Different protein-protein interface patterns predicted by different machine learning methods

Prediction of the tetramer protein complex interaction based on CNN and SVM

Protein-protein interactions play an important role in life activities. The study of protein-protein interactions helps to better understand the mechanism of protein complex interaction, which is crucial for drug design, protein function annotation and three-dimensional structure prediction of protein complexes. In this paper, we study the tetramer protein complex interaction. The research has two parts: The first part is to predict the interaction between chains of the tetramer protein complex. In this part, we proposed a feature map to represent a sample generated by two chains of the tetramer protein complex, and constructed a Convolutional Neural Network (CNN) model to predict the interaction between chains of the tetramer protein complex. The AUC value of testing set is 0.6263, which indicates that our model can be used to predict the interaction between chains of the tetramer protein complex. The second part is to predict the tetramer protein complex interface residue pairs. In this part, we proposed a Support Vector Machine (SVM) ensemble method based on under-sampling and ensemble method to predict the tetramer protein complex interface residue pairs. In the top 10 predictions, when at least one protein-protein interaction interface is correctly predicted, the accuracy of our method is 82.14%. The result shows that our method is effective for the prediction of the tetramer protein complex interface residue pairs.

Protein-protein interaction and non-interaction predictions using gene sequence natural vector

Predicting protein–protein interaction and non-interaction are two important different aspects of multi-body structure predictions, which provide vital information about protein function. Some computational methods have recently been developed to complement experimental methods, but still cannot effectively detect real non-interacting protein pairs. We proposed a gene sequence-based method, named NVDT (Natural Vector combine with Dinucleotide and Triplet nucleotide), for the prediction of interaction and non-interaction. For protein–protein non-interactions (PPNIs), the proposed method obtained accuracies of 86.23% for Homo sapiens and 85.34% for Mus musculus, and it performed well on three types of non-interaction networks. For protein-protein interactions (PPIs), we obtained accuracies of 99.20, 94.94, 98.56, 95.41, and 94.83% for Saccharomyces cerevisiae, Drosophila melanogaster, Helicobacter pylori, Homo sapiens, and Mus musculus, respectively. Furthermore, NVDT outperformed established sequence-based methods and demonstrated high prediction results for cross-species interactions. NVDT is expected to be an effective approach for predicting PPIs and PPNIs.

Protein-protein non-interactions and interactions are distinguished and predicted by gene sequence using single nucleotide and contiguous nucleotides combined with machine learning models.

Residue-Frustration-Based Prediction of Protein-Protein Interactions Using Machine Learning

The study of protein-protein interactions (PPIs) is important in understanding the function of proteins. However, it is still a challenge to investigate the transient protein-protein interaction by experiments. Hence, the computational prediction for protein-protein interactions draws growing attention. Statistics-based features have been widely used in the studies of protein structure prediction and protein folding. Due to the scarcity of experimental data of PPI, it is difficult to construct a conventional statistical feature for PPI prediction, and the application of statistics-based features is very limited in this field. In this paper, we explored the application of frustration, a statistical potential, in PPI prediction. By comparing the energetic contribution of the extra stabilization energy from a given residue pair in the native protein with the statistics of the energies, we obtained the residue pair's frustration index. By calculating the number of residue pairs with a high frustration index, the highly frustrated density, a residue-frustration-based feature, was then obtained to describe the tendency of residues to be involved in PPI. Highly frustrated density, as well as structure-based features, were then used to describe protein residues and combined with the long short-term memory (LSTM) neural network to predict PPI residue pairs. Our model correctly predicted 75% dimers when only the top 2‰ residue pairs were selected in each dimer. Our model, which considers the statistics-based features, is significantly different from the models based on the chemical features of residues. We found that frustration can effectively describe the tendency of residue to be involved in PPI. Frustration-based features can replace chemical features to combine with machine learning and realize the better performance of PPI prediction. It reveals the great potential of statistical potential such as frustration in PPI prediction.

