PIPENN: Protein Interface Prediction with an Ensemble of Neural Nets

Motivation: Protein interactions play an essential role in many biological and cellular processes, such as protein—protein interaction (PPI) in signaling pathways, binding to DNA in transcription, and binding to small molecules in receptor activation or enzymatic activity. Experimental identification of protein binding interface residues is a time-consuming, costly, and challenging task. Several machine learning and other computational approaches exist which predict such interface residues. Here we explore if Deep Learning (DL) can be used effectively for this prediction task, and which learning strategies and architectures may be most efficient. We introduce seven DL architectures that are applied to eleven independent test sets, focused on the residues involved in PPI interfaces and in binding RNA/DNA and small molecule ligands. Results: We constructed a large data set dubbed BioDL, comprising protein-protein interaction data from the PDB and protein-ligand interactions (DNA, RNA and small molecules) from the BioLip database. Additionally, we reused our existing curated homo- and heteromeric PPI data sets. We performed several experiments to assess the impact of different data features, spatial forms, encoding schemes, network initializations, loss functions, regularization mechanisms, and activation functions on the performance of the predictors. Benchmarking the resulting DL models with an independent test set (ZK448) shows no single DL architecture performs best on all instances, but that an ensemble of DL architectures consistently achieves peak prediction performance. Our PIPENN's ensemble predictor outperforms current state-of-the-art sequence-based protein interface predictors on all interaction types, achieving AUCs of 0.718 (protein—protein), 0.823 (protein—nucleotide) and 0.842 (protein—small molecule) respectively. Availability: Source code and data sets at https://github.com/ibivu/

Dynamic residue interaction network analysis of the oseltamivir binding site of N1 neuraminidase and its H274Y mutation site conferring drug resistance in influenza A virus

Background Oseltamivir (OTV)-resistant influenza virus exhibits His-to-Tyr mutation at residue 274 (H274Y) in N1 neuraminidase (NA). However, the molecular mechanisms by which the H274Y mutation in NA reduces its binding affinity to OTV have not been fully elucidated. Methods In this study, we used dynamic residue interaction network (dRIN) analysis based on molecular dynamics simulation to investigate the correlation between the OTV binding site of NA and its H274Y mutation site. Results dRIN analysis revealed that the OTV binding site and H274Y mutation site of NA interact via the three interface residues connecting them. H274Y mutation significantly enhanced the interaction between residue 274 and the three interface residues in NA, thereby significantly decreasing the interaction between OTV and its surrounding loop 150 residues. Thus, we concluded that such changes in residue interactions could reduce the binding affinity of OTV to NA, resulting in drug resistant influenza viruses. Using dRIN analysis, we succeeded in understanding the characteristic changes in residue interactions due to H274Y mutation, which can elucidate the molecular mechanism of reduction in OTV binding affinity to influenza NA. Finally, the dRIN analysis used in this study can be widely applied to various systems such as individual proteins, protein-ligand complexes, and protein-protein complexes, to characterize the dynamic aspects of the interactions.

Alpha-Carbonic Anhydrases from Hydrothermal Vent Sources as Potential Carbon Dioxide Sequestration Agents: In Silico Sequence, Structure and Dynamics Analyses

With the increase in CO2 emissions worldwide and its dire effects, there is a need to reduce CO2 concentrations in the atmosphere. Alpha-carbonic anhydrases (α-CAs) have been identified as suitable sequestration agents. This study reports the sequence and structural analysis of 15 α-CAs from bacteria, originating from hydrothermal vent systems. Structural analysis of the multimers enabled the identification of hotspot and interface residues. Molecular dynamics simulations of the homo-multimers were performed at 300 K, 363 K, 393 K and 423 K to unearth potentially thermostable α-CAs. Average betweenness centrality (BC) calculations confirmed the relevance of some hotspot and interface residues. The key residues responsible for dimer thermostability were identified by comparing fluctuating interfaces with stable ones, and were part of conserved motifs. Crucial long-lived hydrogen bond networks were observed around residues with high BC values. Dynamic cross correlation fortified the relevance of oligomerization of these proteins, thus the importance of simulating them in their multimeric forms. A consensus of the simulation analyses used in this study suggested high thermostability for the α-CA from Nitratiruptor tergarcus. Overall, our novel findings enhance the potential of biotechnology applications through the discovery of alternative thermostable CO2 sequestration agents and their potential protein design.

Uncovering the basis of protein-protein interaction specificity with a combinatorially complete library

Protein-protein interaction specificity is often encoded at the primary sequence level. However, the contributions of individual residues to specificity are usually poorly understood and often obscured by mutational robustness, sequence degeneracy, and epistasis. Using bacterial toxin-antitoxin systems as a model, we screened a combinatorially complete library of antitoxin variants at three key positions against two toxins. This library enabled us to measure the effect of individual substitutions on specificity in hundreds of genetic backgrounds. These distributions allow inferences about the general nature of interface residues in promoting specificity. We find that positive and negative contributions to specificity are neither inherently coupled nor mutually exclusive. Further, a wild-type antitoxin appears optimized for specificity as no substitutions improve discrimination between cognate and non-cognate partners. By comparing crystal structures of paralogous complexes, we provide a rationale for our observations. Collectively, this work provides a generalizable approach to understanding the logic of molecular recognition.

