Computational Prediction Methods Research Articles

Computational Advancements in Cancer Combination Therapy Prediction.

Given the high attrition rate of de novo drug discovery and limited efficacy of single-agent therapies in cancer treatment, combination therapy prediction through in silico drug repurposing has risen as a time- and cost-effective alternative for identifying novel and potentially efficacious therapies for cancer. The purpose of this review is to provide an introduction to computational methods for cancer combination therapy prediction and to summarize recent studies that implement each of these methods. A systematic search of the PubMed database was performed, focusing on studies published within the past 10 years. Our search included reviews and articles of ongoing and retrospective studies. We prioritized articles with findings that suggest considerations for improving combination therapy prediction methods over providing a meta-analysis of all currently available cancer combination therapy prediction methods. Computational methods used for drug combination therapy prediction in cancer research include networks, regression-based machine learning, classifier machine learning models, and deep learning approaches. Each method class has its own advantages and disadvantages, so careful consideration is needed to determine the most suitable class when designing a combination therapy prediction method. Future directions to improve current combination therapy prediction technology include incorporation of disease pathobiology, drug characteristics, patient multiomics data, and drug-drug interactions to determine maximally efficacious and tolerable drug regimens for cancer. As computational methods improve in their capability to integrate patient, drug, and disease data, more comprehensive models can be developed to more accurately predict safe and efficacious combination drug therapies for cancer and other complex diseases.

Multi-task prediction-based graph contrastive learning for inferring the relationship among lncRNAs, miRNAs and diseases.

Identifying the relationships among long non-coding RNAs (lncRNAs), microRNAs (miRNAs) and diseases is highly valuable for diagnosing, preventing, treating and prognosing diseases. The development of effective computational prediction methods can reduce experimental costs. While numerous methods have been proposed, they often to treat the prediction of lncRNA-disease associations (LDAs), miRNA-disease associations (MDAs) and lncRNA-miRNA interactions (LMIs) as separate task. Models capable of predicting all three relationships simultaneously remain relatively scarce. Our aim is to perform multi-task predictions, which not only construct a unified framework, but also facilitate mutual complementarity of information among lncRNAs, miRNAs and diseases. In this work, we propose a novel unsupervised embedding method called graph contrastive learning for multi-task prediction (GCLMTP). Our approach aims to predict LDAs, MDAs and LMIs by simultaneously extracting embedding representations of lncRNAs, miRNAs and diseases. To achieve this, we first construct a triple-layer lncRNA-miRNA-disease heterogeneous graph (LMDHG) that integrates the complex relationships between these entities based on their similarities and correlations. Next, we employ an unsupervised embedding model based on graph contrastive learning to extract potential topological feature of lncRNAs, miRNAs and diseases from the LMDHG. The graph contrastive learning leverages graph convolutional network architectures to maximize the mutual information between patch representations and corresponding high-level summaries of the LMDHG. Subsequently, for the three prediction tasks, multiple classifiers are explored to predict LDA, MDA and LMI scores. Comprehensive experiments are conducted on two datasets (from older and newer versions of the database, respectively). The results show that GCLMTP outperforms other state-of-the-art methods for the disease-related lncRNA and miRNA prediction tasks. Additionally, case studies on two datasets further demonstrate the ability of GCLMTP to accurately discover new associations. To ensure reproducibility of this work, we have made the datasets and source code publicly available at https://github.com/sheng-n/GCLMTP.

Surformer: An interpretable pattern-perceptive survival transformer for cancer survival prediction from histopathology whole slide images