An interpretable machine learning method for homo-trimeric protein interface residue-residue interaction prediction

Protein-protein interaction plays an important role in life activities. A more fine-grained analysis, such as residues and atoms level, will better benefit us to understand the mechanism for inter-protein interaction and drug design. The development of efficient computational methods to reduce trials and errors, as well as assisting experimental researchers to determine the complex structure are some of the ongoing studies in the field. The research of trimer protein interface, especially homotrimer, has been rarely studied. In this paper, we proposed an interpretable machine learning method for homo-trimeric protein interface residue pairs prediction. The structure, sequence, and physicochemical information are intergraded as feature input fed to model for training. Graph model is utilized to present spatial information for intra-protein. Matrix factorization captures the different features' interactions. Kernel function is designed to auto-acquire the adjacent information of our target residue pairs. The accuracy rate achieves 54.5% in an independent test set. Sequence and structure alignment exhibit the ability of model self-study. Our model indicates the biological significance between sequence and structure, and could be auxiliary for reducing trials and errors in the fields of protein complex determination and protein-protein docking, etc. SIGNIFICANCE: Protein complex structures are significant for understanding protein function and promising functional protein design. With data increasing, some computational tools have been developed for protein complex residue contact prediction, which is one of the most significant steps for complex structure prediction. But for homo-trimeric protein, the sequence-based deep learning predictors are infeasible for homologous sequences, and the algorithm black box prevents us from understanding of each step operation. In this way, we propose an interpreting machine learning method for homo-trimeric protein interface residue-residue interaction prediction, and the predictor shows a good performance. Our work provides a computational auxiliary way for determining the homo-trimeric proteins interface residue pairs which will be further verified by wet experiments, and and gives a hand for the downstream works, such as protein-protein docking, protein complex structure prediction and drug design.

Structural Design and Analysis of the RHOA-ARHGEF1 Binding Mode: Challenges and Applications for Protein-Protein Interface Prediction

The interaction between two proteins may involve local movements, such as small side-chains re-positioning or more global allosteric movements, such as domain rearrangement. We studied how one can build a precise and detailed protein-protein interface using existing protein-protein docking methods, and how it can be possible to enhance the initial structures using molecular dynamics simulations and data-driven human inspection. We present how this strategy was applied to the modeling of RHOA-ARHGEF1 interaction using similar complexes of RHOA bound to other members of the Rho guanine nucleotide exchange factor family for comparative assessment. In parallel, a more crude approach based on structural superimposition and molecular replacement was also assessed. Both models were then successfully refined using molecular dynamics simulations leading to protein structures where the major data from scientific literature could be recovered. We expect that the detailed strategy used in this work will prove useful for other protein-protein interface design. The RHOA-ARHGEF1 interface modeled here will be extremely useful for the design of inhibitors targeting this protein-protein interaction (PPI).

A Two-Layer SVM Ensemble-Classifier to Predict Interface Residue Pairs of Protein Trimers

Study of interface residue pairs is important for understanding the interactions between monomers inside a trimer protein–protein complex. We developed a two-layer support vector machine (SVM) ensemble-classifier that considers physicochemical and geometric properties of amino acids and the influence of surrounding amino acids. Different descriptors and different combinations may give different prediction results. We propose feature combination engineering based on correlation coefficients and F-values. The accuracy of our method is 65.38% in independent test set, indicating biological significance. Our predictions are consistent with the experimental results. It shows the effectiveness and reliability of our method to predict interface residue pairs of protein trimers.

Neurocardiac regulation: from cardiac mechanisms to novel therapeutic approaches

Cardiac sympathetic overactivity is a well-established contributor to the progression of neurogenic hypertension and heart failure, yet the underlying pathophysiology remains unclear. Recent studies have highlighted the importance of acutely regulated cyclic nucleotides and their effectors in the control of intracellular calcium and exocytosis. Emerging evidence now suggests that a significant component of sympathetic overactivity and enhanced transmission may arise from impaired cyclic nucleotide signalling, resulting from compromised phosphodiesterase activity, as well as alterations in receptor-coupled G-protein activation. In this review, we address some of the key cellular and molecular pathways that contribute to sympathetic overactivity in hypertension and discuss their potential for therapeutic targeting.

A Novel Index of Contact Frequency from Noise Protein-Protein Interaction Data Help for Accurate Interface Residue Pair Prediction

Protein-protein interactions are important for most biological processes and have been studied for decades. However, the detailed formation mechanism of protein-protein interaction interface is still ambiguous, which makes it difficult to accurately predict the protein-protein interaction interface residue pairs. Here, we extract the interface residue-residue contacts from the decoys in the ZDOCK protein-protein complex decoy set with RMSD mostly larger than 3 Å. To accurately compute the interface residue-residue contacts, we define a new constant called interface residue pairs frequency, which counts the atom contact numbers between two interface residues. We normalize interface residue pairs frequency to pick out the top residue-residue pairs from all the possible pairs preferential to be on correct protein-protein interaction interface. When tested on 37 protein dimers from the decoy set where most decoys are incorrect, our method successfully predicts 30 protein dimers with a success rate of up to 81.1%. Higher accuracy than some other state-of-the-art methods confirmed the performance of our method.

