A machine learning platform to estimate anti-SARS-CoV-2 activities (preprint)

Strategies for drug discovery and repositioning are an urgent need with respect to COVID-19. Here we present "REDIAL-2020", a suite of computational models for estimating small molecule activities in a range of SARS-CoV-2 related assays. Models were trained using publicly available, high throughput screening data and by employing different descriptor types and various machine learning strategies. Here we describe the development and the usage of eleven models spanning across the areas of viral entry, viral replication, live virus infectivity, in vitro infectivity and human cell toxicity. REDIAL-2020 is available as a web application through the DrugCentral web portal (http://drugcentral.org/Redial). In addition, the web-app provides similarity search results that display the most similar molecules to the query, as well as associated experimental data. REDIAL-2020 can serve as a rapid online tool for identifying active molecules for COVID-19 treatment.

The N-terminal domain of spike glycoprotein mediates SARS-CoV-2 infection by associating with L-SIGN and DC-SIGN (preprint)

The widespread occurrence of SARS-CoV-2 has had a profound effect on society and a vaccine is currently being developed. Angiotensin-converting enzyme 2 (ACE2) is the primary host cell receptor that interacts with the receptor-binding domain (RBD) of the SARS-CoV-2 spike protein. Although pneumonia is the main symptom in severe cases of SARS-CoV-2 infection, the expression levels of ACE2 in the lung is low, suggesting the presence of another receptor for the spike protein. In order to identify the additional receptors for the spike protein, we screened a receptor for the SARS-CoV-2 spike protein from the lung cDNA library. We cloned L-SIGN as a specific receptor for the N-terminal domain (NTD) of the SARS-CoV-2 spike protein. The RBD of the spike protein did not bind to L-SIGN. In addition, not only L-SIGN but also DC-SIGN, a closely related C-type lectin receptor to L-SIGN, bound to the NTD of the SARS-CoV-2 spike protein. Importantly, cells expressing L-SIGN and DC-SIGN were both infected by SARS-CoV-2. Furthermore, L-SIGN and DC-SIGN induced membrane fusion by associating with the SARS-CoV-2 spike protein. Serum antibodies from infected patients and a patient-derived monoclonal antibody against NTD inhibited SARS-CoV-2 infection of L-SIGN or DC-SIGN expressing cells. Our results highlight the important role of NTD in SARS-CoV-2 dissemination through L-SIGN and DC-SIGN and the significance of having anti-NTD neutralizing antibodies in antibody-based therapeutics.

A Workflow of Integrated Resources to Catalyze Network Pharmacology Driven COVID-19 Research (preprint)

Motivation: In the event of an outbreak due to an emerging pathogen, time is of the essence to contain or to mitigate the spread of the disease. Drug repositioning is one of the strategies that has the potential to deliver therapeutics relatively quickly. The SARS-CoV-2 pandemic has shown that integrating critical data resources to drive drug-repositioning studies, involving host-host, host-pathogen and drug-target interactions, remains a time-consuming effort that translates to a delay in the development and delivery of a life-saving therapy. Results: Here, we describe a workflow we designed for a semi-automated integration of rapidly emerging datasets that can be generally adopted in a broad network pharmacology research setting. The workflow was used to construct a COVID-19 focused multimodal network that integrates 487 host-pathogen, 74,805 host-host protein and 1,265 drug-target interactions. The resultant Neo4j graph database named "Neo4COVID19" is accessible via a web interface and via API calls based on the Bolt protocol. We believe that our Neo4COVID19 database will be a valuable asset to the research community and will catalyze the discovery of therapeutics to fight COVID-19. Availability: https://neo4covid19.ncats.io . Keywords: SARS-CoV-2, COVID-19, network pharmacology, graph database, Neo4j, data integration, drug repositioning

REDIAL-2020: A Suite of Machine Learning Models to Estimate Anti-SARS-CoV-2 Activities (preprint)

Strategies for drug discovery and repositioning are an urgent need with respect to COVID-19. We developed "REDIAL-2020", a suite of machine learning models for estimating small molecule activity from molecular structure, for a range of SARS-CoV-2 related assays. Each classifier is based on three distinct types of descriptors (fingerprint, physicochemical, and pharmacophore) for parallel model development. These models were trained using high throughput screening data from the NCATS COVID19 portal (https://opendata.ncats.nih.gov/covid19/index.html), with multiple categorical machine learning algorithms. The “best models” are combined in an ensemble consensus predictor that outperforms single models where external validation is available. This suite of machine learning models is available through the DrugCentral web portal (http://drugcentral.org/Redial). Acceptable input formats are: drug name, PubChem CID, or SMILES; the output is an estimate of anti-SARS-CoV-2 activities. The web application reports estimated activity across three areas (viral entry, viral replication, and live virus infectivity) spanning six independent models, followed by a similarity search that displays the most similar molecules to the query among experimentally determined data. The ML models have 60% to 74% external predictivity, based on three separate datasets. Complementing the NCATS COVID19 portal, REDIAL-2020 can serve as a rapid online tool for identifying active molecules for COVID-19 treatment. The source code and specific models are available through Github (https://github.com/sirimullalab/redial-2020), or via Docker Hub (https://hub.docker.com/r/sirimullalab/redial-2020) for users preferring a containerized version.