Classification

Re-occurs among biii.info tags (visualisation, rendering, viewer, classification, ...)|ToDo: Clear up relation between Classification, Clustering, and Prediction and recognition (also in main EDAM)

Description

Phindr3D is a comprehensive shallow-learning framework for automated quantitative phenotyping of three-dimensional (3D) high content screening image data using unsupervised data-driven voxel-based feature learning, which enables computationally facile classification, clustering and data visualization.

Please see our GitHub page and the original publication for details.

Description

KNIME workflow to visualize a dataset described by multiple quantitative features (ex: a list of samples or cells, each described with multiple morphological features) as a 3D cloud of points (each point corresponding to one sample/cell) as well as a line plot (1 line per sample/cell).

For the 3D plot, the workflow uses Principal Component Analysis (PCA) for dimensionality reduction, ie it simplifies the information for each sample from n-features to 3 pseudo-features which are used as x,y,z-coordinates for each sample. The original features should cover similar value range, to make sure the PCA is not biased towards the large values features. One option is to normalize the values (min/max or Z-score). 

Also make sure that the resulting PCA represents a decent % of the original data variance (at least 70%). Otherwise the PCA plot will not be representative of the original data-distribution. The % is shown in the title of the PCA plot.

The workflow is interactive and so selecting in one panel of the figure will highlight in the other panel too.

It was originally published for the visualization of phenotypic kidney features in zebrafish, but the workflow is generic by design and can be reused for any quantitative feature set. 

KNIME-Workflow
Description

ASAP allows to automatically detect, classify and quantify structures acquired by super resolution microscopy. 

Description

ImJoy is a plugin powered hybrid computing platform for deploying deep learning applications such as advanced image analysis tools.

ImJoy runs on mobile and desktop environment cross different operating systems, plugins can run in the browser, localhost, remote and cloud servers.

With ImJoy, delivering Deep Learning tools to the end users is simple and easy thanks to its flexible plugin system and sharable plugin URL. Developer can easily add rich and interactive web interfaces to existing Python code.

has topic