Proteome-Wide Prediction of Novel DNA/RNA-Binding Proteins Using Amino Acid Composition and Periodicity in the Hyperthermophilic Archaeon Pyrococcus furiosus

Abstract

Proteins play a critical role in complex biological systems, yet about half of the proteins in publicly available databases are annotated as functionally unknown. Proteome-wide functional classification using bioinformatics approaches thus is becoming an important method for revealing unknown protein functions. Using the hyperthermophilic archaeon Pyrococcus furiosus as a model species, we used the support vector machine (SVM) method to discriminate DNA/RNA-binding proteins from proteins with other functions, using amino acid composition and periodicities as feature vectors. We defined this value as the composition score (CO) and periodicity score (PD). The P. furiosus proteins were classified into three classes (I–III) on the basis of the two-dimensional correlation analysis of CO score and PD score. As a result, approximately 87% of the functionally known proteins categorized as class I proteins (CO score + PD score > 0.6) were found to be DNA/RNA-binding proteins. Applying the two-dimensional correlation analysis to the 994 hypothetical proteins in P. furiosus, a total of 151 proteins were predicted to be novel DNA/RNA-binding protein candidates. DNA/RNA-binding activities of randomly chosen hypothetical proteins were experimentally verified. Six out of seven candidate proteins in class I possessed DNA/RNA-binding activities, supporting the efficacy of our method.

Identification of protein functions using a machine-learning approach based on sequence-derived properties

“…The 451 traditional features used for prediction of protein function have been described in previous reports [17,[22][23][24]28,32,36,37,[43][44][45][76][77][78]. The present study introduces new features based on negatively and positively charged residues and analyses their utility.…”

Enabling full‐length evolutionary profiles based deep convolutional neural network for predicting DNA‐binding proteins from sequence

“…Some sequence matches are also missed due to insertion and deletions between key residue positions of a novel protein. In such cases, direct methods of functional annotation, which rely on scanning a sequence through sliding windows or use global summary of sequence properties such as amino acid composition have proved useful . Protein‐function annotation on a large scale is done by use of Gene Ontologies .…”

“…In such cases, direct methods of functional annotation, which rely on scanning a sequence through sliding windows or use global summary of sequence properties such as amino acid composition have proved useful. [4][5][6][7][8] Protein-function annotation on a large scale is done by use of Gene Ontologies. 4 However, focusing on individual, well understood biological functions and annotating specific Biological functions gives much more power to a predictive method, as the annotations can incorporate knowledge specifically relevant for that system.…”

Characterization of a heat-stable enzyme possessing GTP-dependent RNA ligase activity from a hyperthermophilic archaeon, Pyrococcus furiosus

“…For example, the results of DNA microarray analysis of Pyrococcus furiosus (Schut et al 2001;Schut et al 2003) and of a genome-wide protein-protein interaction study in Pyrococcus horikoshii OT3 (Usui et al 2005) have contributed to our general understanding of archaeal biology, in addition to pointing to features unique to these species. We have been studying RNA metabolism in P. furiosus Sato et al 2003;Fujishima et al 2007). It has been hypothesized that RNA played a central role in the very beginning of life (Forterre 2005;Gesteland et al 2006); thus, analyzing gene regulation at the RNA level of the organism may contribute to a better understanding of the basis of gene function.…”