Enhancing Protein Function Prediction Performance by Utilizing AlphaFold-Predicted Protein Structures.

The structure of a protein is of great importance in determining its functionality, and this characteristic can be leveraged to train data-driven prediction models. However, the limited number of available protein structures severely limits the performance of these models. AlphaFold2 and its open-source data set of predicted protein structures have provided a promising solution to this problem, and these predicted structures are expected to benefit the model performance by increasing the number of training samples. In this work, we constructed a new data set that acted as a benchmark and implemented a state-of-the-art structure-based approach for determining whether the performance of the function prediction model can be improved by putting additional AlphaFold-predicted structures into the training set and further compared the performance differences between two models separately trained with real structures only and AlphaFold-predicted structures only. Experimental results indicated that structure-based protein function prediction models could benefit from virtual training data consisting of AlphaFold-predicted structures. First, model performances were improved in all three categories of Gene Ontology terms (GO terms) after adding predicted structures as training samples. Second, the model trained only on AlphaFold-predicted virtual samples achieved comparable performances to the model based on experimentally solved real structures, suggesting that predicted structures were almost equally effective in predicting protein functionality.

CollaPPI: A Collaborative Learning Framework for Predicting Protein-Protein Interactions.

Exploring protein-protein interaction (PPI) is of paramount importance for elucidating the intrinsic mechanism of various biological processes. Nevertheless, experimental determination of PPI can be both time-consuming and expensive, motivating the exploration of data-driven deep learning technologies as a viable, efficient, and accurate alternative. Nonetheless, most current deep learning-based methods regarded a pair of proteins to be predicted for possible interaction as two separate entities when extracting PPI features, thus neglecting the knowledge sharing among the collaborative protein and the target protein. Aiming at the above issue, a collaborative learning framework CollaPPI was proposed in this study, where two kinds of collaboration, i.e., protein-level collaboration and task-level collaboration, were incorporated to achieve not only the knowledge-sharing between a pair of proteins, but also the complementation of such shared knowledge between biological domains closely related to PPI (i.e., protein function, and subcellular location). Evaluation results demonstrated that CollaPPI obtained superior performance compared to state-of-the-art methods on two PPI benchmarks. Besides, evaluation results of CollaPPI on the additional PPI type prediction task further proved its excellent generalization ability.

HiSIF-DTA: A Hierarchical Semantic Information Fusion Framework for Drug-Target Affinity Prediction.

Accurately identifying drug-target affinity (DTA) plays a significant role in promoting drug discovery and has attracted increasing attention in recent years. Exploring appropriate protein representation methods and increasing the abundance of protein information is critical in enhancing the accuracy of DTA prediction. Recently, numerous deep learning-based models have been proposed to utilize the sequential or structural features of target proteins. However, these models capture only the low-order semantics that exist in a single protein, while the high-order semantics abundant in biological networks are largely ignored. In this article, we propose HiSIF-DTA'a hierarchical semantic information fusion framework for DTA prediction. In this framework, a hierarchical protein graph is constructed that includes not only contact maps as low-order structural semantics but also protein-rotein interaction (PPI) networks as high-order functional semantics. Particularly, two distinct hierarchical fusion strategies (i.e., Top-down and Bottom-Up) are designed to integrate the different protein semantics, therefore contributing to a richer protein representation. Comprehensive experimental results demonstrate that HiSIF-DTA outperforms current state-of-the-art methods for prediction on the benchmark datasets of the DTA task. Further validation on binary tasks and visualization analysis demonstrates the generalization and interpretation abilities of the proposed method.

Predicting Drug-Target Affinity by Learning Protein Knowledge From Biological Networks.

Predicting drug-target affinity (DTA) is a crucial step in the process of drug discovery. Efficient and accurate prediction of DTA would greatly reduce the time and economic cost of new drug development, which has encouraged the emergence of a large number of deep learning-based DTA prediction methods. In terms of the representation of target proteins, current methods can be classified into 1D sequence- and 2D-protein graph-based methods. However, both two approaches focused only on the inherent properties of the target protein, but neglected the broad prior knowledge regarding protein interactions that have been clearly elucidated in past decades. Aiming at the above issue, this work presents an end-to-end DTA prediction method named MSF-DTA (Multi-Source Feature Fusion-based Drug-Target Affinity). The contributions can be summarized as follows. First, MSF-DTA adopts a novel "neighboring feature"-based protein representation. Instead of utilizing only the inherent features of a target protein, MSF-DTA gathers additional information for the target protein from its biologically related "neighboring" proteins in PPI (i.e., protein-protein interaction) and SSN (i.e., sequence similarity) networks to get prior knowledge. Second, the representation was learned using an advanced graph pre-training framework, VGAE, which could not only gather node features but also learn topological connections, therefore contributing to a richer protein representation and benefiting the downstream DTA prediction task. This study provides new perspective for the DTA prediction task, and evaluation results demonstrated that MSF-DTA obtained superior performances compared to current state-of-the-art methods.

In silico assessment of pharmacotherapy for carbon monoxide induced arrhythmias in healthy and failing human hearts.

