RESUMEN
An ever-increasing array of imaging technologies are being used in the study of complex biological samples, each of which provides complementary, occasionally overlapping information at different length scales and spatial resolutions. It is important to understand the information provided by one technique in the context of the other to achieve a more holistic overview of such complex samples. One way to achieve this is to use annotations from one modality to investigate additional modalities. For microscopy-based techniques, these annotations could be manually generated using digital pathology software or automatically generated by machine learning (including deep learning) methods. Here, we present a generic method for using annotations from one microscopy modality to extract information from complementary modalities. We also present a fast, general, multimodal registration workflow [evaluated on multiple mass spectrometry imaging (MSI) modalities, matrix-assisted laser desorption/ionization, desorption electrospray ionization, and rapid evaporative ionization mass spectrometry] for automatic alignment of complex data sets, demonstrating an order of magnitude speed-up compared to previously published work. To demonstrate the power of the annotation transfer and multimodal registration workflows, we combine MSI, histological staining (such as hematoxylin and eosin), and deep learning (automatic annotation of histology images) to investigate a pancreatic cancer mouse model. Neoplastic pancreatic tissue regions, which were histologically indistinguishable from one another, were observed to be metabolically different. We demonstrate the use of the proposed methods to better understand tumor heterogeneity and the tumor microenvironment by transferring machine learning results freely between the two modalities.
Asunto(s)
Aprendizaje Profundo , Animales , Técnicas Histológicas , Ratones , Imagen Molecular , Espectrometría de Masa por Láser de Matriz Asistida de Ionización Desorción , Flujo de TrabajoRESUMEN
Biochar was prepared from rabbit faeces (RFB550) at 550 °C through pyrolysis and was characterised using elemental analysis, scanning electron microscopy, Brunauer-Emmett-Teller analysis and Fourier transform infrared spectroscopy (FTIR). The related factors, kinetics, isothermal curves and thermodynamics of the adsorption behaviours were investigated by conducting batch experiments. The results revealed the adsorption equilibrium of rhodamine B (RhB) and Congo red (CR) onto RFB550 with initial concentrations of 30 mg · L-1 at 25 °C and 210 min, and the best adsorption was observed when the pH of the RhB and CR solutions was 3 and 5, respectively. Pseudo-second-order kinetics was the most suitable model for describing the adsorption of RhB and CR onto RFB550, indicating that the rate-limiting step was mainly chemical adsorption. The isotherm data were best described by the Freundlich model, and the adsorption process was multi-molecular layer adsorption. Thermodynamic parameters revealed the spontaneous adsorption of RhB and CR onto RFB550. According to the results of the FTIR analysis, the oxygen-containing functional groups and aromatic structures on the surface of RFB550 provided abundant adsorption sites for RhB and CR, and the adsorption mechanism was potentially related to the hydrogen bonds and π-π bonds.
Asunto(s)
Rojo Congo , Contaminantes Químicos del Agua , Adsorción , Animales , Carbón Orgánico , Concentración de Iones de Hidrógeno , Cinética , Estiércol , Conejos , Rodaminas , Espectroscopía Infrarroja por Transformada de Fourier , TermodinámicaRESUMEN
The increasing availability of big Automatic Identification Systems (AIS) sensor data offers great opportunities to track ship activities and mine spatial-temporal patterns of ship traffic worldwide. This research proposes a data integration approach to construct Global Shipping Networks (GSN) from massive historical ship AIS trajectories in a completely bottom-up way. First, a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is applied to temporally identify relevant stop locations, such as marine terminals and their associated events. Second, the semantic meanings of these locations are obtained by mapping them to real ports as identified by the World Port Index (WPI). Stop events are leveraged to develop travel sequences of any ship between stop locations at multiple scales. Last, a GSN is constructed by considering stop locations as nodes and journeys between nodes as links. This approach generates different levels of shipping networks from the terminal, port, and country levels. It is illustrated by a case study that extracts country, port, and terminal level Global Container Shipping Networks (GCSN) from AIS trajectories of more than 4000 container ships in 2015. The main features of these GCSNs and the limitations of this work are finally discussed.
