significance.This study conducted an evaluation about how MP-MRI parameters can be fused, through a deep learning representation, exploiting spatial correlations among multiple lesion observations. The strategy, from a multimodal representation, learns branches representations to exploit radio-logical findings from ADC andKtrans. Besides, the proposed strategy is very compact (151 630 trainable parameters). Hence, the methodology is very fast in training (3 s for an epoch of 320 samples), being potentially applicable in clinical scenarios.
Asunto(s)
Imágenes de Resonancia Magnética Multiparamétrica , Neoplasias de la Próstata , Masculino , Humanos , Neoplasias de la Próstata/diagnóstico por imagen , Neoplasias de la Próstata/patología , Imagen por Resonancia Magnética/métodos , Próstata/patología , Imagen de Difusión por Resonancia Magnética/métodosRESUMEN
Clinically significant regions (CSR), captured over multi-parametric MRI (mp-MRI) images, have emerged as a potential screening test for early prostate cancer detection and characterization. These sequences are able to quantify morphology, micro-circulation, and cellular density patterns that might be related to cancer disease. Nonetheless, this evaluation is mainly carried out by expert radiologists, introducing inter-reader variability in the diagnosis. Therefore, different deep learning models were proposed to support the diagnosis, but a proper representation of prostate lesions remains limited due to the non-alignment among sequences and the dependency of considerable amounts of labeled data for learning. The main limitation of such representation lies in the cross-entropy minimization that only exploits inter-class variation, being insufficient data augmentation and transfer learning strategies. This work introduces a Supervised Contrastive Learning (SCL) strategy that fully exploits the inter and intra-class variability of prostate lesions to robustly represent MRI regions. This strategy extracts lesion sample tuples, with positive and negative labels, regarding a query lesion. Such tuples are involved into an easy-positive, and semi-hard negative mining to project samples that better update the deep representation. The proposed learning strategy achieved an average ROC-AVC of 0.82, to characterize prostate cancer in MRI, using only the 60% of the available annotated data. Clinical relevance - A robust learning scheme that properly finds representations in limited data scenarios to classify clinically significant MRI regions on prostate cancer.
Asunto(s)
Imágenes de Resonancia Magnética Multiparamétrica , Neoplasias de la Próstata , Humanos , Imagen por Resonancia Magnética/métodos , Masculino , Próstata/patología , Neoplasias de la Próstata/diagnóstico , Aprendizaje Automático SupervisadoRESUMEN
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.
Asunto(s)
Adenocarcinoma del Pulmón , Neoplasias Pulmonares , Adenocarcinoma del Pulmón/genética , Alelos , Humanos , Neoplasias Pulmonares/genética , Microscopía , FenotipoRESUMEN
BACKGROUND AND OBJECTIVE: The automatic classification of breast imaging lesions is currently an unsolved problem. This paper describes an innovative representation learning framework for breast cancer diagnosis in mammography that integrates deep learning techniques to automatically learn discriminative features avoiding the design of specific hand-crafted image-based feature detectors. METHODS: A new biopsy proven benchmarking dataset was built from 344 breast cancer patients' cases containing a total of 736 film mammography (mediolateral oblique and craniocaudal) views, representative of manually segmented lesions associated with masses: 426 benign lesions and 310 malignant lesions. The developed method comprises two main stages: (i) preprocessing to enhance image details and (ii) supervised training for learning both the features and the breast imaging lesions classifier. In contrast to previous works, we adopt a hybrid approach where convolutional neural networks are used to learn the representation in a supervised way instead of designing particular descriptors to explain the content of mammography images. RESULTS: Experimental results using the developed benchmarking breast cancer dataset demonstrated that our method exhibits significant improved performance when compared to state-of-the-art image descriptors, such as histogram of oriented gradients (HOG) and histogram of the gradient divergence (HGD), increasing the performance from 0.787 to 0.822 in terms of the area under the ROC curve (AUC). Interestingly, this model also outperforms a set of hand-crafted features that take advantage of additional information from segmentation by the radiologist. Finally, the combination of both representations, learned and hand-crafted, resulted in the best descriptor for mass lesion classification, obtaining 0.826 in the AUC score. CONCLUSIONS: A novel deep learning based framework to automatically address classification of breast mass lesions in mammography was developed.
Asunto(s)
Neoplasias de la Mama/diagnóstico , Aprendizaje Automático , Mamografía , Redes Neurales de la Computación , Biopsia , Neoplasias de la Mama/patología , Femenino , HumanosRESUMEN
OBJECTIVE: The paper addresses the problem of automatic detection of basal cell carcinoma (BCC) in histopathology images. In particular, it proposes a framework to both, learn the image representation in an unsupervised way and visualize discriminative features supported by the learned model. MATERIALS AND METHODS: This paper presents an integrated unsupervised feature learning (UFL) framework for histopathology image analysis that comprises three main stages: (1) local (patch) representation learning using different strategies (sparse autoencoders, reconstruct independent component analysis and topographic independent component analysis (TICA), (2) global (image) representation learning using a bag-of-features representation or a convolutional neural network, and (3) a visual interpretation layer to highlight the most discriminant regions detected by the model. The integrated unsupervised feature learning framework was exhaustively evaluated in a histopathology image dataset for BCC diagnosis. RESULTS: The experimental evaluation produced a classification performance of 98.1%, in terms of the area under receiver-operating-characteristic curve, for the proposed framework outperforming by 7% the state-of-the-art discrete cosine transform patch-based representation. CONCLUSIONS: The proposed UFL-representation-based approach outperforms state-of-the-art methods for BCC detection. Thanks to its visual interpretation layer, the method is able to highlight discriminative tissue regions providing a better diagnosis support. Among the different UFL strategies tested, TICA-learned features exhibited the best performance thanks to its ability to capture low-level invariances, which are inherent to the nature of the problem.
