Subcellular protein distribution analysis software tools | Conventional fluorescence microscopy
Find and compare the best bioinformatics software tools for analyzing subcellular protein distribution on conventional fluorescence microscopy images. Tools are ranked by the biomedical research community.
Provides a method for automated fluorescence microscopy image classification of subcellular protein distribution patterns via deep neural networks (DNNs). Loc-CAT is able to support multi-localization proteins and perform classification of proteins through 29 subcellular localization patterns. This software can classify single labels, multiple labels and mixed labels and also enhance localization accuracy when predicting on multi-label or mixed single and multi-label.
Provides a method to determinate automatically and unbiasedly distributions of protein across cellular compartments. PatternUnmixer is built on a machine-learning approach that calculates the amount of fluorescent signal in different subcellular compartments without the need of hand tuning and by only requiring the acquisition of separate training images of markers for each compartment. This software suits for high-throughput microscopy and works well on real images obtained form mixed patterns.
Performs 2D immunofluorescence images to pinpoint and number synaptic protein puncta. SynPAnal provides an application that intends to partially automate processing tasks of files generated by confocal laser scanning microscopy. The application focuses on the quantification of puncta attributes but can also be applied for basic fluorescent intensity measuring as well as for basic morphometric analysis of neurons.
Computational methods were developed to automatically analyze the images created by the University of California, San Francisco (UCSF) yeast GFP fusion localization project. The automated method provides an objective, quantitative and repeatable assignment of protein locations that can be applied to new collections of yeast images (e.g. for different strains or the same strain under different conditions). It is also important to note that this performance could be achieved without requiring colocalization with any marker proteins.
A cell structure-driven classifier construction approach for predicting image-based protein subcellular location by employing the prior biological structural information. We evaluate S-PSorter on a collection of 1,636 immunohistochemistry images from the Human Protein Atlas database. The experimental results show that S-PSorter achieves an overall accuracy of 89.0%, which is 6.4% higher than the state-of-the-art method.
You can access more results by creating a free plan account or unlimited content via a premium account.