Integrative Neural Network Approach for Protein Interaction Prediction from Heterogeneous Data

Background: Protein-protein interactions (PPI) play a vital role in a wide range of biological processes starting from cell-cell interactions to developmental control in all organisms. However, experimental identification of PPI is often laborious, time-consuming and costly compared to computational prediction. There are several computational prediction models in the literature based on complete training samples, but none of them dealt with the partial training samples. Objective: The objective of this work was to develop an effective PPI prediction model for Arabidopsis Thaliana using partial training samples in a machine learning framework. Methods: We proposed an effective computational PPI prediction model by combining random forest (RF) classifier and autocorrelation (AC) sequence encoding features with 1:2 ratio of positive- PPI and unknown-PPI samples. Results: We observed that the proposed prediction model produces the highest average performance scores of sensitivity (94.62%), AUC (0.92) and pAUC (0.189) with the training datasets and sensitivity (88.14%), AUC (0.89) and pAUC (0.176) with the test datasets of 5-fold crossvalidation compared to other candidate predictors based on LDA, LOGI, ADA, NB, KNN & SVM classifiers. It also computed the highest performance scores of TPR (91.82%) and pAUC (0.174) at FPR= 20% with AUC (0.948) compared to other candidate predictors. Conclusion: Overall performance of the developed model revealed that our proposed predictor might be useful to elucidate the biological function of unseen PPIs from a large number of candidate proteins in Arabidopsis thaliana.

Pathogenic microorganisms exploit host cellular mechanisms and evade host defense mechanisms through molecular pathogen-host interactions (PHIs). Therefore, comprehensive analysis of these PHI networks should be an initial step for developing effective therapeutics against infectious diseases. Computational prediction of PHI data is gaining increasing demand because of scarcity of experimental data. Prediction of protein-protein interactions (PPIs) within PHI systems can be formulated as a classification problem, which requires the knowledge of non-interacting protein pairs. This is a restricting requirement since we lack datasets that report non-interacting protein pairs. In this study, we formulated the "computational prediction of PHI data" problem using kernel embedding of heterogeneous data. This eliminates the abovementioned requirement and enables us to predict new interactions without randomly labeling protein pairs as non-interacting. Domain-domain associations are used to filter the predicted results leading to 175 novel PHIs between 170 human proteins and 105 viral proteins. To compare our results with the state-of-the-art studies that use a binary classification formulation, we modified our settings to consider the same formulation. Detailed evaluations are conducted and our results provide more than 10 percent improvements for accuracy and AUC (area under the receiving operating curve) results in comparison with state-of-the-art methods.

Protein interactions play an essential role in studying living systems and life phenomena. A considerable amount of literature has been published on analyzing and predicting protein interactions, such as support vector machine method, homology-based method and similarity-based method, each has its pros and cons. Most existing methods for predicting protein interactions require prior domain knowledge, making it difficult to effectively extract protein features. Single method is dissatisfactory in predicting protein interactions, declaring the need for a comprehensive method that combines the advantages of various methods. On this basis, a deep ensemble learning method called EnAmDNN (Ensemble Deep Neural Networks with Attention Mechanism) is proposed to predict protein interactions which is an appropriate candidate for comprehensive learning, combining multiple models, and considering the advantages of various methods. Particularly, it encode protein sequences by the local descriptor, auto covariance, conjoint triad, pseudo amino acid composition and combine the vector representation of each protein in the protein interaction network. Then it takes advantage of the multi-layer convolutional neural networks to automatically extract protein features and construct an attention mechanism to analyze deep-seated relationships between proteins. We set up four different structures of deep learning models. In the ensemble learning model, second layer data sets are generated with five-fold cross validation from basic learners, then predict the protein interaction network by combining 16 models. Results on five independent PPI data sets demonstrate that EnAmDNN achieves superior prediction performance than other comparing methods.