Asunto(s)
Carcinoma Basocelular/patología , Sistemas de Apoyo a Decisiones Clínicas , Técnicas de Apoyo para la Decisión , Interpretación de Imagen Asistida por Computador/métodos , Patología Clínica/métodos , Neoplasias Cutáneas/patología , Aprendizaje Automático no Supervisado , Área Bajo la Curva , Automatización de Laboratorios , Biopsia , Carcinoma Basocelular/clasificación , Análisis Discriminante , Humanos , Valor Predictivo de las Pruebas , Curva ROC , Reproducibilidad de los Resultados , Neoplasias Cutáneas/clasificación , Coloración y EtiquetadoRESUMEN
Feature extraction is a fundamental step when mammography image analysis is addressed using learning based approaches. Traditionally, problem dependent handcrafted features are used to represent the content of images. An alternative approach successfully applied in other domains is the use of neural networks to automatically discover good features. This work presents an evaluation of convolutional neural networks to learn features for mammography mass lesions before feeding them to a classification stage. Experimental results showed that this approach is a suitable strategy outperforming the state-of-the-art representation from 79.9% to 86% in terms of area under the ROC curve.
Asunto(s)
Redes Neurales de la Computación , Mamografía , Curva ROCRESUMEN
This paper presents a review of the state-of-the-art in histopathology image representation used in automatic image analysis tasks. Automatic analysis of histopathology images is important for building computer-assisted diagnosis tools, automatic image enhancing systems and virtual microscopy systems, among other applications. Histopathology images have a rich mix of visual patterns with particularities that make them difficult to analyze. The paper discusses these particularities, the acquisition process and the challenges found when doing automatic analysis. Second an overview of recent works and methods addressed to deal with visual content representation in different automatic image analysis tasks is presented. Third an overview of applications of image representation methods in several medical domains and tasks is presented. Finally, the paper concludes with current trends of automatic analysis of histopathology images like digital pathology.
Este artículo presenta una revisión del estado del arte en la representación de imágenes de histopatología utilizada en tareas de análisis automático. El análisis de imágenes hispatológicas es importante en la construcción de herramientas para el diagnóstico asistido por computador, sistemas de mejoramiento automático de imágenes y sistemas de microscopía virtual, entre otras aplicaciones. Estas imágenes tienen una gran mezcla de patrones visuales con características particulares que hacen de su análisis una tarea difícil. El artículo discute estas particularidades, el proceso de adquisición y los retos particulares al realizar un análisis automático. En la segunda sección se presenta una revisión de trabajos y métodos recientes enfocados a la representación del contenido visual en diferentes tareas de análisis automático. En tercer lugar, se presenta una visión general de las aplicaciones para los métodos de representación en diferentes dominios médicos. Finalmente el trabajo concluye con las actuales tendencias del análisis automático de imágenes de histopatología como la patología digital.
Este artigo é uma revisão do estado da arte na representação de imagens histopatológicas utilizadas nas tarefas de análise automáticos. O análise de imagens histopatológicas é importante na construção de ferramentas para o diagnóstico assistido por computador, sistemas de melhoramento automático de imagens e sistemas de microscopia virtual. Essas imagens tem uma grande mistura de padrões visuais com caraterísticas particulares, que fazem do análise uma tarefa difícil. O artigo discute essas particularidades, o processo de aquisição, e os desafios particulares no momento de realizar uma análise automático. Na segunda seção se apresenta uma revisão dos trabalhos e métodos recentes, com foco à representação do conteúdo visual em diferentes tarefas de análise automático. Na terceira, se apresenta uma visão geral das aplicações para os métodos de representação em diferentes domínios médicos. Finalmente, o artigo conclui com as atuais tendências do análise automático de imagens histopatológicas como a patologia digital.
Asunto(s)
Humanos , Procesamiento de Imagen Asistido por Computador , Informática Médica , Patología , Reconocimiento de Normas Patrones AutomatizadasRESUMEN
Post-translational modifications play a key role in tau protein aggregation and related neurodegeneration. Because hyperphosphorylation alone does not necessarily cause tau aggregation, other post-translational modifications have been recently explored. Tau acetylation promotes aggregation and inhibits tau's ability to stabilize microtubules. Recent studies have shown co-localization of acetylated and phosphorylated tau in AD and some 4R tauopathies. We developed a novel monoclonal antibody against acetylated tau at lysine residue 274, which recognizes both 3R and 4R tau, and used immunohistochemistry and immunofluorescence to probe 22 cases, including AD and another eight familial or sporadic tauopathies. Acetylated tau was identified in all tauopathies except argyrophilic grain disease (AGD). AGD is an age-associated, common but atypical 4R tauopathy, not always associated with clinical progression. Pathologically, AGD is characterized by neuropil grains, pre-neurofibrillary tangles, and oligodendroglial coiled bodies, all recognized by phospho-tau antibodies. The lack of acetylated tau in these inclusions suggests that AGD represents a distinctive tauopathy. Our data converge with previous findings to raise the hypothesis that AGD could play a protective role against the spread of AD-related tau pathology. Tau acetylation as a key modification for the propagation tau toxicity deserves further investigation.