Attention mechanism enhanced LSTM with residual architecture and its application for protein-protein interaction residue pairs prediction

Background

Recurrent neural network(RNN) is a good way to process sequential data, but the capability of RNN to compute long sequence data is inefficient. As a variant of RNN, long short term memory(LSTM) solved the problem in some extent. Here we improved LSTM for big data application in protein-protein interaction interface residue pairs prediction based on the following two reasons. On the one hand, there are some deficiencies in LSTM, such as shallow layers, gradient explosion or vanishing, etc. With a dramatic data increasing, the imbalance between algorithm innovation and big data processing has been more serious and urgent. On the other hand, protein-protein interaction interface residue pairs prediction is an important problem in biology, but the low prediction accuracy compels us to propose new computational methods.

Results

In order to surmount aforementioned problems of LSTM, we adopt the residual architecture and add attention mechanism to LSTM. In detail, we redefine the block, and add a connection from front to back in every two layers and attention mechanism to strengthen the capability of mining information. Then we use it to predict protein-protein interaction interface residue pairs, and acquire a quite good accuracy over 72%. What’s more, we compare our method with random experiments, PPiPP, standard LSTM, and some other machine learning methods. Our method shows better performance than the methods mentioned above.

Conclusion

We present an attention mechanism enhanced LSTM with residual architecture, and make deeper network without gradient vanishing or explosion to a certain extent. Then we apply it to a significant problem– protein-protein interaction interface residue pairs prediction and obtain a better accuracy than other methods. Our method provides a new approach for protein-protein interaction computation, which will be helpful for related biomedical researches.

Molecular Dynamics Simulation Reveals Exposed Residues in the Ligand-Binding Domain of the Low-Density Lipoprotein Receptor that Interacts with Vesicular Stomatitis Virus-G Envelope

Familial hypercholesterolemia (FH) is an autosomal dominant disease most often caused by mutations in the low-density lipoprotein receptor (LDLR) gene, which consists of 18 exons spanning 45 kb and codes for a precursor protein of 860 amino acids. Mutations in the LDLR gene lead to a reduced hepatic clearance of LDL as well as a high risk of coronary artery disease (CAD) and sudden cardiac death (SCD). Recently, LDLR transgenes have generated interest as potential therapeutic agents. However, LDLR packaging using a lentiviral vector (LVV) system pseudotyped with a vesicular stomatitis virus (VSV)-G envelope is not efficient. In this study, we modified the LVV system to improve transduction efficiency and investigated the LDLR regions responsible for transduction inhibition. Transduction efficiency of 293T cells with a 5′-LDLReGFP-3′ fusion construct was only 1.55% compared to 42.32% for the eGFP construct. Moreover, co-expression of LDLR affected eGFP packaging. To determine the specific region of the LDLR protein responsible for packaging inhibition, we designed constructs with mutations or sequential deletions at the 3′ and 5′ ends of LDLR cDNA. All constructs except one without the ligand-binding domain (LBD) (pWoLBD–eGFP) resulted in low transduction efficiency, despite successful packaging of viral RNA in the VSV envelope, as confirmed through RT-PCR. When we evaluated a direct interaction between LDLR and the VSV envelope glycoprotein using MD simulation and protein–protein interactions, we uncovered Val119, Thr120, Thr67, and Thr118 as exposed residues in the LDLR receptor that interact with the VSV protein. Together, our results suggest that the LBD of LDLR interacts with the VSV-G protein during viral packaging, which significantly reduces transduction efficiency.

Small protein-protein interfaces rich in electrostatic are often linked to regulatory function