Background and ObjectiveHigh-resolution histopathology whole slide images (WSIs) contain abundant valuable information for cancer prognosis. However, most computational pathology methods for survival prediction have weak interpretability and cannot explain the decision-making processes reasonably. To address this issue, we propose a highly interpretable neural network termed pattern-perceptive survival transformer (Surformer) for cancer survival prediction from WSIs. MethodsNotably, Surformer can quantify specific histological patterns through bag-level labels without any patch/cell-level auxiliary information. Specifically, the proposed ratio-reserved cross-attention module (RRCA) generates global and local features with the learnable prototypes (pglobal, plocals) as detectors and quantifies the patches correlative to each plocal in the form of ratio factors (rfs). Afterward, multi-head self&cross-attention modules proceed with the computation for feature enhancement against noise. Eventually, the designed disentangling loss function guides multiple local features to focus on distinct patterns, thereby assisting rfs from RRCA in achieving more explicit histological feature quantification. ResultsExtensive experiments on five TCGA datasets illustrate that Surformer outperforms existing state-of-the-art methods. In addition, we highlight its interpretation by visualizing rfs distribution across high-risk and low-risk cohorts and retrieving and analyzing critical histological patterns contributing to the survival prediction. ConclusionsSurformer is expected to be exploited as a useful tool for performing histopathology image data-driven analysis and gaining new insights for interpreting the associations between such images and patient survival states.

GDCL-NcDA: identifying non-coding RNA-disease associations via contrastive learning between deep graph learning and deep matrix factorization

Non-coding RNAs (ncRNAs) draw much attention from studies widely in recent years because they play vital roles in life activities. As a good complement to wet experiment methods, computational prediction methods can greatly save experimental costs. However, high false-negative data and insufficient use of multi-source information can affect the performance of computational prediction methods. Furthermore, many computational methods do not have good robustness and generalization on different datasets. In this work, we propose an effective end-to-end computing framework, called GDCL-NcDA, of deep graph learning and deep matrix factorization (DMF) with contrastive learning, which identifies the latent ncRNA-disease association on diverse multi-source heterogeneous networks (MHNs). The diverse MHNs include different similarity networks and proven associations among ncRNAs (miRNAs, circRNAs, and lncRNAs), genes, and diseases. Firstly, GDCL-NcDA employs deep graph convolutional network and multiple attention mechanisms to adaptively integrate multi-source of MHNs and reconstruct the ncRNA-disease association graph. Then, GDCL-NcDA utilizes DMF to predict the latent disease-associated ncRNAs based on the reconstructed graphs to reduce the impact of the false-negatives from the original associations. Finally, GDCL-NcDA uses contrastive learning (CL) to generate a contrastive loss on the reconstructed graphs and the predicted graphs to improve the generalization and robustness of our GDCL-NcDA framework. The experimental results show that GDCL-NcDA outperforms highly related computational methods. Moreover, case studies demonstrate the effectiveness of GDCL-NcDA in identifying the associations among diversiform ncRNAs and diseases.

RDRGSE: A Framework for Noncoding RNA-Drug Resistance Discovery by Incorporating Graph Skeleton Extraction and Attentional Feature Fusion.

Identifying noncoding RNAs (ncRNAs)-drug resistance association computationally would have a marked effect on understanding ncRNA molecular function and drug target mechanisms and alleviating the screening cost of corresponding biological wet experiments. Although graph neural network-based methods have been developed and facilitated the detection of ncRNAs related to drug resistance, it remains a challenge to explore a highly trusty ncRNA-drug resistance association prediction framework, due to inevitable noise edges originating from the batch effect and experimental errors. Herein, we proposed a framework, referred to as RDRGSE (RDR association prediction by using graph skeleton extraction and attentional feature fusion), for detecting ncRNA-drug resistance association. Specifically, starting with the construction of the original ncRNA-drug resistance association as a bipartite graph, RDRGSE took advantage of a bi-view skeleton extraction strategy to obtain two types of skeleton views, followed by a graph neural network-based estimator for iteratively optimizing skeleton views aimed at learning high-quality ncRNA-drug resistance edge embedding and optimal graph skeleton structure, jointly. Then, RDRGSE adopted adaptive attentional feature fusion to obtain final edge embedding and identified potential RDRAs under an end-to-end pattern. Comprehensive experiments were conducted, and experimental results indicated the significant advantage of a skeleton structure for ncRNA-drug resistance association discovery. Compared with state-of-the-art approaches, RDRGSE improved the prediction performance by 6.7% in terms of AUC and 6.1% in terms of AUPR. Also, ablation-like analysis and independent case studies corroborated RDRGSE generalization ability and robustness. Overall, RDRGSE provides a powerful computational method for ncRNA-drug resistance association prediction, which can also serve as a screening tool for drug resistance biomarkers.