RESUMEN
Barrett's esophagus (BE) is a precursor of esophageal adenocarcinoma (EAC). Both low-grade dysplasia (LGD) and high-grade dysplasia (HGD) are associated with an increased risk of progression to EAC. However, histological interpretation and grading of dysplasia (particularly LGD) is subjective and poorly reproducible. This study has combined whole slide imaging with DNA image cytometry to provide a novel method for the detection of abnormal DNA content through image analysis of tissue sections. A total of 20 cases were evaluated, including 8 negative for dysplasia (NFD), 6 LGD, and 6 HGD. Feulgen-stained esophageal sections were scanned in their entirety. Barrett's mucosa was interactively chosen for automatic nuclei segmentation where irrelevant cell types were ignored. The combined DNA content histogram for all nuclei within selected image regions was then obtained. In addition, three histogram measurements were computed, including xER-5C, 2cDI, and DNA-MG. Visual evaluation suggested the shape of DNA content histograms from NFD, LGD, and HGD cases exhibiting identifiable differences. The histogram measurements, xER-5C, 2cDI, and DNA-MG, were shown to be effective in differentiating metaplastic from dysplastic cases with statistical significance. Moreover, they also successfully separated NFD, LGD, and HGD patients with statistical significance. Whole slide image cytometry is a novel and effective method for the detection of abnormal DNA content in BE. Compared with histological review, it is more objective. Compared with flow cytometry and cytology-preparation image cytometry, it is low cost, simple to use, only requires a single 1 µm section, and facilitates selection of tissue and topographical correlation. Whole slide image cytometry can detect differences in DNA content between NFD, LGD, and HGD patients in this cross-sectional study. Abnormal DNA content detection by whole slide image cytometry is a promising biomarker of progression that could affect future diagnostics in BE.
Asunto(s)
Esófago de Barrett/genética , Esófago de Barrett/patología , ADN/análisis , Humanos , Reproducibilidad de los ResultadosRESUMEN
Digital pathology and the adoption of image analysis have grown rapidly in the last few years. This is largely due to the implementation of whole slide scanning, advances in software and computer processing capacity and the increasing importance of tissue-based research for biomarker discovery and stratified medicine. This review sets out the key application areas for digital pathology and image analysis, with a particular focus on research and biomarker discovery. A variety of image analysis applications are reviewed including nuclear morphometry and tissue architecture analysis, but with emphasis on immunohistochemistry and fluorescence analysis of tissue biomarkers. Digital pathology and image analysis have important roles across the drug/companion diagnostic development pipeline including biobanking, molecular pathology, tissue microarray analysis, molecular profiling of tissue and these important developments are reviewed. Underpinning all of these important developments is the need for high quality tissue samples and the impact of pre-analytical variables on tissue research is discussed. This requirement is combined with practical advice on setting up and running a digital pathology laboratory. Finally, we discuss the need to integrate digital image analysis data with epidemiological, clinical and genomic data in order to fully understand the relationship between genotype and phenotype and to drive discovery and the delivery of personalized medicine.