Monitoring heart conditions through electrocardiography (ECG) has been the cornerstone of identifying cardiac irregularities. Cardiologists often rely on a detailed analysis of ECG recordings to pinpoint deviations that are indicative of heart anomalies. This traditional method, while effective, demands significant expertise and is susceptible to inaccuracies due to its manual nature. In the realm of computational analysis, Artificial Neural Networks (ANNs) have gained prominence across various domains, which can be attributed to their superior analytical capabilities. Conversely, Spiking Neural Networks (SNNs), which mimic the neural activity of the brain more closely through impulse-based processing, have not seen widespread adoption. The challenge lies primarily in the complexity of their training methodologies. Despite this, SNNs offer a promising avenue for energy-efficient computational models capable of displaying a high-level performance. This paper introduces an innovative approach employing SNNs augmented with an attention mechanism to enhance feature recognition in ECG signals. By leveraging the inherent efficiency of SNNs, coupled with the precision of attention modules, this model aims to refine the analysis of cardiac signals. The novel aspect of our methodology involves adapting the learned parameters from ANNs to SNNs using leaky integrate-and-fire (LIF) neurons. This transfer learning strategy not only capitalizes on the strengths of both neural network models but also addresses the training challenges associated with SNNs. The proposed method is evaluated through extensive experiments on two publicly available benchmark ECG datasets. The results show that our model achieves an overall accuracy of 93.8% on the MIT-BIH Arrhythmia dataset and 85.8% on the 2017 PhysioNet Challenge dataset. This advancement underscores the potential of SNNs in the field of medical diagnostics, offering a path towards more accurate, efficient, and less resource-intensive analyses of heart diseases.

In the detection of protein complexes, the completeness of a protein–protein interaction (PPI) network is crucial. Complete PPI networks, however, are not available for most species because experimentally identified PPIs are usually very limited. This paper proposes a deep learning based PPI predictor to construct a complete PPI network, from which protein complexes are detected using a spectral clustering method. For this purpose, the unknown PPIs are estimated by using a deep PPI predictor consisting of a semi‐supervised SVM classifier and a deep feature extractor of the convolutional neural network (CNN). Meanwhile, the similarities of gene ontology (GO) annotations contribute to protein interactions, and the differences of subcellular localizations contribute to negative interactions. Considering that, we pretrain the deep CNN feature extractor in a class of deep GO annotation and subcellular localization predictors using datasets from the type species, then transfer it to the PPI prediction model for fine‐tuning. In this way, we have a deep PPI detector enhanced with transfer learning of GO annotation and subcellular localization prediction. Experimental results on benchmark datasets show that the proposed method outperforms the state‐of‐the‐art methods. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

The Sixth International Symposium on Neural Networks (ISNN 2009)

Leveraging deep learning for the representation learning of Gene Ontology (GO) and Gene Ontology Annotation (GOA) holds significant promise for enhancing downstream biological tasks such as protein-protein interaction prediction. Prior approaches have predominantly used text- and graph-based methods, embedding GO and GOA in a single geometric space (e.g. Euclidean or hyperbolic). However, since the GO graph exhibits a complex and nonmonotonic hierarchy, single-space embeddings are insufficient to fully capture its structural nuances. In this study, we address this limitation by exploiting geometric interaction to better reflect the intricate hierarchical structure of GO. Our proposed method, Geometry-Aware Knowledge Graph Embeddings for GO and Genes (GeOKG), leverages interactions among various geometric representations during training, thereby modeling the complex hierarchy of GO more effectively. Experiments at the GO level demonstrate the benefits of incorporating these geometric interactions, while gene-level tests reveal that GeOKG outperforms existing methods in protein-protein interaction prediction. These findings highlight the potential of using geometric interaction for embedding heterogeneous biomedical networks. https://github.com/ukjung21/GeOKG.

The process-induced deformation (PID) during the manufacturing of thermosetting composite materials can significantly compromise manufacturing precision. This paper introduces an innovative method that combines a finite element analysis (FEA), feature classification algorithms, and an Artificial Neural Network (ANN) framework to rapidly predict the PID of a typical L-shaped structure. Initially, a comprehensive range of parameters that influence PID are compiled in this research, followed by the generation of a dataset through FEA considering viscoelastic constitutive models, validated by experimental results. Influential parameters are classified using Random Forest and LASSO regression methods, with each parameter rated according to its impact on PID, delineating their varying degrees of importance. Subsequently, through a hyperparameter analysis, an ANN framework is developed to rapidly predict the PID, while also refining the assessment of the parameters’ significance. This innovative approach achieves a computational time reduction of 98% with less than a 5% loss in accuracy, and highlights that under limited computational conditions, considering only a subset or all of the parameters—the peak temperature, corner angle, coefficient of chemical shrinkage, coefficient of thermal expansion, curing pressure, and E1—minimizes accuracy loss. The study demonstrates that machine learning algorithms can effectively address the challenge of predicting composite material PID, providing valuable insights for practical manufacturing applications.