Turnover number predictions for kinetically uncharacterized enzymes using machine and deep learning

The turnover number kcat, a measure of enzyme efficiency, is central to understanding cellular physiology and resource allocation. As experimental kcat estimates are unavailable for the vast majority of enzymatic reactions, the development of accurate computational prediction methods is highly desirable. However, existing machine learning models are limited to a single, well-studied organism, or they provide inaccurate predictions except for enzymes that are highly similar to proteins in the training set. Here, we present TurNuP, a general and organism-independent model that successfully predicts turnover numbers for natural reactions of wild-type enzymes. We constructed model inputs by representing complete chemical reactions through differential reaction fingerprints and by representing enzymes through a modified and re-trained Transformer Network model for protein sequences. TurNuP outperforms previous models and generalizes well even to enzymes that are not similar to proteins in the training set. Parameterizing metabolic models with TurNuP-predicted kcat values leads to improved proteome allocation predictions. To provide a powerful and convenient tool for the study of molecular biochemistry and physiology, we implemented a TurNuP web server.

Identification of Potential Novel B-Cell Epitopes of Capsid Protein VP2 in Senecavirus A.

Senecavirus A (SVA) is a type of nonenveloped single-stranded, positive-sense RNA virus. The VP2 protein is a structural protein that plays an important role in inducing early and late immune responses of the host. However, its antigenic epitopes have not been fully elucidated. Therefore, defining the B epitopes of the VP2 protein is of great importance to revealing its antigenic characterization. In this study, we analyzed B-cell immunodominant epitopes (IDEs) of the VP2 protein from the SVA strain CH/FJ/2017 using the Pepscan approach and a bioinformatics-based computational prediction method. The following four novel IDEs of VP2 were identified: IDE1, 41TKSDPPSSSTDQPTTT56; IDE2, 145PDGKAKSLQELNEEQW160; IDE3, 161VEMSDDYRTGKNMPF175; and IDE4, 267PYFNGLRNRFTTGT280. Most of the IDEs were highly conserved among the different strains. To our knowledge, the VP2 protein is a major protective antigen of SVA that can induce neutralizing antibodies in animals. Here, we analyzed the immunogenicity and neutralization activity of four IDEs of VP2. Consequently, all four IDEs showed good immunogenicity that could elicit specific antibodies in guinea pigs. A neutralization test in vitro showed that the peptide-specific guinea pig antisera of IDE2 could neutralize SVA strain CH/FJ/2017, and IDE2 was identified as a novel potential neutralizing linear epitope. This is the first time VP2 IDEs have been identified by using the Pepscan method and a bioinformatics-based computational prediction method. These results will help elucidate the antigenic epitopes of VP2 and clarify the basis for immune responses against SVA. IMPORTANCE The clinical symptoms and lesions caused by SVA are indistinguishable from those of other vesicular diseases in pigs. SVA has been associated with recent outbreaks of vesicular disease and epidemic transient neonatal losses in several swine-producing countries. Due to the continuing spread of SVA and the lack of commercial vaccines, the development of improved control strategies is urgently needed. The VP2 protein is a crucial antigen on the capsids of SVA particles. Furthermore, the latest research showed that VP2 could be a promising candidate for the development of novel vaccines and diagnostic tools. Hence, a detailed exploration of epitopes in the VP2 protein is necessary. In this study, four novel B-cell IDEs were identified using two different antisera with two different methods. IDE2 was identified as a new neutralizing linear epitope. Our findings will help in the rational design of epitope vaccines and further understanding of the antigenic structure of VP2.

State-of-the-art computational methods to predict protein-protein interactions with high accuracy and coverage.

Prediction of protein-protein interactions (PPIs) commonly involves a significant computational component. Rapid recent advances in the power of computational methods for protein interaction prediction motivate a review of the state-of-the-art. We review the major approaches, organized according to the primary source of data utilized: protein sequence, protein structure, and protein co-abundance. The advent of deep learning (DL) has brought with it significant advances in interaction prediction, and we show how DL is used for each source data type. We review the literature taxonomically, present example case studies in each category, and conclude with observations about the strengths and weaknesses of machine learning methods in the context of the principal sources of data for protein interaction prediction.