Asunto(s)
Biomarcadores/química , Procesamiento de Imagen Asistido por Computador/métodos , Bancos de Muestras Biológicas , Neoplasias de la Mama/metabolismo , Neoplasias Colorrectales/metabolismo , Biología Computacional/métodos , ADN/química , Femenino , Colorantes Fluorescentes/química , Genotipo , Humanos , Inmunohistoquímica/métodos , Hibridación Fluorescente in Situ , Masculino , Microscopía Fluorescente/métodos , Reconocimiento de Normas Patrones Automatizadas , Fenotipo , Medicina de Precisión/métodos , Neoplasias de la Próstata/metabolismo , Programas Informáticos , Análisis de Matrices TisularesRESUMEN
A novel green light-emitting phosphor Sr3Y(PO4)3Ce(3+), Tb(3+) was synthesized by the traditional high temperature solid state reaction method. Luminescence mechanism and crystal structure were investigated by X-Ray Diffraction (XRD) and photoluminescence spectra (PL). The XRD patterns demonstrate that the samples belong to the single phase of Sr3Y(PO4)3 in experimental doping concentrations range. Obviously, the excitation band of Sr3Y(PO4)3:Tb(3+) and the emission of Sr3Y(PO4)3:Ce(3+) have a significant spectral overlap in the wavelength range of 330~380 nm, which implies the great possibility of an efficient ET from Ce(3+) to Tb(3+). Under the 315 nm ultraviolet excitation, a blue emission(320~420 nm) from Ce(3+) and a yellowish-green emission (480~500, 530~560 nm) from Tb(3+) were obtained from Sr3Y(PO4)3:Ce(3+), Tb(3+). When the Ce(3+) concentration was 7%, the emission could be adjusted from blue to green region by tuning the Tb(3+) doping concentrations from 1% to 50% through an energy transfer process. This text plot the schematic energy levels of Ce(3+), and Tb(3+) with electronic transitions and energy transfer processes in Sr3Y(PO4)3:Ce(3+), Tb(3+), which disclose the electron motion processes of Sr3Y(PO4)3:Ce(3+), Tb(3+). From the dependence of relative emission intensity of Ce(3+), Tb(3+) ((5)D4 --> (7)Fj) and ET efficiency from Ce(3+) to Tb(3+) on the concentrations of Tb(3+), It can be seen that the relative intensity of Tb(3+) and the values of ηET increase gradually with the increasing of Tb(3+) as well as the relative intensity of Ce(3+) decreases remarkably. The largest energy transfer efficiency reaches as high as 80% when the concentration of Tb(3+) was 50%, demonstrating the efficient energy transfer from Ce(3+) to Tb(3+). The CIE chromaticity coordinate positions are plotted, as can be seen the emitting color of Ce(3+) and Tb(3+) singly doped Sr3Y(PO4)3:Ce(3+), Tb(3+) phosphor are blue and yellowish green, respectively. The emitting color of samples Sr3Y(PO4)3:Ce(3+), Tb(3+) changes from blue region to green region with the rising doping contents of Tb(3+). Sr3Y(PO4)3:Ce(3+) and Tb(3+) phosphor can be used as a green light-emitting phosphor in white LED devices and LCD backlights.
RESUMEN
This paper presents a method for using a dual roadside seismic sensor to detect moving vehicles on roadway by installing them on a road shoulder. Seismic signals are split into fixed time intervals in recording. In each interval, the time delay of arrival (TDOA) is estimated using a generalized cross-correlation approach with phase transform (GCC-PHAT). Various kinds of vehicle characterization information, including vehicle speed, axle spacing, detection of both vehicle axles and moving direction, can also be extracted from the collected seismic signals as demonstrated in this paper. The error of both vehicle speed and axle spacing detected by this approach has been shown to be less than 20% through the field tests conducted on an urban street in Seattle. Compared to most existing sensors, this new design of dual seismic sensor is cost effective, easy to install, and effective in gathering information for various traffic management applications.
RESUMEN
Osteoarthritis (OA) is a common chronic disease with age-associated increase in both incidence and prevalence. The cyclin-dependent kinase 5 (CDK5), which is a member of the CDK family, is involved in many chronic diseases. This study was performed to explore the functional role of CDK5 in OA and to discuss the detailed molecular mechanisms. The expressions of CDK5 and ELF3 before or after transfection were detected with reverse transcription-quantitative PCR (RT-qPCR) and western blot. 5-ethynyl-2'-deoxyuridine (Edu) and terminal deoxynucleoitidyl transferase-mediated nick-end labeling (TUNEL) assays were used to detect the proliferation and apoptosis of C28/I2 cells. The levels of inflammatory cytokines were estimated using enzyme-linked immunosorbent assay (ELISA) while the expressions of proteins implicated in extracellular matrix (ECM) degradation- and apoptosis were detected using western blot. Additionally, the activity of CDK5 promoters and its binding with ELF3 were detected using luciferase activity assay and chromatin immunoprecipitation (CHIP) assay. In the present study, it was discovered that the mRNA and protein expressions of CDK5 were significantly increased in IL-1ß-induced C28/I2 cells. After depleting CDK5 expression, the apoptosis, inflammation and ECM in C28/I2 cells with IL-1ß induction were suppressed. It was also found that ELF3 expression was increased in IL-1ß-induced C28/I2 cells and acted as a transcription factor binding to the CDK5 promoter to regulate its transcriptional expression. The further experiments evidenced that ELF3 overexpression partially reversed the inhibitory effects of CDK5 deficiency on IL-1ß-induced apoptosis, inflammation and ECM in C28/I2 cells. Collectively, CDK5 that upregulated by ELF3 transcription could promote the development of OA.