Protein-protein interaction (PPI) is critical for several biological functions in living cells through the formation of an interface. Therefore, it is of interest to characterize protein-protein interfaces using an updated non-redundant structural dataset of 2557 homo (identical subunits) and 393 hetero (different subunits) dimer protein complexes determined by X-ray crystallography. We analyzed the interfaces using van der Waals (vdW), hydrogen bonding and electrostatic energies. Results show that on average homo and hetero interfaces are similar. Hence, we further grouped the 2950 interfaces based on percentage vdW to total energies into dominant (≥60%) and sub-dominant (<60%) vdW interfaces. Majority (92%) of interfaces have dominant vdW energy with large interface size (146 ± 87 (homo) and 137 ± 76 (hetero) residues) and interface area (1622 ± 1135 Ų (homo) and 1579 ± 1060 Ų (hetero)). However, a proportion (8%) of interfaces have sub-dominant vdW energy with small interface size (85 ± 46 (homo) and 88 ± 36 (hetero) residues) and interface area (823 ± 538 Ų (homo) and 881 ± 377 Ų (hetero)). It is found that large interfaces have two-fold more interface area and interface size than small interfaces with increasing hydrogen bonding energy to interface size. However, small interfaces have three-fold more electrostatics energy than large interfaces with increasing electrostatics to interface size. Thus, 8% of complexes having small interfaces with limited interface area and sub-dominant vdW energy are rich in electrostatics. It is interesting to observe that complexes having small interfaces are often associated with regulatory function. Hence, the observed structural features with known molecular function provide insights for the better understanding of PPI.Communicated by Ramaswamy H. Sarma.

Applications of in Silico Methods for Design and Development of Drugs Targeting Protein-Protein Interactions

BACKGROUND

Identification of Protein-Protein Interactions (PPIs) is a major challenge in modern molecular biology and biochemistry research, due to the unquestionable role of proteins in cells, biological process and pathological states. Over the past decade, the PPIs have evolved from being considered a highly challenging field of research to being investigated and examined as targets for pharmacological intervention.

OBJECTIVE

Comprehension of protein interactions is crucial to known how proteins come together to build signalling pathways, to carry out their functions, or to cause diseases, when deregulated. Multiplicity and great amount of PPIs structures offer a huge number of new and potential targets for the treatment of different diseases.

METHODS

Computational techniques are becoming predominant in PPIs studies for their effectiveness, flexibility, accuracy and cost. As a matter of fact, there are effective in silico approaches which are able to identify PPIs and PPI site. Such methods for computational target prediction have been developed through molecular descriptors and data-mining procedures.

RESULTS

In this review, we present different types of interactions between protein-protein and the application of in silico methods for design and development of drugs targeting PPIs. We described computational approaches for the identification of possible targets on protein surface and to detect of stimulator/ inhibitor molecules.

CONCLUSION

A deeper study of the most recent bioinformatics methodologies for PPIs studies is vital for a better understanding of protein complexes and for discover new potential PPI modulators in therapeutic intervention.

The Symmetric Difference Distance: A New Way to Evaluate the Evolution of Interfaces along Molecular Dynamics Trajectories; Application to Influenza Hemagglutinin

We propose a new and easy approach to evaluate structural dissimilarities between frames issued from molecular dynamics, and we test this methodology on human hemagglutinin. This protein is responsible for the entry of the influenza virus into the host cell by endocytosis, and this virus causes seasonal epidemics of infectious disease, which can be estimated to result in hundreds of thousands of deaths each year around the world. We computed the three interfaces between the three protomers of the hemagglutinin H1 homotrimer (PDB code: 1RU7) for each of its conformations generated from molecular dynamics simulation. For each conformation, we considered the set of residues involved in the union of these three interfaces. The dissimilarity between each pair of conformations was measured with our new methodology, the symmetric difference distance between the associated set of residues. The main advantages of the full procedure are: (i) it is parameter free; (ii) no spatial alignment is needed and (iii) it is simple enough so that it can be implemented by a beginner in programming. It is shown to be a relevant tool to follow the evolution of the conformation along the molecular dynamics trajectories.

Pattern to Knowledge: Deep Knowledge-Directed Machine Learning for Residue-Residue Interaction Prediction

Residue-residue close contact (R2R-C) data procured from three-dimensional protein-protein interaction (PPI) experiments is currently used for predicting residue-residue interaction (R2R-I) in PPI. However, due to complex physiochemical environments, R2R-I incidences, facilitated by multiple factors, are usually entangled in the source environment and masked in the acquired data. Here we present a novel method, P2K (Pattern to Knowledge), to disentangle R2R-I patterns and render much succinct discriminative information expressed in different specific R2R-I statistical/functional spaces. Since such knowledge is not visible in the data acquired, we refer to it as deep knowledge. Leveraging the deep knowledge discovered to construct machine learning models for sequence-based R2R-I prediction, without trial-and-error combination of the features over external knowledge of sequences, our R2R-I predictor was validated for its effectiveness under stringent leave-one-complex-out-alone cross-validation in a benchmark dataset, and was surprisingly demonstrated to perform better than an existing sequence-based R2R-I predictor by 28% (p: 1.9E-08). P2K is accessible via our web server on https://p2k.uwaterloo.ca .