Background: Carbon monoxide (CO) is gaining increased attention in air pollution-induced arrhythmias. The severe cardiotoxic consequences of CO urgently require effective pharmacotherapy to treat it. However, existing evidence demonstrates that CO can induce arrhythmias by directly affecting multiple ion channels, which is a pathway distinct from heart ischemia and has received less concern in clinical treatment. Objective: To evaluate the efficacy of some common clinical antiarrhythmic drugs for CO-induced arrhythmias, and to propose a potential pharmacotherapy for CO-induced arrhythmias through the virtual pathological cell and tissue models. Methods: Two pathological models describing CO effects on healthy and failing hearts were constructed as control baseline models. After this, we first assessed the efficacy of some common antiarrhythmic drugs like ranolazine, amiodarone, nifedipine, etc., by incorporating their ion channel-level effects into the cell model. Cellular biomarkers like action potential duration and tissue-level biomarkers such as the QT interval from pseudo-ECGs were obtained to assess the drug efficacy. In addition, we also evaluated multiple specific I Kr activators in a similar way to multi-channel blocking drugs, as the I Kr activator showed great potency in dealing with CO-induced pathological changes. Results: Simulation results showed that the tested seven antiarrhythmic drugs failed to rescue the heart from CO-induced arrhythmias in terms of the action potential and the ECG manifestation. Some of them even worsened the condition of arrhythmogenesis. In contrast, I Kr activators like HW-0168 effectively alleviated the proarrhythmic effects of CO. Conclusion: Current antiarrhythmic drugs including the ranolazine suggested in previous studies did not achieve therapeutic effects for the cardiotoxicity of CO, and we showed that the specific I Kr activator is a promising pharmacotherapy for the treatment of CO-induced arrhythmias.

Mechanistic Insights Into Inflammation-Induced Arrhythmias: A Simulation Study.

Cardiovascular diseases are the primary cause of death of humans, and among these, ventricular arrhythmias are the most common cause of death. There is plausible evidence implicating inflammation in the etiology of ventricular fibrillation (VF). In the case of systemic inflammation caused by an overactive immune response, the induced inflammatory cytokines directly affect the function of ion channels in cardiomyocytes, leading to a prolonged action potential duration (APD). However, the mechanistic links between inflammatory cytokine-induced molecular and cellular influences and inflammation-associated ventricular arrhythmias need to be elucidated. The present study aimed to determine the potential impact of systemic inflammation on ventricular electrophysiology by means of multiscale virtual heart models. The experimental data on the ionic current of three major cytokines [i.e., tumor necrosis factor-α (TNF-α), interleukin-1 (IL-1ß), and interleukin-6 (IL-6)] were incorporated into the cell model, and the effects of each cytokine and their combined effect on the cell action potential (AP) were evaluated. Moreover, the integral effect of these cytokines on the conduction of excitation waves was also investigated in a tissue model. The simulation results suggested that inflammatory cytokines significantly prolonged APD, enhanced the transmural and regional repolarization heterogeneities that predispose to arrhythmias, and reduced the adaptability of ventricular tissue to fast heart rates. In addition, simulated pseudo-ECGs showed a prolonged QT interval-a manifestation consistent with clinical observations. In summary, the present study provides new insights into ventricular arrhythmias associated with inflammation.

A Multi-Scale Computational Model for the Rat Ventricle: Construction, Parallelization, and Applications.

BACKGROUND: Cardiovascular diseases are the top killer of human beings. The ventricular arrhythmia, as a type of malignant cardiac arrhythmias, typically leads to death if not treated within minutes. The multi-scale virtual heart provides an idealized tool for exploring the underlying mechanisms, by means of incorporating abundant experimental data at the level of ion channels and analyzing the subsequent pathological changes at organ levels. However, there are few studies on building a virtual heart model for rats-a species most widely used in experiments. OBJECTIVE: To build a multi-scale computational model for rats, with detailed methodology for the model construction, computational optimization, and its applications. METHODS: First, approaches for building multi-scale models ranging from cellular to 3-D organ levels are introduced, with detailed descriptions of handling the ventricular myocardium heterogeneity, geometry processing, and boundary conditions, etc. Next, for dealing with the expensive computational costs of 3-D models, optimization approaches including an optimized representation and a GPU-based parallelization method are introduced. Finally, methods for reproducing of some key phenomenon (e.g., electrocardiograph, spiral/scroll waves) are demonstrated. RESULTS: Three types of heterogeneity, including the transmural heterogeneity, the interventricular heterogeneity, and the base-apex heterogeneity are incorporated into the model. The normal and reentrant excitation waves, as well as the corresponding pseudo-ECGs are reproduced by the constructed ventricle model. In addition, the temporal and spatial vulnerability to reentry arrhythmias are quantified based on the evaluation experiments of vulnerable window and the critical length. CONCLUSIONS: The constructed multi-scale rat ventricle model is able to reproduce both the physiological and the pathological phenomenon in different scales. Evaluation experiments suggest that the apex is the most susceptible area to arrhythmias. The model can be a promising tool for the investigation of arrhythmogenesis and the screening of anti-arrhythmic drugs.

Proarrhythmic effects of carbon monoxide in human ventricular tissue: insights from computational modeling.

Epidemiological studies have demonstrated that ambient air pollution has been closely associated with cardiovascular diseases. Carbon monoxide (CO) is a common ambient air pollutant that can cause adverse effects on the heart. CO is known to cause tissue ischemia, resulting in ventricular arrhythmias. However, accumulating biological studies showed that CO could exert effects on multiple cardiac ionic channels under normoxic conditions, which might indicate new proarrhythmic mechanisms other than ischemia-mediated electrophysiology changes. In this work, we evaluated the functional impacts of CO on human ventricles using a multi-scale model of human ventricular tissue. Experimental data regarding the effects of CO on different ion channels were incorporated into the cell model to explore the alterations of ventricular electrophysiology. Simulation results suggested that CO significantly prolonged the duration of ventricular action potentials, enhanced the transmural dispersion of repolarization, and reduced the adaptability of ventricular tissue to fast heart rates. In addition, simulated pseudo-ECGs showed consistent manifestations with the clinical observation that CO caused an apparent QT interval prolongation and T-wave widening, indicating that CO affected the heart's abnormal ventricular repolarization.