Binding Site Prediction for Protein-Protein Interactions and Novel Motif Discovery using Re-occurring Polypeptide Sequences

Abstract

BackgroundWhile there are many methods for predicting protein-protein interaction, very few can determine the specific site of interaction on each protein. Characterization of the specific sequence regions mediating interaction (binding sites) is crucial for an understanding of cellular pathways. Experimental methods often report false binding sites due to experimental limitations, while computational methods tend to require data which is not available at the proteome-scale. Here we present PIPE-Sites, a novel method of protein specific binding site prediction based on pairs of re-occurring polypeptide sequences, which have been previously shown to accurately predict protein-protein interactions. PIPE-Sites operates at high specificity and requires only the sequences of query proteins and a database of known binary interactions with no binding site data, making it applicable to binding site prediction at the proteome-scale.ResultsPIPE-Sites was evaluated using a dataset of 265 yeast and 423 human interacting proteins pairs with experimentally-determined binding sites. We found that PIPE-Sites predictions were closer to the confirmed binding site than those of two existing binding site prediction methods based on domain-domain interactions, when applied to the same dataset. Finally, we applied PIPE-Sites to two datasets of 2347 yeast and 14,438 human novel interacting protein pairs predicted to interact with high confidence. An analysis of the predicted interaction sites revealed a number of protein subsequences which are highly re-occurring in binding sites and which may represent novel binding motifs.ConclusionsPIPE-Sites is an accurate method for predicting protein binding sites and is applicable to the proteome-scale. Thus, PIPE-Sites could be useful for exhaustive analysis of protein binding patterns in whole proteomes as well as discovery of novel binding motifs. PIPE-Sites is available online at http://pipe-sites.cgmlab.org/.

Prediction of Protein Metal Binding Sites Using Deep Neural Networks

“…In our experiments, we generated different window sizes (5,7,9,11,13,15,17,19,21,23,25,31,101) for every protein sequence. The results obtained with the PAM features and CNN for all these window sizes are shown in Figure 7.…”

“…[7] Furthermore, various bioinformatics approaches have been developed to predict the metal-binding sites in a single sequence such as a web server for predicting metal-binding sites, [5,8] predicting calcium-binding sites, [6] identifying Cysteines and Histidines in transition-metal-binding sites, [2] protein metal-binding residue prediction, [3] prediction of the functional class of metal-binding proteins, [9] predicting the geometry of metal binding sites, [10] a web server to predict ironÀ sulphur cluster binding, [11] discriminating different types of metal-binding sites, [12] prediction of water and metal binding sites and their affinities, [13] prediction of transition metal-binding sites, [14] prediction of metalloproteins, [15] structurebased de novo prediction of zinc-binding sites, [16] prediction of metal ion-binding sites, [17] recognition of zinc binding sites, [18] binding site prediction for proteinÀ protein interactions. [19] After these studies with traditional machine learning methods, Deep Neural Networks (DNN) have started to be used in recent years. [20] In the last few years, CNN has led to a very good performance on a variety of problems, such as visual recognition, speech recognition, natural language processing, drug discovery and genomics.…”

Computational Prediction of the Comprehensive SARS-CoV-2 vs. Human Interactome to Guide the Design of Therapeutics

“…PIPE has previously been validated on numerous species for both intra-species and inter-species PPI prediction tasks [13,14,15]. Furthermore, the distribution of evidence along the length of each query protein forms a 2D landscape that can indicate the site of interaction (see "Predicted PPI Site of Interaction" subsection 2.2.4 below) [8].…”

“…The PIPE4 algorithm generates its prediction for a given pair of proteins based on a two-dimensional landscape of scores, where the score at location x, y, the number of sequence window similarity "hits", represents the weight of evidence from the x th and y th subsequence of the human and SARS-CoV-2 proteins, respectively. The PIPE-Sites algorithm examines this landscape and deduces which subsequences from each protein are likely to correspond to the site of interaction [8]. Such information can guide subsequent detailed investigations to determine the physical binding site which may form the target for novel interventions to disrupt the PPI.…”

“…We hope to contribute to the scientific effort using the latest version of our sequence-based protein-protein interaction (PPI) predictor, PIPE4 [6] in combination with another state-of-the-art PPI predictor, denoted Scoring PRotein INTeractions (SPRINT) [7]. Finally, the PIPE-Sites algorithm was used to predict the sub-sequence regions with a high likelihood of mediating the physical interaction between two given pairs [8].…”