Prediction of Protein-Protein Interactions from Protein Sequence Using Local Descriptors

Abstract

With a huge amount of protein sequence data, the computational method for protein-protein interaction (PPI) prediction using only the protein sequences information have drawn increasing interest. In this article, we propose a sequence-based method based on a novel representation of local protein sequence descriptors. Local descriptors account for the interactions between residues in both continuous and discontinuous regions of a protein sequence, so this method enables us to extract more PPI information from the sequence. A series of elaborate experiments are performed to optimize the prediction model by varying the parameter k and the distance measuring function of the k-nearest neighbors learning system and the ways of coding a protein pair. When performed on the PPI data of Saccharomyces cerevisiae, the method achieved 86.15% prediction accuracy with 81.03% sensitivity at the precision of 90.24%. An independent data set of 986 Escherichia coli PPIs was used to evaluate this prediction model and the prediction accuracy is 73.02%. Given the complex nature of PPIs, the performance of our method is promising, and it can be a helpful supplement for PPIs prediction.

Identification of Protein–Protein Interactions via a Novel Matrix-Based Sequence Representation Model with Amino Acid Contact Information

“…Shen et al [12] describe a protein sequence by amino acid groups, and its feature vector is formed by the occurrence of conjoint triads (CT). Zhou [13] and Yang [14] split the amino acid sequence into ten local regions of varying length and their compositions are represented by multiple overlapping continuous and discontinuous interaction information within one protein sequence. For each local region, they calculate three local descriptors (LD), such as composition (C), transition (T) and distribution (D).…”

Incorporating Amino Acid Typing Into Nuclear Magnetic Resonance Protein Structure-Based Assignments

“…This work is also a followup to [4] where the contribution of each of the data sources into NVR's accuracy was studied. There are various amino acid groupings in the literature, such as [22,23]. The amino acid groupings mentioned in this work come from external constraints -the Craack approach can classify each amino acid into eight classes and similarly HADAMAC classifies each amino acid into one of seven classes.…”

A Novel Feature Extraction Scheme with Ensemble Coding for Protein–Protein Interaction Prediction

“…These computational methods can be roughly divided into sequence based [11,12,13,14,15,16,17,18,19], structure based [20,21,22,23,24], and function annotation based [25,26,27,28,29] methods with different coding methods, such as autocovariance (AC) [12], local descriptors (LD) [19], conjoint triad (CT) [11], Geary autocorrelation (GAC) [30], Moran autocorrelation (MAC) [31], and normalized Moreau–Broto autocorrelation (NMBAC) [32]. Sequence-based methods have the advantage of not requiring expensive and time-consuming processes to determine protein structures.…”

“…AC considers the neighboring effect and enables the discovery of patterns that run through entire sequences. LD [19] is an alignment-free approach and its effectiveness depends largely on the underlying amino acid groups. Each protein is divided into 10 local regions, with each local region containing 3 LD: composition, transition, and distribution.…”