RESUMEN
Cell line authentication plays a crucial role in the biomedical field, ensuring researchers work with accurately identified cells. Supervised deep learning has made remarkable strides in cell line identification by studying cell morphological features through cell imaging. However, biological batch (bio-batch) effects, a significant issue stemming from the different times at which data is generated, lead to substantial shifts in the underlying data distribution, thus complicating reliable differentiation between cell lines from distinct batch cultures. To address this challenge, we introduce CLANet, a pioneering framework for cross-batch cell line identification using brightfield images, specifically designed to tackle three distinct bio-batch effects. We propose a cell cluster-level selection method to efficiently capture cell density variations, and a self-supervised learning strategy to manage image quality variations, thus producing reliable patch representations. Additionally, we adopt multiple instance learning(MIL) for effective aggregation of instance-level features for cell line identification. Our innovative time-series segment sampling module further enhances MIL's feature-learning capabilities, mitigating biases from varying incubation times across batches. We validate CLANet using data from 32 cell lines across 93 experimental bio-batches from the AstraZeneca Global Cell Bank. Our results show that CLANet outperforms related approaches (e.g. domain adaptation, MIL), demonstrating its effectiveness in addressing bio-batch effects in cell line identification.
Asunto(s)
Autenticación de Línea Celular , Humanos , Páncreas , Factores de TiempoRESUMEN
Yb3+/EP(3+) -co-doped cubic NaYF4 and Yb3+/Er3+/Gd(3+) -tri-doped hexagonal NaYF4 nanocrystals were synthesized by a modified coprecipitation method with ethylenediamine tetraacetic acid (EDTA) as chelating agent. The samples' morphology, crystal phase and upconversion emission were measured with transmission electron microscope (TEM), X-ray diffraction patterns (XRD) and upconversion luminescence spectrum. TEM and XRD results showed that the phase transition from cubic to hexagonal was promoted through Gd3+ doping. It has been reported that the upconversion efficiency of hexagonal NaYF4 is higher than that of cubic NaYF4, however, the effect of crystal phase on upconversion luminescence has not been well understood. This work focuses analysis of measurement results to compare the effect of, crystal phase on the crystal field energy splitting and upconversion emission intensity as well as emission color, and a mechanism of luminescence enhancement and color tunability are revealed. Strong visible upconversion luminescence can be seen clearly by the naked eyes in both cubic phase and hexagonal phase samples upon excitation by a 980 nm laser diode with power of 10 mW, consisting of green emissions centered at around 525/550 nm originating from the transitions of 2H11/2/4 S3/2 --> 4 I15/2 and red emission at about 657 nm from 4F9/2 to 4 I15/2 of Er3+ ions respectively. In comparison to cubic sample, the hexagonal phase sample presented much stronger and sharper upconversion luminescence, whose emission efficiency was enhanced 10 times with an additional transition of 2 H9/2 --> 4I13/2 at 557 nm, furthermore, the intensity ratio of red to green emission increased from 2 :1 to 3 : 1. Doping NaYF4 nanocrystals with Gd3+ ions induced the hexagonal-to-cubic phase transition and thus decreased the crystal symmetry, consequently increased absorption cross-section and 4f-4f transition probabilities by relaxing forbidden selection rules, resulting in stronger emission. In the mean time, the decreasing unit-cell volume of the hexagonal phase increased the crystal field strength around the dopant ions and consequently led to that hexagonal phase samples present much sharper emission compared to cubic counterparts. It demonstrates that phase transition can tune crystal field energy splitting, luminescence intensity and emission color.
