Self-interacting protein detection software tools | Interaction data analysis
Protein self-interaction, i.e. the interaction between two or more identical proteins expressed by one gene, plays an important role in the regulation of cellular functions. Considering the limitations of experimental self-interaction identification, it is necessary to design specific bioinformatics tools for self-interacting protein (SIP) prediction from protein sequence information.
Predicts self-interacting proteins (SIPs) using the information of protein sequences. PSPEL is a matrix-based method that (1) transforms all protein sequences into position-specific-scoring-matrix (PSSM) representation based on protein sequences, (2) uses the low-rank approximation (LRA) descriptor to capture the useful information for SIPs prediction from each protein PSSM, (3) generates a final protein feature vectors and (4) finally uses the machine learning technology to predict SIPs.
Predicts proteome-wide of self-interacting proteins. SLIPPER uses various related annotation information such as interaction partners in the protein interaction network (PIN), domains, and evolutionary rate. It depends on the currently available related biological data. The tool can return probability scores and abundant annotations for proteins submitted by users. It is based on logistic regression and provides features like model organism self-interacting protein.
Predicts donor and acceptor residues in C alpha-H...O and C alpha-H...pi interactions in proteins. The method is based on the recurrent neural network (Jordan network) trained on single amino acid sequence and PSIPRED predicted secondary structure. It can predict those interactions where the donor and acceptor residues are separated by less than and equal to 16 residues.
Detects protein self-interactions (SIPs) only using protein sequence data. RVM-AB employs the Average Blocks (AB) feature extract method to represent protein sequences on a Position Specific Scoring Matrix (PSSM). It is able to decrease the dimension of AB vector for reduce the influence of noise in experiments. This tool can capture useful evolutionary information to improve performance efficiency.
Predicts self-interacting proteins (SIPs). SPAR is based on an improved sequence-encoding scheme that exploits the fine-grained domain–domain interaction (DDI) information from the 3did database. It was tested on the human SIP dataset and also compared with other popular feature-encoding methods commonly used for protein-protein interaction (PPI) prediction. The tool facilitates the high-throughput prediction analysis of protein self-interactions.
You can access more results by creating a free plan account or unlimited content via a premium account.