We use essential cookies to operate our site. With your consent, we may also use non-essential cookies to improve your user experience and to analyze website traffic. Click "Accept" to accept cookies and go directly to the site, click "Reject" to reject all but cookies strictly necessary for the functioning of this site. You can reset your cookie settings at any time by visiting your Bioz "my account" page and selecting the "reset cookie preferences" link.

Accept Reject

Overview
Images
Article Snippets
home > search results > product details
star_border
     Loading Product Details ...      Welcome to Your Next Discovery   
86 / 100
Bioz Stars

WiCell Research Institute  
Open an account
already a user? Sign in
are you a supplier? Contact us
Product Images (1) - All
All
Clone Assay
Derivative Assay
MANN-WHITNEY
A deep learning method that identifies cellular heterogeneity using nanoscale nuclear features 
star_border
a , Positive and negative attribution scores for representative hiPSCs and somatic cells using the occlusion-based method (64 × 64 pixel size with stride of 32 pixels) for AINU trained with single-colour Pol II images. The blue regions correspond to areas whose occlusion decreases the probability of predicting the correct class and therefore considered positive for the prediction, whereas the red regions correspond to ‘distracting’ areas whose occlusion increases the probability of predicting the correct class. b , c , Images showing the CAM data for the hiPSC image in a and its overlay on the original image ( c ). d , Same data as a for AINU trained with dual-colour images of Pol II and H3 in hiPSCs and somatic cells. e – h , AINU trained with dual-colour Pol II and H3 images was challenged on a test set of 71 previously unseen images having the nucleoli occluded by filling them with cloned non-nucleolous regions from the same image. Normalized confusion matrix (with numbers of positively and negatively predicted images in the parentheses). e , Performance of the model for each class; the diagonal reports the accuracy for each class. The ROC curve ( f ) shows the performance of the model at all the classification thresholds and the AUC value. g , h , Precision and recall plots for the somatic cell ( g ) and hiPSC ( h ) classes, reporting the overall AP. i , j , Box plots showing a significant difference (two-sided Mann–Whitney U -test) between the median localizations per cluster ( i ) and median cluster area ( j ) in somatic ( n = 22) and hiPSC ( n = 21) nucleoli. All the box plots depict the median (horizontal line inside box), 25th and 75th percentiles (box), and 25th or 75th percentiles ± 1.5 × interquartile range (whiskers). Distributions were compared as indicated, using the Mann–Whitney U -test. ** P < 0.01. k , Bar plot showing significant difference (two-sided unpaired t -test, P = 0.0028) of ssRT-qPCR level for asincRNA transcribed by Pol II from rDNA IGS 28, between <t>IMR90</t> cells and IMR90-derived hiPSCs (error bars represent s.d.). The error bars, including mean and s.d. values, are shown for n = 3 independent experiments.
A deep learning method that identifies cellular heterogeneity using nanoscale nuclear features Nature Machine Intelligence, 2024 Aug 27
"a , Positive and negative attribution scores for representative hiPSCs and somatic cells using the occlusion-based method (64 × 64 pixel size with stride of 32 pixels) for AINU trained with single-colour Pol II images. The blue regions correspond to areas whose occlusion decreases the probability of predicting the correct class and therefore considered positive for the prediction, whereas the red regions correspond to ‘distracting’ areas whose occlusion increases the probability of predicting the correct class. b , c , Images showing the CAM data for the hiPSC image in a and its overlay on the original image ( c ). d , Same data as a for AINU trained with dual-colour images of Pol II and H3 in hiPSCs and somatic cells. e – h , AINU trained with dual-colour Pol II and H3 images was challenged on a test set of 71 previously unseen images having the nucleoli occluded by filling them with cloned non-nucleolous regions from the same image. Normalized confusion matrix (with numbers of positively and negatively predicted images in the parentheses). e , Performance of the model for each class; the diagonal reports the accuracy for each class. The ROC curve ( f ) shows the performance of the model at all the classification thresholds and the AUC value. g , h , Precision and recall plots for the somatic cell ( g ) and hiPSC ( h ) classes, reporting the overall AP. i , j , Box plots showing a significant difference (two-sided Mann–Whitney U -test) between the median localizations per cluster ( i ) and median cluster area ( j ) in somatic ( n = 22) and hiPSC ( n = 21) nucleoli. All the box plots depict the median (horizontal line inside box), 25th and 75th percentiles (box), and 25th or 75th percentiles ± 1.5 × interquartile range (whiskers). Distributions were compared as indicated, using the Mann–Whitney U -test. ** P < 0.01. k , Bar plot showing significant difference (two-sided unpaired t -test, P = 0.0028) of ssRT-qPCR level for asincRNA transcribed by Pol II from rDNA IGS 28, between <t>IMR90</t> cells and IMR90-derived hiPSCs (error bars represent s.d.). The error bars, including mean and s.d. values, are shown for n = 3 independent experiments. "
Protocol Conditions
Article Snippets for All Techniques

WiCell Research Institute Inc logo

The mission of WiCell is to support regenerative medicine and cell and gene therapy by promoting best practices in cell banking and characterization and providing high quality materials and testing services to advance research and clinical applications at UW-Madison and globally.