RESUMEN
A series of red long afterglow phosphors with composition Zn(x) Mg(1-2) Ga2 O4 : Cr3+ (x = 0, 0.2, 0.6, 0.8, 1.0) were synthesized by a high temperature solid-state reaction method. The X-ray diffraction studies show that the phase of the phosphors is face-centered cubic structure. Photoluminescence spectra show that the red emission of Cr3+ originated from the transition of 2E-4A2. Due to the large overlap between absorption band of Cr3+ and emission band of the host. Cr3+ could obtain the excitation energy from the host via the effective energy transfer. The afterglow decay characteristics show that the phosphor samples with different Zn contents have different afterglow time and the afterglow time also changes with the value of x. The measurement of thermoluminescence reveals that the trap depth of the phosphor samples with different Zn contents is different. The samples with deeper traps have longer afterglow time.
RESUMEN
The Al doping gallate phosphor (Ga(1-x)Al(x))2O3 : Cr3+ (x = 0, 0.1, 0.2, 0.3, 0.4, 0.5) was synthesized by a high temperature solid-state reaction method. The X-ray diffractions show that the phase of the phosphors remains to be Ga2 O3 structure with increase in the contents of Al3+ ion. Beside, the fact that the X-ray diffraction peak shifts towards big angles with increasing Al3+ ions content shows that Al3+ ions entered the Ga2 O3 lattice. The peaks of the excitation spectra located at 258, 300, 410 and 550 nm are attributed to the band to band transition of the matrix, charge transfer band transition, and 4A2 --> 4T1 and 4A2 --> 4T2 transition of Cr3+ ions, respectively. Those excitation spectrum peak positions show different degrees of blue shift with the increase in the Al3+ ions content. The blue shift of the first two peaks are due to the band gap energy of substrate and the electronegativity between Cr3+ ions and ligands increasing, respectively. The blue shift of the energy level transition of Cr3+ ion is attributed to crystal field strength increasing. The Cr3+ ion luminescence changes from a broadband emission to a narrow-band emission with Al3+ doping, because the emission of Cr3+ ion changed from 4 T2 --> 4A2 to 2E --> 4A2 transition with the crystal field change after Al3+ ions doping. The Al3+ ions doping improved the long afterglow luminescence properties of samples, and the sample showed a longer visible near infrared when Al3+ ions content reaches 0.5. The thermoluminescence curve shows the sample with suitable trap energy level, and this is also the cause of the long afterglow luminescence materials.
RESUMEN
As the COVID-19 pandemic fades, the aviation industry is entering a fast recovery period. To analyze airport networks' post-pandemic resilience during the recovery process, this paper proposes a Comprehensive Resilience Assessment (CRA) model approach using the airport networks of China, Europe, and the U.S.A as case studies. The impact of COVID-19 on the networks is analyzed after populating the models of these networks with real air traffic data. The results suggest that the pandemic has caused damage to all three networks, although the damages to the network structures of Europe and the U.S.A are more severe than the damage in China. The analysis suggests that China, as the airport network with less network performance change, has a more stable level of resilience. The analysis also shows that the different levels of stringency policy in prevention and control measures during the epidemic directly affected the recovery rate of the network. This paper provides new insights into the impact of the pandemic on airport network resilience.