Large-scale predicting protein functions through heterogeneous feature fusion.

As the volume of protein sequence and structure data grows rapidly, the functions of the overwhelming majority of proteins cannot be experimentally determined. Automated annotation of protein function at a large scale is becoming increasingly important. Existing computational prediction methods are typically based on expanding the relatively small number of experimentally determined functions to large collections of proteins with various clues, including sequence homology, protein-protein interaction, gene co-expression, etc. Although there has been some progress in protein function prediction in recent years, the development of accurate and reliable solutions still has a long way to go. Here we exploit AlphaFold predicted three-dimensional structural information, together with other non-structural clues, to develop a large-scale approach termed PredGO to annotate Gene Ontology (GO) functions for proteins. We use a pre-trained language model, geometric vector perceptrons and attention mechanisms to extract heterogeneous features of proteins and fuse these features for function prediction. The computational results demonstrate that the proposed method outperforms other state-of-the-art approaches for predicting GO functions of proteins in terms of both coverage and accuracy. The improvement of coverage is because the number of structures predicted by AlphaFold is greatly increased, and on the other hand, PredGO can extensively use non-structural information for functional prediction. Moreover, we show that over 205 000 ($\sim $100%) entries in UniProt for human are annotated by PredGO, over 186 000 ($\sim $90%) of which are based on predicted structure. The webserver and database are available at http://predgo.denglab.org/.

Comparative Evaluation of Electron Ionization Mass Spectral Prediction Methods.

During the past decade promising methods for computational prediction of electron ionization mass spectra have been developed. The most prominent ones are based on quantum chemistry (QCEIMS) and machine learning (CFM-EI, NEIMS). Here we provide a threefold comparison of these methods with respect to spectral prediction and compound identification. We found that there is no unambiguous way to determine the best of these three methods. Among other factors, we find that the choice of spectral distance functions play an important role regarding the performance for compound identification.

Engineering Exciton Dynamics with Synthetic DNA Scaffolds.

ConspectusExcitons are the molecular-scale currency of electronic energy. Control over excitons enables energy to be directed and harnessed for light harvesting, electronics, and sensing. Excitonic circuits achieve such control by arranging electronically active molecules to prescribe desired spatiotemporal dynamics. Photosynthetic solar energy conversion is a canonical example of the power of excitonic circuits, where chromophores are positioned in a protein scaffold to perform efficient light capture, energy transport, and charge separation. Synthetic systems that aim to emulate this functionality include self-assembled aggregates, molecular crystals, and chromophore-modified proteins. While the potential of this approach is clear, these systems lack the structural precision to control excitons or even test the limits of their power. In recent years, DNA origami has emerged as a designer material that exploits biological building blocks to construct nanoscale architectures. The structural precision afforded by DNA origami has enabled the pursuit of naturally inspired organizational principles in a highly precise and scalable manner. In this Account, we describe recent developments in DNA-based platforms that spatially organize chromophores to construct tunable excitonic systems. The high fidelity of DNA base pairing enables the formation of programmable nanoscale architectures, and sequence-specific placement allows for the precise positioning of chromophores within the DNA structure. The integration of a wide range of chromophores across the visible spectrum introduces spectral tunability. These excitonic DNA-chromophore assemblies not only serve as model systems for light harvesting, solar conversion, and sensing but also lay the groundwork for the integration of coupled chromophores into larger-scale nucleic acid architectures.We have used this approach to generate DNA-chromophore assemblies of strongly coupled delocalized excited states through both sequence-specific self-assembly and the covalent attachment of chromophores. These strategies have been leveraged to independently control excitonic coupling and system-bath interaction, which together control energy transfer. We then extended this framework to identify how scaffold configurations can steer the formation of symmetry-breaking charge transfer states, paving the way toward the design of dual light-harvesting and charge separation DNA machinery. In an orthogonal application, we used the programmability of DNA chromophore assemblies to change the optical emission properties of strongly coupled dimers, generating a series of fluorophore-modified constructs with separable emission properties for fluorescence assays. Upcoming advances in the chemical modification of nucleotides, design of large-scale DNA origami, and predictive computational methods will aid in constructing excitonic assemblies for optical and computing applications. Collectively, the development of DNA-chromophore assemblies as a platform for excitonic circuitry offers a pathway to identifying and applying design principles for light harvesting and molecular electronics.

