Cookies disclaimer
This website saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. Only essential cookies are stored. You can disable the usage of cookies by changing the settings of your browser. By browsing our website without changing the browser settings you grant us permission to store that information on your device.
Introduction
Small fragments of proteins can be responsible for amyloid formation. Amyloids often underlie serious diseases, e.g. Alzheimer's and Parkinson's diseases. Our tool FISH Amyloid helps to predict amyloidogenic fragments of proteins.
Methods
We used our new machine learning method based on the co-occurrence of aminoacid couples in short amyloidogenic fragments (hot spots)of proteins. The algorithm was trained on hot-spots, which were no longer than 10 amino acids, obtained from all available experimental databases. Then the method was tested with a 4-fold cross-validation method and the result is presented in the figure below.
where, SP - specificity, SN - sensitivity. In the figure the default threshold is marked. For the classification you can use one of two options. The data from the figure and the data for training can be downloaded:
plot and
data .
Download
We are working on making the package available for download. In the meantime please use our online service
here .
How to cite
If you used our service please cite:
Gasior P, Kotulska M,
FISH Amyloid - a new method for finding amyloidogenic segments in proteins based on site specific co-occurence of aminoacids. BMC Bioinformatics , 2014 Feb 24;15(1):54.
Contact