Asunto(s)
Aviación , COVID-19 , Humanos , Aeropuertos , Pandemias/prevención & control , COVID-19/epidemiología , COVID-19/prevención & control , PolíticasRESUMEN
Using a relatively small training set of ~16 thousand images from macromolecular crystallisation experiments, we compare classification results obtained with four of the most widely-used convolutional deep-learning network architectures that can be implemented without the need for extensive computational resources. We show that the classifiers have different strengths that can be combined to provide an ensemble classifier achieving a classification accuracy comparable to that obtained by a large consortium initiative. We use eight classes to effectively rank the experimental outcomes, thereby providing detailed information that can be used with routine crystallography experiments to automatically identify crystal formation for drug discovery and pave the way for further exploration of the relationship between crystal formation and crystallisation conditions.
Asunto(s)
Aprendizaje Profundo , Redes Neurales de la ComputaciónRESUMEN
Background: Driven by increased prevalence of type 2 diabetes and ageing populations, wounds affect millions of people each year, but monitoring and treatment remain limited. Glucocorticoid (stress hormones) activation by the enzyme 11ß-hydroxysteroid dehydrogenase type 1 (11ß-HSD1) also impairs healing. We recently reported that 11ß-HSD1 inhibition with oral AZD4017 improves acute wound healing by manual 2D optical coherence tomography (OCT), although this method is subjective and labour-intensive. Objectives: Here, we aimed to develop an automated method of 3D OCT for rapid identification and quantification of multiple wound morphologies. Methods: We analysed 204 3D OCT scans of 3 mm punch biopsies representing 24 480 2D wound image frames. A u-net method was used for image segmentation into 4 key wound morphologies: early granulation tissue, late granulation tissue, neo-epidermis, and blood clot. U-net training was conducted with 0.2% of available frames, with a mini-batch accuracy of 86%. The trained model was applied to compare segment area (per frame) and volume (per scan) at days 2 and 7 post-wounding and in AZD4017 compared to placebo. Results: Automated OCT distinguished wound tissue morphologies, quantifying their volumetric transition during healing, and correlating with corresponding manual measurements. Further, AZD4017 improved epidermal re-epithelialisation (by manual OCT) with a corresponding trend towards increased neo-epidermis volume (by automated OCT). Conclusion: Machine learning and OCT can quantify wound healing for automated, non-invasive monitoring in real-time. This sensitive and reproducible new approach offers a step-change in wound healing research, paving the way for further development in chronic wounds.
RESUMEN
The geometric design of the combinations of horizontal and sag vertical curves (sag combinations or sag combined curves) is vital to road safety. However, there is little research that investigates the safety effects of their geometric attributes based on the analysis of real-world crash data. To this end, the crash, traffic, geometric design, and roadway configuration data are collected from 157 sag combinations on six freeways in Washington State, during 2011-2017. Poisson, negative binomial (NB), hierarchical Poisson, and hierarchical NB models are developed for analyzing the crash frequency of sag combinations. The models are estimated and compared in the context of Bayesian inference. The results indicate that significant over-dispersion and cross-group heterogeneity exist in the crash data and that the hierarchical NB model yields the best overall performance. The parameter estimates show that: five geometric attributes, including horizontal curvature, vertical curvature, departure grade, the ratio of horizontal curvature to vertical curvature, and the layout of front dislocation, have significant effects on the crash frequency of sag combinations. Freeway section length, annual average daily traffic, and speed limits are also important predictors of crash frequency. The analysis results and the proposed model are useful for evaluating the safety performance of freeway sag combinations and optimizing their geometric design based on substantive safety evaluation.
Asunto(s)
Accidentes de Tránsito , Modelos Estadísticos , Humanos , Teorema de Bayes , Seguridad , Washingtón , Planificación AmbientalRESUMEN
Car-following is a control process in which a following vehicle adjusts its acceleration to keep a safe distance from the lead vehicle. Recently, there has been a booming of data-driven models that enable more accurate modeling of car-following through real-world driving datasets. Although there are several public datasets available, their formats are not always consistent, making it challenging to determine the state-of-the-art models and how well a new model performs compared to existing ones. To address this gap and promote the development of microscopic traffic flow modeling, we establish the first public benchmark dataset for car-following behavior modeling. This benchmark consists of more than 80 K car-following events extracted from five public driving datasets under the same criteria. To give an overview of current progress in car-following modeling, we implemented and tested representative baseline models within the benchmark. The established benchmark provides researchers with consistent data formats and metrics for cross-comparing different car-following models, coming with open datasets and codes.