Flutter in a simplified blade cascade: Limits of the quasi-steady approximation

Flow-induced vibration in turbomachinery represents a major and persistent concern, especially in modern turbine and compressor designs with long and slender blades operating in transonic flow conditions. There is a wide range of computational and experimental methods for blade flutter prediction and analysis. In certain situations, the quasi-steady approximation can be utilized, considering the unsteady flow as a sequence of steady flow fields for each position of the oscillation cycle. The study is focused on experimental investigation of the limits of applicability of the quasisteady approximation in the case of a simplified linear five-blade cascade with the middle blade undergoing high-frequency torsional oscillation due to kinematic excitation. A measurement campaign of more than 100 wind tunnel runs was carried out for flow velocities ranging from high subsonic to transonic regimes (M = 0, 0.529, 0.777 and 1.018), frequency ratios 0 - 0.75 and reduced frequencies k = 0 – 0.41. A comparison of quasi-steady and time-resolved blade surface pressure measurements is reported, and the degree of unsteadiness of the airflow is quantified. For low reduced frequencies the stationary distributions match almost perfectly the time-resolved profiles. The degree of unsteadiness remains below 2% up to k = 0.1 for the subsonic and supercritical flow regimes. For reduced frequencies above 0.2, the global degree of unsteadiness increases quickly up to 10%, with local differences between the stationary and time-resolved pressure profiles up to 40%. In the case of transonic flow regime, the flow unsteadiness is generally higher and further complicated by intermittency — stochastic transition from supersonic to subsonic flow in the aft part of the blade.

GRA-GCN: dense granule protein prediction in Apicomplexa protozoa through graph convolutional network.

Dense granule proteins (GRAs) are secreted by Apicomplexa protozoa, which are closely related to an extensive variety of farm animal diseases. Predicting GRAs is an integral part in prevention and treatment of parasitic diseases. Considering that biological experiment approach is time-consuming and labor-intensive, computational method is a superior choice. Hence, developing an effective computational method for GRAs prediction is of urgency. In this paper, we present a novel computational method named GRA-GCN through graph convolutional network. In terms of the graph theory, the GRAs prediction can be regarded as a node classification task. GRA-GCN leverages k-nearest neighbor algorithm to construct the feature graph for aggregating more informative representation. To our knowledge, this is the first attempt to utilize computational approach for GRAs prediction. Evaluated by 5-fold cross-validations, the GRA-GCN method achieves satisfactory performance, and is superior to four classic machine learning-based methods and three state-of-the-art models. The analysis of the comprehensive experiment results and a case study could offer valuable information for understanding complex mechanisms, and would contribute to accurate prediction of GRAs. Moreover, we also implement a web server at http://dgpd.tlds.cc/GRAGCN/index/, for facilitating the process of using our model.

DLC-ac4C: A Prediction Model for N4-acetylcytidine Sites in Human mRNA Based on DenseNet and Bidirectional LSTM Methods.