BackgroundComputational prediction of protein interactions typically use protein domains as classifier features because they capture conserved information of interaction surfaces. However, approaches relying on domains as features cannot be applied to proteins without any domain information. In this paper, we explore the contribution of pure amino acid composition (AAC) for protein interaction prediction. This simple feature, which is based on normalized counts of single or pairs of amino acids, is applicable to proteins from any sequenced organism and can be used to compensate for the lack of domain information.ResultsAAC performed at par with protein interaction prediction based on domains on three yeast protein interaction datasets. Similar behavior was obtained using different classifiers, indicating that our results are a function of features and not of classifiers. In addition to yeast datasets, AAC performed comparably on worm and fly datasets. Prediction of interactions for the entire yeast proteome identified a large number of novel interactions, the majority of which co-localized or participated in the same processes. Our high confidence interaction network included both well-studied and uncharacterized proteins. Proteins with known function were involved in actin assembly and cell budding. Uncharacterized proteins interacted with proteins involved in reproduction and cell budding, thus providing putative biological roles for the uncharacterized proteins.ConclusionAAC is a simple, yet powerful feature for predicting protein interactions, and can be used alone or in conjunction with protein domains to predict new and validate existing interactions. More importantly, AAC alone performs at par with existing, but more complex, features indicating the presence of sequence-level information that is predictive of interaction, but which is not necessarily restricted to domains.

Cliques (maximal complete subnets) in protein-protein interaction (PPI) network are an important resource used to analyze protein complexes and functional modules. Clique-based methods of predicting PPI complement the data defection from biological experiments. However, clique-based predicting methods only depend on the topology of network. The false-positive and false-negative interactions in a network usually interfere with prediction. Therefore, we propose a method combining clique-based method of prediction and gene ontology (GO) annotations to overcome the shortcoming and improve the accuracy of predictions. According to different GO correcting rules, we generate two predicted interaction sets which guarantee the quality and quantity of predicted protein interactions. The proposed method is applied to the PPI network from the Database of Interacting Proteins (DIP) and most of the predicted interactions are verified by another biological database, BioGRID. The predicted protein interactions are appended to the original protein network, which leads to clique extension and shows the significance of biological meaning.

Objectives: To design a new framework to efficiently parallelize the steps of VLASPD algorithm using a hybridized apriori and fp-growth on GPU; to implement the existing and proposed framework in CUDA;to improve the performance factors like computational time, memory and CPU utilization.Methods/Statistical Analysis: This paper proposes the acceleration of Protein-Protein Interactions (PPIs) prediction on Graphics Processing Units(GPUs). A GPU can provide more processing cores and computational power in the same cost as a CPU.Findings: The frequently occurring patterns in the protein sequences can be used for PPIs prediction.The moving of the approaches from fixed length to variable length lead to computational complexity but also is found to be advantageous.Applications/Improvements:Sequence biology is since being researched by various computer engineers, the GPUs can be employed for predicting various sequence interactions like DNA-Proteins, etc. Since the GPU runs the parallel code efficiently, the methodology can be further improved if efficiently parallelized.

Prediction of protein-protein interaction (PPI) is one of the most challenging problems in biology. Although great progress has been devoted to the development of methodology for predicting PPIs and PIN using machine learning methods, the problem is still far from being solved since the application of most existing methods is limited. In this study, we propose a method for PPI prediction based on amino acids differences between pairs of protein sequences. 10-fold cross-validation tests based on human PPI datasets with balanced positive-to-negative ratios indicate that it performs comparably well. Therefore, our finding suggests that amino acids differences of interacting protein pairs are relevant to the prediction of PPIs and hence provide important information on sequence-based encoding schemes.

An artificial neural network for mixed frequency data

Improved prediction of protein-protein interactions using novel negative samples, features, and an ensemble classifier.

Corrosion inhibitors have been utilized for various industries globally. The usage of corrosion inhibitors depends on the condition at which the inhibitor is applied, and it can be difficult to select the proper inhibitor for a multitude of conditions. A laboratory testing of the various inhibitors as well as the multiple conditions can be tedious, costly and time consuming. This study attempts to propose a neural network prediction model of the behavior of corrosion inhibitors under various conditions. An artificial neural network is one of the methods that can be utilized to investigate and propose a prediction model based on various factors involved in corrosion inhibition. In this study, a 3 layers multilayer perceptron (MLP) network was used to predict the behaviors of the corrosion inhibitors. The layers were categorized into input layers, hidden layers and out layers. The model employed the dataset obtained from a previous study on the corrosion inhibition of L-valine for mild steel in 5% HCI. The data was segregated into 60% for training, 20% for testing and 20% for validation. It was found that the result simulates a reliable prediction model. The reliability was determined via the Regression value (R) and Mean Squared Error (MSE). High value of R and low value of MSE indicates a reliable prediction model in this study. In conclusion, this study is aimed to develop a reliable neural network prediction model based on the dataset from previous experimental work and compare the impact of different network architecture on the performance of the model.