Abstract
Proteins are essential molecules, that must correctly perform their roles for the good health of living organisms. The majority of proteins operate in complexes and the way they interact has pivotal influence on the proper functioning of such organisms. In this study we address the problem of protein–protein interaction and we propose and investigate a method based on the use of an ensemble of autoencoders. Our approach, entitled , adopts a strategy based on two autoencoders, one for each type of interactions (positive and negative) and we advance three types of neural network architectures for the autoencoders. Experiments were performed on several data sets comprising proteins from four different species. The results indicate good performances of our proposed model, with accuracy and AUC values of over 0.97 in all cases. The best performing model relies on a Siamese architecture in both the encoder and the decoder, which advantageously captures common features in protein pairs. Comparisons with other machine learning techniques applied for the same problem prove that outperforms most of its contenders, for the considered data sets.
Highlights
All molecular interactions in a cell have been termed the interactome
The first data set used in our experiments is Pan’s human protein–protein interactions data set [39], which contains positive samples collected from the HPRD-2007 database
We propose a procedure for the binary classification of protein–protein interactions having as focal points two autoencoders that are trained to encode relationships between proteins that do or do not interact
Summary
All molecular interactions in a cell have been termed the interactome. Most such interactions involve proteins, which can bind to other proteins or to small molecules. The interactome can assist in identifying functions of unknown proteins, considering that proteins that interact are often times involved in similar cellular processes [3]. By determining all interactions of a new protein, one can infer its function, assuming that the interacting proteins are already accounted for. Interaction information can be instrumental in the field of drug design, as knowledge about certain proteins’ interactions and binding sites can be used to architect drugs that target those specific proteins
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.