N4 acetylcytidine (ac4C) is a highly conserved nucleoside modification that is essential for the regulation of immune functions in organisms. Currently, the identification of ac4C is primarily achieved using biological methods, which can be time-consuming and labor-intensive. In contrast, accurate identification of ac4C by computational methods has become a more effective method for classification and prediction. To the best of our knowledge, although there are several computational methods for ac4C locus prediction, the performance of the models they constructed is poor, and the network structure they used is relatively simple and suffers from the disadvantage of network degradation. This study aims to improve these limitations by proposing a predictive model based on integrated deep learning to better help identify ac4C sites. In this study, we propose a new integrated deep learning prediction framework, DLC-ac4C. First, we encode RNA sequences based on three feature encoding schemes, namely C2 encoding, nucleotide chemical property (NCP) encoding, and nucleotide density (ND) encoding. Second, one-dimensional convolutional layers and densely connected convolutional networks (DenseNet) are used to learn local features, and bi-directional long short-term memory networks (Bi-LSTM) are used to learn global features. Third, a channel attention mechanism is introduced to determine the importance of sequence characteristics. Finally, a homomorphic integration strategy is used to limit the generalization error of the model, which further improves the performance of the model. The DLC-ac4C model performed well in terms of sensitivity (Sn), specificity (Sp), accuracy (Acc), Mathews correlation coefficient (MCC), and area under the curve (AUC) for the independent test data with 86.23%, 79.71%, 82.97%, 66.08%, and 90.42%, respectively, which was significantly better than the prediction accuracy of the existing methods. Our model not only combines DenseNet and Bi-LSTM, but also uses the channel attention mechanism to better capture hidden information features from a sequence perspective, and can identify ac4C sites more effectively.

Protein Secondary Structure Prediction Using Cascaded Feature Learning Model

The protein secondary structure prediction (PSSP) is pivotal for predicting tertiary structure, which is proliferating in demand for drug design and development. Further, it can be used to learn different protein functions. Although there are many computational methods for protein structure prediction, none of them have succeeded 100% in solving the protein structure prediction problem. This paper proposes a deep learning model, namely Cascaded Feature Learning Model (CFLM) that uses a multi-stage transfer learning approach based on the Residual Dense Network (RDN) for predicting protein secondary structure. The model is trained with different protein datasets at various levels of transfer learning and accepts selected protein features such as solvent accessibility, physicochemical properties, PSSM (position-specific scoring matrix), and PSFM (position-specific frequency matrix) as input. The Q3 and Q8 accuracy obtained on CASP 13 and 14 benchmark datasets with the proposed approach are 91.23% and 91.45%, and 76.83% and 78.04%, respectively. The performance of CFLM is also compared with some of the recent PSSP approaches and it is observed that the proposed approach improves the prediction accuracy by 2.8% in terms of Q3 and 1.81% in terms of Q8 in the CASP 14 dataset.

Deep learning-assisted prediction of protein-protein interactions in Arabidopsis thaliana.

Currently, the experimentally identified interactome of Arabidopsis (Arabidopsis thaliana) is still far from complete, suggesting that computational prediction methods can complement experimental techniques. Motivated by the prosperity and success of deep learning algorithms and natural language processing techniques, we introduce an integrative deep learning framework, DeepAraPPI, allowing us to predict protein-protein interactions (PPIs) of Arabidopsis utilizing sequence, domain and Gene Ontology (GO) information. Our current DeepAraPPI comprises (i) a word2vec encoding-based Siamese recurrent convolutional neural network (RCNN) model, (ii) a Domain2vec encoding-based multiple layer perceptron (MLP) model, and (iii) a GO2vec encoding-based MLP model. Finally, DeepAraPPI combines prediction results of the three individual predictors through a logistic regression model. Compiling high-quality positive and negative training and test samples by applying strict filtering strategies, DeepAraPPI shows superior performance compared to existing state-of-the-art Arabidopsis PPI prediction methods. DeepAraPPI also provides better cross-species predictive ability in rice (Oryza sativa) than traditional machine learning methods, although the overall performance in cross-species prediction remains to be improved. DeepAraPPI is freely accessible at http://zzdlab.com/deeparappi/. In the meantime, we have also made the source code and datasets of DeepAraPPI available at https://github.com/zjy1125/DeepAraPPI.

RNAJP: enhanced RNA 3D structure predictions with non-canonical interactions and global topology sampling.

