Recent computational drug repositioning strategies against SARS-CoV-2

Leveraging machine learning for drug repurposing in rheumatoid arthritis

Rheumatoid arthritis (RA) presents a significant challenge in clinical management because of the dearth of effective drugs despite advances in understanding its mechanisms. Drug repurposing has emerged as a promising strategy to address this gap, offering potential cost savings and expediting drug discovery. Notably, computational methods, particularly machine learning (ML), have shown promise in RA drug repurposing. In this review, we survey various drug-repurposing approaches, both classical and contemporary, highlighting the pivotal role of ML. We summarize RA candidate drugs identified through computational strategies and discuss prevailing challenges in this domain. Leveraging ML, alongside a deepening understanding of RA mechanisms, holds promise for enhancing pharmacological treatment options for patients with RA.

A deep learning drug screening framework for integrating local-global characteristics: A novel attempt for limited data

At the beginning of the "Disease X" outbreak, drug discovery and development are often challenged by insufficient and unbalanced data. To address this problem and maximize the information value of limited data, we propose a drug screening model, LGCNN, based on convolutional neural network (CNN), which enables rapid drug screening by integrating features of drug molecular structures and drug-target interactions at both local and global (LG) levels. Experimental results show that LGCNN exhibits better performance compared to other state-of-the-art classification methods under limited data. In addition, LGCNN was applied to anti-SARS-CoV-2 drug screening to realize therapeutic drug mining against COVID-19. LGCNN transcends the limitations of traditional models for predicting interactions between single drug targets and shows new advantages in predicting multi-target drug-target interactions. Notably, the cross-coronavirus generalizability of the model is also implied by the analysis of targets, drugs, and mechanisms in the prediction results. In conclusion, LGCNN provides new ideas and methods for rapid drug screening in emergency situations where data are scarce.

Breaking the Chain: Protease Inhibitors as Game Changers in Respiratory Viruses Management

Respiratory viral infections (VRTIs) rank among the leading causes of global morbidity and mortality, affecting millions of individuals each year across all age groups. These infections are caused by various pathogens, including rhinoviruses (RVs), adenoviruses (AdVs), and coronaviruses (CoVs), which are particularly prevalent during colder seasons. Although many VRTIs are self-limiting, their frequent recurrence and potential for severe health complications highlight the critical need for effective therapeutic strategies. Viral proteases are crucial for the maturation and replication of viruses, making them promising therapeutic targets. This review explores the pivotal role of viral proteases in the lifecycle of respiratory viruses and the development of protease inhibitors as a strategic response to these infections. Recent advances in antiviral therapy have highlighted the effectiveness of protease inhibitors in curtailing the spread and severity of viral diseases, especially during the ongoing COVID-19 pandemic. It also assesses the current efforts aimed at identifying and developing inhibitors targeting key proteases from major respiratory viruses, including human RVs, AdVs, and (severe acute respiratory syndrome coronavirus-2) SARS-CoV-2. Despite the recent identification of SARS-CoV-2, within the last five years, the scientific community has devoted considerable time and resources to investigate existing drugs and develop new inhibitors targeting the virus's main protease. However, research efforts in identifying inhibitors of the proteases of RVs and AdVs are limited. Therefore, herein, it is proposed to utilize this knowledge to develop new inhibitors for the proteases of other viruses affecting the respiratory tract or to develop dual inhibitors. Finally, by detailing the mechanisms of action and therapeutic potentials of these inhibitors, this review aims to demonstrate their significant role in transforming the management of respiratory viral diseases and to offer insights into future research directions.

Drug Repositioning Based on Deep Sparse Autoencoder and Drug-Disease Similarity

Drug repositioning is critical to drug development. Previous drug repositioning methods mainly constructed drug-disease heterogeneous networks to extract drug-disease features. However, these methods faced difficulty when we are using structurally simple models to deal with complex heterogeneous networks. Therefore, in this study, the researchers introduced a drug repositioning method named DRDSA. The method utilizes a deep sparse autoencoder and integrates drug-disease similarities. First, the researchers constructed a drug-disease feature network by incorporating information from drug chemical structure, disease semantic data, and existing known drug-disease associations. Then, we learned the low-dimensional representation of the feature network using a deep sparse autoencoder. Finally, we utilized a deep neural network to make predictions on new drug-disease associations based on the feature representation. The experimental results show that our proposed method has achieved optimal results on all four benchmark datasets, especially on the CTD dataset where AUC and AUPR reached 0.9619 and 0.9676, respectively, outperforming other baseline methods. In the case study, the researchers predicted the top ten antiviral drugs for COVID-19. Remarkably, six out of these predictions were subsequently validated by other literature sources.

Fuzzy optimization for identifying antiviral targets for treating SARS-CoV-2 infection in the heart

In this paper, a fuzzy hierarchical optimization framework is proposed for identifying potential antiviral targets for treating severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection in the heart. The proposed framework comprises four objectives for evaluating the elimination of viral biomass growth and the minimization of side effects during treatment. In the application of the framework, Dulbecco's modified eagle medium (DMEM) and Ham's medium were used as uptake nutrients on an antiviral target discovery platform. The prediction results from the framework reveal that most of the antiviral enzymes in the aforementioned media are involved in fatty acid metabolism and amino acid metabolism. However, six enzymes involved in cholesterol biosynthesis in Ham's medium and three enzymes involved in glycolysis in DMEM are unable to eliminate the growth of the SARS-CoV-2 biomass. Three enzymes involved in glycolysis, namely BPGM, GAPDH, and ENO1, in DMEM combine with the supplemental uptake of L-cysteine to increase the cell viability grade and metabolic deviation grade. Moreover, six enzymes involved in cholesterol biosynthesis reduce and fail to reduce viral biomass growth in a culture medium if a cholesterol uptake reaction does not occur and occurs in this medium, respectively.