CoRNeA: A Pipeline to Decrypt the Inter-Protein Interfaces from Amino Acid Sequence Information

Decrypting the interface residues of the protein complexes provides insight into the functions of the proteins and, hence, the overall cellular machinery. Computational methods have been devised in the past to predict the interface residues using amino acid sequence information, but all these methods have been majorly applied to predict for prokaryotic protein complexes. Since the composition and rate of evolution of the primary sequence is different between prokaryotes and eukaryotes, it is important to develop a method specifically for eukaryotic complexes. Here, we report a new hybrid pipeline for predicting the protein-protein interaction interfaces in a pairwise manner from the amino acid sequence information of the interacting proteins. It is based on the framework of Co-evolution, machine learning (Random Forest), and Network Analysis named CoRNeA trained specifically on eukaryotic protein complexes. We use Co-evolution, physicochemical properties, and contact potential as major group of features to train the Random Forest classifier. We also incorporate the intra-contact information of the individual proteins to eliminate false positives from the predictions keeping in mind that the amino acid sequence of a protein also holds information for its own folding and not only the interface propensities. Our prediction on example datasets shows that CoRNeA not only enhances the prediction of true interface residues but also reduces false positive rates significantly.

ConvsPPIS: Identifying Protein-protein Interaction Sites by an Ensemble Convolutional Neural Network with Feature Graph

Background/Objective: Protein-protein interactions are essentials for most cellular processes and thus, unveiling how proteins interact with is a crucial question that can be better understood by recognizing which residues participate in the interaction. Although many computational approaches have been proposed to predict interface residues, their feature perspective and model learning ability are not enough to achieve ideal results. So, our objective is to improve the predictive performance under considering feature perspective and new learning algorithm. Method: In this study, we proposed an ensemble deep convolutional neural network, which explores the context and positional context of consecutive residues within a protein sub-sequence. Specifically, unlike the feature view of previous methods, ConvsPPIS uses evolutionary, physicochemical, and structural protein characteristics to construct their own feature graph respectively. After that, three independent deep convolutional neural networks are trained on each type of feature graph for learning the underlying pattern in sub-sequence. Lastly, we integrated those three deep networks into an ensemble predictor with leveraging complementary information of those features to predict potential interface residues. Results: Some comparative experiments have conducted through 10-fold cross-validation. The results indicated that ConvsPPIS achieved superior performance on DBv5-Sel dataset with an accuracy of 88%. Additional experiments on CAPRI-Alone dataset demonstrated ConvsPPIS has also better prediction performance. Conclusion: The ConvsPPIS method provided a new perspective to capture protein feature expression for identifying protein-protein interaction sites. The results proved the superiority of this method.

Computational Investigation Of Structural Interfaces Of Protein Complexes With Short Linear Motifs

Protein complexes with short linear motifs (SLiMs) are known to play important regulatory functions in eukaryotes. In this investigation, I have studied the structures deposited in PDB with SLiMs. The structures Were grouped into three broad categories of protein-protein, protein-peptide and the rest as others. Protein-peptide complexes Were found to be most highly represented. The interfaces Were evaluated for geometric features and conformational variables. It was observed that protein-protein and protein-peptide complexes show characteristic differences in residue pairings, which Were quantified by evaluating normalized contact residue pairing frequencies. Interface residues adopt characteristic canonical residue conformations in the Ramachandran space, with a pronounced preference for positive ϕ conformations. It was observed that phosphorylated residues have an unusual propensity to adopt the unusual positive ϕ conformations at the interface.

Hot-spots and their contribution to the self-assembly of the viral capsid: in-vitro validation

The viral capsid is a macromolecular complex formed by self-assembled proteins (CPs) which, in many cases, are biopolymers with an identical amino acid sequence. Specific CP-CP interactions drive the capsid self-assembly process. However, it is believed that only a small set of protein-protein interface residues significantly contribute to the formation of the capsid; the so-called “hot-spots”. Here, we investigate the effect of in-vitro point-mutations on the Bromoviridae family structure-conserved interface residues of the icosahedral Cowpea Chlorotic Mottle Virus, previously hypothesized as hot-spots. We study the self-assembly of those mutated recombinant CPs for the formation of capsids by Thermal Shift Assay (TSA). We show that the TSA biophysical technique is a reliable way to characterize capsid assembly. Our results show that point-mutations on non-conserved interface residues produce capsids indistinguishable from the wild-type. In contrast, a single mutation on structure-conserved residues E176 or V189 prevents the formation of the capsid while maintaining the tertiary fold of the CP. Our findings provide experimental evidence of the in-silico conservation-based hot-spot prediction accuracy. As a whole, our methodology provides a framework that could aid in the rational development of molecules to inhibit virus formation, or advance capsid bioengineering to design for their stability, function and applications.