RNA 3D structures are critical for understanding their functions. However, only a limited number of RNA structures have been experimentally solved, so computational prediction methods are highly desirable. Nevertheless, accurate prediction of RNA 3D structures, especially those containing multiway junctions, remains a significant challenge, mainly due to the complicated non-canonical base pairing and stacking interactions in the junction loops and the possible long-range interactions between loop structures. Here we present RNAJP ('RNA Junction Prediction'), a nucleotide- and helix-level coarse-grained model for the prediction of RNA 3D structures, particularly junction structures, from a given 2D structure. Through global sampling of the 3D arrangements of the helices in junctions using molecular dynamics simulations and in explicit consideration of non-canonical base pairing and base stacking interactions as well as long-range loop-loop interactions, the model can provide significantly improved predictions for multibranched junction structures than existing methods. Moreover, integrated with additional restraints from experiments, such as junction topology and long-range interactions, the model may serve as a useful structure generator for various applications.

Network-based drug repurposing for the treatment of COVID-19 patients in different clinical stages

In the severe acute respiratory coronavirus disease 2019 (COVID-19) pandemic, there is an urgent need to develop effective treatments. Through a network-based drug repurposing approach, several effective drug candidates are identified for treating COVID-19 patients in different clinical stages. The proposed approach takes advantage of computational prediction methods by integrating publicly available clinical transcriptome and experimental data. We identify 51 drugs that regulate proteins interacted with SARS-CoV-2 protein through biological pathways against COVID-19, some of which have been experimented in clinical trials. Among the repurposed drug candidates, lovastatin leads to differential gene expression in clinical transcriptome for mild COVID-19 patients, and estradiol cypionate mainly regulates hormone-related biological functions to treat severe COVID-19 patients. Multi-target mechanisms of drug candidates are also explored. Erlotinib targets the viral protein interacted with cytokine and cytokine receptors to affect SARS-CoV-2 attachment and invasion. Lovastatin and testosterone block the angiotensin system to suppress the SARS-CoV-2 infection. In summary, our study has identified effective drug candidates against COVID-19 for patients in different clinical stages and provides comprehensive understanding of potential drug mechanisms.

Identification of SARS-CoV-2 Main Protease (Mpro) Cleavage Sites Using Two-Dimensional Electrophoresis and In Silico Cleavage Site Prediction

The main protease (Mpro) of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) plays a crucial role in its life cycle. The Mpro-mediated limited proteolysis of the viral polyproteins is necessary for the replication of the virus, and cleavage of the host proteins of the infected cells may also contribute to viral pathogenesis, such as evading the immune responses or triggering cell toxicity. Therefore, the identification of host substrates of the viral protease is of special interest. To identify cleavage sites in cellular substrates of SARS-CoV-2 Mpro, we determined changes in the HEK293T cellular proteome upon expression of the Mpro using two-dimensional gel electrophoresis. The candidate cellular substrates of Mpro were identified by mass spectrometry, and then potential cleavage sites were predicted in silico using NetCorona 1.0 and 3CLP web servers. The existence of the predicted cleavage sites was investigated by in vitro cleavage reactions using recombinant protein substrates containing the candidate target sequences, followed by the determination of cleavage positions using mass spectrometry. Unknown and previously described SARS-CoV-2 Mpro cleavage sites and cellular substrates were also identified. Identification of target sequences is important to understand the specificity of the enzyme, as well as aiding the improvement and development of computational methods for cleavage site prediction.

Pseudoknots in RNA Structure Prediction.

RNA molecules play active roles in the cell and are important for numerous applications in biotechnology and medicine. The function of an RNA molecule stems from its structure. RNA structure determination is time consuming, challenging, and expensive using experimental methods. Thus, much research has been directed at RNA structure prediction through computational means. Many of these methods focus primarily on the secondary structure of the molecule, ignoring the possibility of pseudoknotted structures. However, pseudoknots are known to play functional roles in many RNA molecules or in their method of interaction with other molecules. Improving the accuracy and efficiency of computational methods that predict pseudoknots is an ongoing challenge for single RNA molecules, RNA-RNA interactions, and RNA-protein interactions. To improve the accuracy of prediction, many methods focus on specific applications while restricting the length and the class of the pseudoknotted structures they can identify. In recent years, computational methods for structure prediction have begun to catch up with the impressive developments seen in biotechnology. Here, we provide a non-comprehensive overview of available pseudoknot prediction methods and their best-use cases. © 2023 Wiley Periodicals LLC.