A Hybrid Protocol for Identifying Comorbidity-Based Potential Drugs for COVID-19 Using Biomedical Literature Mining, Network Analysis, and Deep Learning.

Coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV2) has spread on an unprecedented scale around the globe. Despite of 141,975 published papers on COVID-19 and several hundreds of new studies carried out every day, this pandemic remains as a global challenge. Biomedical literature mining helps the researchers to understand the etiology of the disease and to gain an in-depth knowledge of the disease, potential drugs, vaccines developed and novel therapies. In addition to the available treatments, there is a huge need to address the comorbidity-based disease mortality in case of COVID-19 patients with type 2 diabetes mellitus (T2D), hypertension and cardiovascular disease (CVD). In this chapter, we provide a hybrid protocol based on biomedical literature mining, network analysis of omics data, and deep learning for the identification of most potential drugs for COVID-19.

COVID-19 Literature Mining and Analysis Research

By 2019 COVID-19, since the epidemic, the number of relevant documents exponentially level rise. Faced with a large amount of literature, this research provides convenience for exploring the connection between research topics and fields and quickly understanding relevant literature information. We pass on the data set after data cleansing using the LDA(Latent Dirichlet allocation) methods, and Berts and K-means modeling method extracting topic keywords. Use knowledge graph tools to output relevant visual graphics and systematically extract adequate information. Through text mining of biomedical research papers related to COVID-19, the improved model is used to analyze and make recommendations to respond to and prevent the COVID-19 pandemic. This research can support the rapid and in-depth analysis of a large number of relevant documents and can be used in future research to support real-time scientific disease research. © 2022 IEEE.

A high-throughput, online tool for investigating host-pathogen macromolecular interactions buried in scientific literature

This work introduces a low-latency, searchable web tool for biologist and healthcare researchers to quickly explore a large number of host-pathogen interactions (HPI) reported in scientific publication. Our database contains 23,581 generic HPI and 257 COVID-19 related HPI extracted from 32 million PubMed s. The data was automatically collected by running our high-precision biomedical text mining system, which consumes much less effort than manual curation while still provides reliable output. Web URL: philm2web.live © 2021 IEEE.

COVID-19 Drug Repurposing: A Network-Based Framework for Exploring Biomedical Literature and Clinical Trials for Possible Treatments.

BACKGROUND: With the Coronavirus becoming a new reality of our world, global efforts continue to seek answers to many questions regarding the spread, variants, vaccinations, and medications. Particularly, with the emergence of several strains (e.g., Delta, Omicron), vaccines will need further development to offer complete protection against the new variants. It is critical to identify antiviral treatments while the development of vaccines continues. In this regard, the repurposing of already FDA-approved drugs remains a major effort. In this paper, we investigate the hypothesis that a combination of FDA-approved drugs may be considered as a candidate for COVID-19 treatment if (1) there exists an evidence in the COVID-19 biomedical literature that suggests such a combination, and (2) there is match in the clinical trials space that validates this drug combination. METHODS: We present a computational framework that is designed for detecting drug combinations, using the following components (a) a Text-mining module: to extract drug names from the abstract section of the biomedical publications and the intervention/treatment sections of clinical trial records. (b) a network model constructed from the drug names and their associations, (c) a clique similarity algorithm to identify candidate drug treatments. RESULT AND CONCLUSIONS: Our framework has identified treatments in the form of two, three, or four drug combinations (e.g., hydroxychloroquine, doxycycline, and azithromycin). The identifications of the various treatment candidates provided sufficient evidence that supports the trustworthiness of our hypothesis.

Spike protein-based epitopes predicted against SARS-CoV-2 through literature mining.

BACKGROUND: With the diffusion of SARS-CoV-2 around the world, human health is being threatened. As there is no effective vaccine yet, the development of the vaccine is urgently in progress. MATERIALS AND METHODS: Immunoinformatics methods were applied to predict epitopes from the Spike protein through mining literature associated with B- and T-cell epitopes prediction published or preprinted since the outbreak of the virus till June 1, 2020. 3D structure of the Spike protein were obtained (PDB ID: 6VSB) for prediction of discontinuous B-cell epitopes and localization of epitopes in the hotspot regions. RESULTS: Methods provided by the Immune Epitope Database (IEDB) server were the most frequently used to predict epitopes. Sequence alignment of the epitopes extracted from literature with the Spike protein demonstrated that the epitopes in different studies converged to multiple short hotspot regions. There were three hotspot regions found in RBD of the Spike protein harboring B-cell linear epitopes ('RQIAPGQTGKIADYNYKLPD', 'SYGFQPTNGVGYQ' and 'YAWNRKRISNCVA') predicted to have high antigenicity score. Two T-cell epitopes ('KPFERDISTEIYQ' and 'NYNYLYRLFR') predicted to be highly antigenic in the original studies were discovered in the hotspot region. Toxicity and allergenicity analysis confirmed all the five epitopes are of non-toxin, and four of them are of non-allergen. The five epitopes identified in hotspot regions of RBD were found fully exposed based on the 3D structure of the Spike protein. CONCLUSION: The five epitopes we discovered from literature mining may be potential candidates for diagnostics and vaccine development against SARS-CoV-2.

TWIRLS, a knowledge-mining technology, suggests a possible mechanism for the pathological changes in the human host after coronavirus infection via ACE2.

Faced with the current large-scale public health emergency, collecting, sorting, and analyzing biomedical information related to the "SARS-CoV-2" should be done as quickly as possible to gain a global perspective, which is a basic requirement for strengthening epidemic control capacity. However, for human researchers studying viruses and hosts, the vast amount of information available cannot be processed effectively and in a timely manner, particularly if our scientific understanding is also limited, which further lowers the information processing efficiency. We present TWIRLS (Topic-wise inference engine of massive biomedical literatures), a method that can deal with various scientific problems, such as liver cancer, acute myeloid leukemia, and so forth, which can automatically acquire, organize, and classify information. Additionally, this information can be combined with independent functional data sources to build an inference system via a machine-based approach, which can provide relevant knowledge to help human researchers quickly establish subject cognition and to make more effective decisions. Using TWIRLS, we automatically analyzed more than three million words in more than 14,000 literature articles in only 4 hr. We found that an important regulatory factor angiotensin-converting enzyme 2 (ACE2) may be involved in host pathological changes on binding to the coronavirus after infection. On triggering functional changes in ACE2/AT2R, the cytokine homeostasis regulation axis becomes imbalanced via the Renin-Angiotensin System and IP-10, leading to a cytokine storm. Through a preliminary analysis of blood indices of COVID-19 patients with a history of hypertension, we found that non-ARB (Angiotensin II receptor blockers) users had more symptoms of severe illness than ARB users. This suggests ARBs could potentially be used to treat acute lung injury caused by coronavirus infection.