Amyloid fibers have long been associated with several debilitating diseases and with protein expression and purification problems in the field of biotechnology. However growing evidence of specific biological functions are now arising and the extraordinary self-assembly and controlled fibrillation potential of amyloid is currently being exploited as source for new nanomaterials. Despite fibril structural similarity, proteins that can undergo structural changes which lead to amyloid formation are quite diverse and share no obvious sequence or structural homology. Increased understanding of which peptides and proteins undergo amyloid formation and the driving forces responsible for amyloid-like fiber formation and stabilization are thus of paramount importance.
The Amyloidogenic Propensity Prediction Neural Network (APPNN) present here, is a newly phenomenological amyloidogenic propensity predictor that was developed based on a machine learning approach through recursive feature selection and feed-forward neural networks and that proved capable of accurately and reliably predicting the amyloidogenic propensity from the polypeptide sequence alone.
This algorithm was implemented in Matlab and ported to R. It is distributed in the form of source files that can be used within Matlab (with a graphical user interface) or R environments.
Copyright (C) 2014 Carlos Familia, Sarah Dennison, Alexandre Quintas, David Phoenix
This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, version 3 of the License.
This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.