RESUMEN
As the automobile market gradually develops towards intelligence, networking, and information-orientated, intelligent identification based on connected vehicle data becomes a key technology. Specifically, real-time crash identification using vehicle operation data can enable automotive companies to obtain timely information on the safety of user vehicle usage so that timely customer service and roadside rescue can be provided. In this paper, an accurate vehicle crash identification algorithm is developed based on machine learning techniques using electric vehicles' operation data provided by SAIC-GM-Wuling. The point of battery disconnection is identified as a potential crash event. Data before and after the battery disconnection is retrieved for feature extraction. Two different feature extraction methods are used: one directly extracts the descriptive statistical features of various variables, and the other directly unfolds the multivariate time series data. The AdaBoost algorithm is used to classify whether a potential crash event is a real crash using the constructed features. Models trained with the two different features are fused for the final outputs. The results show that the final model is simple, effective, and has a fast inference speed. The model has an F1 score of 0.98 on testing data for crash classification, and the identified crash times are all within 10 s around the true crash times. All data and code are available at https://github.com/MeixinZhu/vehicle-crash-identification.
Asunto(s)
Accidentes de Tránsito , Conducción de Automóvil , Accidentes de Tránsito/prevención & control , Algoritmos , Automóviles , Humanos , TecnologíaRESUMEN
Cell Painting is a high-content image-based assay applied in drug discovery to predict bioactivity, assess toxicity and understand mechanisms of action of chemical and genetic perturbations. We investigate label-free Cell Painting by predicting the five fluorescent Cell Painting channels from brightfield input. We train and validate two deep learning models with a dataset representing 17 batches, and we evaluate on batches treated with compounds from a phenotypic set. The mean Pearson correlation coefficient of the predicted images across all channels is 0.84. Without incorporating features into the model training, we achieved a mean correlation of 0.45 with ground truth features extracted using a segmentation-based feature extraction pipeline. Additionally, we identified 30 features which correlated greater than 0.8 to the ground truth. Toxicity analysis on the label-free Cell Painting resulted a sensitivity of 62.5% and specificity of 99.3% on images from unseen batches. We provide a breakdown of the feature profiles by channel and feature type to understand the potential and limitations of label-free morphological profiling. We demonstrate that label-free Cell Painting has the potential to be used for downstream analyses and could allow for repurposing imaging channels for other non-generic fluorescent stains of more targeted biological interest.
Asunto(s)
Bioensayo , Descubrimiento de Drogas , Bioensayo/métodos , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
Cell line authentication is important in the biomedical field to ensure that researchers are not working with misidentified cells. Short tandem repeat is the gold standard method, but has its own limitations, including being expensive and time-consuming. Deep neural networks achieve great success in the analysis of cellular images in a cost-effective way. However, because of the lack of centralized available datasets, whether or not cell line authentication can be replaced or supported by cell image classification is still a question. Moreover, the relationship between the incubation times and cellular images has not been explored in previous studies. In this study, we automated the process of the cell line authentication by using deep learning analysis of brightfield cell line images. We proposed a novel multi-task framework to identify cell lines from cell images and predict the duration of how long cell lines have been incubated simultaneously. Using thirty cell lines' data from the AstraZeneca Cell Bank, we demonstrated that our proposed method can accurately identify cell lines from brightfield images with a 99.8% accuracy and predicts the incubation durations for cell images with the coefficient of determination score of 0.927. Considering that new cell lines are continually added to the AstraZeneca Cell Bank, we integrated the transfer learning technique with the proposed system to deal with data from new cell lines not included in the pre-trained model. Our method achieved excellent performance with a precision of 97.7% and recall of 95.8% in the detection of 14 new cell lines. These results demonstrated that our proposed framework can effectively identify cell lines using brightfield images.